diff --git a/.devcontainer/Dockerfile b/.devcontainer/Dockerfile index 364066ee..160a9b91 100644 --- a/.devcontainer/Dockerfile +++ b/.devcontainer/Dockerfile @@ -1,2 +1,7 @@ -FROM python -WORKDIR ~/ +FROM ubuntu:20.04 +WORKDIR / +RUN apt-get -y update +RUN DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends tzdata +RUN apt-get install -y python3 python3-dev git python3-pip python3-kivy python-is-python3 libgl1-mesa-dev build-essential +RUN ln -s $(which pip3) /usr/bin/pip +RUN pip install pymongo pandas numpy scipy scikit-learn matplotlib pylint kivy \ No newline at end of file diff --git a/.devcontainer/dev-dockerfile b/.devcontainer/dev-dockerfile new file mode 100644 index 00000000..74659d49 --- /dev/null +++ b/.devcontainer/dev-dockerfile @@ -0,0 +1,2 @@ +FROM titanscout2022/tra-analysis-base:latest +WORKDIR / \ No newline at end of file diff --git a/.devcontainer/devcontainer.json b/.devcontainer/devcontainer.json index a1f40089..3eb4364b 100644 --- a/.devcontainer/devcontainer.json +++ b/.devcontainer/devcontainer.json @@ -1,7 +1,7 @@ { "name": "TRA Analysis Development Environment", "build": { - "dockerfile": "Dockerfile", + "dockerfile": "dev-dockerfile", }, "settings": { "terminal.integrated.shell.linux": "/bin/bash", @@ -24,5 +24,5 @@ "ms-python.python", "waderyan.gitblame" ], - "postCreateCommand": "apt install vim -y ; pip install -r data-analysis/requirements.txt ; pip install -r analysis-master/requirements.txt ; pip install pylint ; pip install tra-analysis" -} \ No newline at end of file + "postCreateCommand": "/usr/bin/pip3 install -r ${containerWorkspaceFolder}/analysis-master/requirements.txt && /usr/bin/pip3 install --no-cache-dir pylint && /usr/bin/pip3 install pytest" + } \ No newline at end of file diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md new file mode 100644 index 00000000..4030f6fe --- /dev/null +++ b/.github/PULL_REQUEST_TEMPLATE.md @@ -0,0 +1,7 @@ +Fixes # + +## Proposed Changes + + - + - + - diff --git a/.github/workflows/ut-superscript.yml b/.github/workflows/ut-superscript.yml deleted file mode 100644 index fcd2b69f..00000000 --- a/.github/workflows/ut-superscript.yml +++ /dev/null @@ -1,38 +0,0 @@ -# This workflow will install Python dependencies, run tests and lint with a variety of Python versions -# For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions - -name: Superscript Unit Tests - -on: - push: - branches: [ master ] - pull_request: - branches: [ master ] - -jobs: - build: - - runs-on: ubuntu-latest - strategy: - matrix: - python-version: [3.7, 3.8] - - env: - working-directory: ./data-analysis/ - - steps: - - uses: actions/checkout@v2 - - name: Set up Python ${{ matrix.python-version }} - uses: actions/setup-python@v2 - with: - python-version: ${{ matrix.python-version }} - - name: Install dependencies - run: | - python -m pip install --upgrade pip - pip install pytest - if [ -f requirements.txt ]; then pip install -r requirements.txt; fi - working-directory: ${{ env.working-directory }} - - name: Test with pytest - run: | - pytest - working-directory: ${{ env.working-directory }} diff --git a/.gitignore b/.gitignore index 2545560b..6c766f6c 100644 --- a/.gitignore +++ b/.gitignore @@ -1,41 +1,9 @@ -benchmark_data.csv -data-analysis/keys/keytemp.json -data-analysis/__pycache__/analysis.cpython-37.pyc -apps/android/source/app/src/main/res/drawable-v24/uuh.png -apps/android/source/app/src/main/java/com/example/titanscouting/tits.java +/.vscode/ -data-analysis/analysis.cp37-win_amd64.pyd -data-analysis/analysis/analysis.c -data-analysis/analysis/analysis.cp37-win_amd64.pyd -data-analysis/analysis/build/temp.win-amd64-3.7/Release/analysis.cp37-win_amd64.exp -data-analysis/analysis/build/temp.win-amd64-3.7/Release/analysis.cp37-win_amd64.lib -data-analysis/analysis/build/temp.win-amd64-3.7/Release/analysis.obj -data-analysis/test.ipynb -data-analysis/.ipynb_checkpoints/test-checkpoint.ipynb -.vscode/settings.json -.vscode -data-analysis/arthur_pull.ipynb -data-analysis/keys.txt -data-analysis/check_for_new_matches.ipynb -data-analysis/test.ipynb -data-analysis/visualize_pit.ipynb -data-analysis/config/keys.config -analysis-master/analysis/__pycache__/ -analysis-master/analysis/metrics/__pycache__/ -data-analysis/__pycache__/ -analysis-master/analysis.egg-info/ -analysis-master/build/ -analysis-master/metrics/ -data-analysis/config-pop.json -data-analysis/__pycache__/ -analysis-master/__pycache__/ -analysis-master/.pytest_cache/ -data-analysis/.pytest_cache/ -data-analysis/test.py -analysis-master/tra_analysis.egg-info -analysis-master/tra_analysis/__pycache__ -analysis-master/tra_analysis/.ipynb_checkpoints -.pytest_cache -analysis-master/tra_analysis/metrics/__pycache__ -analysis-master/dist -data-analysis/config/ \ No newline at end of file +**/__pycache__/ +**/.pytest_cache/ +**/*.pyc + +**/build/ +**/*.egg-info/ +**/dist/ \ No newline at end of file diff --git a/README.md b/README.md index 6d0be0eb..b4936e71 100644 --- a/README.md +++ b/README.md @@ -42,7 +42,7 @@ tra-analysis operates like any other python package. Consult the [documentation] Although any modern 64 bit platform should be supported, the following platforms have been tested to be working: * AMD64 (Tested on Zen, Zen+, and Zen 2) -* Intel 64/x86_64/x64 (Tested on Kaby Lake) +* Intel 64/x86_64/x64 (Tested on Kaby Lake, Ice Lake) * ARM64 (Tested on Broadcom BCM2836 SoC, Broadcom BCM2711 SoC) The following OSes have been tested to be working: @@ -60,43 +60,11 @@ The following python versions are supported: # `data-analysis` -To facilitate data analysis of collected scouting data in a user firendly tool, we created the data-analysis application. At its core it uses the tra-analysis package to conduct any number of user selected tests on data collected from the TRA scouting app. It uploads these tests back to MongoDB where it can be viewed from the app at any time. - -The data-analysis application also uses the TRA API to interface with MongoDB and uses the TBA API to collect additional data (match win/loss). - -The application can be configured with a configuration tool or by editing the config.json directly. - -## Prerequisites - ---- - -Before installing and using data-analysis, make sure that you have installed the folowing prerequisites: -- A common operating system like **Windows** or (*most*) distributions of **Linux**. BSD may work but has not been tested nor is it reccomended. -- [Python](https://www.python.org/) version **3.6** or higher -- [Pip](https://pip.pypa.io/en/stable/) (installation instructions [here](https://pip.pypa.io/en/stable/installing/)) - -## Installing Requirements - ---- - -Once navigated to the data-analysis folder run `pip install -r requirements.txt` to install all of the required python libraries. - -## Scripts - ---- - -The data-analysis application is a collection of various scripts and one config file. For users, only the main application `superscript.py` and the config file `config.json` are important. - -To run the data-analysis application, navigate to the data-analysis folder once all requirements have been installed and run `python superscript.py`. If you encounter the error: - -`pymongo.errors.ConfigurationError: Empty host (or extra comma in host list).` - -don't worry, you may have just not configured the application correctly, but would otherwise work. Refer to [the documentation](https://titanscouting.github.io/analysis/data_analysis/Config) to learn how to configure data-analysis. +Data analysis has been separated into its own [repository](https://github.com/titanscouting/tra-data-analysis). # Contributing Read our included contributing guidelines (`CONTRIBUTING.md`) for more information and feel free to reach out to any current maintainer for more information. # Build Statuses -![Analysis Unit Tests](https://github.com/titanscout2022/red-alliance-analysis/workflows/Analysis%20Unit%20Tests/badge.svg) -![Superscript Unit Tests](https://github.com/titanscout2022/red-alliance-analysis/workflows/Superscript%20Unit%20Tests/badge.svg?branch=master) +![Analysis Unit Tests](https://github.com/titanscout2022/red-alliance-analysis/workflows/Analysis%20Unit%20Tests/badge.svg) \ No newline at end of file diff --git a/analysis-master/docker/Dockerfile b/analysis-master/docker/Dockerfile deleted file mode 100644 index aaa49e55..00000000 --- a/analysis-master/docker/Dockerfile +++ /dev/null @@ -1,5 +0,0 @@ -FROM python -WORKDIR ~/ -COPY ./ ./ -RUN pip install -r requirements.txt -CMD ["bash"] \ No newline at end of file diff --git a/analysis-master/docker/start-docker.sh b/analysis-master/docker/start-docker.sh deleted file mode 100644 index baf16097..00000000 --- a/analysis-master/docker/start-docker.sh +++ /dev/null @@ -1,3 +0,0 @@ -cd .. -docker build -t tra-analysis-amd64-dev -f docker/Dockerfile . -docker run -it tra-analysis-amd64-dev \ No newline at end of file diff --git a/analysis-master/requirements.txt b/analysis-master/requirements.txt index 1ecfd056..3d106798 100644 --- a/analysis-master/requirements.txt +++ b/analysis-master/requirements.txt @@ -1,6 +1,6 @@ -numba numpy scipy scikit-learn six -matplotlib \ No newline at end of file +matplotlib +pyparsing \ No newline at end of file diff --git a/analysis-master/setup.py b/analysis-master/setup.py index 9c9cbf28..26a22f93 100644 --- a/analysis-master/setup.py +++ b/analysis-master/setup.py @@ -1,4 +1,5 @@ import setuptools +import tra_analysis requirements = [] @@ -8,11 +9,11 @@ with open("requirements.txt", 'r') as file: setuptools.setup( name="tra_analysis", - version="2.1.0", + version=tra_analysis.__version__, author="The Titan Scouting Team", author_email="titanscout2022@gmail.com", description="Analysis package developed by Titan Scouting for The Red Alliance", - long_description="", + long_description="../README.md", long_description_content_type="text/markdown", url="https://github.com/titanscout2022/tr2022-strategy", packages=setuptools.find_packages(), @@ -21,6 +22,8 @@ setuptools.setup( classifiers=[ "Programming Language :: Python :: 3", "Operating System :: OS Independent", + "Topic :: Data Analysis" ], python_requires='>=3.6', + keywords="data analysis tools" ) \ No newline at end of file diff --git a/analysis-master/test_analysis.py b/analysis-master/test_analysis.py index d281b5ef..ebba8da5 100644 --- a/analysis-master/test_analysis.py +++ b/analysis-master/test_analysis.py @@ -1,35 +1,233 @@ -from tra_analysis import analysis as an -from tra_analysis import metrics -from tra_analysis import fits +import numpy as np +import sklearn +from sklearn import metrics + +from tra_analysis import Analysis as an +from tra_analysis import Array +from tra_analysis import ClassificationMetric +from tra_analysis import CorrelationTest +from tra_analysis import Fit +from tra_analysis import KNN +from tra_analysis import NaiveBayes +from tra_analysis import RandomForest +from tra_analysis import RegressionMetric +from tra_analysis import Sort +from tra_analysis import StatisticalTest +from tra_analysis import SVM + +from tra_analysis.equation.parser import BNF + +test_data_linear = [1, 3, 6, 7, 9] +test_data_linear2 = [2, 2, 5, 7, 13] +test_data_linear3 = [2, 5, 8, 6, 14] +test_data_array = Array(test_data_linear) + +x_data_circular = [] +y_data_circular = [] + +y_data_ccu = [1, 3, 7, 14, 21] +y_data_ccd = [1, 5, 7, 8.5, 8.66] + +test_data_scrambled = [-32, 34, 19, 72, -65, -11, -43, 6, 85, -17, -98, -26, 12, 20, 9, -92, -40, 98, -78, 17, -20, 49, 93, -27, -24, -66, 40, 84, 1, -64, -68, -25, -42, -46, -76, 43, -3, 30, -14, -34, -55, -13, 41, -30, 0, -61, 48, 23, 60, 87, 80, 77, 53, 73, 79, 24, -52, 82, 8, -44, 65, 47, -77, 94, 7, 37, -79, 36, -94, 91, 59, 10, 97, -38, -67, 83, 54, 31, -95, -63, 16, -45, 21, -12, 66, -48, -18, -96, -90, -21, -83, -74, 39, 64, 69, -97, 13, 55, 27, -39] +test_data_sorted = [-98, -97, -96, -95, -94, -92, -90, -83, -79, -78, -77, -76, -74, -68, -67, -66, -65, -64, -63, -61, -55, -52, -48, -46, -45, -44, -43, -42, -40, -39, -38, -34, -32, -30, -27, -26, -25, -24, -21, -20, -18, -17, -14, -13, -12, -11, -3, 0, 1, 6, 7, 8, 9, 10, 12, 13, 16, 17, 19, 20, 21, 23, 24, 27, 30, 31, 34, 36, 37, 39, 40, 41, 43, 47, 48, 49, 53, 54, 55, 59, 60, 64, 65, 66, 69, 72, 73, 77, 79, 80, 82, 83, 84, 85, 87, 91, 93, 94, 97, 98] + +test_data_2D_pairs = np.array([[-1, -1], [-2, -1], [1, 1], [2, 1]]) +test_data_2D_positive = np.array([[23, 51], [21, 32], [15, 25], [17, 31]]) +test_output = np.array([1, 3, 4, 5]) +test_labels_2D_pairs = np.array([1, 1, 2, 2]) +validation_data_2D_pairs = np.array([[-0.8, -1], [0.8, 1.2]]) +validation_labels_2D_pairs = np.array([1, 2]) + +def test_basicstats(): -def test_(): - test_data_linear = [1, 3, 6, 7, 9] - x_data_circular = [] - y_data_circular = [] - y_data_ccu = [1, 3, 7, 14, 21] - y_data_ccd = [1, 5, 7, 8.5, 8.66] - test_data_scrambled = [-32, 34, 19, 72, -65, -11, -43, 6, 85, -17, -98, -26, 12, 20, 9, -92, -40, 98, -78, 17, -20, 49, 93, -27, -24, -66, 40, 84, 1, -64, -68, -25, -42, -46, -76, 43, -3, 30, -14, -34, -55, -13, 41, -30, 0, -61, 48, 23, 60, 87, 80, 77, 53, 73, 79, 24, -52, 82, 8, -44, 65, 47, -77, 94, 7, 37, -79, 36, -94, 91, 59, 10, 97, -38, -67, 83, 54, 31, -95, -63, 16, -45, 21, -12, 66, -48, -18, -96, -90, -21, -83, -74, 39, 64, 69, -97, 13, 55, 27, -39] - test_data_sorted = [-98, -97, -96, -95, -94, -92, -90, -83, -79, -78, -77, -76, -74, -68, -67, -66, -65, -64, -63, -61, -55, -52, -48, -46, -45, -44, -43, -42, -40, -39, -38, -34, -32, -30, -27, -26, -25, -24, -21, -20, -18, -17, -14, -13, -12, -11, -3, 0, 1, 6, 7, 8, 9, 10, 12, 13, 16, 17, 19, 20, 21, 23, 24, 27, 30, 31, 34, 36, 37, 39, 40, 41, 43, 47, 48, 49, 53, 54, 55, 59, 60, 64, 65, 66, 69, 72, 73, 77, 79, 80, 82, 83, 84, 85, 87, 91, 93, 94, 97, 98] assert an.basic_stats(test_data_linear) == {"mean": 5.2, "median": 6.0, "standard-deviation": 2.85657137141714, "variance": 8.16, "minimum": 1.0, "maximum": 9.0} assert an.z_score(3.2, 6, 1.5) == -1.8666666666666665 assert an.z_normalize([test_data_linear], 1).tolist() == [[0.07537783614444091, 0.22613350843332272, 0.45226701686664544, 0.5276448530110863, 0.6784005252999682]] + +def test_regression(): + assert all(isinstance(item, str) for item in an.regression(test_data_linear, y_data_ccu, ["lin"])) == True #assert all(isinstance(item, str) for item in an.regression(test_data_linear, y_data_ccd, ["log"])) == True #assert all(isinstance(item, str) for item in an.regression(test_data_linear, y_data_ccu, ["exp"])) == True #assert all(isinstance(item, str) for item in an.regression(test_data_linear, y_data_ccu, ["ply"])) == True #assert all(isinstance(item, str) for item in an.regression(test_data_linear, y_data_ccd, ["sig"])) == True + +def test_metrics(): + assert an.Metric().elo(1500, 1500, [1, 0], 400, 24) == 1512.0 assert an.Metric().glicko2(1500, 250, 0.06, [1500, 1400], [250, 240], [1, 0]) == (1478.864307445517, 195.99122679202452, 0.05999602937563585) #assert an.Metric().trueskill([[(25, 8.33), (24, 8.25), (32, 7.5)], [(25, 8.33), (25, 8.33), (21, 6.5)]], [1, 0]) == [(metrics.trueskill.Rating(mu=21.346, sigma=7.875), metrics.trueskill.Rating(mu=20.415, sigma=7.808), metrics.trueskill.Rating(mu=29.037, sigma=7.170)), (metrics.trueskill.Rating(mu=28.654, sigma=7.875), metrics.trueskill.Rating(mu=28.654, sigma=7.875), metrics.trueskill.Rating(mu=23.225, sigma=6.287))] - assert all(a == b for a, b in zip(an.Sort().quicksort(test_data_scrambled), test_data_sorted)) - assert all(a == b for a, b in zip(an.Sort().mergesort(test_data_scrambled), test_data_sorted)) - assert all(a == b for a, b in zip(an.Sort().introsort(test_data_scrambled), test_data_sorted)) - assert all(a == b for a, b in zip(an.Sort().heapsort(test_data_scrambled), test_data_sorted)) - assert all(a == b for a, b in zip(an.Sort().insertionsort(test_data_scrambled), test_data_sorted)) - assert all(a == b for a, b in zip(an.Sort().timsort(test_data_scrambled), test_data_sorted)) - assert all(a == b for a, b in zip(an.Sort().selectionsort(test_data_scrambled), test_data_sorted)) - assert all(a == b for a, b in zip(an.Sort().shellsort(test_data_scrambled), test_data_sorted)) - assert all(a == b for a, b in zip(an.Sort().bubblesort(test_data_scrambled), test_data_sorted)) - assert all(a == b for a, b in zip(an.Sort().cyclesort(test_data_scrambled), test_data_sorted)) - assert all(a == b for a, b in zip(an.Sort().cocktailsort(test_data_scrambled), test_data_sorted)) - assert fits.CircleFit(x=[0,0,-1,1], y=[1, -1, 0, 0]).LSC() == (0.0, 0.0, 1.0, 0.0) \ No newline at end of file + +def test_array(): + + assert test_data_array.elementwise_mean() == 5.2 + assert test_data_array.elementwise_median() == 6.0 + assert test_data_array.elementwise_stdev() == 2.85657137141714 + assert test_data_array.elementwise_variance() == 8.16 + assert test_data_array.elementwise_npmin() == 1 + assert test_data_array.elementwise_npmax() == 9 + assert test_data_array.elementwise_stats() == (5.2, 6.0, 2.85657137141714, 8.16, 1, 9) + + for i in range(len(test_data_array)): + assert test_data_array[i] == test_data_linear[i] + + test_data_array[0] = 100 + expected = [100, 3, 6, 7, 9] + for i in range(len(test_data_array)): + assert test_data_array[i] == expected[i] + +def test_classifmetric(): + + classif_metric = ClassificationMetric(test_data_linear2, test_data_linear) + assert classif_metric[0].all() == metrics.confusion_matrix(test_data_linear, test_data_linear2).all() + assert classif_metric[1] == metrics.classification_report(test_data_linear, test_data_linear2) + +def test_correlationtest(): + + assert all(np.isclose(list(CorrelationTest.anova_oneway(test_data_linear, test_data_linear2).values()), [0.05825242718446602, 0.8153507906592907], rtol=1e-10)) + assert all(np.isclose(list(CorrelationTest.pearson(test_data_linear, test_data_linear2).values()), [0.9153061540753287, 0.02920895440940868], rtol=1e-10)) + assert all(np.isclose(list(CorrelationTest.spearman(test_data_linear, test_data_linear2).values()), [0.9746794344808964, 0.004818230468198537], rtol=1e-10)) + assert all(np.isclose(list(CorrelationTest.point_biserial(test_data_linear, test_data_linear2).values()), [0.9153061540753287, 0.02920895440940868], rtol=1e-10)) + assert all(np.isclose(list(CorrelationTest.kendall(test_data_linear, test_data_linear2).values()), [0.9486832980505137, 0.022977401503206086], rtol=1e-10)) + assert all(np.isclose(list(CorrelationTest.kendall_weighted(test_data_linear, test_data_linear2).values()), [0.9750538072369643, np.nan], rtol=1e-10, equal_nan=True)) + +def test_fit(): + + assert Fit.CircleFit(x=[0,0,-1,1], y=[1, -1, 0, 0]).LSC() == (0.0, 0.0, 1.0, 0.0) + +def test_knn(): + + model, metric = KNN.knn_classifier(test_data_2D_pairs, test_labels_2D_pairs, 2) + assert isinstance(model, sklearn.neighbors.KNeighborsClassifier) + assert np.array([[0,0], [2,0]]).all() == metric[0].all() + assert ' precision recall f1-score support\n\n 1 0.00 0.00 0.00 0.0\n 2 0.00 0.00 0.00 2.0\n\n accuracy 0.00 2.0\n macro avg 0.00 0.00 0.00 2.0\nweighted avg 0.00 0.00 0.00 2.0\n' == metric[1] + model, metric = KNN.knn_regressor(test_data_2D_pairs, test_output, 2) + assert isinstance(model, sklearn.neighbors.KNeighborsRegressor) + assert (-25.0, 6.5, 2.5495097567963922) == metric + +def test_naivebayes(): + + model, metric = NaiveBayes.gaussian(test_data_2D_pairs, test_labels_2D_pairs) + assert isinstance(model, sklearn.naive_bayes.GaussianNB) + assert metric[0].all() == np.array([[0, 0], [2, 0]]).all() + + model, metric = NaiveBayes.multinomial(test_data_2D_positive, test_labels_2D_pairs) + assert isinstance(model, sklearn.naive_bayes.MultinomialNB) + assert metric[0].all() == np.array([[0, 0], [2, 0]]).all() + + model, metric = NaiveBayes.bernoulli(test_data_2D_pairs, test_labels_2D_pairs) + assert isinstance(model, sklearn.naive_bayes.BernoulliNB) + assert metric[0].all() == np.array([[0, 0], [2, 0]]).all() + + model, metric = NaiveBayes.complement(test_data_2D_positive, test_labels_2D_pairs) + assert isinstance(model, sklearn.naive_bayes.ComplementNB) + assert metric[0].all() == np.array([[0, 0], [2, 0]]).all() + +def test_randomforest(): + + model, metric = RandomForest.random_forest_classifier(test_data_2D_pairs, test_labels_2D_pairs, 0.3, 2) + assert isinstance(model, sklearn.ensemble.RandomForestClassifier) + assert metric[0].all() == np.array([[0, 0], [2, 0]]).all() + model, metric = RandomForest.random_forest_regressor(test_data_2D_pairs, test_labels_2D_pairs, 0.3, 2) + assert isinstance(model, sklearn.ensemble.RandomForestRegressor) + assert metric == (0.0, 1.0, 1.0) + +def test_regressionmetric(): + + assert RegressionMetric(test_data_linear, test_data_linear2)== (0.7705314009661837, 3.8, 1.9493588689617927) + +def test_sort(): + sorts = [Sort.quicksort, Sort.mergesort, Sort.heapsort, Sort.introsort, Sort.insertionsort, Sort.timsort, Sort.selectionsort, Sort.shellsort, Sort.bubblesort, Sort.cyclesort, Sort.cocktailsort] + for sort in sorts: + assert all(a == b for a, b in zip(sort(test_data_scrambled), test_data_sorted)) + +def test_statisticaltest(): + + #print(StatisticalTest.tukey_multicomparison([test_data_linear, test_data_linear2, test_data_linear3])) + assert StatisticalTest.tukey_multicomparison([test_data_linear, test_data_linear2, test_data_linear3]) == \ + {'group 1 and group 2': [0.32571517201527916, False], 'group 1 and group 3': [0.977145516045838, False], 'group 2 and group 3': [0.6514303440305589, False]} + #assert all(np.isclose([i[0] for i in list(StatisticalTest.tukey_multicomparison([test_data_linear, test_data_linear2, test_data_linear3]).values], + # [0.32571517201527916, 0.977145516045838, 0.6514303440305589])) + #assert [i[1] for i in StatisticalTest.tukey_multicomparison([test_data_linear, test_data_linear2, test_data_linear3]).values] == \ + # [False, False, False] + +def test_svm(): + + data = test_data_2D_pairs + labels = test_labels_2D_pairs + test_data = validation_data_2D_pairs + test_labels = validation_labels_2D_pairs + + lin_kernel = SVM.PrebuiltKernel.Linear() + #ply_kernel = SVM.PrebuiltKernel.Polynomial(3, 0) + rbf_kernel = SVM.PrebuiltKernel.RBF('scale') + sig_kernel = SVM.PrebuiltKernel.Sigmoid(0) + + lin_kernel = SVM.fit(lin_kernel, data, labels) + #ply_kernel = SVM.fit(ply_kernel, data, labels) + rbf_kernel = SVM.fit(rbf_kernel, data, labels) + sig_kernel = SVM.fit(sig_kernel, data, labels) + + for i in range(len(test_data)): + + assert lin_kernel.predict([test_data[i]]).tolist() == [test_labels[i]] + + #for i in range(len(test_data)): + + # assert ply_kernel.predict([test_data[i]]).tolist() == [test_labels[i]] + + for i in range(len(test_data)): + + assert rbf_kernel.predict([test_data[i]]).tolist() == [test_labels[i]] + + for i in range(len(test_data)): + + assert sig_kernel.predict([test_data[i]]).tolist() == [test_labels[i]] + +def test_equation(): + + parser = BNF() + correctParse = { + "9": 9.0, + "-9": -9.0, + "--9": 9.0, + "-E": -2.718281828459045, + "9 + 3 + 6": 18.0, + "9 + 3 / 11": 9.272727272727273, + "(9 + 3)": 12.0, + "(9+3) / 11": 1.0909090909090908, + "9 - 12 - 6": -9.0, + "9 - (12 - 6)": 3.0, + "2*3.14159": 6.28318, + "3.1415926535*3.1415926535 / 10": 0.9869604400525172, + "PI * PI / 10": 0.9869604401089358, + "PI*PI/10": 0.9869604401089358, + "PI^2": 9.869604401089358, + "round(PI^2)": 10, + "6.02E23 * 8.048": 4.844896e+24, + "e / 3": 0.9060939428196817, + "sin(PI/2)": 1.0, + "10+sin(PI/4)^2": 10.5, + "trunc(E)": 2, + "trunc(-E)": -2, + "round(E)": 3, + "round(-E)": -3, + "E^PI": 23.140692632779263, + "exp(0)": 1.0, + "exp(1)": 2.718281828459045, + "2^3^2": 512.0, + "(2^3)^2": 64.0, + "2^3+2": 10.0, + "2^3+5": 13.0, + "2^9": 512.0, + "sgn(-2)": -1, + "sgn(0)": 0, + "sgn(0.1)": 1, + "sgn(cos(PI/4))": 1, + "sgn(cos(PI/2))": 0, + "sgn(cos(PI*3/4))": -1, + "+(sgn(cos(PI/4)))": 1, + "-(sgn(cos(PI/4)))": -1, + } + for key in list(correctParse.keys()): + assert parser.eval(key) == correctParse[key] \ No newline at end of file diff --git a/analysis-master/tra_analysis/.ipynb_checkpoints/equation-checkpoint.ipynb b/analysis-master/tra_analysis/.ipynb_checkpoints/equation-checkpoint.ipynb deleted file mode 100644 index 9245ab26..00000000 --- a/analysis-master/tra_analysis/.ipynb_checkpoints/equation-checkpoint.ipynb +++ /dev/null @@ -1,35 +0,0 @@ -{ - "cells": [ - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "string = \"3+4+5\"\n", - "re.sub(\"\\d+[+]{1}\\d+\", string, sum([int(i) for i in re.split(\"[+]{1}\", re.search(\"\\d+[+]{1}\\d+\", string).group())]))" - ] - } - ], - "metadata": { - "kernelspec": { - "display_name": "Python 3", - "language": "python", - "name": "python3" - }, - "language_info": { - "codemirror_mode": { - "name": "ipython", - "version": 3 - }, - "file_extension": ".py", - "mimetype": "text/x-python", - "name": "python", - "nbconvert_exporter": "python", - "pygments_lexer": "ipython3", - "version": "3.7.6" - } - }, - "nbformat": 4, - "nbformat_minor": 4 -} diff --git a/analysis-master/tra_analysis/Analysis.py b/analysis-master/tra_analysis/Analysis.py new file mode 100644 index 00000000..7bf68c8d --- /dev/null +++ b/analysis-master/tra_analysis/Analysis.py @@ -0,0 +1,628 @@ +# Titan Robotics Team 2022: Analysis Module +# Written by Arthur Lu +# Notes: +# this should be imported as a python module using 'from tra_analysis import Analysis' +# this should be included in the local directory or environment variable +# this module has been optimized for multhreaded computing +# current benchmark of optimization: 1.33 times faster +# setup: + +__version__ = "3.0.2" + +# changelog should be viewed using print(analysis.__changelog__) +__changelog__ = """changelog: + 3.0.2: + - fixed __all__ + 3.0.1: + - removed numba dependency and calls + 3.0.0: + - exported several submodules to their own files while preserving backwards compatibility: + - Array + - ClassificationMetric + - CorrelationTest + - KNN + - NaiveBayes + - RandomForest + - RegressionMetric + - Sort + - StatisticalTest + - SVM + - note: above listed submodules will not be supported in the future + - future changes to all submodules will be held in their respective changelogs + - future changes altering the parent package will be held in the __changelog__ of the parent package (in __init__.py) + - changed reference to module name to Analysis + 2.3.1: + - fixed bugs in Array class + 2.3.0: + - overhauled Array class + 2.2.3: + - fixed spelling of RandomForest + - made n_neighbors required for KNN + - made n_classifiers required for SVM + 2.2.2: + - fixed 2.2.1 changelog entry + - changed regression to return dictionary + 2.2.1: + - changed all references to parent package analysis to tra_analysis + 2.2.0: + - added Sort class + - added several array sorting functions to Sort class including: + - quick sort + - merge sort + - intro(spective) sort + - heap sort + - insertion sort + - tim sort + - selection sort + - bubble sort + - cycle sort + - cocktail sort + - tested all sorting algorithms with both lists and numpy arrays + - depreciated sort function from Array class + - added warnings as an import + 2.1.4: + - added sort and search functions to Array class + 2.1.3: + - changed output of basic_stats and histo_analysis to libraries + - fixed __all__ + 2.1.2: + - renamed ArrayTest class to Array + 2.1.1: + - added add, mul, neg, and inv functions to ArrayTest class + - added normalize function to ArrayTest class + - added dot and cross functions to ArrayTest class + 2.1.0: + - added ArrayTest class + - added elementwise mean, median, standard deviation, variance, min, max functions to ArrayTest class + - added elementwise_stats to ArrayTest which encapsulates elementwise statistics + - appended to __all__ to reflect changes + 2.0.6: + - renamed func functions in regression to lin, log, exp, and sig + 2.0.5: + - moved random_forrest_regressor and random_forrest_classifier to RandomForrest class + - renamed Metrics to Metric + - renamed RegressionMetrics to RegressionMetric + - renamed ClassificationMetrics to ClassificationMetric + - renamed CorrelationTests to CorrelationTest + - renamed StatisticalTests to StatisticalTest + - reflected rafactoring to all mentions of above classes/functions + 2.0.4: + - fixed __all__ to reflected the correct functions and classes + - fixed CorrelationTests and StatisticalTests class functions to require self invocation + - added missing math import + - fixed KNN class functions to require self invocation + - fixed Metrics class functions to require self invocation + - various spelling fixes in CorrelationTests and StatisticalTests + 2.0.3: + - bug fixes with CorrelationTests and StatisticalTests + - moved glicko2 and trueskill to the metrics subpackage + - moved elo to a new metrics subpackage + 2.0.2: + - fixed docs + 2.0.1: + - fixed docs + 2.0.0: + - cleaned up wild card imports with scipy and sklearn + - added CorrelationTests class + - added StatisticalTests class + - added several correlation tests to CorrelationTests + - added several statistical tests to StatisticalTests + 1.13.9: + - moved elo, glicko2, trueskill functions under class Metrics + 1.13.8: + - moved Glicko2 to a seperate package + 1.13.7: + - fixed bug with trueskill + 1.13.6: + - cleaned up imports + 1.13.5: + - cleaned up package + 1.13.4: + - small fixes to regression to improve performance + 1.13.3: + - filtered nans from regression + 1.13.2: + - removed torch requirement, and moved Regression back to regression.py + 1.13.1: + - bug fix with linear regression not returning a proper value + - cleaned up regression + - fixed bug with polynomial regressions + 1.13.0: + - fixed all regressions to now properly work + 1.12.6: + - fixed bg with a division by zero in histo_analysis + 1.12.5: + - fixed numba issues by removing numba from elo, glicko2 and trueskill + 1.12.4: + - renamed gliko to glicko + 1.12.3: + - removed depreciated code + 1.12.2: + - removed team first time trueskill instantiation in favor of integration in superscript.py + 1.12.1: + - improved readibility of regression outputs by stripping tensor data + - used map with lambda to acheive the improved readibility + - lost numba jit support with regression, and generated_jit hangs at execution + - TODO: reimplement correct numba integration in regression + 1.12.0: + - temporarily fixed polynomial regressions by using sklearn's PolynomialFeatures + 1.11.010: + - alphabeticaly ordered import lists + 1.11.9: + - bug fixes + 1.11.8: + - bug fixes + 1.11.7: + - bug fixes + 1.11.6: + - tested min and max + - bug fixes + 1.11.5: + - added min and max in basic_stats + 1.11.4: + - bug fixes + 1.11.3: + - bug fixes + 1.11.2: + - consolidated metrics + - fixed __all__ + 1.11.1: + - added test/train split to RandomForestClassifier and RandomForestRegressor + 1.11.0: + - added RandomForestClassifier and RandomForestRegressor + - note: untested + 1.10.0: + - added numba.jit to remaining functions + 1.9.2: + - kernelized PCA and KNN + 1.9.1: + - fixed bugs with SVM and NaiveBayes + 1.9.0: + - added SVM class, subclasses, and functions + - note: untested + 1.8.0: + - added NaiveBayes classification engine + - note: untested + 1.7.0: + - added knn() + - added confusion matrix to decisiontree() + 1.6.2: + - changed layout of __changelog to be vscode friendly + 1.6.1: + - added additional hyperparameters to decisiontree() + 1.6.0: + - fixed __version__ + - fixed __all__ order + - added decisiontree() + 1.5.3: + - added pca + 1.5.2: + - reduced import list + - added kmeans clustering engine + 1.5.1: + - simplified regression by using .to(device) + 1.5.0: + - added polynomial regression to regression(); untested + 1.4.0: + - added trueskill() + 1.3.2: + - renamed regression class to Regression, regression_engine() to regression gliko2_engine class to Gliko2 + 1.3.1: + - changed glicko2() to return tuple instead of array + 1.3.0: + - added glicko2_engine class and glicko() + - verified glicko2() accuracy + 1.2.3: + - fixed elo() + 1.2.2: + - added elo() + - elo() has bugs to be fixed + 1.2.1: + - readded regrression import + 1.2.0: + - integrated regression.py as regression class + - removed regression import + - fixed metadata for regression class + - fixed metadata for analysis class + 1.1.1: + - regression_engine() bug fixes, now actaully regresses + 1.1.0: + - added regression_engine() + - added all regressions except polynomial + 1.0.7: + - updated _init_device() + 1.0.6: + - removed useless try statements + 1.0.5: + - removed impossible outcomes + 1.0.4: + - added performance metrics (r^2, mse, rms) + 1.0.3: + - resolved nopython mode for mean, median, stdev, variance + 1.0.2: + - snapped (removed) majority of uneeded imports + - forced object mode (bad) on all jit + - TODO: stop numba complaining about not being able to compile in nopython mode + 1.0.1: + - removed from sklearn import * to resolve uneeded wildcard imports + 1.0.0: + - removed c_entities,nc_entities,obstacles,objectives from __all__ + - applied numba.jit to all functions + - depreciated and removed stdev_z_split + - cleaned up histo_analysis to include numpy and numba.jit optimizations + - depreciated and removed all regression functions in favor of future pytorch optimizer + - depreciated and removed all nonessential functions (basic_analysis, benchmark, strip_data) + - optimized z_normalize using sklearn.preprocessing.normalize + - TODO: implement kernel/function based pytorch regression optimizer + 0.9.0: + - refactored + - numpyed everything + - removed stats in favor of numpy functions + 0.8.5: + - minor fixes + 0.8.4: + - removed a few unused dependencies + 0.8.3: + - added p_value function + 0.8.2: + - updated __all__ correctly to contain changes made in v 0.8.0 and v 0.8.1 + 0.8.1: + - refactors + - bugfixes + 0.8.0: + - depreciated histo_analysis_old + - depreciated debug + - altered basic_analysis to take array data instead of filepath + - refactor + - optimization + 0.7.2: + - bug fixes + 0.7.1: + - bug fixes + 0.7.0: + - added tanh_regression (logistical regression) + - bug fixes + 0.6.5: + - added z_normalize function to normalize dataset + - bug fixes + 0.6.4: + - bug fixes + 0.6.3: + - bug fixes + 0.6.2: + - bug fixes + 0.6.1: + - corrected __all__ to contain all of the functions + 0.6.0: + - added calc_overfit, which calculates two measures of overfit, error and performance + - added calculating overfit to optimize_regression + 0.5.0: + - added optimize_regression function, which is a sample function to find the optimal regressions + - optimize_regression function filters out some overfit funtions (functions with r^2 = 1) + - planned addition: overfit detection in the optimize_regression function + 0.4.2: + - added __changelog__ + - updated debug function with log and exponential regressions + 0.4.1: + - added log regressions + - added exponential regressions + - added log_regression and exp_regression to __all__ + 0.3.8: + - added debug function to further consolidate functions + 0.3.7: + - added builtin benchmark function + - added builtin random (linear) data generation function + - added device initialization (_init_device) + 0.3.6: + - reorganized the imports list to be in alphabetical order + - added search and regurgitate functions to c_entities, nc_entities, obstacles, objectives + 0.3.5: + - major bug fixes + - updated historical analysis + - depreciated old historical analysis + 0.3.4: + - added __version__, __author__, __all__ + - added polynomial regression + - added root mean squared function + - added r squared function + 0.3.3: + - bug fixes + - added c_entities + 0.3.2: + - bug fixes + - added nc_entities, obstacles, objectives + - consolidated statistics.py to analysis.py + 0.3.1: + - compiled 1d, column, and row basic stats into basic stats function + 0.3.0: + - added historical analysis function + 0.2.x: + - added z score test + 0.1.x: + - major bug fixes + 0.0.x: + - added loading csv + - added 1d, column, row basic stats +""" + +__author__ = ( + "Arthur Lu ", +) + +__all__ = [ + 'load_csv', + 'basic_stats', + 'z_score', + 'z_normalize', + 'histo_analysis', + 'regression', + 'Metric', + 'kmeans', + 'pca', + 'decisiontree', + # all statistics functions left out due to integration in other functions +] + +# now back to your regularly scheduled programming: + +# imports (now in alphabetical order! v 0.3.006): + +import csv +from tra_analysis.metrics import elo as Elo +from tra_analysis.metrics import glicko2 as Glicko2 +import math +import numpy as np +import scipy +from scipy import optimize, stats +import sklearn +from sklearn import preprocessing, pipeline, linear_model, metrics, cluster, decomposition, tree, neighbors, naive_bayes, svm, model_selection, ensemble +from tra_analysis.metrics import trueskill as Trueskill +import warnings + +# import submodules + +from .Array import Array +from .ClassificationMetric import ClassificationMetric +from .CorrelationTest_obj import CorrelationTest +from .KNN_obj import KNN +from .NaiveBayes_obj import NaiveBayes +from .RandomForest_obj import RandomForest +from .RegressionMetric import RegressionMetric +from .Sort_obj import Sort +from .StatisticalTest_obj import StatisticalTest +from . import SVM + +class error(ValueError): + pass + +def load_csv(filepath): + with open(filepath, newline='') as csvfile: + file_array = np.array(list(csv.reader(csvfile))) + csvfile.close() + return file_array + +# expects 1d array +def basic_stats(data): + + data_t = np.array(data).astype(float) + + _mean = mean(data_t) + _median = median(data_t) + _stdev = stdev(data_t) + _variance = variance(data_t) + _min = npmin(data_t) + _max = npmax(data_t) + + return {"mean": _mean, "median": _median, "standard-deviation": _stdev, "variance": _variance, "minimum": _min, "maximum": _max} + +# returns z score with inputs of point, mean and standard deviation of spread +def z_score(point, mean, stdev): + score = (point - mean) / stdev + + return score + +# expects 2d array, normalizes across all axes +def z_normalize(array, *args): + + array = np.array(array) + for arg in args: + array = sklearn.preprocessing.normalize(array, axis = arg) + + return array + +# expects 2d array of [x,y] +def histo_analysis(hist_data): + + if len(hist_data[0]) > 2: + + hist_data = np.array(hist_data) + derivative = np.array(len(hist_data) - 1, dtype = float) + t = np.diff(hist_data) + derivative = t[1] / t[0] + np.sort(derivative) + + return {"mean": basic_stats(derivative)["mean"], "deviation": basic_stats(derivative)["standard-deviation"]} + + else: + + return None + +def regression(inputs, outputs, args): # inputs, outputs expects N-D array + + X = np.array(inputs) + y = np.array(outputs) + + regressions = {} + + if 'lin' in args: # formula: ax + b + + try: + + def lin(x, a, b): + + return a * x + b + + popt, pcov = scipy.optimize.curve_fit(lin, X, y) + + coeffs = popt.flatten().tolist() + regressions["lin"] = (str(coeffs[0]) + "*x+" + str(coeffs[1])) + + except Exception as e: + + pass + + if 'log' in args: # formula: a log (b(x + c)) + d + + try: + + def log(x, a, b, c, d): + + return a * np.log(b*(x + c)) + d + + popt, pcov = scipy.optimize.curve_fit(log, X, y) + + coeffs = popt.flatten().tolist() + regressions["log"] = (str(coeffs[0]) + "*log(" + str(coeffs[1]) + "*(x+" + str(coeffs[2]) + "))+" + str(coeffs[3])) + + except Exception as e: + + pass + + if 'exp' in args: # formula: a e ^ (b(x + c)) + d + + try: + + def exp(x, a, b, c, d): + + return a * np.exp(b*(x + c)) + d + + popt, pcov = scipy.optimize.curve_fit(exp, X, y) + + coeffs = popt.flatten().tolist() + regressions["exp"] = (str(coeffs[0]) + "*e^(" + str(coeffs[1]) + "*(x+" + str(coeffs[2]) + "))+" + str(coeffs[3])) + + except Exception as e: + + pass + + if 'ply' in args: # formula: a + bx^1 + cx^2 + dx^3 + ... + + inputs = np.array([inputs]) + outputs = np.array([outputs]) + + plys = {} + limit = len(outputs[0]) + + for i in range(2, limit): + + model = sklearn.preprocessing.PolynomialFeatures(degree = i) + model = sklearn.pipeline.make_pipeline(model, sklearn.linear_model.LinearRegression()) + model = model.fit(np.rot90(inputs), np.rot90(outputs)) + + params = model.steps[1][1].intercept_.tolist() + params = np.append(params, model.steps[1][1].coef_[0].tolist()[1::]) + params = params.flatten().tolist() + + temp = "" + counter = 0 + for param in params: + temp += "(" + str(param) + "*x^" + str(counter) + ")" + counter += 1 + plys["x^" + str(i)] = (temp) + + regressions["ply"] = (plys) + + if 'sig' in args: # formula: a tanh (b(x + c)) + d + + try: + + def sig(x, a, b, c, d): + + return a * np.tanh(b*(x + c)) + d + + popt, pcov = scipy.optimize.curve_fit(sig, X, y) + + coeffs = popt.flatten().tolist() + regressions["sig"] = (str(coeffs[0]) + "*tanh(" + str(coeffs[1]) + "*(x+" + str(coeffs[2]) + "))+" + str(coeffs[3])) + + except Exception as e: + + pass + + return regressions + +class Metric: + + def elo(self, starting_score, opposing_score, observed, N, K): + + return Elo.calculate(starting_score, opposing_score, observed, N, K) + + def glicko2(self, starting_score, starting_rd, starting_vol, opposing_score, opposing_rd, observations): + + player = Glicko2.Glicko2(rating = starting_score, rd = starting_rd, vol = starting_vol) + + player.update_player([x for x in opposing_score], [x for x in opposing_rd], observations) + + return (player.rating, player.rd, player.vol) + + def trueskill(self, teams_data, observations): # teams_data is array of array of tuples ie. [[(mu, sigma), (mu, sigma), (mu, sigma)], [(mu, sigma), (mu, sigma), (mu, sigma)]] + + team_ratings = [] + + for team in teams_data: + team_temp = () + for player in team: + player = Trueskill.Rating(player[0], player[1]) + team_temp = team_temp + (player,) + team_ratings.append(team_temp) + + return Trueskill.rate(team_ratings, ranks=observations) + +def mean(data): + + return np.mean(data) + +def median(data): + + return np.median(data) + +def stdev(data): + + return np.std(data) + +def variance(data): + + return np.var(data) + +def npmin(data): + + return np.amin(data) + +def npmax(data): + + return np.amax(data) + +def kmeans(data, n_clusters=8, init="k-means++", n_init=10, max_iter=300, tol=0.0001, precompute_distances="auto", verbose=0, random_state=None, copy_x=True, n_jobs=None, algorithm="auto"): + + kernel = sklearn.cluster.KMeans(n_clusters = n_clusters, init = init, n_init = n_init, max_iter = max_iter, tol = tol, precompute_distances = precompute_distances, verbose = verbose, random_state = random_state, copy_x = copy_x, n_jobs = n_jobs, algorithm = algorithm) + kernel.fit(data) + predictions = kernel.predict(data) + centers = kernel.cluster_centers_ + + return centers, predictions + +def pca(data, n_components = None, copy = True, whiten = False, svd_solver = "auto", tol = 0.0, iterated_power = "auto", random_state = None): + + kernel = sklearn.decomposition.PCA(n_components = n_components, copy = copy, whiten = whiten, svd_solver = svd_solver, tol = tol, iterated_power = iterated_power, random_state = random_state) + + return kernel.fit_transform(data) + +def decisiontree(data, labels, test_size = 0.3, criterion = "gini", splitter = "default", max_depth = None): #expects *2d data and 1d labels + + data_train, data_test, labels_train, labels_test = sklearn.model_selection.train_test_split(data, labels, test_size=test_size, random_state=1) + model = sklearn.tree.DecisionTreeClassifier(criterion = criterion, splitter = splitter, max_depth = max_depth) + model = model.fit(data_train,labels_train) + predictions = model.predict(data_test) + metrics = ClassificationMetric(predictions, labels_test) + + return model, metrics \ No newline at end of file diff --git a/analysis-master/tra_analysis/Array.py b/analysis-master/tra_analysis/Array.py new file mode 100644 index 00000000..1699c3c4 --- /dev/null +++ b/analysis-master/tra_analysis/Array.py @@ -0,0 +1,164 @@ +# Titan Robotics Team 2022: Array submodule +# Written by Arthur Lu +# Notes: +# this should be imported as a python module using 'from tra_analysis import Array' +# setup: + +__version__ = "1.0.3" + +__changelog__ = """changelog: + 1.0.3: + - fixed __all__ + 1.0.2: + - fixed several implementation bugs with magic methods + 1.0.1: + - removed search and __search functions + 1.0.0: + - ported analysis.Array() here +""" + +__author__ = ( + "Arthur Lu ", +) + +__all__ = [ + "Array", +] + +import numpy as np +import warnings + +class Array(): # tests on nd arrays independent of basic_stats + + def __init__(self, narray): + + self.array = np.array(narray) + + def __str__(self): + + return str(self.array) + + def __repr__(self): + + return str(self.array) + + def elementwise_mean(self, axis = 0): # expects arrays that are size normalized + + return np.mean(self.array, axis = axis) + + def elementwise_median(self, axis = 0): + + return np.median(self.array, axis = axis) + + def elementwise_stdev(self, axis = 0): + + return np.std(self.array, axis = axis) + + def elementwise_variance(self, axis = 0): + + return np.var(self.array, axis = axis) + + def elementwise_npmin(self, axis = 0): + return np.amin(self.array, axis = axis) + + + def elementwise_npmax(self, axis = 0): + return np.amax(self.array, axis = axis) + + def elementwise_stats(self, axis = 0): + + _mean = self.elementwise_mean(axis = axis) + _median = self.elementwise_median(axis = axis) + _stdev = self.elementwise_stdev(axis = axis) + _variance = self.elementwise_variance(axis = axis) + _min = self.elementwise_npmin(axis = axis) + _max = self.elementwise_npmax(axis = axis) + + return _mean, _median, _stdev, _variance, _min, _max + + def __getitem__(self, key): + + return self.array[key] + + def __setitem__(self, key, value): + + self.array[key] = value + + def __len__(self): + + return len(self.array) + + def normalize(self): + + a = np.atleast_1d(np.linalg.norm(self.array)) + a[a==0] = 1 + return Array(self.array / np.expand_dims(a, -1)) + + def __add__(self, other): + + return Array(self.array + other.array) + + def __sub__(self, other): + + return Array(self.array - other.array) + + def __neg__(self): + + return Array(-self.array) + + def __abs__(self): + + return Array(abs(self.array)) + + def __invert__(self): + + return Array(1/self.array) + + def __mul__(self, other): + + if(isinstance(other, Array)): + return Array(self.array.dot(other.array)) + elif(isinstance(other, int)): + return Array(other * self.array) + else: + raise Exception("unsupported multiplication between Array and " + str(type(other))) + + def __rmul__(self, other): + + return self.__mul__(other) + + def cross(self, other): + + return np.cross(self.array, other.array) + + def transpose(self): + + return Array(np.transpose(self.array)) + + def sort(self, array): # depreciated + warnings.warn("Array.sort has been depreciated in favor of Sort") + array_length = len(array) + if array_length <= 1: + return array + middle_index = int(array_length / 2) + left = array[0:middle_index] + right = array[middle_index:] + left = self.sort(left) + right = self.sort(right) + return self.__merge(left, right) + + def __merge(self, left, right): + sorted_list = [] + left = left[:] + right = right[:] + while len(left) > 0 or len(right) > 0: + if len(left) > 0 and len(right) > 0: + if left[0] <= right[0]: + sorted_list.append(left.pop(0)) + else: + sorted_list.append(right.pop(0)) + elif len(left) > 0: + sorted_list.append(left.pop(0)) + elif len(right) > 0: + sorted_list.append(right.pop(0)) + return sorted_list \ No newline at end of file diff --git a/analysis-master/tra_analysis/ClassificationMetric.py b/analysis-master/tra_analysis/ClassificationMetric.py new file mode 100644 index 00000000..a1afcf25 --- /dev/null +++ b/analysis-master/tra_analysis/ClassificationMetric.py @@ -0,0 +1,39 @@ +# Titan Robotics Team 2022: ClassificationMetric submodule +# Written by Arthur Lu +# Notes: +# this should be imported as a python module using 'from tra_analysis import ClassificationMetric' +# setup: + +__version__ = "1.0.1" + +__changelog__ = """changelog: + 1.0.1: + - fixed __all__ + 1.0.0: + - ported analysis.ClassificationMetric() here +""" + +__author__ = ( + "Arthur Lu ", +) + +__all__ = [ + "ClassificationMetric", +] + +import sklearn +from sklearn import metrics + +class ClassificationMetric(): + + def __new__(cls, predictions, targets): + + return cls.cm(cls, predictions, targets), cls.cr(cls, predictions, targets) + + def cm(self, predictions, targets): + + return sklearn.metrics.confusion_matrix(targets, predictions) + + def cr(self, predictions, targets): + + return sklearn.metrics.classification_report(targets, predictions) \ No newline at end of file diff --git a/analysis-master/tra_analysis/CorrelationTest.py b/analysis-master/tra_analysis/CorrelationTest.py new file mode 100644 index 00000000..bc35ce92 --- /dev/null +++ b/analysis-master/tra_analysis/CorrelationTest.py @@ -0,0 +1,67 @@ +# Titan Robotics Team 2022: CorrelationTest submodule +# Written by Arthur Lu +# Notes: +# this should be imported as a python module using 'from tra_analysis import CorrelationTest' +# setup: + +__version__ = "1.0.1" + +__changelog__ = """changelog: + 1.0.1: + - fixed __all__ + 1.0.0: + - ported analysis.CorrelationTest() here + - removed classness +""" + +__author__ = ( + "Arthur Lu ", +) + +__all__ = [ + "anova_oneway", + "pearson", + "spearman", + "point_biserial", + "kendall", + "kendall_weighted", + "mgc", +] + +import scipy +from scipy import stats + +def anova_oneway(*args): #expects arrays of samples + + results = scipy.stats.f_oneway(*args) + return {"f-value": results[0], "p-value": results[1]} + +def pearson(x, y): + + results = scipy.stats.pearsonr(x, y) + return {"r-value": results[0], "p-value": results[1]} + +def spearman(a, b = None, axis = 0, nan_policy = 'propagate'): + + results = scipy.stats.spearmanr(a, b = b, axis = axis, nan_policy = nan_policy) + return {"r-value": results[0], "p-value": results[1]} + +def point_biserial(x, y): + + results = scipy.stats.pointbiserialr(x, y) + return {"r-value": results[0], "p-value": results[1]} + +def kendall(x, y, initial_lexsort = None, nan_policy = 'propagate', method = 'auto'): + + results = scipy.stats.kendalltau(x, y, initial_lexsort = initial_lexsort, nan_policy = nan_policy, method = method) + return {"tau": results[0], "p-value": results[1]} + +def kendall_weighted(x, y, rank = True, weigher = None, additive = True): + + results = scipy.stats.weightedtau(x, y, rank = rank, weigher = weigher, additive = additive) + return {"tau": results[0], "p-value": results[1]} + +def mgc(x, y, compute_distance = None, reps = 1000, workers = 1, is_twosamp = False, random_state = None): + + results = scipy.stats.multiscale_graphcorr(x, y, compute_distance = compute_distance, reps = reps, workers = workers, is_twosamp = is_twosamp, random_state = random_state) + return {"k-value": results[0], "p-value": results[1], "data": results[2]} # unsure if MGC test returns a k value \ No newline at end of file diff --git a/analysis-master/tra_analysis/CorrelationTest_obj.py b/analysis-master/tra_analysis/CorrelationTest_obj.py new file mode 100644 index 00000000..16168094 --- /dev/null +++ b/analysis-master/tra_analysis/CorrelationTest_obj.py @@ -0,0 +1,41 @@ +# Only included for backwards compatibility! Do not update, CorrelationTest is preferred and supported. + +import scipy +from scipy import stats + +class CorrelationTest: + + def anova_oneway(self, *args): #expects arrays of samples + + results = scipy.stats.f_oneway(*args) + return {"f-value": results[0], "p-value": results[1]} + + def pearson(self, x, y): + + results = scipy.stats.pearsonr(x, y) + return {"r-value": results[0], "p-value": results[1]} + + def spearman(self, a, b = None, axis = 0, nan_policy = 'propagate'): + + results = scipy.stats.spearmanr(a, b = b, axis = axis, nan_policy = nan_policy) + return {"r-value": results[0], "p-value": results[1]} + + def point_biserial(self, x,y): + + results = scipy.stats.pointbiserialr(x, y) + return {"r-value": results[0], "p-value": results[1]} + + def kendall(self, x, y, initial_lexsort = None, nan_policy = 'propagate', method = 'auto'): + + results = scipy.stats.kendalltau(x, y, initial_lexsort = initial_lexsort, nan_policy = nan_policy, method = method) + return {"tau": results[0], "p-value": results[1]} + + def kendall_weighted(self, x, y, rank = True, weigher = None, additive = True): + + results = scipy.stats.weightedtau(x, y, rank = rank, weigher = weigher, additive = additive) + return {"tau": results[0], "p-value": results[1]} + + def mgc(self, x, y, compute_distance = None, reps = 1000, workers = 1, is_twosamp = False, random_state = None): + + results = scipy.stats.multiscale_graphcorr(x, y, compute_distance = compute_distance, reps = reps, workers = workers, is_twosamp = is_twosamp, random_state = random_state) + return {"k-value": results[0], "p-value": results[1], "data": results[2]} # unsure if MGC test returns a k value \ No newline at end of file diff --git a/analysis-master/tra_analysis/fits.py b/analysis-master/tra_analysis/Fit.py similarity index 96% rename from analysis-master/tra_analysis/fits.py rename to analysis-master/tra_analysis/Fit.py index 00935cb3..9780331a 100644 --- a/analysis-master/tra_analysis/fits.py +++ b/analysis-master/tra_analysis/Fit.py @@ -4,10 +4,12 @@ # this module is cuda-optimized (as appropriate) and vectorized (except for one small part) # setup: -__version__ = "0.0.1" +__version__ = "0.0.2" # changelog should be viewed using print(analysis.fits.__changelog__) __changelog__ = """changelog: + 0.0.2: + - renamed module to Fit 0.0.1: - initial release, add circle fitting with LSC """ diff --git a/analysis-master/tra_analysis/KNN.py b/analysis-master/tra_analysis/KNN.py new file mode 100644 index 00000000..d594c72f --- /dev/null +++ b/analysis-master/tra_analysis/KNN.py @@ -0,0 +1,45 @@ +# Titan Robotics Team 2022: KNN submodule +# Written by Arthur Lu +# Notes: +# this should be imported as a python module using 'from tra_analysis import KNN' +# setup: + +__version__ = "1.0.0" + +__changelog__ = """changelog: + 1.0.0: + - ported analysis.KNN() here + - removed classness +""" + +__author__ = ( + "Arthur Lu ", + "James Pan " +) + +__all__ = [ + 'knn_classifier', + 'knn_regressor' +] + +import sklearn +from sklearn import model_selection, neighbors +from . import ClassificationMetric, RegressionMetric + +def knn_classifier(data, labels, n_neighbors = 5, test_size = 0.3, algorithm='auto', leaf_size=30, metric='minkowski', metric_params=None, n_jobs=None, p=2, weights='uniform'): #expects *2d data and 1d labels post-scaling + + data_train, data_test, labels_train, labels_test = sklearn.model_selection.train_test_split(data, labels, test_size=test_size, random_state=1) + model = sklearn.neighbors.KNeighborsClassifier(n_neighbors = n_neighbors, weights = weights, algorithm = algorithm, leaf_size = leaf_size, p = p, metric = metric, metric_params = metric_params, n_jobs = n_jobs) + model.fit(data_train, labels_train) + predictions = model.predict(data_test) + + return model, ClassificationMetric(predictions, labels_test) + +def knn_regressor(data, outputs, n_neighbors = 5, test_size = 0.3, weights = "uniform", algorithm = "auto", leaf_size = 30, p = 2, metric = "minkowski", metric_params = None, n_jobs = None): + + data_train, data_test, outputs_train, outputs_test = sklearn.model_selection.train_test_split(data, outputs, test_size=test_size, random_state=1) + model = sklearn.neighbors.KNeighborsRegressor(n_neighbors = n_neighbors, weights = weights, algorithm = algorithm, leaf_size = leaf_size, p = p, metric = metric, metric_params = metric_params, n_jobs = n_jobs) + model.fit(data_train, outputs_train) + predictions = model.predict(data_test) + + return model, RegressionMetric.RegressionMetric(predictions, outputs_test) \ No newline at end of file diff --git a/analysis-master/tra_analysis/KNN_obj.py b/analysis-master/tra_analysis/KNN_obj.py new file mode 100644 index 00000000..b506bf6c --- /dev/null +++ b/analysis-master/tra_analysis/KNN_obj.py @@ -0,0 +1,25 @@ +# Only included for backwards compatibility! Do not update, NaiveBayes is preferred and supported. + +import sklearn +from sklearn import model_selection, neighbors +from . import ClassificationMetric, RegressionMetric + +class KNN: + + def knn_classifier(self, data, labels, n_neighbors, test_size = 0.3, algorithm='auto', leaf_size=30, metric='minkowski', metric_params=None, n_jobs=None, p=2, weights='uniform'): #expects *2d data and 1d labels post-scaling + + data_train, data_test, labels_train, labels_test = sklearn.model_selection.train_test_split(data, labels, test_size=test_size, random_state=1) + model = sklearn.neighbors.KNeighborsClassifier() + model.fit(data_train, labels_train) + predictions = model.predict(data_test) + + return model, ClassificationMetric(predictions, labels_test) + + def knn_regressor(self, data, outputs, n_neighbors, test_size = 0.3, weights = "uniform", algorithm = "auto", leaf_size = 30, p = 2, metric = "minkowski", metric_params = None, n_jobs = None): + + data_train, data_test, outputs_train, outputs_test = sklearn.model_selection.train_test_split(data, outputs, test_size=test_size, random_state=1) + model = sklearn.neighbors.KNeighborsRegressor(n_neighbors = n_neighbors, weights = weights, algorithm = algorithm, leaf_size = leaf_size, p = p, metric = metric, metric_params = metric_params, n_jobs = n_jobs) + model.fit(data_train, outputs_train) + predictions = model.predict(data_test) + + return model, RegressionMetric(predictions, outputs_test) \ No newline at end of file diff --git a/analysis-master/tra_analysis/NaiveBayes.py b/analysis-master/tra_analysis/NaiveBayes.py new file mode 100644 index 00000000..f6b68f1e --- /dev/null +++ b/analysis-master/tra_analysis/NaiveBayes.py @@ -0,0 +1,64 @@ +# Titan Robotics Team 2022: NaiveBayes submodule +# Written by Arthur Lu +# Notes: +# this should be imported as a python module using 'from tra_analysis import NaiveBayes' +# setup: + +__version__ = "1.0.0" + +__changelog__ = """changelog: + 1.0.0: + - ported analysis.NaiveBayes() here + - removed classness +""" + +__author__ = ( + "Arthur Lu ", +) + +__all__ = [ + 'gaussian', + 'multinomial' + 'bernoulli', + 'complement' +] + +import sklearn +from sklearn import model_selection, naive_bayes +from . import ClassificationMetric, RegressionMetric + +def gaussian(data, labels, test_size = 0.3, priors = None, var_smoothing = 1e-09): + + data_train, data_test, labels_train, labels_test = sklearn.model_selection.train_test_split(data, labels, test_size=test_size, random_state=1) + model = sklearn.naive_bayes.GaussianNB(priors = priors, var_smoothing = var_smoothing) + model.fit(data_train, labels_train) + predictions = model.predict(data_test) + + return model, ClassificationMetric(predictions, labels_test) + +def multinomial(data, labels, test_size = 0.3, alpha=1.0, fit_prior=True, class_prior=None): + + data_train, data_test, labels_train, labels_test = sklearn.model_selection.train_test_split(data, labels, test_size=test_size, random_state=1) + model = sklearn.naive_bayes.MultinomialNB(alpha = alpha, fit_prior = fit_prior, class_prior = class_prior) + model.fit(data_train, labels_train) + predictions = model.predict(data_test) + + return model, ClassificationMetric(predictions, labels_test) + +def bernoulli(data, labels, test_size = 0.3, alpha=1.0, binarize=0.0, fit_prior=True, class_prior=None): + + data_train, data_test, labels_train, labels_test = sklearn.model_selection.train_test_split(data, labels, test_size=test_size, random_state=1) + model = sklearn.naive_bayes.BernoulliNB(alpha = alpha, binarize = binarize, fit_prior = fit_prior, class_prior = class_prior) + model.fit(data_train, labels_train) + predictions = model.predict(data_test) + + return model, ClassificationMetric(predictions, labels_test) + +def complement(data, labels, test_size = 0.3, alpha=1.0, fit_prior=True, class_prior=None, norm=False): + + data_train, data_test, labels_train, labels_test = sklearn.model_selection.train_test_split(data, labels, test_size=test_size, random_state=1) + model = sklearn.naive_bayes.ComplementNB(alpha = alpha, fit_prior = fit_prior, class_prior = class_prior, norm = norm) + model.fit(data_train, labels_train) + predictions = model.predict(data_test) + + return model, ClassificationMetric(predictions, labels_test) \ No newline at end of file diff --git a/analysis-master/tra_analysis/NaiveBayes_obj.py b/analysis-master/tra_analysis/NaiveBayes_obj.py new file mode 100644 index 00000000..70e4d437 --- /dev/null +++ b/analysis-master/tra_analysis/NaiveBayes_obj.py @@ -0,0 +1,43 @@ +# Only included for backwards compatibility! Do not update, NaiveBayes is preferred and supported. + +import sklearn +from sklearn import model_selection, naive_bayes +from . import ClassificationMetric, RegressionMetric + +class NaiveBayes: + + def guassian(self, data, labels, test_size = 0.3, priors = None, var_smoothing = 1e-09): + + data_train, data_test, labels_train, labels_test = sklearn.model_selection.train_test_split(data, labels, test_size=test_size, random_state=1) + model = sklearn.naive_bayes.GaussianNB(priors = priors, var_smoothing = var_smoothing) + model.fit(data_train, labels_train) + predictions = model.predict(data_test) + + return model, ClassificationMetric(predictions, labels_test) + + def multinomial(self, data, labels, test_size = 0.3, alpha=1.0, fit_prior=True, class_prior=None): + + data_train, data_test, labels_train, labels_test = sklearn.model_selection.train_test_split(data, labels, test_size=test_size, random_state=1) + model = sklearn.naive_bayes.MultinomialNB(alpha = alpha, fit_prior = fit_prior, class_prior = class_prior) + model.fit(data_train, labels_train) + predictions = model.predict(data_test) + + return model, ClassificationMetric(predictions, labels_test) + + def bernoulli(self, data, labels, test_size = 0.3, alpha=1.0, binarize=0.0, fit_prior=True, class_prior=None): + + data_train, data_test, labels_train, labels_test = sklearn.model_selection.train_test_split(data, labels, test_size=test_size, random_state=1) + model = sklearn.naive_bayes.BernoulliNB(alpha = alpha, binarize = binarize, fit_prior = fit_prior, class_prior = class_prior) + model.fit(data_train, labels_train) + predictions = model.predict(data_test) + + return model, ClassificationMetric(predictions, labels_test) + + def complement(self, data, labels, test_size = 0.3, alpha=1.0, fit_prior=True, class_prior=None, norm=False): + + data_train, data_test, labels_train, labels_test = sklearn.model_selection.train_test_split(data, labels, test_size=test_size, random_state=1) + model = sklearn.naive_bayes.ComplementNB(alpha = alpha, fit_prior = fit_prior, class_prior = class_prior, norm = norm) + model.fit(data_train, labels_train) + predictions = model.predict(data_test) + + return model, ClassificationMetric(predictions, labels_test) \ No newline at end of file diff --git a/analysis-master/tra_analysis/RandomForest.py b/analysis-master/tra_analysis/RandomForest.py new file mode 100644 index 00000000..44bee009 --- /dev/null +++ b/analysis-master/tra_analysis/RandomForest.py @@ -0,0 +1,46 @@ +# Titan Robotics Team 2022: RandomForest submodule +# Written by Arthur Lu +# Notes: +# this should be imported as a python module using 'from tra_analysis import RandomForest' +# setup: + +__version__ = "1.0.1" + +__changelog__ = """changelog: + 1.0.1: + - fixed __all__ + 1.0.0: + - ported analysis.RandomFores() here + - removed classness +""" + +__author__ = ( + "Arthur Lu ", +) + +__all__ = [ + "random_forest_classifier", + "random_forest_regressor", +] + +import sklearn +from sklearn import ensemble, model_selection +from . import ClassificationMetric, RegressionMetric + +def random_forest_classifier(data, labels, test_size, n_estimators, criterion="gini", max_depth=None, min_samples_split=2, min_samples_leaf=1, min_weight_fraction_leaf=0.0, max_features="auto", max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, bootstrap=True, oob_score=False, n_jobs=None, random_state=None, verbose=0, warm_start=False, class_weight=None): + + data_train, data_test, labels_train, labels_test = sklearn.model_selection.train_test_split(data, labels, test_size=test_size, random_state=1) + kernel = sklearn.ensemble.RandomForestClassifier(n_estimators = n_estimators, criterion = criterion, max_depth = max_depth, min_samples_split = min_samples_split, min_samples_leaf = min_samples_leaf, min_weight_fraction_leaf = min_weight_fraction_leaf, max_leaf_nodes = max_leaf_nodes, min_impurity_decrease = min_impurity_decrease, bootstrap = bootstrap, oob_score = oob_score, n_jobs = n_jobs, random_state = random_state, verbose = verbose, warm_start = warm_start, class_weight = class_weight) + kernel.fit(data_train, labels_train) + predictions = kernel.predict(data_test) + + return kernel, ClassificationMetric(predictions, labels_test) + +def random_forest_regressor(data, outputs, test_size, n_estimators, criterion="mse", max_depth=None, min_samples_split=2, min_samples_leaf=1, min_weight_fraction_leaf=0.0, max_features="auto", max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, bootstrap=True, oob_score=False, n_jobs=None, random_state=None, verbose=0, warm_start=False): + + data_train, data_test, outputs_train, outputs_test = sklearn.model_selection.train_test_split(data, outputs, test_size=test_size, random_state=1) + kernel = sklearn.ensemble.RandomForestRegressor(n_estimators = n_estimators, criterion = criterion, max_depth = max_depth, min_samples_split = min_samples_split, min_weight_fraction_leaf = min_weight_fraction_leaf, max_features = max_features, max_leaf_nodes = max_leaf_nodes, min_impurity_decrease = min_impurity_decrease, min_impurity_split = min_impurity_split, bootstrap = bootstrap, oob_score = oob_score, n_jobs = n_jobs, random_state = random_state, verbose = verbose, warm_start = warm_start) + kernel.fit(data_train, outputs_train) + predictions = kernel.predict(data_test) + + return kernel, RegressionMetric.RegressionMetric(predictions, outputs_test) \ No newline at end of file diff --git a/analysis-master/tra_analysis/RandomForest_obj.py b/analysis-master/tra_analysis/RandomForest_obj.py new file mode 100644 index 00000000..c33f8dce --- /dev/null +++ b/analysis-master/tra_analysis/RandomForest_obj.py @@ -0,0 +1,25 @@ +# Only included for backwards compatibility! Do not update, RandomForest is preferred and supported. + +import sklearn +from sklearn import ensemble, model_selection +from . import ClassificationMetric, RegressionMetric + +class RandomForest: + + def random_forest_classifier(self, data, labels, test_size, n_estimators, criterion="gini", max_depth=None, min_samples_split=2, min_samples_leaf=1, min_weight_fraction_leaf=0.0, max_features="auto", max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, bootstrap=True, oob_score=False, n_jobs=None, random_state=None, verbose=0, warm_start=False, class_weight=None): + + data_train, data_test, labels_train, labels_test = sklearn.model_selection.train_test_split(data, labels, test_size=test_size, random_state=1) + kernel = sklearn.ensemble.RandomForestClassifier(n_estimators = n_estimators, criterion = criterion, max_depth = max_depth, min_samples_split = min_samples_split, min_samples_leaf = min_samples_leaf, min_weight_fraction_leaf = min_weight_fraction_leaf, max_leaf_nodes = max_leaf_nodes, min_impurity_decrease = min_impurity_decrease, bootstrap = bootstrap, oob_score = oob_score, n_jobs = n_jobs, random_state = random_state, verbose = verbose, warm_start = warm_start, class_weight = class_weight) + kernel.fit(data_train, labels_train) + predictions = kernel.predict(data_test) + + return kernel, ClassificationMetric(predictions, labels_test) + + def random_forest_regressor(self, data, outputs, test_size, n_estimators, criterion="mse", max_depth=None, min_samples_split=2, min_samples_leaf=1, min_weight_fraction_leaf=0.0, max_features="auto", max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, bootstrap=True, oob_score=False, n_jobs=None, random_state=None, verbose=0, warm_start=False): + + data_train, data_test, outputs_train, outputs_test = sklearn.model_selection.train_test_split(data, outputs, test_size=test_size, random_state=1) + kernel = sklearn.ensemble.RandomForestRegressor(n_estimators = n_estimators, criterion = criterion, max_depth = max_depth, min_samples_split = min_samples_split, min_weight_fraction_leaf = min_weight_fraction_leaf, max_features = max_features, max_leaf_nodes = max_leaf_nodes, min_impurity_decrease = min_impurity_decrease, min_impurity_split = min_impurity_split, bootstrap = bootstrap, oob_score = oob_score, n_jobs = n_jobs, random_state = random_state, verbose = verbose, warm_start = warm_start) + kernel.fit(data_train, outputs_train) + predictions = kernel.predict(data_test) + + return kernel, RegressionMetric(predictions, outputs_test) \ No newline at end of file diff --git a/analysis-master/tra_analysis/RegressionMetric.py b/analysis-master/tra_analysis/RegressionMetric.py new file mode 100644 index 00000000..0b985493 --- /dev/null +++ b/analysis-master/tra_analysis/RegressionMetric.py @@ -0,0 +1,42 @@ +# Titan Robotics Team 2022: RegressionMetric submodule +# Written by Arthur Lu +# Notes: +# this should be imported as a python module using 'from tra_analysis import RegressionMetric' +# setup: + +__version__ = "1.0.0" + +__changelog__ = """changelog: + 1.0.0: + - ported analysis.RegressionMetric() here +""" + +__author__ = ( + "Arthur Lu ", +) + +__all__ = [ + 'RegressionMetric' +] + +import numpy as np +import sklearn +from sklearn import metrics + +class RegressionMetric(): + + def __new__(cls, predictions, targets): + + return cls.r_squared(cls, predictions, targets), cls.mse(cls, predictions, targets), cls.rms(cls, predictions, targets) + + def r_squared(self, predictions, targets): # assumes equal size inputs + + return sklearn.metrics.r2_score(targets, predictions) + + def mse(self, predictions, targets): + + return sklearn.metrics.mean_squared_error(targets, predictions) + + def rms(self, predictions, targets): + + return np.sqrt(sklearn.metrics.mean_squared_error(targets, predictions)) \ No newline at end of file diff --git a/analysis-master/tra_analysis/SVM.py b/analysis-master/tra_analysis/SVM.py new file mode 100644 index 00000000..acf189f3 --- /dev/null +++ b/analysis-master/tra_analysis/SVM.py @@ -0,0 +1,88 @@ +# Titan Robotics Team 2022: SVM submodule +# Written by Arthur Lu +# Notes: +# this should be imported as a python module using 'from tra_analysis import SVM' +# setup: + +__version__ = "1.0.2" + +__changelog__ = """changelog: + 1.0.2: + - fixed __all__ + 1.0.1: + - removed unessasary self calls + - removed classness + 1.0.0: + - ported analysis.SVM() here +""" + +__author__ = ( + "Arthur Lu ", +) + +__all__ = [ + "CustomKernel", + "StandardKernel", + "PrebuiltKernel", + "fit", + "eval_classification", + "eval_regression", +] + +import sklearn +from sklearn import svm +from . import ClassificationMetric, RegressionMetric + +class CustomKernel: + + def __new__(cls, C, kernel, degre, gamma, coef0, shrinking, probability, tol, cache_size, class_weight, verbose, max_iter, decision_function_shape, random_state): + + return sklearn.svm.SVC(C = C, kernel = kernel, gamma = gamma, coef0 = coef0, shrinking = shrinking, probability = probability, tol = tol, cache_size = cache_size, class_weight = class_weight, verbose = verbose, max_iter = max_iter, decision_function_shape = decision_function_shape, random_state = random_state) + +class StandardKernel: + + def __new__(cls, kernel, C=1.0, degree=3, gamma='auto_deprecated', coef0=0.0, shrinking=True, probability=False, tol=0.001, cache_size=200, class_weight=None, verbose=False, max_iter=-1, decision_function_shape='ovr', random_state=None): + + return sklearn.svm.SVC(C = C, kernel = kernel, gamma = gamma, coef0 = coef0, shrinking = shrinking, probability = probability, tol = tol, cache_size = cache_size, class_weight = class_weight, verbose = verbose, max_iter = max_iter, decision_function_shape = decision_function_shape, random_state = random_state) + +class PrebuiltKernel: + + class Linear: + + def __new__(cls): + + return sklearn.svm.SVC(kernel = 'linear') + + class Polynomial: + + def __new__(cls, power, r_bias): + + return sklearn.svm.SVC(kernel = 'polynomial', degree = power, coef0 = r_bias) + + class RBF: + + def __new__(cls, gamma): + + return sklearn.svm.SVC(kernel = 'rbf', gamma = gamma) + + class Sigmoid: + + def __new__(cls, r_bias): + + return sklearn.svm.SVC(kernel = 'sigmoid', coef0 = r_bias) + +def fit(kernel, train_data, train_outputs): # expects *2d data, 1d labels or outputs + + return kernel.fit(train_data, train_outputs) + +def eval_classification(kernel, test_data, test_outputs): + + predictions = kernel.predict(test_data) + + return ClassificationMetric(predictions, test_outputs) + +def eval_regression(kernel, test_data, test_outputs): + + predictions = kernel.predict(test_data) + + return RegressionMetric(predictions, test_outputs) \ No newline at end of file diff --git a/analysis-master/tra_analysis/Sort.py b/analysis-master/tra_analysis/Sort.py new file mode 100644 index 00000000..63dc3677 --- /dev/null +++ b/analysis-master/tra_analysis/Sort.py @@ -0,0 +1,424 @@ +# Titan Robotics Team 2022: Sort submodule +# Written by Arthur Lu and James Pan +# Notes: +# this should be imported as a python module using 'from tra_analysis import Sort' +# setup: + +__version__ = "1.0.1" + +__changelog__ = """changelog: + 1.0.1: + - fixed __all__ + 1.0.0: + - ported analysis.Sort() here + - removed classness +""" + +__author__ = ( + "Arthur Lu ", + "James Pan " +) + +__all__ = [ + "quicksort", + "mergesort", + "introsort", + "heapsort", + "insertionsort", + "timsort", + "selectionsort", + "shellsort", + "bubblesort", + "cyclesort", + "cocktailsort", +] + +import numpy as np + +def quicksort(a): + + def sort(array): + + less = [] + equal = [] + greater = [] + + if len(array) > 1: + pivot = array[0] + for x in array: + if x < pivot: + less.append(x) + elif x == pivot: + equal.append(x) + elif x > pivot: + greater.append(x) + return sort(less)+equal+sort(greater) + else: + return array + + return np.array(sort(a)) + +def mergesort(a): + + def sort(array): + + array = array + + if len(array) >1: + middle = len(array) // 2 + L = array[:middle] + R = array[middle:] + + sort(L) + sort(R) + + i = j = k = 0 + + while i < len(L) and j < len(R): + if L[i] < R[j]: + array[k] = L[i] + i+= 1 + else: + array[k] = R[j] + j+= 1 + k+= 1 + + while i < len(L): + array[k] = L[i] + i+= 1 + k+= 1 + + while j < len(R): + array[k] = R[j] + j+= 1 + k+= 1 + + return array + + return sort(a) + +def introsort(a): + + def sort(array, start, end, maxdepth): + + array = array + + if end - start <= 1: + return + elif maxdepth == 0: + heapsort(array, start, end) + else: + p = partition(array, start, end) + sort(array, start, p + 1, maxdepth - 1) + sort(array, p + 1, end, maxdepth - 1) + + return array + + def partition(array, start, end): + pivot = array[start] + i = start - 1 + j = end + + while True: + i = i + 1 + while array[i] < pivot: + i = i + 1 + j = j - 1 + while array[j] > pivot: + j = j - 1 + + if i >= j: + return j + + swap(array, i, j) + + def swap(array, i, j): + array[i], array[j] = array[j], array[i] + + def heapsort(array, start, end): + build_max_heap(array, start, end) + for i in range(end - 1, start, -1): + swap(array, start, i) + max_heapify(array, index=0, start=start, end=i) + + def build_max_heap(array, start, end): + def parent(i): + return (i - 1)//2 + length = end - start + index = parent(length - 1) + while index >= 0: + max_heapify(array, index, start, end) + index = index - 1 + + def max_heapify(array, index, start, end): + def left(i): + return 2*i + 1 + def right(i): + return 2*i + 2 + + size = end - start + l = left(index) + r = right(index) + if (l < size and array[start + l] > array[start + index]): + largest = l + else: + largest = index + if (r < size and array[start + r] > array[start + largest]): + largest = r + if largest != index: + swap(array, start + largest, start + index) + max_heapify(array, largest, start, end) + + maxdepth = (len(a).bit_length() - 1)*2 + + return sort(a, 0, len(a), maxdepth) + +def heapsort(a): + + def sort(array): + + array = array + + n = len(array) + + for i in range(n//2 - 1, -1, -1): + heapify(array, n, i) + + for i in range(n-1, 0, -1): + array[i], array[0] = array[0], array[i] + heapify(array, i, 0) + + return array + + def heapify(array, n, i): + + array = array + + largest = i + l = 2 * i + 1 + r = 2 * i + 2 + + if l < n and array[i] < array[l]: + largest = l + + if r < n and array[largest] < array[r]: + largest = r + + if largest != i: + array[i],array[largest] = array[largest],array[i] + heapify(array, n, largest) + + return array + + return sort(a) + +def insertionsort(a): + + def sort(array): + + array = array + + for i in range(1, len(array)): + + key = array[i] + + j = i-1 + while j >=0 and key < array[j] : + array[j+1] = array[j] + j -= 1 + array[j+1] = key + + return array + + return sort(a) + +def timsort(a, block = 32): + + BLOCK = block + + def sort(array, n): + + array = array + + for i in range(0, n, BLOCK): + insertionsort(array, i, min((i+31), (n-1))) + + size = BLOCK + while size < n: + + for left in range(0, n, 2*size): + + mid = left + size - 1 + right = min((left + 2*size - 1), (n-1)) + merge(array, left, mid, right) + + size = 2*size + + return array + + def insertionsort(array, left, right): + + array = array + + for i in range(left + 1, right+1): + + temp = array[i] + j = i - 1 + while j >= left and array[j] > temp : + + array[j+1] = array[j] + j -= 1 + + array[j+1] = temp + + return array + + + def merge(array, l, m, r): + + len1, len2 = m - l + 1, r - m + left, right = [], [] + for i in range(0, len1): + left.append(array[l + i]) + for i in range(0, len2): + right.append(array[m + 1 + i]) + + i, j, k = 0, 0, l + + while i < len1 and j < len2: + + if left[i] <= right[j]: + array[k] = left[i] + i += 1 + + else: + array[k] = right[j] + j += 1 + + k += 1 + + while i < len1: + + array[k] = left[i] + k += 1 + i += 1 + + while j < len2: + array[k] = right[j] + k += 1 + j += 1 + + return sort(a, len(a)) + +def selectionsort(a): + array = a + for i in range(len(array)): + min_idx = i + for j in range(i+1, len(array)): + if array[min_idx] > array[j]: + min_idx = j + array[i], array[min_idx] = array[min_idx], array[i] + return array + +def shellsort(a): + array = a + n = len(array) + gap = n//2 + + while gap > 0: + + for i in range(gap,n): + + temp = array[i] + j = i + while j >= gap and array[j-gap] >temp: + array[j] = array[j-gap] + j -= gap + array[j] = temp + gap //= 2 + + return array + +def bubblesort(a): + + def sort(array): + for i, num in enumerate(array): + try: + if array[i+1] < num: + array[i] = array[i+1] + array[i+1] = num + sort(array) + except IndexError: + pass + return array + + return sort(a) + +def cyclesort(a): + + def sort(array): + + array = array + writes = 0 + + for cycleStart in range(0, len(array) - 1): + item = array[cycleStart] + + pos = cycleStart + for i in range(cycleStart + 1, len(array)): + if array[i] < item: + pos += 1 + + if pos == cycleStart: + continue + + while item == array[pos]: + pos += 1 + array[pos], item = item, array[pos] + writes += 1 + + while pos != cycleStart: + + pos = cycleStart + for i in range(cycleStart + 1, len(array)): + if array[i] < item: + pos += 1 + + while item == array[pos]: + pos += 1 + array[pos], item = item, array[pos] + writes += 1 + + return array + + return sort(a) + +def cocktailsort(a): + + def sort(array): + + array = array + + n = len(array) + swapped = True + start = 0 + end = n-1 + while (swapped == True): + swapped = False + for i in range (start, end): + if (array[i] > array[i + 1]) : + array[i], array[i + 1]= array[i + 1], array[i] + swapped = True + if (swapped == False): + break + swapped = False + end = end-1 + for i in range(end-1, start-1, -1): + if (array[i] > array[i + 1]): + array[i], array[i + 1] = array[i + 1], array[i] + swapped = True + start = start + 1 + + return array + + return sort(a) \ No newline at end of file diff --git a/analysis-master/tra_analysis/Sort_obj.py b/analysis-master/tra_analysis/Sort_obj.py new file mode 100644 index 00000000..b80b4760 --- /dev/null +++ b/analysis-master/tra_analysis/Sort_obj.py @@ -0,0 +1,391 @@ +# Only included for backwards compatibility! Do not update, Sort is preferred and supported. + +class Sort: # if you haven't used a sort, then you've never lived + + def quicksort(self, a): + + def sort(array): + + less = [] + equal = [] + greater = [] + + if len(array) > 1: + pivot = array[0] + for x in array: + if x < pivot: + less.append(x) + elif x == pivot: + equal.append(x) + elif x > pivot: + greater.append(x) + return sort(less)+equal+sort(greater) + else: + return array + + return np.array(sort(a)) + + def mergesort(self, a): + + def sort(array): + + array = array + + if len(array) >1: + middle = len(array) // 2 + L = array[:middle] + R = array[middle:] + + sort(L) + sort(R) + + i = j = k = 0 + + while i < len(L) and j < len(R): + if L[i] < R[j]: + array[k] = L[i] + i+= 1 + else: + array[k] = R[j] + j+= 1 + k+= 1 + + while i < len(L): + array[k] = L[i] + i+= 1 + k+= 1 + + while j < len(R): + array[k] = R[j] + j+= 1 + k+= 1 + + return array + + return sort(a) + + def introsort(self, a): + + def sort(array, start, end, maxdepth): + + array = array + + if end - start <= 1: + return + elif maxdepth == 0: + heapsort(array, start, end) + else: + p = partition(array, start, end) + sort(array, start, p + 1, maxdepth - 1) + sort(array, p + 1, end, maxdepth - 1) + + return array + + def partition(array, start, end): + pivot = array[start] + i = start - 1 + j = end + + while True: + i = i + 1 + while array[i] < pivot: + i = i + 1 + j = j - 1 + while array[j] > pivot: + j = j - 1 + + if i >= j: + return j + + swap(array, i, j) + + def swap(array, i, j): + array[i], array[j] = array[j], array[i] + + def heapsort(array, start, end): + build_max_heap(array, start, end) + for i in range(end - 1, start, -1): + swap(array, start, i) + max_heapify(array, index=0, start=start, end=i) + + def build_max_heap(array, start, end): + def parent(i): + return (i - 1)//2 + length = end - start + index = parent(length - 1) + while index >= 0: + max_heapify(array, index, start, end) + index = index - 1 + + def max_heapify(array, index, start, end): + def left(i): + return 2*i + 1 + def right(i): + return 2*i + 2 + + size = end - start + l = left(index) + r = right(index) + if (l < size and array[start + l] > array[start + index]): + largest = l + else: + largest = index + if (r < size and array[start + r] > array[start + largest]): + largest = r + if largest != index: + swap(array, start + largest, start + index) + max_heapify(array, largest, start, end) + + maxdepth = (len(a).bit_length() - 1)*2 + + return sort(a, 0, len(a), maxdepth) + + def heapsort(self, a): + + def sort(array): + + array = array + + n = len(array) + + for i in range(n//2 - 1, -1, -1): + heapify(array, n, i) + + for i in range(n-1, 0, -1): + array[i], array[0] = array[0], array[i] + heapify(array, i, 0) + + return array + + def heapify(array, n, i): + + array = array + + largest = i + l = 2 * i + 1 + r = 2 * i + 2 + + if l < n and array[i] < array[l]: + largest = l + + if r < n and array[largest] < array[r]: + largest = r + + if largest != i: + array[i],array[largest] = array[largest],array[i] + heapify(array, n, largest) + + return array + + return sort(a) + + def insertionsort(self, a): + + def sort(array): + + array = array + + for i in range(1, len(array)): + + key = array[i] + + j = i-1 + while j >=0 and key < array[j] : + array[j+1] = array[j] + j -= 1 + array[j+1] = key + + return array + + return sort(a) + + def timsort(self, a, block = 32): + + BLOCK = block + + def sort(array, n): + + array = array + + for i in range(0, n, BLOCK): + insertionsort(array, i, min((i+31), (n-1))) + + size = BLOCK + while size < n: + + for left in range(0, n, 2*size): + + mid = left + size - 1 + right = min((left + 2*size - 1), (n-1)) + merge(array, left, mid, right) + + size = 2*size + + return array + + def insertionsort(array, left, right): + + array = array + + for i in range(left + 1, right+1): + + temp = array[i] + j = i - 1 + while j >= left and array[j] > temp : + + array[j+1] = array[j] + j -= 1 + + array[j+1] = temp + + return array + + + def merge(array, l, m, r): + + len1, len2 = m - l + 1, r - m + left, right = [], [] + for i in range(0, len1): + left.append(array[l + i]) + for i in range(0, len2): + right.append(array[m + 1 + i]) + + i, j, k = 0, 0, l + + while i < len1 and j < len2: + + if left[i] <= right[j]: + array[k] = left[i] + i += 1 + + else: + array[k] = right[j] + j += 1 + + k += 1 + + while i < len1: + + array[k] = left[i] + k += 1 + i += 1 + + while j < len2: + array[k] = right[j] + k += 1 + j += 1 + + return sort(a, len(a)) + + def selectionsort(self, a): + array = a + for i in range(len(array)): + min_idx = i + for j in range(i+1, len(array)): + if array[min_idx] > array[j]: + min_idx = j + array[i], array[min_idx] = array[min_idx], array[i] + return array + + def shellsort(self, a): + array = a + n = len(array) + gap = n//2 + + while gap > 0: + + for i in range(gap,n): + + temp = array[i] + j = i + while j >= gap and array[j-gap] >temp: + array[j] = array[j-gap] + j -= gap + array[j] = temp + gap //= 2 + + return array + + def bubblesort(self, a): + + def sort(array): + for i, num in enumerate(array): + try: + if array[i+1] < num: + array[i] = array[i+1] + array[i+1] = num + sort(array) + except IndexError: + pass + return array + + return sort(a) + + def cyclesort(self, a): + + def sort(array): + + array = array + writes = 0 + + for cycleStart in range(0, len(array) - 1): + item = array[cycleStart] + + pos = cycleStart + for i in range(cycleStart + 1, len(array)): + if array[i] < item: + pos += 1 + + if pos == cycleStart: + continue + + while item == array[pos]: + pos += 1 + array[pos], item = item, array[pos] + writes += 1 + + while pos != cycleStart: + + pos = cycleStart + for i in range(cycleStart + 1, len(array)): + if array[i] < item: + pos += 1 + + while item == array[pos]: + pos += 1 + array[pos], item = item, array[pos] + writes += 1 + + return array + + return sort(a) + + def cocktailsort(self, a): + + def sort(array): + + array = array + + n = len(array) + swapped = True + start = 0 + end = n-1 + while (swapped == True): + swapped = False + for i in range (start, end): + if (array[i] > array[i + 1]) : + array[i], array[i + 1]= array[i + 1], array[i] + swapped = True + if (swapped == False): + break + swapped = False + end = end-1 + for i in range(end-1, start-1, -1): + if (array[i] > array[i + 1]): + array[i], array[i + 1] = array[i + 1], array[i] + swapped = True + start = start + 1 + + return array + + return sort(a) \ No newline at end of file diff --git a/analysis-master/tra_analysis/StatisticalTest.py b/analysis-master/tra_analysis/StatisticalTest.py new file mode 100644 index 00000000..44fa3a07 --- /dev/null +++ b/analysis-master/tra_analysis/StatisticalTest.py @@ -0,0 +1,314 @@ +# Titan Robotics Team 2022: StatisticalTest submodule +# Written by Arthur Lu +# Notes: +# this should be imported as a python module using 'from tra_analysis import StatisticalTest' +# setup: + +__version__ = "1.0.2" + +__changelog__ = """changelog: + 1.0.2: + - added tukey_multicomparison + - fixed styling + 1.0.1: + - fixed typo in __all__ + 1.0.0: + - ported analysis.StatisticalTest() here + - removed classness +""" + +__author__ = ( + "Arthur Lu ", + "James Pan ", +) + +__all__ = [ + 'ttest_onesample', + 'ttest_independent', + 'ttest_statistic', + 'ttest_related', + 'ks_fitness', + 'chisquare', + 'powerdivergence' + 'ks_twosample', + 'es_twosample', + 'mw_rank', + 'mw_tiecorrection', + 'rankdata', + 'wilcoxon_ranksum', + 'wilcoxon_signedrank', + 'kw_htest', + 'friedman_chisquare', + 'bm_wtest', + 'combine_pvalues', + 'jb_fitness', + 'ab_equality', + 'bartlett_variance', + 'levene_variance', + 'sw_normality', + 'shapiro', + 'ad_onesample', + 'ad_ksample', + 'binomial', + 'fk_variance', + 'mood_mediantest', + 'mood_equalscale', + 'skewtest', + 'kurtosistest', + 'normaltest', + 'tukey_multicomparison' +] + +import numpy as np +import scipy +from scipy import stats, interpolate + +def ttest_onesample(a, popmean, axis = 0, nan_policy = 'propagate'): + + results = scipy.stats.ttest_1samp(a, popmean, axis = axis, nan_policy = nan_policy) + return {"t-value": results[0], "p-value": results[1]} + +def ttest_independent(a, b, equal = True, nan_policy = 'propagate'): + + results = scipy.stats.ttest_ind(a, b, equal_var = equal, nan_policy = nan_policy) + return {"t-value": results[0], "p-value": results[1]} + +def ttest_statistic(o1, o2, equal = True): + + results = scipy.stats.ttest_ind_from_stats(o1["mean"], o1["std"], o1["nobs"], o2["mean"], o2["std"], o2["nobs"], equal_var = equal) + return {"t-value": results[0], "p-value": results[1]} + +def ttest_related(a, b, axis = 0, nan_policy='propagate'): + + results = scipy.stats.ttest_rel(a, b, axis = axis, nan_policy = nan_policy) + return {"t-value": results[0], "p-value": results[1]} + +def ks_fitness(rvs, cdf, args = (), N = 20, alternative = 'two-sided', mode = 'approx'): + + results = scipy.stats.kstest(rvs, cdf, args = args, N = N, alternative = alternative, mode = mode) + return {"ks-value": results[0], "p-value": results[1]} + +def chisquare(f_obs, f_exp = None, ddof = None, axis = 0): + + results = scipy.stats.chisquare(f_obs, f_exp = f_exp, ddof = ddof, axis = axis) + return {"chisquared-value": results[0], "p-value": results[1]} + +def powerdivergence(f_obs, f_exp = None, ddof = None, axis = 0, lambda_ = None): + + results = scipy.stats.power_divergence(f_obs, f_exp = f_exp, ddof = ddof, axis = axis, lambda_ = lambda_) + return {"powerdivergence-value": results[0], "p-value": results[1]} + +def ks_twosample(x, y, alternative = 'two_sided', mode = 'auto'): + + results = scipy.stats.ks_2samp(x, y, alternative = alternative, mode = mode) + return {"ks-value": results[0], "p-value": results[1]} + +def es_twosample(x, y, t = (0.4, 0.8)): + + results = scipy.stats.epps_singleton_2samp(x, y, t = t) + return {"es-value": results[0], "p-value": results[1]} + +def mw_rank(x, y, use_continuity = True, alternative = None): + + results = scipy.stats.mannwhitneyu(x, y, use_continuity = use_continuity, alternative = alternative) + return {"u-value": results[0], "p-value": results[1]} + +def mw_tiecorrection(rank_values): + + results = scipy.stats.tiecorrect(rank_values) + return {"correction-factor": results} + +def rankdata(a, method = 'average'): + + results = scipy.stats.rankdata(a, method = method) + return results + +def wilcoxon_ranksum(a, b): # this seems to be superceded by Mann Whitney Wilcoxon U Test + + results = scipy.stats.ranksums(a, b) + return {"u-value": results[0], "p-value": results[1]} + +def wilcoxon_signedrank(x, y = None, zero_method = 'wilcox', correction = False, alternative = 'two-sided'): + + results = scipy.stats.wilcoxon(x, y = y, zero_method = zero_method, correction = correction, alternative = alternative) + return {"t-value": results[0], "p-value": results[1]} + +def kw_htest(*args, nan_policy = 'propagate'): + + results = scipy.stats.kruskal(*args, nan_policy = nan_policy) + return {"h-value": results[0], "p-value": results[1]} + +def friedman_chisquare(*args): + + results = scipy.stats.friedmanchisquare(*args) + return {"chisquared-value": results[0], "p-value": results[1]} + +def bm_wtest(x, y, alternative = 'two-sided', distribution = 't', nan_policy = 'propagate'): + + results = scipy.stats.brunnermunzel(x, y, alternative = alternative, distribution = distribution, nan_policy = nan_policy) + return {"w-value": results[0], "p-value": results[1]} + +def combine_pvalues(pvalues, method = 'fisher', weights = None): + + results = scipy.stats.combine_pvalues(pvalues, method = method, weights = weights) + return {"combined-statistic": results[0], "p-value": results[1]} + +def jb_fitness(x): + + results = scipy.stats.jarque_bera(x) + return {"jb-value": results[0], "p-value": results[1]} + +def ab_equality(x, y): + + results = scipy.stats.ansari(x, y) + return {"ab-value": results[0], "p-value": results[1]} + +def bartlett_variance(*args): + + results = scipy.stats.bartlett(*args) + return {"t-value": results[0], "p-value": results[1]} + +def levene_variance(*args, center = 'median', proportiontocut = 0.05): + + results = scipy.stats.levene(*args, center = center, proportiontocut = proportiontocut) + return {"w-value": results[0], "p-value": results[1]} + +def sw_normality(x): + + results = scipy.stats.shapiro(x) + return {"w-value": results[0], "p-value": results[1]} + +def shapiro(x): + + return "destroyed by facts and logic" + +def ad_onesample(x, dist = 'norm'): + + results = scipy.stats.anderson(x, dist = dist) + return {"d-value": results[0], "critical-values": results[1], "significance-value": results[2]} + +def ad_ksample(samples, midrank = True): + + results = scipy.stats.anderson_ksamp(samples, midrank = midrank) + return {"d-value": results[0], "critical-values": results[1], "significance-value": results[2]} + +def binomial(x, n = None, p = 0.5, alternative = 'two-sided'): + + results = scipy.stats.binom_test(x, n = n, p = p, alternative = alternative) + return {"p-value": results} + +def fk_variance(*args, center = 'median', proportiontocut = 0.05): + + results = scipy.stats.fligner(*args, center = center, proportiontocut = proportiontocut) + return {"h-value": results[0], "p-value": results[1]} # unknown if the statistic is an h value + +def mood_mediantest(*args, ties = 'below', correction = True, lambda_ = 1, nan_policy = 'propagate'): + + results = scipy.stats.median_test(*args, ties = ties, correction = correction, lambda_ = lambda_, nan_policy = nan_policy) + return {"chisquared-value": results[0], "p-value": results[1], "m-value": results[2], "table": results[3]} + +def mood_equalscale(x, y, axis = 0): + + results = scipy.stats.mood(x, y, axis = axis) + return {"z-score": results[0], "p-value": results[1]} + +def skewtest(a, axis = 0, nan_policy = 'propogate'): + + results = scipy.stats.skewtest(a, axis = axis, nan_policy = nan_policy) + return {"z-score": results[0], "p-value": results[1]} + +def kurtosistest(a, axis = 0, nan_policy = 'propogate'): + + results = scipy.stats.kurtosistest(a, axis = axis, nan_policy = nan_policy) + return {"z-score": results[0], "p-value": results[1]} + +def normaltest(a, axis = 0, nan_policy = 'propogate'): + + results = scipy.stats.normaltest(a, axis = axis, nan_policy = nan_policy) + return {"z-score": results[0], "p-value": results[1]} + +def get_tukeyQcrit(k, df, alpha=0.05): + ''' + From statsmodels.sandbox.stats.multicomp + + return critical values for Tukey's HSD (Q) + + Parameters + ---------- + k : int in {2, ..., 10} + number of tests + df : int + degrees of freedom of error term + alpha : {0.05, 0.01} + type 1 error, 1-confidence level + + not enough error checking for limitations + ''' + # qtable from statsmodels.sandbox.stats.multicomp + qcrit = ''' + 2 3 4 5 6 7 8 9 10 + 5 3.64 5.70 4.60 6.98 5.22 7.80 5.67 8.42 6.03 8.91 6.33 9.32 6.58 9.67 6.80 9.97 6.99 10.24 + 6 3.46 5.24 4.34 6.33 4.90 7.03 5.30 7.56 5.63 7.97 5.90 8.32 6.12 8.61 6.32 8.87 6.49 9.10 + 7 3.34 4.95 4.16 5.92 4.68 6.54 5.06 7.01 5.36 7.37 5.61 7.68 5.82 7.94 6.00 8.17 6.16 8.37 + 8 3.26 4.75 4.04 5.64 4.53 6.20 4.89 6.62 5.17 6.96 5.40 7.24 5.60 7.47 5.77 7.68 5.92 7.86 + 9 3.20 4.60 3.95 5.43 4.41 5.96 4.76 6.35 5.02 6.66 5.24 6.91 5.43 7.13 5.59 7.33 5.74 7.49 + 10 3.15 4.48 3.88 5.27 4.33 5.77 4.65 6.14 4.91 6.43 5.12 6.67 5.30 6.87 5.46 7.05 5.60 7.21 + 11 3.11 4.39 3.82 5.15 4.26 5.62 4.57 5.97 4.82 6.25 5.03 6.48 5.20 6.67 5.35 6.84 5.49 6.99 + 12 3.08 4.32 3.77 5.05 4.20 5.50 4.51 5.84 4.75 6.10 4.95 6.32 5.12 6.51 5.27 6.67 5.39 6.81 + 13 3.06 4.26 3.73 4.96 4.15 5.40 4.45 5.73 4.69 5.98 4.88 6.19 5.05 6.37 5.19 6.53 5.32 6.67 + 14 3.03 4.21 3.70 4.89 4.11 5.32 4.41 5.63 4.64 5.88 4.83 6.08 4.99 6.26 5.13 6.41 5.25 6.54 + 15 3.01 4.17 3.67 4.84 4.08 5.25 4.37 5.56 4.59 5.80 4.78 5.99 4.94 6.16 5.08 6.31 5.20 6.44 + 16 3.00 4.13 3.65 4.79 4.05 5.19 4.33 5.49 4.56 5.72 4.74 5.92 4.90 6.08 5.03 6.22 5.15 6.35 + 17 2.98 4.10 3.63 4.74 4.02 5.14 4.30 5.43 4.52 5.66 4.70 5.85 4.86 6.01 4.99 6.15 5.11 6.27 + 18 2.97 4.07 3.61 4.70 4.00 5.09 4.28 5.38 4.49 5.60 4.67 5.79 4.82 5.94 4.96 6.08 5.07 6.20 + 19 2.96 4.05 3.59 4.67 3.98 5.05 4.25 5.33 4.47 5.55 4.65 5.73 4.79 5.89 4.92 6.02 5.04 6.14 + 20 2.95 4.02 3.58 4.64 3.96 5.02 4.23 5.29 4.45 5.51 4.62 5.69 4.77 5.84 4.90 5.97 5.01 6.09 + 24 2.92 3.96 3.53 4.55 3.90 4.91 4.17 5.17 4.37 5.37 4.54 5.54 4.68 5.69 4.81 5.81 4.92 5.92 + 30 2.89 3.89 3.49 4.45 3.85 4.80 4.10 5.05 4.30 5.24 4.46 5.40 4.60 5.54 4.72 5.65 4.82 5.76 + 40 2.86 3.82 3.44 4.37 3.79 4.70 4.04 4.93 4.23 5.11 4.39 5.26 4.52 5.39 4.63 5.50 4.73 5.60 + 60 2.83 3.76 3.40 4.28 3.74 4.59 3.98 4.82 4.16 4.99 4.31 5.13 4.44 5.25 4.55 5.36 4.65 5.45 + 120 2.80 3.70 3.36 4.20 3.68 4.50 3.92 4.71 4.10 4.87 4.24 5.01 4.36 5.12 4.47 5.21 4.56 5.30 + infinity 2.77 3.64 3.31 4.12 3.63 4.40 3.86 4.60 4.03 4.76 4.17 4.88 4.29 4.99 4.39 5.08 4.47 5.16 + ''' + res = [line.split() for line in qcrit.replace('infinity','9999').split('\n')] + c=np.array(res[2:-1]).astype(float) + #c[c==9999] = np.inf + ccols = np.arange(2,11) + crows = c[:,0] + cv005 = c[:, 1::2] + cv001 = c[:, 2::2] + + if alpha == 0.05: + intp = interpolate.interp1d(crows, cv005[:,k-2]) + elif alpha == 0.01: + intp = interpolate.interp1d(crows, cv001[:,k-2]) + else: + raise ValueError('only implemented for alpha equal to 0.01 and 0.05') + return intp(df) + +def tukey_multicomparison(groups, alpha=0.05): + #formulas according to https://astatsa.com/OneWay_Anova_with_TukeyHSD/ + + k = len(groups) + df = 0 + means = [] + MSE = 0 + for group in groups: + df+= len(group) + mean = sum(group)/len(group) + means.append(mean) + MSE += sum([(i-mean)**2 for i in group]) + df -= k + MSE /= df + + q_dict = {} + crit_q = get_tukeyQcrit(k, df, alpha) + + for i in range(k-1): + for j in range(i+1, k): + numerator = abs(means[i] - means[j]) + denominator = np.sqrt( MSE / ( 2/(1/len(groups[i]) + 1/len(groups[j])) )) + q = numerator/denominator + q_dict["group "+ str(i+1) + " and group " + str(j+1)] = [q, q>crit_q] + + return q_dict \ No newline at end of file diff --git a/analysis-master/tra_analysis/StatisticalTest_obj.py b/analysis-master/tra_analysis/StatisticalTest_obj.py new file mode 100644 index 00000000..b45c2f9f --- /dev/null +++ b/analysis-master/tra_analysis/StatisticalTest_obj.py @@ -0,0 +1,170 @@ +# Only included for backwards compatibility! Do not update, StatisticalTest is preferred and supported. + +import scipy +from scipy import stats + +class StatisticalTest: + + def ttest_onesample(self, a, popmean, axis = 0, nan_policy = 'propagate'): + + results = scipy.stats.ttest_1samp(a, popmean, axis = axis, nan_policy = nan_policy) + return {"t-value": results[0], "p-value": results[1]} + + def ttest_independent(self, a, b, equal = True, nan_policy = 'propagate'): + + results = scipy.stats.ttest_ind(a, b, equal_var = equal, nan_policy = nan_policy) + return {"t-value": results[0], "p-value": results[1]} + + def ttest_statistic(self, o1, o2, equal = True): + + results = scipy.stats.ttest_ind_from_stats(o1["mean"], o1["std"], o1["nobs"], o2["mean"], o2["std"], o2["nobs"], equal_var = equal) + return {"t-value": results[0], "p-value": results[1]} + + def ttest_related(self, a, b, axis = 0, nan_policy='propagate'): + + results = scipy.stats.ttest_rel(a, b, axis = axis, nan_policy = nan_policy) + return {"t-value": results[0], "p-value": results[1]} + + def ks_fitness(self, rvs, cdf, args = (), N = 20, alternative = 'two-sided', mode = 'approx'): + + results = scipy.stats.kstest(rvs, cdf, args = args, N = N, alternative = alternative, mode = mode) + return {"ks-value": results[0], "p-value": results[1]} + + def chisquare(self, f_obs, f_exp = None, ddof = None, axis = 0): + + results = scipy.stats.chisquare(f_obs, f_exp = f_exp, ddof = ddof, axis = axis) + return {"chisquared-value": results[0], "p-value": results[1]} + + def powerdivergence(self, f_obs, f_exp = None, ddof = None, axis = 0, lambda_ = None): + + results = scipy.stats.power_divergence(f_obs, f_exp = f_exp, ddof = ddof, axis = axis, lambda_ = lambda_) + return {"powerdivergence-value": results[0], "p-value": results[1]} + + def ks_twosample(self, x, y, alternative = 'two_sided', mode = 'auto'): + + results = scipy.stats.ks_2samp(x, y, alternative = alternative, mode = mode) + return {"ks-value": results[0], "p-value": results[1]} + + def es_twosample(self, x, y, t = (0.4, 0.8)): + + results = scipy.stats.epps_singleton_2samp(x, y, t = t) + return {"es-value": results[0], "p-value": results[1]} + + def mw_rank(self, x, y, use_continuity = True, alternative = None): + + results = scipy.stats.mannwhitneyu(x, y, use_continuity = use_continuity, alternative = alternative) + return {"u-value": results[0], "p-value": results[1]} + + def mw_tiecorrection(self, rank_values): + + results = scipy.stats.tiecorrect(rank_values) + return {"correction-factor": results} + + def rankdata(self, a, method = 'average'): + + results = scipy.stats.rankdata(a, method = method) + return results + + def wilcoxon_ranksum(self, a, b): # this seems to be superceded by Mann Whitney Wilcoxon U Test + + results = scipy.stats.ranksums(a, b) + return {"u-value": results[0], "p-value": results[1]} + + def wilcoxon_signedrank(self, x, y = None, zero_method = 'wilcox', correction = False, alternative = 'two-sided'): + + results = scipy.stats.wilcoxon(x, y = y, zero_method = zero_method, correction = correction, alternative = alternative) + return {"t-value": results[0], "p-value": results[1]} + + def kw_htest(self, *args, nan_policy = 'propagate'): + + results = scipy.stats.kruskal(*args, nan_policy = nan_policy) + return {"h-value": results[0], "p-value": results[1]} + + def friedman_chisquare(self, *args): + + results = scipy.stats.friedmanchisquare(*args) + return {"chisquared-value": results[0], "p-value": results[1]} + + def bm_wtest(self, x, y, alternative = 'two-sided', distribution = 't', nan_policy = 'propagate'): + + results = scipy.stats.brunnermunzel(x, y, alternative = alternative, distribution = distribution, nan_policy = nan_policy) + return {"w-value": results[0], "p-value": results[1]} + + def combine_pvalues(self, pvalues, method = 'fisher', weights = None): + + results = scipy.stats.combine_pvalues(pvalues, method = method, weights = weights) + return {"combined-statistic": results[0], "p-value": results[1]} + + def jb_fitness(self, x): + + results = scipy.stats.jarque_bera(x) + return {"jb-value": results[0], "p-value": results[1]} + + def ab_equality(self, x, y): + + results = scipy.stats.ansari(x, y) + return {"ab-value": results[0], "p-value": results[1]} + + def bartlett_variance(self, *args): + + results = scipy.stats.bartlett(*args) + return {"t-value": results[0], "p-value": results[1]} + + def levene_variance(self, *args, center = 'median', proportiontocut = 0.05): + + results = scipy.stats.levene(*args, center = center, proportiontocut = proportiontocut) + return {"w-value": results[0], "p-value": results[1]} + + def sw_normality(self, x): + + results = scipy.stats.shapiro(x) + return {"w-value": results[0], "p-value": results[1]} + + def shapiro(self, x): + + return "destroyed by facts and logic" + + def ad_onesample(self, x, dist = 'norm'): + + results = scipy.stats.anderson(x, dist = dist) + return {"d-value": results[0], "critical-values": results[1], "significance-value": results[2]} + + def ad_ksample(self, samples, midrank = True): + + results = scipy.stats.anderson_ksamp(samples, midrank = midrank) + return {"d-value": results[0], "critical-values": results[1], "significance-value": results[2]} + + def binomial(self, x, n = None, p = 0.5, alternative = 'two-sided'): + + results = scipy.stats.binom_test(x, n = n, p = p, alternative = alternative) + return {"p-value": results} + + def fk_variance(self, *args, center = 'median', proportiontocut = 0.05): + + results = scipy.stats.fligner(*args, center = center, proportiontocut = proportiontocut) + return {"h-value": results[0], "p-value": results[1]} # unknown if the statistic is an h value + + def mood_mediantest(self, *args, ties = 'below', correction = True, lambda_ = 1, nan_policy = 'propagate'): + + results = scipy.stats.median_test(*args, ties = ties, correction = correction, lambda_ = lambda_, nan_policy = nan_policy) + return {"chisquared-value": results[0], "p-value": results[1], "m-value": results[2], "table": results[3]} + + def mood_equalscale(self, x, y, axis = 0): + + results = scipy.stats.mood(x, y, axis = axis) + return {"z-score": results[0], "p-value": results[1]} + + def skewtest(self, a, axis = 0, nan_policy = 'propogate'): + + results = scipy.stats.skewtest(a, axis = axis, nan_policy = nan_policy) + return {"z-score": results[0], "p-value": results[1]} + + def kurtosistest(self, a, axis = 0, nan_policy = 'propogate'): + + results = scipy.stats.kurtosistest(a, axis = axis, nan_policy = nan_policy) + return {"z-score": results[0], "p-value": results[1]} + + def normaltest(self, a, axis = 0, nan_policy = 'propogate'): + + results = scipy.stats.normaltest(a, axis = axis, nan_policy = nan_policy) + return {"z-score": results[0], "p-value": results[1]} \ No newline at end of file diff --git a/analysis-master/tra_analysis/__init__.py b/analysis-master/tra_analysis/__init__.py index e69de29b..2aef5c1b 100644 --- a/analysis-master/tra_analysis/__init__.py +++ b/analysis-master/tra_analysis/__init__.py @@ -0,0 +1,68 @@ +# Titan Robotics Team 2022: tra_analysis package +# Written by Arthur Lu, Jacob Levine, Dev Singh, and James Pan +# Notes: +# this should be imported as a python package using 'import tra_analysis' +# this should be included in the local directory or environment variable +# this module has been optimized for multhreaded computing +# current benchmark of optimization: 1.33 times faster +# setup: + +__version__ = "3.0.0" + +# changelog should be viewed using print(analysis.__changelog__) +__changelog__ = """changelog: + 3.0.0: + - incremented version to release 3.0.0 + 3.0.0-rc2: + - fixed __changelog__ + - fixed __all__ of Analysis, Array, ClassificationMetric, CorrelationTest, RandomForest, Sort, SVM + - populated __all__ + 3.0.0-alpha.4: + - changed version to 3 because of significant changes + - added backwards compatibility import of analysis + 2.1.0-alpha.3: + - fixed indentation in meta data + 2.1.0-alpha.2: + - updated SVM import + 2.1.0-alpha.1: + - moved multiple submodules under analysis to their own modules/files + - added header, __version__, __changelog__, __author__, __all__ (unpopulated) +""" + +__author__ = ( + "Arthur Lu ", + "Jacob Levine ", + "Dev Singh ", + "James Pan " +) + +__all__ = [ + "Analysis", + "Array", + "ClassificationMetric", + "CorrelationTest", + "Expression", + "Fit", + "KNN", + "NaiveBayes", + "RandomForest", + "RegressionMetric", + "Sort", + "StatisticalTest", + "SVM" +] + +from . import Analysis as Analysis +from . import Analysis as analysis +from .Array import Array +from .ClassificationMetric import ClassificationMetric +from . import CorrelationTest +from .equation import Expression +from . import Fit +from . import KNN +from . import NaiveBayes +from . import RandomForest +from .RegressionMetric import RegressionMetric +from . import Sort +from . import StatisticalTest +from . import SVM \ No newline at end of file diff --git a/analysis-master/tra_analysis/analysis.py b/analysis-master/tra_analysis/analysis.py deleted file mode 100644 index 14de855a..00000000 --- a/analysis-master/tra_analysis/analysis.py +++ /dev/null @@ -1,1531 +0,0 @@ -# Titan Robotics Team 2022: Data Analysis Module -# Written by Arthur Lu, Jacob Levine, and Dev Singh -# Notes: -# this should be imported as a python module using 'from tra_analysis import analysis' -# this should be included in the local directory or environment variable -# this module has been optimized for multhreaded computing -# current benchmark of optimization: 1.33 times faster -# setup: - -__version__ = "2.3.1" - -# changelog should be viewed using print(analysis.__changelog__) -__changelog__ = """changelog: - 2.3.1: - - fixed bugs in Array class - 2.3.0: - - overhauled Array class - 2.2.3: - - fixed spelling of RandomForest - - made n_neighbors required for KNN - - made n_classifiers required for SVM - 2.2.2: - - fixed 2.2.1 changelog entry - - changed regression to return dictionary - 2.2.1: - - changed all references to parent package analysis to tra_analysis - 2.2.0: - - added Sort class - - added several array sorting functions to Sort class including: - - quick sort - - merge sort - - intro(spective) sort - - heap sort - - insertion sort - - tim sort - - selection sort - - bubble sort - - cycle sort - - cocktail sort - - tested all sorting algorithms with both lists and numpy arrays - - depreciated sort function from Array class - - added warnings as an import - 2.1.4: - - added sort and search functions to Array class - 2.1.3: - - changed output of basic_stats and histo_analysis to libraries - - fixed __all__ - 2.1.2: - - renamed ArrayTest class to Array - 2.1.1: - - added add, mul, neg, and inv functions to ArrayTest class - - added normalize function to ArrayTest class - - added dot and cross functions to ArrayTest class - 2.1.0: - - added ArrayTest class - - added elementwise mean, median, standard deviation, variance, min, max functions to ArrayTest class - - added elementwise_stats to ArrayTest which encapsulates elementwise statistics - - appended to __all__ to reflect changes - 2.0.6: - - renamed func functions in regression to lin, log, exp, and sig - 2.0.5: - - moved random_forrest_regressor and random_forrest_classifier to RandomForrest class - - renamed Metrics to Metric - - renamed RegressionMetrics to RegressionMetric - - renamed ClassificationMetrics to ClassificationMetric - - renamed CorrelationTests to CorrelationTest - - renamed StatisticalTests to StatisticalTest - - reflected rafactoring to all mentions of above classes/functions - 2.0.4: - - fixed __all__ to reflected the correct functions and classes - - fixed CorrelationTests and StatisticalTests class functions to require self invocation - - added missing math import - - fixed KNN class functions to require self invocation - - fixed Metrics class functions to require self invocation - - various spelling fixes in CorrelationTests and StatisticalTests - 2.0.3: - - bug fixes with CorrelationTests and StatisticalTests - - moved glicko2 and trueskill to the metrics subpackage - - moved elo to a new metrics subpackage - 2.0.2: - - fixed docs - 2.0.1: - - fixed docs - 2.0.0: - - cleaned up wild card imports with scipy and sklearn - - added CorrelationTests class - - added StatisticalTests class - - added several correlation tests to CorrelationTests - - added several statistical tests to StatisticalTests - 1.13.9: - - moved elo, glicko2, trueskill functions under class Metrics - 1.13.8: - - moved Glicko2 to a seperate package - 1.13.7: - - fixed bug with trueskill - 1.13.6: - - cleaned up imports - 1.13.5: - - cleaned up package - 1.13.4: - - small fixes to regression to improve performance - 1.13.3: - - filtered nans from regression - 1.13.2: - - removed torch requirement, and moved Regression back to regression.py - 1.13.1: - - bug fix with linear regression not returning a proper value - - cleaned up regression - - fixed bug with polynomial regressions - 1.13.0: - - fixed all regressions to now properly work - 1.12.6: - - fixed bg with a division by zero in histo_analysis - 1.12.5: - - fixed numba issues by removing numba from elo, glicko2 and trueskill - 1.12.4: - - renamed gliko to glicko - 1.12.3: - - removed depreciated code - 1.12.2: - - removed team first time trueskill instantiation in favor of integration in superscript.py - 1.12.1: - - improved readibility of regression outputs by stripping tensor data - - used map with lambda to acheive the improved readibility - - lost numba jit support with regression, and generated_jit hangs at execution - - TODO: reimplement correct numba integration in regression - 1.12.0: - - temporarily fixed polynomial regressions by using sklearn's PolynomialFeatures - 1.11.010: - - alphabeticaly ordered import lists - 1.11.9: - - bug fixes - 1.11.8: - - bug fixes - 1.11.7: - - bug fixes - 1.11.6: - - tested min and max - - bug fixes - 1.11.5: - - added min and max in basic_stats - 1.11.4: - - bug fixes - 1.11.3: - - bug fixes - 1.11.2: - - consolidated metrics - - fixed __all__ - 1.11.1: - - added test/train split to RandomForestClassifier and RandomForestRegressor - 1.11.0: - - added RandomForestClassifier and RandomForestRegressor - - note: untested - 1.10.0: - - added numba.jit to remaining functions - 1.9.2: - - kernelized PCA and KNN - 1.9.1: - - fixed bugs with SVM and NaiveBayes - 1.9.0: - - added SVM class, subclasses, and functions - - note: untested - 1.8.0: - - added NaiveBayes classification engine - - note: untested - 1.7.0: - - added knn() - - added confusion matrix to decisiontree() - 1.6.2: - - changed layout of __changelog to be vscode friendly - 1.6.1: - - added additional hyperparameters to decisiontree() - 1.6.0: - - fixed __version__ - - fixed __all__ order - - added decisiontree() - 1.5.3: - - added pca - 1.5.2: - - reduced import list - - added kmeans clustering engine - 1.5.1: - - simplified regression by using .to(device) - 1.5.0: - - added polynomial regression to regression(); untested - 1.4.0: - - added trueskill() - 1.3.2: - - renamed regression class to Regression, regression_engine() to regression gliko2_engine class to Gliko2 - 1.3.1: - - changed glicko2() to return tuple instead of array - 1.3.0: - - added glicko2_engine class and glicko() - - verified glicko2() accuracy - 1.2.3: - - fixed elo() - 1.2.2: - - added elo() - - elo() has bugs to be fixed - 1.2.1: - - readded regrression import - 1.2.0: - - integrated regression.py as regression class - - removed regression import - - fixed metadata for regression class - - fixed metadata for analysis class - 1.1.1: - - regression_engine() bug fixes, now actaully regresses - 1.1.0: - - added regression_engine() - - added all regressions except polynomial - 1.0.7: - - updated _init_device() - 1.0.6: - - removed useless try statements - 1.0.5: - - removed impossible outcomes - 1.0.4: - - added performance metrics (r^2, mse, rms) - 1.0.3: - - resolved nopython mode for mean, median, stdev, variance - 1.0.2: - - snapped (removed) majority of uneeded imports - - forced object mode (bad) on all jit - - TODO: stop numba complaining about not being able to compile in nopython mode - 1.0.1: - - removed from sklearn import * to resolve uneeded wildcard imports - 1.0.0: - - removed c_entities,nc_entities,obstacles,objectives from __all__ - - applied numba.jit to all functions - - depreciated and removed stdev_z_split - - cleaned up histo_analysis to include numpy and numba.jit optimizations - - depreciated and removed all regression functions in favor of future pytorch optimizer - - depreciated and removed all nonessential functions (basic_analysis, benchmark, strip_data) - - optimized z_normalize using sklearn.preprocessing.normalize - - TODO: implement kernel/function based pytorch regression optimizer - 0.9.0: - - refactored - - numpyed everything - - removed stats in favor of numpy functions - 0.8.5: - - minor fixes - 0.8.4: - - removed a few unused dependencies - 0.8.3: - - added p_value function - 0.8.2: - - updated __all__ correctly to contain changes made in v 0.8.0 and v 0.8.1 - 0.8.1: - - refactors - - bugfixes - 0.8.0: - - depreciated histo_analysis_old - - depreciated debug - - altered basic_analysis to take array data instead of filepath - - refactor - - optimization - 0.7.2: - - bug fixes - 0.7.1: - - bug fixes - 0.7.0: - - added tanh_regression (logistical regression) - - bug fixes - 0.6.5: - - added z_normalize function to normalize dataset - - bug fixes - 0.6.4: - - bug fixes - 0.6.3: - - bug fixes - 0.6.2: - - bug fixes - 0.6.1: - - corrected __all__ to contain all of the functions - 0.6.0: - - added calc_overfit, which calculates two measures of overfit, error and performance - - added calculating overfit to optimize_regression - 0.5.0: - - added optimize_regression function, which is a sample function to find the optimal regressions - - optimize_regression function filters out some overfit funtions (functions with r^2 = 1) - - planned addition: overfit detection in the optimize_regression function - 0.4.2: - - added __changelog__ - - updated debug function with log and exponential regressions - 0.4.1: - - added log regressions - - added exponential regressions - - added log_regression and exp_regression to __all__ - 0.3.8: - - added debug function to further consolidate functions - 0.3.7: - - added builtin benchmark function - - added builtin random (linear) data generation function - - added device initialization (_init_device) - 0.3.6: - - reorganized the imports list to be in alphabetical order - - added search and regurgitate functions to c_entities, nc_entities, obstacles, objectives - 0.3.5: - - major bug fixes - - updated historical analysis - - depreciated old historical analysis - 0.3.4: - - added __version__, __author__, __all__ - - added polynomial regression - - added root mean squared function - - added r squared function - 0.3.3: - - bug fixes - - added c_entities - 0.3.2: - - bug fixes - - added nc_entities, obstacles, objectives - - consolidated statistics.py to analysis.py - 0.3.1: - - compiled 1d, column, and row basic stats into basic stats function - 0.3.0: - - added historical analysis function - 0.2.x: - - added z score test - 0.1.x: - - major bug fixes - 0.0.x: - - added loading csv - - added 1d, column, row basic stats -""" - -__author__ = ( - "Arthur Lu ", - "Jacob Levine ", -) - -__all__ = [ - 'load_csv', - 'basic_stats', - 'z_score', - 'z_normalize', - 'histo_analysis', - 'regression', - 'Metric', - 'RegressionMetric', - 'ClassificationMetric', - 'kmeans', - 'pca', - 'decisiontree', - 'KNN', - 'NaiveBayes', - 'SVM', - 'RandomForrest', - 'CorrelationTest', - 'StatisticalTest', - 'Array', - # all statistics functions left out due to integration in other functions -] - -# now back to your regularly scheduled programming: - -# imports (now in alphabetical order! v 0.3.006): - -import csv -from tra_analysis.metrics import elo as Elo -from tra_analysis.metrics import glicko2 as Glicko2 -import math -import numba -from numba import jit -import numpy as np -import scipy -from scipy import optimize, stats -import sklearn -from sklearn import preprocessing, pipeline, linear_model, metrics, cluster, decomposition, tree, neighbors, naive_bayes, svm, model_selection, ensemble -from tra_analysis.metrics import trueskill as Trueskill -import warnings - -class error(ValueError): - pass - -def load_csv(filepath): - with open(filepath, newline='') as csvfile: - file_array = np.array(list(csv.reader(csvfile))) - csvfile.close() - return file_array - -# expects 1d array -@jit(forceobj=True) -def basic_stats(data): - - data_t = np.array(data).astype(float) - - _mean = mean(data_t) - _median = median(data_t) - _stdev = stdev(data_t) - _variance = variance(data_t) - _min = npmin(data_t) - _max = npmax(data_t) - - return {"mean": _mean, "median": _median, "standard-deviation": _stdev, "variance": _variance, "minimum": _min, "maximum": _max} - -# returns z score with inputs of point, mean and standard deviation of spread -@jit(forceobj=True) -def z_score(point, mean, stdev): - score = (point - mean) / stdev - - return score - -# expects 2d array, normalizes across all axes -@jit(forceobj=True) -def z_normalize(array, *args): - - array = np.array(array) - for arg in args: - array = sklearn.preprocessing.normalize(array, axis = arg) - - return array - -@jit(forceobj=True) -# expects 2d array of [x,y] -def histo_analysis(hist_data): - - if len(hist_data[0]) > 2: - - hist_data = np.array(hist_data) - derivative = np.array(len(hist_data) - 1, dtype = float) - t = np.diff(hist_data) - derivative = t[1] / t[0] - np.sort(derivative) - - return {"mean": basic_stats(derivative)["mean"], "deviation": basic_stats(derivative)["standard-deviation"]} - - else: - - return None - -def regression(inputs, outputs, args): # inputs, outputs expects N-D array - - X = np.array(inputs) - y = np.array(outputs) - - regressions = {} - - if 'lin' in args: # formula: ax + b - - try: - - def lin(x, a, b): - - return a * x + b - - popt, pcov = scipy.optimize.curve_fit(lin, X, y) - - coeffs = popt.flatten().tolist() - regressions["lin"] = (str(coeffs[0]) + "*x+" + str(coeffs[1])) - - except Exception as e: - - pass - - if 'log' in args: # formula: a log (b(x + c)) + d - - try: - - def log(x, a, b, c, d): - - return a * np.log(b*(x + c)) + d - - popt, pcov = scipy.optimize.curve_fit(log, X, y) - - coeffs = popt.flatten().tolist() - regressions["log"] = (str(coeffs[0]) + "*log(" + str(coeffs[1]) + "*(x+" + str(coeffs[2]) + "))+" + str(coeffs[3])) - - except Exception as e: - - pass - - if 'exp' in args: # formula: a e ^ (b(x + c)) + d - - try: - - def exp(x, a, b, c, d): - - return a * np.exp(b*(x + c)) + d - - popt, pcov = scipy.optimize.curve_fit(exp, X, y) - - coeffs = popt.flatten().tolist() - regressions["exp"] = (str(coeffs[0]) + "*e^(" + str(coeffs[1]) + "*(x+" + str(coeffs[2]) + "))+" + str(coeffs[3])) - - except Exception as e: - - pass - - if 'ply' in args: # formula: a + bx^1 + cx^2 + dx^3 + ... - - inputs = np.array([inputs]) - outputs = np.array([outputs]) - - plys = {} - limit = len(outputs[0]) - - for i in range(2, limit): - - model = sklearn.preprocessing.PolynomialFeatures(degree = i) - model = sklearn.pipeline.make_pipeline(model, sklearn.linear_model.LinearRegression()) - model = model.fit(np.rot90(inputs), np.rot90(outputs)) - - params = model.steps[1][1].intercept_.tolist() - params = np.append(params, model.steps[1][1].coef_[0].tolist()[1::]) - params = params.flatten().tolist() - - temp = "" - counter = 0 - for param in params: - temp += "(" + str(param) + "*x^" + str(counter) + ")" - counter += 1 - plys["x^" + str(i)] = (temp) - - regressions["ply"] = (plys) - - if 'sig' in args: # formula: a tanh (b(x + c)) + d - - try: - - def sig(x, a, b, c, d): - - return a * np.tanh(b*(x + c)) + d - - popt, pcov = scipy.optimize.curve_fit(sig, X, y) - - coeffs = popt.flatten().tolist() - regressions["sig"] = (str(coeffs[0]) + "*tanh(" + str(coeffs[1]) + "*(x+" + str(coeffs[2]) + "))+" + str(coeffs[3])) - - except Exception as e: - - pass - - return regressions - -class Metric: - - def elo(self, starting_score, opposing_score, observed, N, K): - - return Elo.calculate(starting_score, opposing_score, observed, N, K) - - def glicko2(self, starting_score, starting_rd, starting_vol, opposing_score, opposing_rd, observations): - - player = Glicko2.Glicko2(rating = starting_score, rd = starting_rd, vol = starting_vol) - - player.update_player([x for x in opposing_score], [x for x in opposing_rd], observations) - - return (player.rating, player.rd, player.vol) - - def trueskill(self, teams_data, observations): # teams_data is array of array of tuples ie. [[(mu, sigma), (mu, sigma), (mu, sigma)], [(mu, sigma), (mu, sigma), (mu, sigma)]] - - team_ratings = [] - - for team in teams_data: - team_temp = () - for player in team: - player = Trueskill.Rating(player[0], player[1]) - team_temp = team_temp + (player,) - team_ratings.append(team_temp) - - return Trueskill.rate(team_ratings, ranks=observations) - -class RegressionMetric(): - - def __new__(cls, predictions, targets): - - return cls.r_squared(cls, predictions, targets), cls.mse(cls, predictions, targets), cls.rms(cls, predictions, targets) - - def r_squared(self, predictions, targets): # assumes equal size inputs - - return sklearn.metrics.r2_score(targets, predictions) - - def mse(self, predictions, targets): - - return sklearn.metrics.mean_squared_error(targets, predictions) - - def rms(self, predictions, targets): - - return math.sqrt(sklearn.metrics.mean_squared_error(targets, predictions)) - -class ClassificationMetric(): - - def __new__(cls, predictions, targets): - - return cls.cm(cls, predictions, targets), cls.cr(cls, predictions, targets) - - def cm(self, predictions, targets): - - return sklearn.metrics.confusion_matrix(targets, predictions) - - def cr(self, predictions, targets): - - return sklearn.metrics.classification_report(targets, predictions) - -@jit(nopython=True) -def mean(data): - - return np.mean(data) - -@jit(nopython=True) -def median(data): - - return np.median(data) - -@jit(nopython=True) -def stdev(data): - - return np.std(data) - -@jit(nopython=True) -def variance(data): - - return np.var(data) - -@jit(nopython=True) -def npmin(data): - - return np.amin(data) - -@jit(nopython=True) -def npmax(data): - - return np.amax(data) - -@jit(forceobj=True) -def kmeans(data, n_clusters=8, init="k-means++", n_init=10, max_iter=300, tol=0.0001, precompute_distances="auto", verbose=0, random_state=None, copy_x=True, n_jobs=None, algorithm="auto"): - - kernel = sklearn.cluster.KMeans(n_clusters = n_clusters, init = init, n_init = n_init, max_iter = max_iter, tol = tol, precompute_distances = precompute_distances, verbose = verbose, random_state = random_state, copy_x = copy_x, n_jobs = n_jobs, algorithm = algorithm) - kernel.fit(data) - predictions = kernel.predict(data) - centers = kernel.cluster_centers_ - - return centers, predictions - -@jit(forceobj=True) -def pca(data, n_components = None, copy = True, whiten = False, svd_solver = "auto", tol = 0.0, iterated_power = "auto", random_state = None): - - kernel = sklearn.decomposition.PCA(n_components = n_components, copy = copy, whiten = whiten, svd_solver = svd_solver, tol = tol, iterated_power = iterated_power, random_state = random_state) - - return kernel.fit_transform(data) - -@jit(forceobj=True) -def decisiontree(data, labels, test_size = 0.3, criterion = "gini", splitter = "default", max_depth = None): #expects *2d data and 1d labels - - data_train, data_test, labels_train, labels_test = sklearn.model_selection.train_test_split(data, labels, test_size=test_size, random_state=1) - model = sklearn.tree.DecisionTreeClassifier(criterion = criterion, splitter = splitter, max_depth = max_depth) - model = model.fit(data_train,labels_train) - predictions = model.predict(data_test) - metrics = ClassificationMetric(predictions, labels_test) - - return model, metrics - -class KNN: - - def knn_classifier(self, data, labels, n_neighbors, test_size = 0.3, algorithm='auto', leaf_size=30, metric='minkowski', metric_params=None, n_jobs=None, p=2, weights='uniform'): #expects *2d data and 1d labels post-scaling - - data_train, data_test, labels_train, labels_test = sklearn.model_selection.train_test_split(data, labels, test_size=test_size, random_state=1) - model = sklearn.neighbors.KNeighborsClassifier() - model.fit(data_train, labels_train) - predictions = model.predict(data_test) - - return model, ClassificationMetric(predictions, labels_test) - - def knn_regressor(self, data, outputs, n_neighbors, test_size = 0.3, weights = "uniform", algorithm = "auto", leaf_size = 30, p = 2, metric = "minkowski", metric_params = None, n_jobs = None): - - data_train, data_test, outputs_train, outputs_test = sklearn.model_selection.train_test_split(data, outputs, test_size=test_size, random_state=1) - model = sklearn.neighbors.KNeighborsRegressor(n_neighbors = n_neighbors, weights = weights, algorithm = algorithm, leaf_size = leaf_size, p = p, metric = metric, metric_params = metric_params, n_jobs = n_jobs) - model.fit(data_train, outputs_train) - predictions = model.predict(data_test) - - return model, RegressionMetric(predictions, outputs_test) - -class NaiveBayes: - - def guassian(self, data, labels, test_size = 0.3, priors = None, var_smoothing = 1e-09): - - data_train, data_test, labels_train, labels_test = sklearn.model_selection.train_test_split(data, labels, test_size=test_size, random_state=1) - model = sklearn.naive_bayes.GaussianNB(priors = priors, var_smoothing = var_smoothing) - model.fit(data_train, labels_train) - predictions = model.predict(data_test) - - return model, ClassificationMetric(predictions, labels_test) - - def multinomial(self, data, labels, test_size = 0.3, alpha=1.0, fit_prior=True, class_prior=None): - - data_train, data_test, labels_train, labels_test = sklearn.model_selection.train_test_split(data, labels, test_size=test_size, random_state=1) - model = sklearn.naive_bayes.MultinomialNB(alpha = alpha, fit_prior = fit_prior, class_prior = class_prior) - model.fit(data_train, labels_train) - predictions = model.predict(data_test) - - return model, ClassificationMetric(predictions, labels_test) - - def bernoulli(self, data, labels, test_size = 0.3, alpha=1.0, binarize=0.0, fit_prior=True, class_prior=None): - - data_train, data_test, labels_train, labels_test = sklearn.model_selection.train_test_split(data, labels, test_size=test_size, random_state=1) - model = sklearn.naive_bayes.BernoulliNB(alpha = alpha, binarize = binarize, fit_prior = fit_prior, class_prior = class_prior) - model.fit(data_train, labels_train) - predictions = model.predict(data_test) - - return model, ClassificationMetric(predictions, labels_test) - - def complement(self, data, labels, test_size = 0.3, alpha=1.0, fit_prior=True, class_prior=None, norm=False): - - data_train, data_test, labels_train, labels_test = sklearn.model_selection.train_test_split(data, labels, test_size=test_size, random_state=1) - model = sklearn.naive_bayes.ComplementNB(alpha = alpha, fit_prior = fit_prior, class_prior = class_prior, norm = norm) - model.fit(data_train, labels_train) - predictions = model.predict(data_test) - - return model, ClassificationMetric(predictions, labels_test) - -class SVM: - - class CustomKernel: - - def __new__(cls, C, kernel, degre, gamma, coef0, shrinking, probability, tol, cache_size, class_weight, verbose, max_iter, decision_function_shape, random_state): - - return sklearn.svm.SVC(C = C, kernel = kernel, gamma = gamma, coef0 = coef0, shrinking = shrinking, probability = probability, tol = tol, cache_size = cache_size, class_weight = class_weight, verbose = verbose, max_iter = max_iter, decision_function_shape = decision_function_shape, random_state = random_state) - - class StandardKernel: - - def __new__(cls, kernel, C=1.0, degree=3, gamma='auto_deprecated', coef0=0.0, shrinking=True, probability=False, tol=0.001, cache_size=200, class_weight=None, verbose=False, max_iter=-1, decision_function_shape='ovr', random_state=None): - - return sklearn.svm.SVC(C = C, kernel = kernel, gamma = gamma, coef0 = coef0, shrinking = shrinking, probability = probability, tol = tol, cache_size = cache_size, class_weight = class_weight, verbose = verbose, max_iter = max_iter, decision_function_shape = decision_function_shape, random_state = random_state) - - class PrebuiltKernel: - - class Linear: - - def __new__(cls): - - return sklearn.svm.SVC(kernel = 'linear') - - class Polynomial: - - def __new__(cls, power, r_bias): - - return sklearn.svm.SVC(kernel = 'polynomial', degree = power, coef0 = r_bias) - - class RBF: - - def __new__(cls, gamma): - - return sklearn.svm.SVC(kernel = 'rbf', gamma = gamma) - - class Sigmoid: - - def __new__(cls, r_bias): - - return sklearn.svm.SVC(kernel = 'sigmoid', coef0 = r_bias) - - def fit(self, kernel, train_data, train_outputs): # expects *2d data, 1d labels or outputs - - return kernel.fit(train_data, train_outputs) - - def eval_classification(self, kernel, test_data, test_outputs): - - predictions = kernel.predict(test_data) - - return ClassificationMetric(predictions, test_outputs) - - def eval_regression(self, kernel, test_data, test_outputs): - - predictions = kernel.predict(test_data) - - return RegressionMetric(predictions, test_outputs) - -class RandomForest: - - def random_forest_classifier(self, data, labels, test_size, n_estimators, criterion="gini", max_depth=None, min_samples_split=2, min_samples_leaf=1, min_weight_fraction_leaf=0.0, max_features="auto", max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, bootstrap=True, oob_score=False, n_jobs=None, random_state=None, verbose=0, warm_start=False, class_weight=None): - - data_train, data_test, labels_train, labels_test = sklearn.model_selection.train_test_split(data, labels, test_size=test_size, random_state=1) - kernel = sklearn.ensemble.RandomForestClassifier(n_estimators = n_estimators, criterion = criterion, max_depth = max_depth, min_samples_split = min_samples_split, min_samples_leaf = min_samples_leaf, min_weight_fraction_leaf = min_weight_fraction_leaf, max_leaf_nodes = max_leaf_nodes, min_impurity_decrease = min_impurity_decrease, bootstrap = bootstrap, oob_score = oob_score, n_jobs = n_jobs, random_state = random_state, verbose = verbose, warm_start = warm_start, class_weight = class_weight) - kernel.fit(data_train, labels_train) - predictions = kernel.predict(data_test) - - return kernel, ClassificationMetric(predictions, labels_test) - - def random_forest_regressor(self, data, outputs, test_size, n_estimators, criterion="mse", max_depth=None, min_samples_split=2, min_samples_leaf=1, min_weight_fraction_leaf=0.0, max_features="auto", max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, bootstrap=True, oob_score=False, n_jobs=None, random_state=None, verbose=0, warm_start=False): - - data_train, data_test, outputs_train, outputs_test = sklearn.model_selection.train_test_split(data, outputs, test_size=test_size, random_state=1) - kernel = sklearn.ensemble.RandomForestRegressor(n_estimators = n_estimators, criterion = criterion, max_depth = max_depth, min_samples_split = min_samples_split, min_weight_fraction_leaf = min_weight_fraction_leaf, max_features = max_features, max_leaf_nodes = max_leaf_nodes, min_impurity_decrease = min_impurity_decrease, min_impurity_split = min_impurity_split, bootstrap = bootstrap, oob_score = oob_score, n_jobs = n_jobs, random_state = random_state, verbose = verbose, warm_start = warm_start) - kernel.fit(data_train, outputs_train) - predictions = kernel.predict(data_test) - - return kernel, RegressionMetric(predictions, outputs_test) - -class CorrelationTest: - - def anova_oneway(self, *args): #expects arrays of samples - - results = scipy.stats.f_oneway(*args) - return {"f-value": results[0], "p-value": results[1]} - - def pearson(self, x, y): - - results = scipy.stats.pearsonr(x, y) - return {"r-value": results[0], "p-value": results[1]} - - def spearman(self, a, b = None, axis = 0, nan_policy = 'propagate'): - - results = scipy.stats.spearmanr(a, b = b, axis = axis, nan_policy = nan_policy) - return {"r-value": results[0], "p-value": results[1]} - - def point_biserial(self, x,y): - - results = scipy.stats.pointbiserialr(x, y) - return {"r-value": results[0], "p-value": results[1]} - - def kendall(self, x, y, initial_lexsort = None, nan_policy = 'propagate', method = 'auto'): - - results = scipy.stats.kendalltau(x, y, initial_lexsort = initial_lexsort, nan_policy = nan_policy, method = method) - return {"tau": results[0], "p-value": results[1]} - - def kendall_weighted(self, x, y, rank = True, weigher = None, additive = True): - - results = scipy.stats.weightedtau(x, y, rank = rank, weigher = weigher, additive = additive) - return {"tau": results[0], "p-value": results[1]} - - def mgc(self, x, y, compute_distance = None, reps = 1000, workers = 1, is_twosamp = False, random_state = None): - - results = scipy.stats.multiscale_graphcorr(x, y, compute_distance = compute_distance, reps = reps, workers = workers, is_twosamp = is_twosamp, random_state = random_state) - return {"k-value": results[0], "p-value": results[1], "data": results[2]} # unsure if MGC test returns a k value - -class StatisticalTest: - - def ttest_onesample(self, a, popmean, axis = 0, nan_policy = 'propagate'): - - results = scipy.stats.ttest_1samp(a, popmean, axis = axis, nan_policy = nan_policy) - return {"t-value": results[0], "p-value": results[1]} - - def ttest_independent(self, a, b, equal = True, nan_policy = 'propagate'): - - results = scipy.stats.ttest_ind(a, b, equal_var = equal, nan_policy = nan_policy) - return {"t-value": results[0], "p-value": results[1]} - - def ttest_statistic(self, o1, o2, equal = True): - - results = scipy.stats.ttest_ind_from_stats(o1["mean"], o1["std"], o1["nobs"], o2["mean"], o2["std"], o2["nobs"], equal_var = equal) - return {"t-value": results[0], "p-value": results[1]} - - def ttest_related(self, a, b, axis = 0, nan_policy='propagate'): - - results = scipy.stats.ttest_rel(a, b, axis = axis, nan_policy = nan_policy) - return {"t-value": results[0], "p-value": results[1]} - - def ks_fitness(self, rvs, cdf, args = (), N = 20, alternative = 'two-sided', mode = 'approx'): - - results = scipy.stats.kstest(rvs, cdf, args = args, N = N, alternative = alternative, mode = mode) - return {"ks-value": results[0], "p-value": results[1]} - - def chisquare(self, f_obs, f_exp = None, ddof = None, axis = 0): - - results = scipy.stats.chisquare(f_obs, f_exp = f_exp, ddof = ddof, axis = axis) - return {"chisquared-value": results[0], "p-value": results[1]} - - def powerdivergence(self, f_obs, f_exp = None, ddof = None, axis = 0, lambda_ = None): - - results = scipy.stats.power_divergence(f_obs, f_exp = f_exp, ddof = ddof, axis = axis, lambda_ = lambda_) - return {"powerdivergence-value": results[0], "p-value": results[1]} - - def ks_twosample(self, x, y, alternative = 'two_sided', mode = 'auto'): - - results = scipy.stats.ks_2samp(x, y, alternative = alternative, mode = mode) - return {"ks-value": results[0], "p-value": results[1]} - - def es_twosample(self, x, y, t = (0.4, 0.8)): - - results = scipy.stats.epps_singleton_2samp(x, y, t = t) - return {"es-value": results[0], "p-value": results[1]} - - def mw_rank(self, x, y, use_continuity = True, alternative = None): - - results = scipy.stats.mannwhitneyu(x, y, use_continuity = use_continuity, alternative = alternative) - return {"u-value": results[0], "p-value": results[1]} - - def mw_tiecorrection(self, rank_values): - - results = scipy.stats.tiecorrect(rank_values) - return {"correction-factor": results} - - def rankdata(self, a, method = 'average'): - - results = scipy.stats.rankdata(a, method = method) - return results - - def wilcoxon_ranksum(self, a, b): # this seems to be superceded by Mann Whitney Wilcoxon U Test - - results = scipy.stats.ranksums(a, b) - return {"u-value": results[0], "p-value": results[1]} - - def wilcoxon_signedrank(self, x, y = None, zero_method = 'wilcox', correction = False, alternative = 'two-sided'): - - results = scipy.stats.wilcoxon(x, y = y, zero_method = zero_method, correction = correction, alternative = alternative) - return {"t-value": results[0], "p-value": results[1]} - - def kw_htest(self, *args, nan_policy = 'propagate'): - - results = scipy.stats.kruskal(*args, nan_policy = nan_policy) - return {"h-value": results[0], "p-value": results[1]} - - def friedman_chisquare(self, *args): - - results = scipy.stats.friedmanchisquare(*args) - return {"chisquared-value": results[0], "p-value": results[1]} - - def bm_wtest(self, x, y, alternative = 'two-sided', distribution = 't', nan_policy = 'propagate'): - - results = scipy.stats.brunnermunzel(x, y, alternative = alternative, distribution = distribution, nan_policy = nan_policy) - return {"w-value": results[0], "p-value": results[1]} - - def combine_pvalues(self, pvalues, method = 'fisher', weights = None): - - results = scipy.stats.combine_pvalues(pvalues, method = method, weights = weights) - return {"combined-statistic": results[0], "p-value": results[1]} - - def jb_fitness(self, x): - - results = scipy.stats.jarque_bera(x) - return {"jb-value": results[0], "p-value": results[1]} - - def ab_equality(self, x, y): - - results = scipy.stats.ansari(x, y) - return {"ab-value": results[0], "p-value": results[1]} - - def bartlett_variance(self, *args): - - results = scipy.stats.bartlett(*args) - return {"t-value": results[0], "p-value": results[1]} - - def levene_variance(self, *args, center = 'median', proportiontocut = 0.05): - - results = scipy.stats.levene(*args, center = center, proportiontocut = proportiontocut) - return {"w-value": results[0], "p-value": results[1]} - - def sw_normality(self, x): - - results = scipy.stats.shapiro(x) - return {"w-value": results[0], "p-value": results[1]} - - def shapiro(self, x): - - return "destroyed by facts and logic" - - def ad_onesample(self, x, dist = 'norm'): - - results = scipy.stats.anderson(x, dist = dist) - return {"d-value": results[0], "critical-values": results[1], "significance-value": results[2]} - - def ad_ksample(self, samples, midrank = True): - - results = scipy.stats.anderson_ksamp(samples, midrank = midrank) - return {"d-value": results[0], "critical-values": results[1], "significance-value": results[2]} - - def binomial(self, x, n = None, p = 0.5, alternative = 'two-sided'): - - results = scipy.stats.binom_test(x, n = n, p = p, alternative = alternative) - return {"p-value": results} - - def fk_variance(self, *args, center = 'median', proportiontocut = 0.05): - - results = scipy.stats.fligner(*args, center = center, proportiontocut = proportiontocut) - return {"h-value": results[0], "p-value": results[1]} # unknown if the statistic is an h value - - def mood_mediantest(self, *args, ties = 'below', correction = True, lambda_ = 1, nan_policy = 'propagate'): - - results = scipy.stats.median_test(*args, ties = ties, correction = correction, lambda_ = lambda_, nan_policy = nan_policy) - return {"chisquared-value": results[0], "p-value": results[1], "m-value": results[2], "table": results[3]} - - def mood_equalscale(self, x, y, axis = 0): - - results = scipy.stats.mood(x, y, axis = axis) - return {"z-score": results[0], "p-value": results[1]} - - def skewtest(self, a, axis = 0, nan_policy = 'propogate'): - - results = scipy.stats.skewtest(a, axis = axis, nan_policy = nan_policy) - return {"z-score": results[0], "p-value": results[1]} - - def kurtosistest(self, a, axis = 0, nan_policy = 'propogate'): - - results = scipy.stats.kurtosistest(a, axis = axis, nan_policy = nan_policy) - return {"z-score": results[0], "p-value": results[1]} - - def normaltest(self, a, axis = 0, nan_policy = 'propogate'): - - results = scipy.stats.normaltest(a, axis = axis, nan_policy = nan_policy) - return {"z-score": results[0], "p-value": results[1]} - -class Array(): # tests on nd arrays independent of basic_stats - - def __init__(self, narray): - - self.array = np.array(narray) - - def __str__(self): - - return str(self.array) - - def elementwise_mean(self, *args, axis = 0): # expects arrays that are size normalized - if len(*args) == 0: - return np.mean(self.array, axis = axis) - else: - return np.mean([*args], axis = axis) - - def elementwise_median(self, *args, axis = 0): - - if len(*args) == 0: - return np.median(self.array, axis = axis) - else: - return np.median([*args], axis = axis) - - def elementwise_stdev(self, *args, axis = 0): - - if len(*args) == 0: - return np.std(self.array, axis = axis) - else: - return np.std([*args], axis = axis) - - def elementwise_variance(self, *args, axis = 0): - - if len(*args) == 0: - return np.var(self.array, axis = axis) - else: - return np.var([*args], axis = axis) - - def elementwise_npmin(self, *args, axis = 0): - - if len(*args) == 0: - return np.amin(self.array, axis = axis) - else: - return np.amin([*args], axis = axis) - - def elementwise_npmax(self, *args, axis = 0): - - if len(*args) == 0: - return np.amax(self.array, axis = axis) - else: - return np.amax([*args], axis = axis) - - def elementwise_stats(self, *args, axis = 0): - - _mean = self.elementwise_mean(*args, axis = axis) - _median = self.elementwise_median(*args, axis = axis) - _stdev = self.elementwise_stdev(*args, axis = axis) - _variance = self.elementwise_variance(*args, axis = axis) - _min = self.elementwise_npmin(*args, axis = axis) - _max = self.elementwise_npmax(*args, axis = axis) - - return _mean, _median, _stdev, _variance, _min, _max - - def __getitem__(self, key): - - return self.array[key] - - def __setitem__(self, key, value): - - self.array[key] == value - - def normalize(self, array): - - a = np.atleast_1d(np.linalg.norm(array)) - a[a==0] = 1 - return array / np.expand_dims(a, -1) - - def __add__(self, other): - - return self.array + other.array - - def __sub__(self, other): - - return self.array - other.array - - def __neg__(self): - - return -self.array - - def __abs__(self): - - return abs(self.array) - - def __invert__(self): - - return 1/self.array - - def __mul__(self, other): - - return self.array.dot(other.array) - - def __rmul__(self, other): - - return self.array.dot(other.array) - - def cross(self, other): - - return np.cross(self.array, other.array) - - def sort(self, array): # depreciated - warnings.warn("Array.sort has been depreciated in favor of Sort") - array_length = len(array) - if array_length <= 1: - return array - middle_index = int(array_length / 2) - left = array[0:middle_index] - right = array[middle_index:] - left = self.sort(left) - right = self.sort(right) - return self.__merge(left, right) - - - def __merge(self, left, right): - sorted_list = [] - left = left[:] - right = right[:] - while len(left) > 0 or len(right) > 0: - if len(left) > 0 and len(right) > 0: - if left[0] <= right[0]: - sorted_list.append(left.pop(0)) - else: - sorted_list.append(right.pop(0)) - elif len(left) > 0: - sorted_list.append(left.pop(0)) - elif len(right) > 0: - sorted_list.append(right.pop(0)) - return sorted_list - - def search(self, arr, x): - return self.__search(arr, 0, len(arr) - 1, x) - - def __search(self, arr, low, high, x): - if high >= low: - mid = (high + low) // 2 - if arr[mid] == x: - return mid - elif arr[mid] > x: - return binary_search(arr, low, mid - 1, x) - else: - return binary_search(arr, mid + 1, high, x) - else: - return -1 - -class Sort: # if you haven't used a sort, then you've never lived - - def quicksort(self, a): - - def sort(array): - - less = [] - equal = [] - greater = [] - - if len(array) > 1: - pivot = array[0] - for x in array: - if x < pivot: - less.append(x) - elif x == pivot: - equal.append(x) - elif x > pivot: - greater.append(x) - return sort(less)+equal+sort(greater) - else: - return array - - return np.array(sort(a)) - - def mergesort(self, a): - - def sort(array): - - array = array - - if len(array) >1: - middle = len(array) // 2 - L = array[:middle] - R = array[middle:] - - sort(L) - sort(R) - - i = j = k = 0 - - while i < len(L) and j < len(R): - if L[i] < R[j]: - array[k] = L[i] - i+= 1 - else: - array[k] = R[j] - j+= 1 - k+= 1 - - while i < len(L): - array[k] = L[i] - i+= 1 - k+= 1 - - while j < len(R): - array[k] = R[j] - j+= 1 - k+= 1 - - return array - - return sort(a) - - def introsort(self, a): - - def sort(array, start, end, maxdepth): - - array = array - - if end - start <= 1: - return - elif maxdepth == 0: - heapsort(array, start, end) - else: - p = partition(array, start, end) - sort(array, start, p + 1, maxdepth - 1) - sort(array, p + 1, end, maxdepth - 1) - - return array - - def partition(array, start, end): - pivot = array[start] - i = start - 1 - j = end - - while True: - i = i + 1 - while array[i] < pivot: - i = i + 1 - j = j - 1 - while array[j] > pivot: - j = j - 1 - - if i >= j: - return j - - swap(array, i, j) - - def swap(array, i, j): - array[i], array[j] = array[j], array[i] - - def heapsort(array, start, end): - build_max_heap(array, start, end) - for i in range(end - 1, start, -1): - swap(array, start, i) - max_heapify(array, index=0, start=start, end=i) - - def build_max_heap(array, start, end): - def parent(i): - return (i - 1)//2 - length = end - start - index = parent(length - 1) - while index >= 0: - max_heapify(array, index, start, end) - index = index - 1 - - def max_heapify(array, index, start, end): - def left(i): - return 2*i + 1 - def right(i): - return 2*i + 2 - - size = end - start - l = left(index) - r = right(index) - if (l < size and array[start + l] > array[start + index]): - largest = l - else: - largest = index - if (r < size and array[start + r] > array[start + largest]): - largest = r - if largest != index: - swap(array, start + largest, start + index) - max_heapify(array, largest, start, end) - - maxdepth = (len(a).bit_length() - 1)*2 - - return sort(a, 0, len(a), maxdepth) - - def heapsort(self, a): - - def sort(array): - - array = array - - n = len(array) - - for i in range(n//2 - 1, -1, -1): - heapify(array, n, i) - - for i in range(n-1, 0, -1): - array[i], array[0] = array[0], array[i] - heapify(array, i, 0) - - return array - - def heapify(array, n, i): - - array = array - - largest = i - l = 2 * i + 1 - r = 2 * i + 2 - - if l < n and array[i] < array[l]: - largest = l - - if r < n and array[largest] < array[r]: - largest = r - - if largest != i: - array[i],array[largest] = array[largest],array[i] - heapify(array, n, largest) - - return array - - return sort(a) - - def insertionsort(self, a): - - def sort(array): - - array = array - - for i in range(1, len(array)): - - key = array[i] - - j = i-1 - while j >=0 and key < array[j] : - array[j+1] = array[j] - j -= 1 - array[j+1] = key - - return array - - return sort(a) - - def timsort(self, a, block = 32): - - BLOCK = block - - def sort(array, n): - - array = array - - for i in range(0, n, BLOCK): - insertionsort(array, i, min((i+31), (n-1))) - - size = BLOCK - while size < n: - - for left in range(0, n, 2*size): - - mid = left + size - 1 - right = min((left + 2*size - 1), (n-1)) - merge(array, left, mid, right) - - size = 2*size - - return array - - def insertionsort(array, left, right): - - array = array - - for i in range(left + 1, right+1): - - temp = array[i] - j = i - 1 - while j >= left and array[j] > temp : - - array[j+1] = array[j] - j -= 1 - - array[j+1] = temp - - return array - - - def merge(array, l, m, r): - - len1, len2 = m - l + 1, r - m - left, right = [], [] - for i in range(0, len1): - left.append(array[l + i]) - for i in range(0, len2): - right.append(array[m + 1 + i]) - - i, j, k = 0, 0, l - - while i < len1 and j < len2: - - if left[i] <= right[j]: - array[k] = left[i] - i += 1 - - else: - array[k] = right[j] - j += 1 - - k += 1 - - while i < len1: - - array[k] = left[i] - k += 1 - i += 1 - - while j < len2: - array[k] = right[j] - k += 1 - j += 1 - - return sort(a, len(a)) - - def selectionsort(self, a): - array = a - for i in range(len(array)): - min_idx = i - for j in range(i+1, len(array)): - if array[min_idx] > array[j]: - min_idx = j - array[i], array[min_idx] = array[min_idx], array[i] - return array - - def shellsort(self, a): - array = a - n = len(array) - gap = n//2 - - while gap > 0: - - for i in range(gap,n): - - temp = array[i] - j = i - while j >= gap and array[j-gap] >temp: - array[j] = array[j-gap] - j -= gap - array[j] = temp - gap //= 2 - - return array - - def bubblesort(self, a): - - def sort(array): - for i, num in enumerate(array): - try: - if array[i+1] < num: - array[i] = array[i+1] - array[i+1] = num - sort(array) - except IndexError: - pass - return array - - return sort(a) - - def cyclesort(self, a): - - def sort(array): - - array = array - writes = 0 - - for cycleStart in range(0, len(array) - 1): - item = array[cycleStart] - - pos = cycleStart - for i in range(cycleStart + 1, len(array)): - if array[i] < item: - pos += 1 - - if pos == cycleStart: - continue - - while item == array[pos]: - pos += 1 - array[pos], item = item, array[pos] - writes += 1 - - while pos != cycleStart: - - pos = cycleStart - for i in range(cycleStart + 1, len(array)): - if array[i] < item: - pos += 1 - - while item == array[pos]: - pos += 1 - array[pos], item = item, array[pos] - writes += 1 - - return array - - return sort(a) - - def cocktailsort(self, a): - - def sort(array): - - array = array - - n = len(array) - swapped = True - start = 0 - end = n-1 - while (swapped == True): - swapped = False - for i in range (start, end): - if (array[i] > array[i + 1]) : - array[i], array[i + 1]= array[i + 1], array[i] - swapped = True - if (swapped == False): - break - swapped = False - end = end-1 - for i in range(end-1, start-1, -1): - if (array[i] > array[i + 1]): - array[i], array[i + 1] = array[i + 1], array[i] - swapped = True - start = start + 1 - - return array - - return sort(a) \ No newline at end of file diff --git a/analysis-master/tra_analysis/equation.ipynb b/analysis-master/tra_analysis/equation.ipynb deleted file mode 100644 index 0d8ef4ea..00000000 --- a/analysis-master/tra_analysis/equation.ipynb +++ /dev/null @@ -1,162 +0,0 @@ -{ - "cells": [ - { - "cell_type": "code", - "execution_count": 2, - "metadata": {}, - "outputs": [], - "source": [ - "import re\n", - "from decimal import Decimal\n", - "from functools import reduce" - ] - }, - { - "cell_type": "code", - "execution_count": 3, - "metadata": {}, - "outputs": [], - "source": [ - "def add(string):\n", - " while(len(re.findall(\"[+]{1}[-]?\", string)) != 0):\n", - " string = re.sub(\"[-]?\\d+[.]?\\d*[+]{1}[-]?\\d+[.]?\\d*\", str(\"%f\" % reduce((lambda x, y: x + y), [Decimal(i) for i in re.split(\"[+]{1}\", re.search(\"[-]?\\d+[.]?\\d*[+]{1}[-]?\\d+[.]?\\d*\", string).group())])), string, 1)\n", - " return string" - ] - }, - { - "cell_type": "code", - "execution_count": 4, - "metadata": {}, - "outputs": [], - "source": [ - "def sub(string):\n", - " while(len(re.findall(\"\\d+[.]?\\d*[-]{1,2}\\d+[.]?\\d*\", string)) != 0):\n", - " g = re.search(\"\\d+[.]?\\d*[-]{1,2}\\d+[.]?\\d*\", string).group()\n", - " if(re.search(\"[-]{1,2}\", g).group() == \"-\"):\n", - " r = re.sub(\"[-]{1}\", \"+-\", g, 1)\n", - " string = re.sub(g, r, string, 1)\n", - " elif(re.search(\"[-]{1,2}\", g).group() == \"--\"):\n", - " r = re.sub(\"[-]{2}\", \"+\", g, 1)\n", - " string = re.sub(g, r, string, 1)\n", - " else:\n", - " pass\n", - " return string" - ] - }, - { - "cell_type": "code", - "execution_count": 5, - "metadata": {}, - "outputs": [], - "source": [ - "def mul(string):\n", - " while(len(re.findall(\"[*]{1}[-]?\", string)) != 0):\n", - " string = re.sub(\"[-]?\\d+[.]?\\d*[*]{1}[-]?\\d+[.]?\\d*\", str(\"%f\" % reduce((lambda x, y: x * y), [Decimal(i) for i in re.split(\"[*]{1}\", re.search(\"[-]?\\d+[.]?\\d*[*]{1}[-]?\\d+[.]?\\d*\", string).group())])), string, 1)\n", - " return string" - ] - }, - { - "cell_type": "code", - "execution_count": 6, - "metadata": {}, - "outputs": [], - "source": [ - "def div(string):\n", - " while(len(re.findall(\"[/]{1}[-]?\", string)) != 0):\n", - " string = re.sub(\"[-]?\\d+[.]?\\d*[/]{1}[-]?\\d+[.]?\\d*\", str(\"%f\" % reduce((lambda x, y: x / y), [Decimal(i) for i in re.split(\"[/]{1}\", re.search(\"[-]?\\d+[.]?\\d*[/]{1}[-]?\\d+[.]?\\d*\", string).group())])), string, 1)\n", - " return string" - ] - }, - { - "cell_type": "code", - "execution_count": 7, - "metadata": {}, - "outputs": [], - "source": [ - "def exp(string):\n", - " while(len(re.findall(\"[\\^]{1}[-]?\", string)) != 0):\n", - " string = re.sub(\"[-]?\\d+[.]?\\d*[\\^]{1}[-]?\\d+[.]?\\d*\", str(\"%f\" % reduce((lambda x, y: x ** y), [Decimal(i) for i in re.split(\"[\\^]{1}\", re.search(\"[-]?\\d+[.]?\\d*[\\^]{1}[-]?\\d+[.]?\\d*\", string).group())])), string, 1)\n", - " return string" - ] - }, - { - "cell_type": "code", - "execution_count": 12, - "metadata": {}, - "outputs": [], - "source": [ - "def evaluate(string):\n", - " string = exp(string)\n", - " string = div(string)\n", - " string = mul(string)\n", - " string = sub(string)\n", - " print(string)\n", - " string = add(string)\n", - " return string" - ] - }, - { - "cell_type": "code", - "execution_count": 13, - "metadata": {}, - "outputs": [ - { - "output_type": "error", - "ename": "SyntaxError", - "evalue": "unexpected EOF while parsing (, line 1)", - "traceback": [ - "\u001b[1;36m File \u001b[1;32m\"\"\u001b[1;36m, line \u001b[1;32m1\u001b[0m\n\u001b[1;33m def parentheses(string):\u001b[0m\n\u001b[1;37m ^\u001b[0m\n\u001b[1;31mSyntaxError\u001b[0m\u001b[1;31m:\u001b[0m unexpected EOF while parsing\n" - ] - } - ], - "source": [ - "def parentheses(string):" - ] - }, - { - "cell_type": "code", - "execution_count": 22, - "metadata": {}, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": "-158456325028528675187087900672.000000+0.8\n" - }, - { - "output_type": "execute_result", - "data": { - "text/plain": "'-158456325028528675187087900672.000000'" - }, - "metadata": {}, - "execution_count": 22 - } - ], - "source": [ - "string = \"8^32*4/-2+0.8\"\n", - "evaluate(string)" - ] - } - ], - "metadata": { - "kernelspec": { - "display_name": "Python 3", - "language": "python", - "name": "python3" - }, - "language_info": { - "codemirror_mode": { - "name": "ipython", - "version": 3 - }, - "file_extension": ".py", - "mimetype": "text/x-python", - "name": "python", - "nbconvert_exporter": "python", - "pygments_lexer": "ipython3", - "version": "3.7.6-final" - } - }, - "nbformat": 4, - "nbformat_minor": 4 -} \ No newline at end of file diff --git a/analysis-master/tra_analysis/equation/Expression.py b/analysis-master/tra_analysis/equation/Expression.py new file mode 100644 index 00000000..4ab2767a --- /dev/null +++ b/analysis-master/tra_analysis/equation/Expression.py @@ -0,0 +1,37 @@ +# Titan Robotics Team 2022: Expression submodule +# Written by Arthur Lu +# Notes: +# this should be imported as a python module using 'from tra_analysis.Equation import Expression' +# TODO: +# - add option to pick parser backend +# - fix unit tests +# setup: + +__version__ = "0.0.1-alpha" + +__changelog__ = """changelog: + 0.0.1-alpha: + - used the HybridExpressionParser as backend for Expression +""" + +__author__ = ( + "Arthur Lu ", +) + +__all__ = { + "Expression" +} + +import re +from .parser import BNF, RegexInplaceParser, HybridExpressionParser, Core, equation_base + +class Expression(HybridExpressionParser): + + expression = None + core = None + + def __init__(self,expression,argorder=[],*args,**kwargs): + self.core = Core() + equation_base.equation_extend(self.core) + self.core.recalculateFMatch() + super().__init__(self.core, expression, argorder=[],*args,**kwargs) \ No newline at end of file diff --git a/analysis-master/tra_analysis/equation/__init__.py b/analysis-master/tra_analysis/equation/__init__.py new file mode 100644 index 00000000..8bfe8316 --- /dev/null +++ b/analysis-master/tra_analysis/equation/__init__.py @@ -0,0 +1,22 @@ +# Titan Robotics Team 2022: Expression submodule +# Written by Arthur Lu +# Notes: +# this should be imported as a python module using 'from tra_analysis import Equation' +# setup: + +__version__ = "0.0.1-alpha" + +__changelog__ = """changelog: + 0.0.1-alpha: + - made first prototype of Expression +""" + +__author__ = ( + "Arthur Lu ", +) + +__all__ = { + "Expression" +} + +from .Expression import Expression \ No newline at end of file diff --git a/analysis-master/tra_analysis/equation/parser/BNF.py b/analysis-master/tra_analysis/equation/parser/BNF.py new file mode 100644 index 00000000..97b2bfb4 --- /dev/null +++ b/analysis-master/tra_analysis/equation/parser/BNF.py @@ -0,0 +1,97 @@ +from __future__ import division +from pyparsing import (Literal, CaselessLiteral, Word, Combine, Group, Optional, ZeroOrMore, Forward, nums, alphas, oneOf) +from . import py2 +import math +import operator + +class BNF(object): + + def pushFirst(self, strg, loc, toks): + self.exprStack.append(toks[0]) + + def pushUMinus(self, strg, loc, toks): + if toks and toks[0] == '-': + self.exprStack.append('unary -') + + def __init__(self): + """ + expop :: '^' + multop :: '*' | '/' + addop :: '+' | '-' + integer :: ['+' | '-'] '0'..'9'+ + atom :: PI | E | real | fn '(' expr ')' | '(' expr ')' + factor :: atom [ expop factor ]* + term :: factor [ multop factor ]* + expr :: term [ addop term ]* + """ + point = Literal(".") + e = CaselessLiteral("E") + fnumber = Combine(Word("+-" + nums, nums) + + Optional(point + Optional(Word(nums))) + + Optional(e + Word("+-" + nums, nums))) + ident = Word(alphas, alphas + nums + "_$") + plus = Literal("+") + minus = Literal("-") + mult = Literal("*") + div = Literal("/") + lpar = Literal("(").suppress() + rpar = Literal(")").suppress() + addop = plus | minus + multop = mult | div + expop = Literal("^") + pi = CaselessLiteral("PI") + expr = Forward() + atom = ((Optional(oneOf("- +")) + + (ident + lpar + expr + rpar | pi | e | fnumber).setParseAction(self.pushFirst)) + | Optional(oneOf("- +")) + Group(lpar + expr + rpar) + ).setParseAction(self.pushUMinus) + factor = Forward() + factor << atom + \ + ZeroOrMore((expop + factor).setParseAction(self.pushFirst)) + term = factor + \ + ZeroOrMore((multop + factor).setParseAction(self.pushFirst)) + expr << term + \ + ZeroOrMore((addop + term).setParseAction(self.pushFirst)) + + self.bnf = expr + + epsilon = 1e-12 + + self.opn = {"+": operator.add, + "-": operator.sub, + "*": operator.mul, + "/": operator.truediv, + "^": operator.pow} + self.fn = {"sin": math.sin, + "cos": math.cos, + "tan": math.tan, + "exp": math.exp, + "abs": abs, + "trunc": lambda a: int(a), + "round": round, + "sgn": lambda a: abs(a) > epsilon and py2.cmp(a, 0) or 0} + + def evaluateStack(self, s): + op = s.pop() + if op == 'unary -': + return -self.evaluateStack(s) + if op in "+-*/^": + op2 = self.evaluateStack(s) + op1 = self.evaluateStack(s) + return self.opn[op](op1, op2) + elif op == "PI": + return math.pi + elif op == "E": + return math.e + elif op in self.fn: + return self.fn[op](self.evaluateStack(s)) + elif op[0].isalpha(): + return 0 + else: + return float(op) + + def eval(self, num_string, parseAll=True): + self.exprStack = [] + results = self.bnf.parseString(num_string, parseAll) + val = self.evaluateStack(self.exprStack[:]) + return val \ No newline at end of file diff --git a/analysis-master/tra_analysis/equation/parser/Hybrid.py b/analysis-master/tra_analysis/equation/parser/Hybrid.py new file mode 100644 index 00000000..4f41c7b1 --- /dev/null +++ b/analysis-master/tra_analysis/equation/parser/Hybrid.py @@ -0,0 +1,521 @@ +from .Hybrid_Utils import Core, ExpressionFunction, ExpressionVariable, ExpressionValue +import sys + +if sys.version_info >= (3,): + xrange = range + basestring = str + +class HybridExpressionParser(object): + + def __init__(self,core,expression,argorder=[],*args,**kwargs): + super(HybridExpressionParser,self).__init__(*args,**kwargs) + if isinstance(expression,type(self)): # clone the object + self.core = core + self.__args = list(expression.__args) + self.__vars = dict(expression.__vars) # intenral array of preset variables + self.__argsused = set(expression.__argsused) + self.__expr = list(expression.__expr) + self.variables = {} # call variables + else: + self.__expression = expression + self.__args = argorder; + self.__vars = {} # intenral array of preset variables + self.__argsused = set() + self.__expr = [] # compiled equation tokens + self.variables = {} # call variables + self.__compile() + del self.__expression + + def __getitem__(self, name): + if name in self.__argsused: + if name in self.__vars: + return self.__vars[name] + else: + return None + else: + raise KeyError(name) + + def __setitem__(self,name,value): + + if name in self.__argsused: + self.__vars[name] = value + else: + raise KeyError(name) + + def __delitem__(self,name): + + if name in self.__argsused: + if name in self.__vars: + del self.__vars[name] + else: + raise KeyError(name) + + def __contains__(self, name): + + return name in self.__argsused + + def __call__(self,*args,**kwargs): + + if len(self.__expr) == 0: + return None + self.variables = {} + self.variables.update(self.core.constants) + self.variables.update(self.__vars) + if len(args) > len(self.__args): + raise TypeError("<{0:s}.{1:s}({2:s}) object at {3:0=#10x}>() takes at most {4:d} arguments ({5:d} given)".format( + type(self).__module__,type(self).__name__,repr(self),id(self),len(self.__args),len(args))) + for i in xrange(len(args)): + if i < len(self.__args): + if self.__args[i] in kwargs: + raise TypeError("<{0:s}.{1:s}({2:s}) object at {3:0=#10x}>() got multiple values for keyword argument '{4:s}'".format( + type(self).__module__,type(self).__name__,repr(self),id(self),self.__args[i])) + self.variables[self.__args[i]] = args[i] + self.variables.update(kwargs) + for arg in self.__argsused: + if arg not in self.variables: + min_args = len(self.__argsused - (set(self.__vars.keys()) | set(self.core.constants.keys()))) + raise TypeError("<{0:s}.{1:s}({2:s}) object at {3:0=#10x}>() takes at least {4:d} arguments ({5:d} given) '{6:s}' not defined".format( + type(self).__module__,type(self).__name__,repr(self),id(self),min_args,len(args)+len(kwargs),arg)) + expr = self.__expr[::-1] + args = [] + while len(expr) > 0: + t = expr.pop() + r = t(args,self) + args.append(r) + if len(args) > 1: + return args + else: + return args[0] + + def __next(self,__expect_op): + if __expect_op: + m = self.core.gematch.match(self.__expression) + if m != None: + self.__expression = self.__expression[m.end():] + g = m.groups() + return g[0],'CLOSE' + m = self.core.smatch.match(self.__expression) + if m != None: + self.__expression = self.__expression[m.end():] + return ",",'SEP' + m = self.core.omatch.match(self.__expression) + if m != None: + self.__expression = self.__expression[m.end():] + g = m.groups() + return g[0],'OP' + else: + m = self.core.gsmatch.match(self.__expression) + if m != None: + self.__expression = self.__expression[m.end():] + g = m.groups() + return g[0],'OPEN' + m = self.core.vmatch.match(self.__expression) + if m != None: + self.__expression = self.__expression[m.end():] + g = m.groupdict(0) + if g['dec']: + if g["ivalue"]: + return complex(int(g["rsign"]+"1")*float(g["rvalue"])*10**int(g["rexpoent"]),int(g["isign"]+"1")*float(g["ivalue"])*10**int(g["iexpoent"])),'VALUE' + elif g["rexpoent"] or g["rvalue"].find('.')>=0: + return int(g["rsign"]+"1")*float(g["rvalue"])*10**int(g["rexpoent"]),'VALUE' + else: + return int(g["rsign"]+"1")*int(g["rvalue"]),'VALUE' + elif g["hex"]: + return int(g["hexsign"]+"1")*int(g["hexvalue"],16),'VALUE' + elif g["oct"]: + return int(g["octsign"]+"1")*int(g["octvalue"],8),'VALUE' + elif g["bin"]: + return int(g["binsign"]+"1")*int(g["binvalue"],2),'VALUE' + else: + raise NotImplemented("'{0:s}' Values Not Implemented Yet".format(m.string)) + m = self.core.nmatch.match(self.__expression) + if m != None: + self.__expression = self.__expression[m.end():] + g = m.groups() + return g[0],'NAME' + m = self.core.fmatch.match(self.__expression) + if m != None: + self.__expression = self.__expression[m.end():] + g = m.groups() + return g[0],'FUNC' + m = self.core.umatch.match(self.__expression) + if m != None: + self.__expression = self.__expression[m.end():] + g = m.groups() + return g[0],'UNARY' + return None + + def show(self): + """Show RPN tokens + + This will print out the internal token list (RPN) of the expression + one token perline. + """ + for expr in self.__expr: + print(expr) + + def __str__(self): + """str(fn) + + Generates a Printable version of the Expression + + Returns + ------- + str + Latex String respresation of the Expression, suitable for rendering the equation + """ + expr = self.__expr[::-1] + if len(expr) == 0: + return "" + args = []; + while len(expr) > 0: + t = expr.pop() + r = t.toStr(args,self) + args.append(r) + if len(args) > 1: + return args + else: + return args[0] + + def __repr__(self): + """repr(fn) + + Generates a String that correctrly respresents the equation + + Returns + ------- + str + Convert the Expression to a String that passed to the constructor, will constuct + an identical equation object (in terms of sequence of tokens, and token type/value) + """ + expr = self.__expr[::-1] + if len(expr) == 0: + return "" + args = []; + while len(expr) > 0: + t = expr.pop() + r = t.toRepr(args,self) + args.append(r) + if len(args) > 1: + return args + else: + return args[0] + + def __iter__(self): + return iter(self.__argsused) + + def __lt__(self, other): + if isinstance(other, Expression): + return repr(self) < repr(other) + else: + raise TypeError("{0:s} is not an {1:s} Object, and can't be compared to an Expression Object".format(repr(other), type(other))) + + def __eq__(self, other): + if isinstance(other, Expression): + return repr(self) == repr(other) + else: + raise TypeError("{0:s} is not an {1:s} Object, and can't be compared to an Expression Object".format(repr(other), type(other))) + + def __combine(self,other,op): + if op not in self.core.ops or not isinstance(other,(int,float,complex,type(self),basestring)): + return NotImplemented + else: + obj = type(self)(self) + if isinstance(other,(int,float,complex)): + obj.__expr.append(ExpressionValue(other)) + else: + if isinstance(other,basestring): + try: + other = type(self)(other) + except: + raise SyntaxError("Can't Convert string, \"{0:s}\" to an Expression Object".format(other)) + obj.__expr += other.__expr + obj.__argsused |= other.__argsused + for v in other.__args: + if v not in obj.__args: + obj.__args.append(v) + for k,v in other.__vars.items(): + if k not in obj.__vars: + obj.__vars[k] = v + elif v != obj.__vars[k]: + raise RuntimeError("Predifined Variable Conflict in '{0:s}' two differing values defined".format(k)) + fn = self.core.ops[op] + obj.__expr.append(ExpressionFunction(fn['func'],fn['args'],fn['str'],fn['latex'],op,False)) + return obj + + def __rcombine(self,other,op): + if op not in self.core.ops or not isinstance(other,(int,float,complex,type(self),basestring)): + return NotImplemented + else: + obj = type(self)(self) + if isinstance(other,(int,float,complex)): + obj.__expr.insert(0,ExpressionValue(other)) + else: + if isinstance(other,basestring): + try: + other = type(self)(other) + except: + raise SyntaxError("Can't Convert string, \"{0:s}\" to an Expression Object".format(other)) + obj.__expr = other.__expr + self.__expr + obj.__argsused = other.__argsused | self.__expr + __args = other.__args + for v in obj.__args: + if v not in __args: + __args.append(v) + obj.__args = __args + for k,v in other.__vars.items(): + if k not in obj.__vars: + obj.__vars[k] = v + elif v != obj.__vars[k]: + raise RuntimeError("Predifined Variable Conflict in '{0:s}' two differing values defined".format(k)) + fn = self.core.ops[op] + obj.__expr.append(ExpressionFunction(fn['func'],fn['args'],fn['str'],fn['latex'],op,False)) + return obj + + def __icombine(self,other,op): + if op not in self.core.ops or not isinstance(other,(int,float,complex,type(self),basestring)): + return NotImplemented + else: + obj = self + if isinstance(other,(int,float,complex)): + obj.__expr.append(ExpressionValue(other)) + else: + if isinstance(other,basestring): + try: + other = type(self)(other) + except: + raise SyntaxError("Can't Convert string, \"{0:s}\" to an Expression Object".format(other)) + obj.__expr += other.__expr + obj.__argsused |= other.__argsused + for v in other.__args: + if v not in obj.__args: + obj.__args.append(v) + for k,v in other.__vars.items(): + if k not in obj.__vars: + obj.__vars[k] = v + elif v != obj.__vars[k]: + raise RuntimeError("Predifined Variable Conflict in '{0:s}' two differing values defined".format(k)) + fn = self.core.ops[op] + obj.__expr.append(ExpressionFunction(fn['func'],fn['args'],fn['str'],fn['latex'],op,False)) + return obj + + def __apply(self,op): + fn = self.core.unary_ops[op] + obj = type(self)(self) + obj.__expr.append(ExpressionFunction(fn['func'],1,fn['str'],fn['latex'],op,False)) + return obj + + def __applycall(self,op): + fn = self.core.functions[op] + if 1 not in fn['args'] or '*' not in fn['args']: + raise RuntimeError("Can't Apply {0:s} function, dosen't accept only 1 argument".format(op)) + obj = type(self)(self) + obj.__expr.append(ExpressionFunction(fn['func'],1,fn['str'],fn['latex'],op,False)) + return obj + + def __add__(self,other): + return self.__combine(other,'+') + + def __sub__(self,other): + return self.__combine(other,'-') + + def __mul__(self,other): + return self.__combine(other,'*') + + def __div__(self,other): + return self.__combine(other,'/') + + def __truediv__(self,other): + return self.__combine(other,'/') + + def __pow__(self,other): + return self.__combine(other,'^') + + def __mod__(self,other): + return self.__combine(other,'%') + + def __and__(self,other): + return self.__combine(other,'&') + + def __or__(self,other): + return self.__combine(other,'|') + + def __xor__(self,other): + return self.__combine(other,'') + + def __radd__(self,other): + return self.__rcombine(other,'+') + + def __rsub__(self,other): + return self.__rcombine(other,'-') + + def __rmul__(self,other): + return self.__rcombine(other,'*') + + def __rdiv__(self,other): + return self.__rcombine(other,'/') + + def __rtruediv__(self,other): + return self.__rcombine(other,'/') + + def __rpow__(self,other): + return self.__rcombine(other,'^') + + def __rmod__(self,other): + return self.__rcombine(other,'%') + + def __rand__(self,other): + return self.__rcombine(other,'&') + + def __ror__(self,other): + return self.__rcombine(other,'|') + + def __rxor__(self,other): + return self.__rcombine(other,'') + + def __iadd__(self,other): + return self.__icombine(other,'+') + + def __isub__(self,other): + return self.__icombine(other,'-') + + def __imul__(self,other): + return self.__icombine(other,'*') + + def __idiv__(self,other): + return self.__icombine(other,'/') + + def __itruediv__(self,other): + return self.__icombine(other,'/') + + def __ipow__(self,other): + return self.__icombine(other,'^') + + def __imod__(self,other): + return self.__icombine(other,'%') + + def __iand__(self,other): + return self.__icombine(other,'&') + + def __ior__(self,other): + return self.__icombine(other,'|') + + def __ixor__(self,other): + return self.__icombine(other,'') + + def __neg__(self): + return self.__apply('-') + + def __invert__(self): + return self.__apply('!') + + def __abs__(self): + return self.__applycall('abs') + + def __getfunction(self,op): + if op[1] == 'FUNC': + fn = self.core.functions[op[0]] + fn['type'] = 'FUNC' + elif op[1] == 'UNARY': + fn = self.core.unary_ops[op[0]] + fn['type'] = 'UNARY' + fn['args'] = 1 + elif op[1] == 'OP': + fn = self.core.ops[op[0]] + fn['type'] = 'OP' + return fn + + def __compile(self): + self.__expr = [] + stack = [] + argc = [] + __expect_op = False + v = self.__next(__expect_op) + while v != None: + if not __expect_op and v[1] == "OPEN": + stack.append(v) + __expect_op = False + elif __expect_op and v[1] == "CLOSE": + op = stack.pop() + while op[1] != "OPEN": + fs = self.__getfunction(op) + self.__expr.append(ExpressionFunction(fs['func'],fs['args'],fs['str'],fs['latex'],op[0],False)) + op = stack.pop() + if len(stack) > 0 and stack[-1][0] in self.core.functions: + op = stack.pop() + fs = self.core.functions[op[0]] + args = argc.pop() + if fs['args'] != '+' and (args != fs['args'] and args not in fs['args']): + raise SyntaxError("Invalid number of arguments for {0:s} function".format(op[0])) + self.__expr.append(ExpressionFunction(fs['func'],args,fs['str'],fs['latex'],op[0],True)) + __expect_op = True + elif __expect_op and v[0] == ",": + argc[-1] += 1 + op = stack.pop() + while op[1] != "OPEN": + fs = self.__getfunction(op) + self.__expr.append(ExpressionFunction(fs['func'],fs['args'],fs['str'],fs['latex'],op[0],False)) + op = stack.pop() + stack.append(op) + __expect_op = False + elif __expect_op and v[0] in self.core.ops: + fn = self.core.ops[v[0]] + if len(stack) == 0: + stack.append(v) + __expect_op = False + v = self.__next(__expect_op) + continue + op = stack.pop() + if op[0] == "(": + stack.append(op) + stack.append(v) + __expect_op = False + v = self.__next(__expect_op) + continue + fs = self.__getfunction(op) + while True: + if (fn['prec'] >= fs['prec']): + self.__expr.append(ExpressionFunction(fs['func'],fs['args'],fs['str'],fs['latex'],op[0],False)) + if len(stack) == 0: + stack.append(v) + break + op = stack.pop() + if op[0] == "(": + stack.append(op) + stack.append(v) + break + fs = self.__getfunction(op) + else: + stack.append(op) + stack.append(v) + break + __expect_op = False + elif not __expect_op and v[0] in self.core.unary_ops: + fn = self.core.unary_ops[v[0]] + stack.append(v) + __expect_op = False + elif not __expect_op and v[0] in self.core.functions: + stack.append(v) + argc.append(1) + __expect_op = False + elif not __expect_op and v[1] == 'NAME': + self.__argsused.add(v[0]) + if v[0] not in self.__args: + self.__args.append(v[0]) + self.__expr.append(ExpressionVariable(v[0])) + __expect_op = True + elif not __expect_op and v[1] == 'VALUE': + self.__expr.append(ExpressionValue(v[0])) + __expect_op = True + else: + raise SyntaxError("Invalid Token \"{0:s}\" in Expression, Expected {1:s}".format(v,"Op" if __expect_op else "Value")) + v = self.__next(__expect_op) + if len(stack) > 0: + op = stack.pop() + while op != "(": + fs = self.__getfunction(op) + self.__expr.append(ExpressionFunction(fs['func'],fs['args'],fs['str'],fs['latex'],op[0],False)) + if len(stack) > 0: + op = stack.pop() + else: + break \ No newline at end of file diff --git a/analysis-master/tra_analysis/equation/parser/Hybrid_Utils/ExpressionCore.py b/analysis-master/tra_analysis/equation/parser/Hybrid_Utils/ExpressionCore.py new file mode 100644 index 00000000..f45de197 --- /dev/null +++ b/analysis-master/tra_analysis/equation/parser/Hybrid_Utils/ExpressionCore.py @@ -0,0 +1,237 @@ +import math +import sys +import re + +if sys.version_info >= (3,): + xrange = range + basestring = str + +class ExpressionObject(object): + def __init__(self,*args,**kwargs): + super(ExpressionObject,self).__init__(*args,**kwargs) + + def toStr(self,args,expression): + return "" + + def toRepr(self,args,expression): + return "" + + def __call__(self,args,expression): + pass + +class ExpressionValue(ExpressionObject): + def __init__(self,value,*args,**kwargs): + super(ExpressionValue,self).__init__(*args,**kwargs) + self.value = value + + def toStr(self,args,expression): + if (isinstance(self.value,complex)): + V = [self.value.real,self.value.imag] + E = [0,0] + B = [0,0] + out = ["",""] + for i in xrange(2): + if V[i] == 0: + E[i] = 0 + B[i] = 0 + else: + E[i] = int(math.floor(math.log10(abs(V[i])))) + B[i] = V[i]*10**-E[i] + if E[i] in [0,1,2,3] and str(V[i])[-2:] == ".0": + B[i] = int(V[i]) + E[i] = 0 + if E[i] in [-1,-2] and len(str(V[i])) <= 7: + B[i] = V[i] + E[i] = 0 + if i == 1: + fmt = "{{0:+{0:s}}}" + else: + fmt = "{{0:-{0:s}}}" + if type(B[i]) == int: + out[i] += fmt.format('d').format(B[i]) + else: + out[i] += fmt.format('.5f').format(B[i]).rstrip("0.") + if i == 1: + out[i] += "\\imath" + if E[i] != 0: + out[i] += "\\times10^{{{0:d}}}".format(E[i]) + return "\\left(" + ''.join(out) + "\\right)" + elif (isinstance(self.value,float)): + V = self.value + E = 0 + B = 0 + out = "" + if V == 0: + E = 0 + B = 0 + else: + E = int(math.floor(math.log10(abs(V)))) + B = V*10**-E + if E in [0,1,2,3] and str(V)[-2:] == ".0": + B = int(V) + E = 0 + if E in [-1,-2] and len(str(V)) <= 7: + B = V + E = 0 + if type(B) == int: + out += "{0:-d}".format(B) + else: + out += "{0:-.5f}".format(B).rstrip("0.") + if E != 0: + out += "\\times10^{{{0:d}}}".format(E) + return "\\left(" + out + "\\right)" + else: + return out + else: + return str(self.value) + + def toRepr(self,args,expression): + return str(self.value) + + def __call__(self,args,expression): + return self.value + + def __repr__(self): + return "<{0:s}.{1:s}({2:s}) object at {3:0=#10x}>".format(type(self).__module__,type(self).__name__,str(self.value),id(self)) + +class ExpressionFunction(ExpressionObject): + def __init__(self,function,nargs,form,display,id,isfunc,*args,**kwargs): + super(ExpressionFunction,self).__init__(*args,**kwargs) + self.function = function + self.nargs = nargs + self.form = form + self.display = display + self.id = id + self.isfunc = isfunc + + def toStr(self,args,expression): + params = [] + for i in xrange(self.nargs): + params.append(args.pop()) + if self.isfunc: + return str(self.display.format(','.join(params[::-1]))) + else: + return str(self.display.format(*params[::-1])) + + def toRepr(self,args,expression): + params = [] + for i in xrange(self.nargs): + params.append(args.pop()) + if self.isfunc: + return str(self.form.format(','.join(params[::-1]))) + else: + return str(self.form.format(*params[::-1])) + + def __call__(self,args,expression): + params = [] + for i in xrange(self.nargs): + params.append(args.pop()) + return self.function(*params[::-1]) + + def __repr__(self): + return "<{0:s}.{1:s}({2:s},{3:d}) object at {4:0=#10x}>".format(type(self).__module__,type(self).__name__,str(self.id),self.nargs,id(self)) + +class ExpressionVariable(ExpressionObject): + def __init__(self,name,*args,**kwargs): + super(ExpressionVariable,self).__init__(*args,**kwargs) + self.name = name + + def toStr(self,args,expression): + return str(self.name) + + def toRepr(self,args,expression): + return str(self.name) + + def __call__(self,args,expression): + if self.name in expression.variables: + return expression.variables[self.name] + else: + return 0 # Default variables to return 0 + + def __repr__(self): + return "<{0:s}.{1:s}({2:s}) object at {3:0=#10x}>".format(type(self).__module__,type(self).__name__,str(self.name),id(self)) + +class Core(): + + constants = {} + unary_ops = {} + ops = {} + functions = {} + smatch = re.compile(r"\s*,") + vmatch = re.compile(r"\s*" + "(?:" + "(?P" + "(?P[+-]?)" + r"\s*0o" + "(?P[0-7]+)" + ")|(?P" + "(?P[+-]?)" + r"\s*0x" + "(?P[0-9a-fA-F]+)" + ")|(?P" + "(?P[+-]?)" + r"\s*0b" + "(?P[01]+)" + ")|(?P" + "(?P[+-]?)" + r"\s*" + r"(?P(?:\d+\.\d+|\d+\.|\.\d+|\d+))" + "(?:" + "[Ee]" + r"(?P[+-]?\d+)" + ")?" + "(?:" + r"\s*" + r"(?P(?(rvalue)\+|))?" + r"\s*" + "(?P(?(rvalue)(?(sep)[+-]?|[+-])|[+-]?)?)" + r"\s*" + r"(?P(?:\d+\.\d+|\d+\.|\.\d+|\d+))" + "(?:" + "[Ee]" + r"(?P[+-]?\d+)" + ")?" + "[ij]" + ")?" + ")" + ")") + nmatch = re.compile(r"\s*([a-zA-Z_][a-zA-Z0-9_]*)") + gsmatch = re.compile(r'\s*(\()') + gematch = re.compile(r'\s*(\))') + + def recalculateFMatch(self): + + fks = sorted(self.functions.keys(), key=len, reverse=True) + oks = sorted(self.ops.keys(), key=len, reverse=True) + uks = sorted(self.unary_ops.keys(), key=len, reverse=True) + self.fmatch = re.compile(r'\s*(' + '|'.join(map(re.escape,fks)) + ')') + self.omatch = re.compile(r'\s*(' + '|'.join(map(re.escape,oks)) + ')') + self.umatch = re.compile(r'\s*(' + '|'.join(map(re.escape,uks)) + ')') + + def addFn(self,id,str,latex,args,func): + self.functions[id] = { + 'str': str, + 'latex': latex, + 'args': args, + 'func': func} + + def addOp(self,id,str,latex,single,prec,func): + if single: + raise RuntimeError("Single Ops Not Yet Supported") + self.ops[id] = { + 'str': str, + 'latex': latex, + 'args': 2, + 'prec': prec, + 'func': func} + + def addUnaryOp(self,id,str,latex,func): + self.unary_ops[id] = { + 'str': str, + 'latex': latex, + 'args': 1, + 'prec': 0, + 'func': func} + + def addConst(self,name,value): + self.constants[name] = value \ No newline at end of file diff --git a/analysis-master/tra_analysis/equation/parser/Hybrid_Utils/__init__.py b/analysis-master/tra_analysis/equation/parser/Hybrid_Utils/__init__.py new file mode 100644 index 00000000..9fcda82e --- /dev/null +++ b/analysis-master/tra_analysis/equation/parser/Hybrid_Utils/__init__.py @@ -0,0 +1,2 @@ +from . import equation_base as equation_base +from .ExpressionCore import ExpressionValue, ExpressionFunction, ExpressionVariable, Core \ No newline at end of file diff --git a/analysis-master/tra_analysis/equation/parser/Hybrid_Utils/equation_base.py b/analysis-master/tra_analysis/equation/parser/Hybrid_Utils/equation_base.py new file mode 100644 index 00000000..5710c965 --- /dev/null +++ b/analysis-master/tra_analysis/equation/parser/Hybrid_Utils/equation_base.py @@ -0,0 +1,106 @@ +try: + import numpy as np + has_numpy = True +except ImportError: + import math + has_numpy = False +try: + import scipy.constants + has_scipy = True +except ImportError: + has_scipy = False +import operator as op +from .similar import sim, nsim, gsim, lsim + +def equation_extend(core): + def product(*args): + if len(args) == 1 and has_numpy: + return np.prod(args[0]) + else: + return reduce(op.mul,args,1) + + def sumargs(*args): + if len(args) == 1: + return sum(args[0]) + else: + return sum(args) + + core.addOp('+',"({0:s} + {1:s})","\\left({0:s} + {1:s}\\right)",False,3,op.add) + core.addOp('-',"({0:s} - {1:s})","\\left({0:s} - {1:s}\\right)",False,3,op.sub) + core.addOp('*',"({0:s} * {1:s})","\\left({0:s} \\times {1:s}\\right)",False,2,op.mul) + core.addOp('/',"({0:s} / {1:s})","\\frac{{{0:s}}}{{{1:s}}}",False,2,op.truediv) + core.addOp('%',"({0:s} % {1:s})","\\left({0:s} \\bmod {1:s}\\right)",False,2,op.mod) + core.addOp('^',"({0:s} ^ {1:s})","{0:s}^{{{1:s}}}",False,1,op.pow) + core.addOp('**',"({0:s} ^ {1:s})","{0:s}^{{{1:s}}}",False,1,op.pow) + core.addOp('&',"({0:s} & {1:s})","\\left({0:s} \\land {1:s}\\right)",False,4,op.and_) + core.addOp('|',"({0:s} | {1:s})","\\left({0:s} \\lor {1:s}\\right)",False,4,op.or_) + core.addOp('',"({0:s} {1:s})","\\left({0:s} \\oplus {1:s}\\right)",False,4,op.xor) + core.addOp('&|',"({0:s} {1:s})","\\left({0:s} \\oplus {1:s}\\right)",False,4,op.xor) + core.addOp('|&',"({0:s} {1:s})","\\left({0:s} \\oplus {1:s}\\right)",False,4,op.xor) + core.addOp('==',"({0:s} == {1:s})","\\left({0:s} = {1:s}\\right)",False,5,op.eq) + core.addOp('=',"({0:s} == {1:s})","\\left({0:s} = {1:s}\\right)",False,5,op.eq) + core.addOp('~',"({0:s} ~ {1:s})","\\left({0:s} \\approx {1:s}\\right)",False,5,sim) + core.addOp('!~',"({0:s} !~ {1:s})","\\left({0:s} \\not\\approx {1:s}\\right)",False,5,nsim) + core.addOp('!=',"({0:s} != {1:s})","\\left({0:s} \\neg {1:s}\\right)",False,5,op.ne) + core.addOp('<>',"({0:s} != {1:s})","\\left({0:s} \\neg {1:s}\\right)",False,5,op.ne) + core.addOp('><',"({0:s} != {1:s})","\\left({0:s} \\neg {1:s}\\right)",False,5,op.ne) + core.addOp('<',"({0:s} < {1:s})","\\left({0:s} < {1:s}\\right)",False,5,op.lt) + core.addOp('>',"({0:s} > {1:s})","\\left({0:s} > {1:s}\\right)",False,5,op.gt) + core.addOp('<=',"({0:s} <= {1:s})","\\left({0:s} \\leq {1:s}\\right)",False,5,op.le) + core.addOp('>=',"({0:s} >= {1:s})","\\left({0:s} \\geq {1:s}\\right)",False,5,op.ge) + core.addOp('=<',"({0:s} <= {1:s})","\\left({0:s} \\leq {1:s}\\right)",False,5,op.le) + core.addOp('=>',"({0:s} >= {1:s})","\\left({0:s} \\geq {1:s}\\right)",False,5,op.ge) + core.addOp('<~',"({0:s} <~ {1:s})","\\left({0:s} \lessapprox {1:s}\\right)",False,5,lsim) + core.addOp('>~',"({0:s} >~ {1:s})","\\left({0:s} \\gtrapprox {1:s}\\right)",False,5,gsim) + core.addOp('~<',"({0:s} <~ {1:s})","\\left({0:s} \lessapprox {1:s}\\right)",False,5,lsim) + core.addOp('~>',"({0:s} >~ {1:s})","\\left({0:s} \\gtrapprox {1:s}\\right)",False,5,gsim) + core.addUnaryOp('!',"(!{0:s})","\\neg{0:s}",op.not_) + core.addUnaryOp('-',"-{0:s}","-{0:s}",op.neg) + core.addFn('abs',"abs({0:s})","\\left|{0:s}\\right|",1,op.abs) + core.addFn('sum',"sum({0:s})","\\sum\\left({0:s}\\right)",'+',sumargs) + core.addFn('prod',"prod({0:s})","\\prod\\left({0:s}\\right)",'+',product) + if has_numpy: + core.addFn('floor',"floor({0:s})","\\lfloor {0:s} \\rfloor",1,np.floor) + core.addFn('ceil',"ceil({0:s})","\\lceil {0:s} \\rceil",1,np.ceil) + core.addFn('round',"round({0:s})","\\lfloor {0:s} \\rceil",1,np.round) + core.addFn('sin',"sin({0:s})","\\sin\\left({0:s}\\right)",1,np.sin) + core.addFn('cos',"cos({0:s})","\\cos\\left({0:s}\\right)",1,np.cos) + core.addFn('tan',"tan({0:s})","\\tan\\left({0:s}\\right)",1,np.tan) + core.addFn('re',"re({0:s})","\\Re\\left({0:s}\\right)",1,np.real) + core.addFn('im',"re({0:s})","\\Im\\left({0:s}\\right)",1,np.imag) + core.addFn('sqrt',"sqrt({0:s})","\\sqrt{{{0:s}}}",1,np.sqrt) + core.addConst("pi",np.pi) + core.addConst("e",np.e) + core.addConst("Inf",np.Inf) + core.addConst("NaN",np.NaN) + else: + core.addFn('floor',"floor({0:s})","\\lfloor {0:s} \\rfloor",1,math.floor) + core.addFn('ceil',"ceil({0:s})","\\lceil {0:s} \\rceil",1,math.ceil) + core.addFn('round',"round({0:s})","\\lfloor {0:s} \\rceil",1,round) + core.addFn('sin',"sin({0:s})","\\sin\\left({0:s}\\right)",1,math.sin) + core.addFn('cos',"cos({0:s})","\\cos\\left({0:s}\\right)",1,math.cos) + core.addFn('tan',"tan({0:s})","\\tan\\left({0:s}\\right)",1,math.tan) + core.addFn('re',"re({0:s})","\\Re\\left({0:s}\\right)",1,complex.real) + core.addFn('im',"re({0:s})","\\Im\\left({0:s}\\right)",1,complex.imag) + core.addFn('sqrt',"sqrt({0:s})","\\sqrt{{{0:s}}}",1,math.sqrt) + core.addConst("pi",math.pi) + core.addConst("e",math.e) + core.addConst("Inf",float("Inf")) + core.addConst("NaN",float("NaN")) + if has_scipy: + core.addConst("h",scipy.constants.h) + core.addConst("hbar",scipy.constants.hbar) + core.addConst("m_e",scipy.constants.m_e) + core.addConst("m_p",scipy.constants.m_p) + core.addConst("m_n",scipy.constants.m_n) + core.addConst("c",scipy.constants.c) + core.addConst("N_A",scipy.constants.N_A) + core.addConst("mu_0",scipy.constants.mu_0) + core.addConst("eps_0",scipy.constants.epsilon_0) + core.addConst("k",scipy.constants.k) + core.addConst("G",scipy.constants.G) + core.addConst("g",scipy.constants.g) + core.addConst("q",scipy.constants.e) + core.addConst("R",scipy.constants.R) + core.addConst("sigma",scipy.constants.e) + core.addConst("Rb",scipy.constants.Rydberg) \ No newline at end of file diff --git a/analysis-master/tra_analysis/equation/parser/Hybrid_Utils/similar.py b/analysis-master/tra_analysis/equation/parser/Hybrid_Utils/similar.py new file mode 100644 index 00000000..faf2979e --- /dev/null +++ b/analysis-master/tra_analysis/equation/parser/Hybrid_Utils/similar.py @@ -0,0 +1,49 @@ +_tol = 1e-5 + +def sim(a,b): + if (a==b): + return True + elif a == 0 or b == 0: + return False + if (a_tol + else: + return (1-b/a)>_tol + +def gsim(a,b): + if a >= b: + return True + return (1-a/b)<=_tol + +def lsim(a,b): + if a <= b: + return True + return (1-b/a)<=_tol + +def set_tol(value=1e-5): + r"""Set Error Tolerance + + Set the tolerance for detriming if two numbers are simliar, i.e + :math:`\left|\frac{a}{b}\right| = 1 \pm tolerance` + + Parameters + ---------- + value: float + The Value to set the tolerance to show be very small as it respresents the + percentage of acceptable error in detriming if two values are the same. + """ + global _tol + if isinstance(value,float): + _tol = value + else: + raise TypeError(type(value)) \ No newline at end of file diff --git a/analysis-master/tra_analysis/equation/parser/RegexInplaceParser.py b/analysis-master/tra_analysis/equation/parser/RegexInplaceParser.py new file mode 100644 index 00000000..d8886878 --- /dev/null +++ b/analysis-master/tra_analysis/equation/parser/RegexInplaceParser.py @@ -0,0 +1,51 @@ +import re +from decimal import Decimal +from functools import reduce + +class RegexInplaceParser(object): + + def __init__(self, string): + + self.string = string + + def add(self, string): + while(len(re.findall("[+]{1}[-]?", string)) != 0): + string = re.sub("[-]?\d+[.]?\d*[+]{1}[-]?\d+[.]?\d*", str("%f" % reduce((lambda x, y: x + y), [Decimal(i) for i in re.split("[+]{1}", re.search("[-]?\d+[.]?\d*[+]{1}[-]?\d+[.]?\d*", string).group())])), string, 1) + return string + + def sub(self, string): + while(len(re.findall("\d+[.]?\d*[-]{1,2}\d+[.]?\d*", string)) != 0): + g = re.search("\d+[.]?\d*[-]{1,2}\d+[.]?\d*", string).group() + if(re.search("[-]{1,2}", g).group() == "-"): + r = re.sub("[-]{1}", "+-", g, 1) + string = re.sub(g, r, string, 1) + elif(re.search("[-]{1,2}", g).group() == "--"): + r = re.sub("[-]{2}", "+", g, 1) + string = re.sub(g, r, string, 1) + else: + pass + return string + + def mul(self, string): + while(len(re.findall("[*]{1}[-]?", string)) != 0): + string = re.sub("[-]?\d+[.]?\d*[*]{1}[-]?\d+[.]?\d*", str("%f" % reduce((lambda x, y: x * y), [Decimal(i) for i in re.split("[*]{1}", re.search("[-]?\d+[.]?\d*[*]{1}[-]?\d+[.]?\d*", string).group())])), string, 1) + return string + + def div(self, string): + while(len(re.findall("[/]{1}[-]?", string)) != 0): + string = re.sub("[-]?\d+[.]?\d*[/]{1}[-]?\d+[.]?\d*", str("%f" % reduce((lambda x, y: x / y), [Decimal(i) for i in re.split("[/]{1}", re.search("[-]?\d+[.]?\d*[/]{1}[-]?\d+[.]?\d*", string).group())])), string, 1) + return string + + def exp(self, string): + while(len(re.findall("[\^]{1}[-]?", string)) != 0): + string = re.sub("[-]?\d+[.]?\d*[\^]{1}[-]?\d+[.]?\d*", str("%f" % reduce((lambda x, y: x ** y), [Decimal(i) for i in re.split("[\^]{1}", re.search("[-]?\d+[.]?\d*[\^]{1}[-]?\d+[.]?\d*", string).group())])), string, 1) + return string + + def evaluate(self): + string = self.string + string = self.exp(string) + string = self.div(string) + string = self.mul(string) + string = self.sub(string) + string = self.add(string) + return string \ No newline at end of file diff --git a/analysis-master/tra_analysis/equation/parser/__init__.py b/analysis-master/tra_analysis/equation/parser/__init__.py new file mode 100644 index 00000000..7c0a4447 --- /dev/null +++ b/analysis-master/tra_analysis/equation/parser/__init__.py @@ -0,0 +1,34 @@ +# Titan Robotics Team 2022: Expression submodule +# Written by Arthur Lu +# Notes: +# this should be imported as a python module using 'from tra_analysis.Equation import parser' +# setup: + +__version__ = "0.0.4-alpha" + +__changelog__ = """changelog: + 0.0.4-alpha: + - moved individual parsers to their own files + 0.0.3-alpha: + - readded old regex based parser as RegexInplaceParser + 0.0.2-alpha: + - wrote BNF using pyparsing and uses a BNF metasyntax + - renamed this submodule parser + 0.0.1-alpha: + - took items from equation.ipynb and ported here +""" + +__author__ = ( + "Arthur Lu ", +) + +__all__ = { + "BNF", + "RegexInplaceParser", + "HybridExpressionParser" +} + +from .BNF import BNF as BNF +from .RegexInplaceParser import RegexInplaceParser as RegexInplaceParser +from .Hybrid import HybridExpressionParser +from .Hybrid_Utils import equation_base, Core \ No newline at end of file diff --git a/analysis-master/tra_analysis/equation/parser/py2.py b/analysis-master/tra_analysis/equation/parser/py2.py new file mode 100644 index 00000000..862f0e98 --- /dev/null +++ b/analysis-master/tra_analysis/equation/parser/py2.py @@ -0,0 +1,21 @@ +# Titan Robotics Team 2022: py2 module +# Written by Arthur Lu +# Notes: +# this module should only be used internally, contains old python 2.X functions that have been removed. +# setup: + +from __future__ import division + +__version__ = "1.0.0" + +__changelog__ = """changelog: + 1.0.0: + - added cmp function +""" + +__author__ = ( + "Arthur Lu ", +) + +def cmp(a, b): + return (a > b) - (a < b) \ No newline at end of file diff --git a/analysis-master/tra_analysis/regression.py b/analysis-master/tra_analysis/regression_old.py similarity index 100% rename from analysis-master/tra_analysis/regression.py rename to analysis-master/tra_analysis/regression_old.py diff --git a/data-analysis/config.json b/data-analysis/config.json deleted file mode 100644 index f143132b..00000000 --- a/data-analysis/config.json +++ /dev/null @@ -1,46 +0,0 @@ -{ - "max-threads": 0.5, - "team": "", - "competition": "", - "key":{ - "database":"", - "tba":"" - }, - "statistics":{ - "match":{ - "balls-blocked":["basic_stats","historical_analysis","regression_linear","regression_logarithmic","regression_exponential","regression_polynomial","regression_sigmoidal"], - "balls-collected":["basic_stats","historical_analysis","regression_linear","regression_logarithmic","regression_exponential","regression_polynomial","regression_sigmoidal"], - "balls-lower-teleop":["basic_stats","historical_analysis","regression_linear","regression_logarithmic","regression_exponential","regression_polynomial","regression_sigmoidal"], - "balls-lower-auto":["basic_stats","historical_analysis","regression_linear","regression_logarithmic","regression_exponential","regression_polynomial","regression_sigmoidal"], - "balls-started":["basic_stats","historical_analyss","regression_linear","regression_logarithmic","regression_exponential","regression_polynomial","regression_sigmoidal"], - "balls-upper-teleop":["basic_stats","historical_analysis","regression_linear","regression_logarithmic","regression_exponential","regression_polynomial","regression_sigmoidal"], - "balls-upper-auto":["basic_stats","historical_analysis","regression_linear","regression_logarithmic","regression_exponential","regression_polynomial","regression_sigmoidal"] - - }, - "metric":{ - "elo":{ - "score":1500, - "N":400, - "K":24 - }, - "gl2":{ - "score":1500, - "rd":250, - "vol":0.06 - }, - "ts":{ - "mu":25, - "sigma":8.33 - } - }, - "pit":{ - "wheel-mechanism":true, - "low-balls":true, - "high-balls":true, - "wheel-success":true, - "strategic-focus":true, - "climb-mechanism":true, - "attitude":true - } - } -} \ No newline at end of file diff --git a/data-analysis/data.py b/data-analysis/data.py deleted file mode 100644 index 641aba7c..00000000 --- a/data-analysis/data.py +++ /dev/null @@ -1,129 +0,0 @@ -import requests -import pymongo -import pandas as pd -import time - -def pull_new_tba_matches(apikey, competition, cutoff): - api_key= apikey - x=requests.get("https://www.thebluealliance.com/api/v3/event/"+competition+"/matches/simple", headers={"X-TBA-Auth_Key":api_key}) - out = [] - for i in x.json(): - if i["actual_time"] != None and i["actual_time"]-cutoff >= 0 and i["comp_level"] == "qm": - out.append({"match" : i['match_number'], "blue" : list(map(lambda x: int(x[3:]), i['alliances']['blue']['team_keys'])), "red" : list(map(lambda x: int(x[3:]), i['alliances']['red']['team_keys'])), "winner": i["winning_alliance"]}) - return out - -def get_team_match_data(apikey, competition, team_num): - client = pymongo.MongoClient(apikey) - db = client.data_scouting - mdata = db.matchdata - out = {} - for i in mdata.find({"competition" : competition, "team_scouted": team_num}): - out[i['match']] = i['data'] - return pd.DataFrame(out) - -def get_team_pit_data(apikey, competition, team_num): - client = pymongo.MongoClient(apikey) - db = client.data_scouting - mdata = db.pitdata - out = {} - return mdata.find_one({"competition" : competition, "team_scouted": team_num})["data"] - -def get_team_metrics_data(apikey, competition, team_num): - client = pymongo.MongoClient(apikey) - db = client.data_processing - mdata = db.team_metrics - return mdata.find_one({"competition" : competition, "team": team_num}) - -def get_match_data_formatted(apikey, competition): - client = pymongo.MongoClient(apikey) - db = client.data_scouting - mdata = db.teamlist - x=mdata.find_one({"competition":competition}) - out = {} - for i in x: - try: - out[int(i)] = unkeyify_2l(get_team_match_data(apikey, competition, int(i)).transpose().to_dict()) - except: - pass - return out - -def get_metrics_data_formatted(apikey, competition): - client = pymongo.MongoClient(apikey) - db = client.data_scouting - mdata = db.teamlist - x=mdata.find_one({"competition":competition}) - out = {} - for i in x: - try: - out[int(i)] = d.get_team_metrics_data(apikey, competition, int(i)) - except: - pass - return out - -def get_pit_data_formatted(apikey, competition): - client = pymongo.MongoClient(apikey) - db = client.data_scouting - mdata = db.teamlist - x=mdata.find_one({"competition":competition}) - out = {} - for i in x: - try: - out[int(i)] = get_team_pit_data(apikey, competition, int(i)) - except: - pass - return out - -def get_pit_variable_data(apikey, competition): - client = pymongo.MongoClient(apikey) - db = client.data_processing - mdata = db.team_pit - out = {} - return mdata.find() - -def get_pit_variable_formatted(apikey, competition): - temp = get_pit_variable_data(apikey, competition) - out = {} - for i in temp: - out[i["variable"]] = i["data"] - return out - -def push_team_tests_data(apikey, competition, team_num, data, dbname = "data_processing", colname = "team_tests"): - client = pymongo.MongoClient(apikey) - db = client[dbname] - mdata = db[colname] - mdata.replace_one({"competition" : competition, "team": team_num}, {"_id": competition+str(team_num)+"am", "competition" : competition, "team" : team_num, "data" : data}, True) - -def push_team_metrics_data(apikey, competition, team_num, data, dbname = "data_processing", colname = "team_metrics"): - client = pymongo.MongoClient(apikey) - db = client[dbname] - mdata = db[colname] - mdata.replace_one({"competition" : competition, "team": team_num}, {"_id": competition+str(team_num)+"am", "competition" : competition, "team" : team_num, "metrics" : data}, True) - -def push_team_pit_data(apikey, competition, variable, data, dbname = "data_processing", colname = "team_pit"): - client = pymongo.MongoClient(apikey) - db = client[dbname] - mdata = db[colname] - mdata.replace_one({"competition" : competition, "variable": variable}, {"competition" : competition, "variable" : variable, "data" : data}, True) - -def get_analysis_flags(apikey, flag): - client = pymongo.MongoClient(apikey) - db = client.data_processing - mdata = db.flags - return mdata.find_one({flag:{"$exists":True}}) - -def set_analysis_flags(apikey, flag, data): - client = pymongo.MongoClient(apikey) - db = client.data_processing - mdata = db.flags - return mdata.replace_one({flag:{"$exists":True}}, data, True) - -def unkeyify_2l(layered_dict): - out = {} - for i in layered_dict.keys(): - add = [] - sortkey = [] - for j in layered_dict[i].keys(): - add.append([j,layered_dict[i][j]]) - add.sort(key = lambda x: x[0]) - out[i] = list(map(lambda x: x[1], add)) - return out \ No newline at end of file diff --git a/data-analysis/requirements.txt b/data-analysis/requirements.txt deleted file mode 100644 index 58d1bd37..00000000 --- a/data-analysis/requirements.txt +++ /dev/null @@ -1,4 +0,0 @@ -requests -pymongo -pandas -tra-analysis \ No newline at end of file diff --git a/data-analysis/superscript.py b/data-analysis/superscript.py deleted file mode 100644 index a3f04095..00000000 --- a/data-analysis/superscript.py +++ /dev/null @@ -1,536 +0,0 @@ -# Titan Robotics Team 2022: Superscript Script -# Written by Arthur Lu, Jacob Levine, and Dev Singh -# Notes: -# setup: - -__version__ = "0.8.2" - -# changelog should be viewed using print(analysis.__changelog__) -__changelog__ = """changelog: - 0.8.2: - - readded while true to main function - - added more thread config options - 0.8.1: - - optimized matchloop further by bypassing GIL - 0.8.0: - - added multithreading to matchloop - - tweaked user log - 0.7.0: - - finished implementing main function - 0.6.2: - - integrated get_team_rankings.py as get_team_metrics() function - - integrated visualize_pit.py as graph_pit_histogram() function - 0.6.1: - - bug fixes with analysis.Metric() calls - - modified metric functions to use config.json defined default values - 0.6.0: - - removed main function - - changed load_config function - - added save_config function - - added load_match function - - renamed simpleloop to matchloop - - moved simplestats function inside matchloop - - renamed load_metrics to load_metric - - renamed metricsloop to metricloop - - split push to database functions amon push_match, push_metric, push_pit - - moved - 0.5.2: - - made changes due to refactoring of analysis - 0.5.1: - - text fixes - - removed matplotlib requirement - 0.5.0: - - improved user interface - 0.4.2: - - removed unessasary code - 0.4.1: - - fixed bug where X range for regression was determined before sanitization - - better sanitized data - 0.4.0: - - fixed spelling issue in __changelog__ - - addressed nan bug in regression - - fixed errors on line 335 with metrics calling incorrect key "glicko2" - - fixed errors in metrics computing - 0.3.0: - - added analysis to pit data - 0.2.1: - - minor stability patches - - implemented db syncing for timestamps - - fixed bugs - 0.2.0: - - finalized testing and small fixes - 0.1.4: - - finished metrics implement, trueskill is bugged - 0.1.3: - - working - 0.1.2: - - started implement of metrics - 0.1.1: - - cleaned up imports - 0.1.0: - - tested working, can push to database - 0.0.9: - - tested working - - prints out stats for the time being, will push to database later - 0.0.8: - - added data import - - removed tba import - - finished main method - 0.0.7: - - added load_config - - optimized simpleloop for readibility - - added __all__ entries - - added simplestats engine - - pending testing - 0.0.6: - - fixes - 0.0.5: - - imported pickle - - created custom database object - 0.0.4: - - fixed simpleloop to actually return a vector - 0.0.3: - - added metricsloop which is unfinished - 0.0.2: - - added simpleloop which is untested until data is provided - 0.0.1: - - created script - - added analysis, numba, numpy imports -""" - -__author__ = ( - "Arthur Lu ", - "Jacob Levine ", -) - -__all__ = [ - "load_config", - "save_config", - "get_previous_time", - "load_match", - "matchloop", - "load_metric", - "metricloop", - "load_pit", - "pitloop", - "push_match", - "push_metric", - "push_pit", -] - -# imports: - -from tra_analysis import analysis as an -import data as d -from collections import defaultdict -import json -import math -import numpy as np -import os -from os import system, name -from pathlib import Path -from multiprocessing import Pool -import matplotlib.pyplot as plt -from concurrent.futures import ThreadPoolExecutor -import time -import warnings - -global exec_threads - -def main(): - - global exec_threads - - warnings.filterwarnings("ignore") - - while (True): - - current_time = time.time() - print("[OK] time: " + str(current_time)) - - config = load_config("config.json") - competition = config["competition"] - match_tests = config["statistics"]["match"] - pit_tests = config["statistics"]["pit"] - metrics_tests = config["statistics"]["metric"] - print("[OK] configs loaded") - - print("[OK] starting threads") - cfg_max_threads = config["max-threads"] - sys_max_threads = os.cpu_count() - if cfg_max_threads > -sys_max_threads and cfg_max_threads < 0 : - alloc_processes = sys_max_threads + cfg_max_threads - elif cfg_max_threads > 0 and cfg_max_threads < 1: - alloc_processes = math.floor(cfg_max_threads * sys_max_threads) - elif cfg_max_threads > 1 and cfg_max_threads <= sys_max_threads: - alloc_processes = cfg_max_threads - elif cfg_max_threads == 0: - alloc_processes = sys_max_threads - else: - print("[Err] Invalid number of processes, must be between -" + str(sys_max_threads) + " and " + str(sys_max_threads)) - exit() - exec_threads = Pool(processes = alloc_processes) - print("[OK] " + str(alloc_processes) + " threads started") - - apikey = config["key"]["database"] - tbakey = config["key"]["tba"] - print("[OK] loaded keys") - - previous_time = get_previous_time(apikey) - print("[OK] analysis backtimed to: " + str(previous_time)) - - print("[OK] loading data") - start = time.time() - match_data = load_match(apikey, competition) - pit_data = load_pit(apikey, competition) - print("[OK] loaded data in " + str(time.time() - start) + " seconds") - - print("[OK] running match stats") - start = time.time() - matchloop(apikey, competition, match_data, match_tests) - print("[OK] finished match stats in " + str(time.time() - start) + " seconds") - - print("[OK] running team metrics") - start = time.time() - metricloop(tbakey, apikey, competition, previous_time, metrics_tests) - print("[OK] finished team metrics in " + str(time.time() - start) + " seconds") - - print("[OK] running pit analysis") - start = time.time() - pitloop(apikey, competition, pit_data, pit_tests) - print("[OK] finished pit analysis in " + str(time.time() - start) + " seconds") - - set_current_time(apikey, current_time) - print("[OK] finished all tests, looping") - - clear() - -def clear(): - - # for windows - if name == 'nt': - _ = system('cls') - - # for mac and linux(here, os.name is 'posix') - else: - _ = system('clear') - -def load_config(file): - - config_vector = {} - with open(file) as f: - config_vector = json.load(f) - - return config_vector - -def save_config(file, config_vector): - - with open(file) as f: - json.dump(config_vector, f) - -def get_previous_time(apikey): - - previous_time = d.get_analysis_flags(apikey, "latest_update") - - if previous_time == None: - - d.set_analysis_flags(apikey, "latest_update", 0) - previous_time = 0 - - else: - - previous_time = previous_time["latest_update"] - - return previous_time - -def set_current_time(apikey, current_time): - - d.set_analysis_flags(apikey, "latest_update", {"latest_update":current_time}) - -def load_match(apikey, competition): - - return d.get_match_data_formatted(apikey, competition) - -def simplestats(data_test): - - data = np.array(data_test[0]) - data = data[np.isfinite(data)] - ranges = list(range(len(data))) - - test = data_test[1] - - if test == "basic_stats": - return an.basic_stats(data) - - if test == "historical_analysis": - return an.histo_analysis([ranges, data]) - - if test == "regression_linear": - return an.regression(ranges, data, ['lin']) - - if test == "regression_logarithmic": - return an.regression(ranges, data, ['log']) - - if test == "regression_exponential": - return an.regression(ranges, data, ['exp']) - - if test == "regression_polynomial": - return an.regression(ranges, data, ['ply']) - - if test == "regression_sigmoidal": - return an.regression(ranges, data, ['sig']) - -def matchloop(apikey, competition, data, tests): # expects 3D array with [Team][Variable][Match] - - global exec_threads - - class AutoVivification(dict): - def __getitem__(self, item): - try: - return dict.__getitem__(self, item) - except KeyError: - value = self[item] = type(self)() - return value - - return_vector = {} - - team_filtered = [] - variable_filtered = [] - variable_data = [] - test_filtered = [] - result_filtered = [] - return_vector = AutoVivification() - - for team in data: - - for variable in data[team]: - - if variable in tests: - - for test in tests[variable]: - - team_filtered.append(team) - variable_filtered.append(variable) - variable_data.append((data[team][variable], test)) - test_filtered.append(test) - - result_filtered = exec_threads.map(simplestats, variable_data) - i = 0 - - result_filtered = list(result_filtered) - - for result in result_filtered: - - return_vector[team_filtered[i]][variable_filtered[i]][test_filtered[i]] = result - i += 1 - - push_match(apikey, competition, return_vector) - -def load_metric(apikey, competition, match, group_name, metrics): - - group = {} - - for team in match[group_name]: - - db_data = d.get_team_metrics_data(apikey, competition, team) - - if d.get_team_metrics_data(apikey, competition, team) == None: - - elo = {"score": metrics["elo"]["score"]} - gl2 = {"score": metrics["gl2"]["score"], "rd": metrics["gl2"]["rd"], "vol": metrics["gl2"]["vol"]} - ts = {"mu": metrics["ts"]["mu"], "sigma": metrics["ts"]["sigma"]} - - group[team] = {"elo": elo, "gl2": gl2, "ts": ts} - - else: - - metrics = db_data["metrics"] - - elo = metrics["elo"] - gl2 = metrics["gl2"] - ts = metrics["ts"] - - group[team] = {"elo": elo, "gl2": gl2, "ts": ts} - - return group - -def metricloop(tbakey, apikey, competition, timestamp, metrics): # listener based metrics update - - elo_N = metrics["elo"]["N"] - elo_K = metrics["elo"]["K"] - - matches = d.pull_new_tba_matches(tbakey, competition, timestamp) - - red = {} - blu = {} - - for match in matches: - - red = load_metric(apikey, competition, match, "red", metrics) - blu = load_metric(apikey, competition, match, "blue", metrics) - - elo_red_total = 0 - elo_blu_total = 0 - - gl2_red_score_total = 0 - gl2_blu_score_total = 0 - - gl2_red_rd_total = 0 - gl2_blu_rd_total = 0 - - gl2_red_vol_total = 0 - gl2_blu_vol_total = 0 - - for team in red: - - elo_red_total += red[team]["elo"]["score"] - - gl2_red_score_total += red[team]["gl2"]["score"] - gl2_red_rd_total += red[team]["gl2"]["rd"] - gl2_red_vol_total += red[team]["gl2"]["vol"] - - for team in blu: - - elo_blu_total += blu[team]["elo"]["score"] - - gl2_blu_score_total += blu[team]["gl2"]["score"] - gl2_blu_rd_total += blu[team]["gl2"]["rd"] - gl2_blu_vol_total += blu[team]["gl2"]["vol"] - - red_elo = {"score": elo_red_total / len(red)} - blu_elo = {"score": elo_blu_total / len(blu)} - - red_gl2 = {"score": gl2_red_score_total / len(red), "rd": gl2_red_rd_total / len(red), "vol": gl2_red_vol_total / len(red)} - blu_gl2 = {"score": gl2_blu_score_total / len(blu), "rd": gl2_blu_rd_total / len(blu), "vol": gl2_blu_vol_total / len(blu)} - - - if match["winner"] == "red": - - observations = {"red": 1, "blu": 0} - - elif match["winner"] == "blue": - - observations = {"red": 0, "blu": 1} - - else: - - observations = {"red": 0.5, "blu": 0.5} - - red_elo_delta = an.Metric().elo(red_elo["score"], blu_elo["score"], observations["red"], elo_N, elo_K) - red_elo["score"] - blu_elo_delta = an.Metric().elo(blu_elo["score"], red_elo["score"], observations["blu"], elo_N, elo_K) - blu_elo["score"] - - new_red_gl2_score, new_red_gl2_rd, new_red_gl2_vol = an.Metric().glicko2(red_gl2["score"], red_gl2["rd"], red_gl2["vol"], [blu_gl2["score"]], [blu_gl2["rd"]], [observations["red"], observations["blu"]]) - new_blu_gl2_score, new_blu_gl2_rd, new_blu_gl2_vol = an.Metric().glicko2(blu_gl2["score"], blu_gl2["rd"], blu_gl2["vol"], [red_gl2["score"]], [red_gl2["rd"]], [observations["blu"], observations["red"]]) - - red_gl2_delta = {"score": new_red_gl2_score - red_gl2["score"], "rd": new_red_gl2_rd - red_gl2["rd"], "vol": new_red_gl2_vol - red_gl2["vol"]} - blu_gl2_delta = {"score": new_blu_gl2_score - blu_gl2["score"], "rd": new_blu_gl2_rd - blu_gl2["rd"], "vol": new_blu_gl2_vol - blu_gl2["vol"]} - - for team in red: - - red[team]["elo"]["score"] = red[team]["elo"]["score"] + red_elo_delta - - red[team]["gl2"]["score"] = red[team]["gl2"]["score"] + red_gl2_delta["score"] - red[team]["gl2"]["rd"] = red[team]["gl2"]["rd"] + red_gl2_delta["rd"] - red[team]["gl2"]["vol"] = red[team]["gl2"]["vol"] + red_gl2_delta["vol"] - - for team in blu: - - blu[team]["elo"]["score"] = blu[team]["elo"]["score"] + blu_elo_delta - - blu[team]["gl2"]["score"] = blu[team]["gl2"]["score"] + blu_gl2_delta["score"] - blu[team]["gl2"]["rd"] = blu[team]["gl2"]["rd"] + blu_gl2_delta["rd"] - blu[team]["gl2"]["vol"] = blu[team]["gl2"]["vol"] + blu_gl2_delta["vol"] - - temp_vector = {} - temp_vector.update(red) - temp_vector.update(blu) - - push_metric(apikey, competition, temp_vector) - -def load_pit(apikey, competition): - - return d.get_pit_data_formatted(apikey, competition) - -def pitloop(apikey, competition, pit, tests): - - return_vector = {} - for team in pit: - for variable in pit[team]: - if variable in tests: - if not variable in return_vector: - return_vector[variable] = [] - return_vector[variable].append(pit[team][variable]) - - push_pit(apikey, competition, return_vector) - -def push_match(apikey, competition, results): - - for team in results: - - d.push_team_tests_data(apikey, competition, team, results[team]) - -def push_metric(apikey, competition, metric): - - for team in metric: - - d.push_team_metrics_data(apikey, competition, team, metric[team]) - -def push_pit(apikey, competition, pit): - - for variable in pit: - - d.push_team_pit_data(apikey, competition, variable, pit[variable]) - -def get_team_metrics(apikey, tbakey, competition): - - metrics = d.get_metrics_data_formatted(apikey, competition) - - elo = {} - gl2 = {} - - for team in metrics: - - elo[team] = metrics[team]["metrics"]["elo"]["score"] - gl2[team] = metrics[team]["metrics"]["gl2"]["score"] - - elo = {k: v for k, v in sorted(elo.items(), key=lambda item: item[1])} - gl2 = {k: v for k, v in sorted(gl2.items(), key=lambda item: item[1])} - - elo_ranked = [] - - for team in elo: - - elo_ranked.append({"team": str(team), "elo": str(elo[team])}) - - gl2_ranked = [] - - for team in gl2: - - gl2_ranked.append({"team": str(team), "gl2": str(gl2[team])}) - - return {"elo-ranks": elo_ranked, "glicko2-ranks": gl2_ranked} - -def graph_pit_histogram(apikey, competition, figsize=(80,15)): - - pit = d.get_pit_variable_formatted(apikey, competition) - - fig, ax = plt.subplots(1, len(pit), sharey=True, figsize=figsize) - - i = 0 - - for variable in pit: - - ax[i].hist(pit[variable]) - ax[i].invert_xaxis() - - ax[i].set_xlabel('') - ax[i].set_ylabel('Frequency') - ax[i].set_title(variable) - - plt.yticks(np.arange(len(pit[variable]))) - - i+=1 - - plt.show() - -main() \ No newline at end of file diff --git a/data-analysis/test_superscript.py b/data-analysis/test_superscript.py deleted file mode 100644 index f6709195..00000000 --- a/data-analysis/test_superscript.py +++ /dev/null @@ -1,2 +0,0 @@ -def test_(): - assert 1 == 1 \ No newline at end of file