Merge pull request #85 from titanscouting/analysis-v4

Analysis v4
This commit is contained in:
Arthur Lu 2022-03-13 21:15:40 -07:00 committed by GitHub
commit 12e0a263bd
30 changed files with 348 additions and 1234 deletions

View File

@ -1,7 +1,6 @@
FROM ubuntu:20.04
FROM python:slim
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
RUN apt-get -y update; apt-get -y upgrade
RUN apt-get -y install git
COPY requirements.txt .
RUN pip install -r requirements.txt

View File

@ -1,2 +0,0 @@
FROM titanscout2022/tra-analysis-base:latest
WORKDIR /

View File

@ -1,28 +1,22 @@
{
"name": "TRA Analysis Development Environment",
"build": {
"dockerfile": "dev-dockerfile",
"dockerfile": "Dockerfile",
},
"settings": {
"terminal.integrated.shell.linux": "/bin/bash",
"python.pythonPath": "/usr/local/bin/python",
"python.pythonPath": "",
"python.linting.enabled": true,
"python.linting.pylintEnabled": true,
"python.formatting.autopep8Path": "/usr/local/py-utils/bin/autopep8",
"python.formatting.blackPath": "/usr/local/py-utils/bin/black",
"python.formatting.yapfPath": "/usr/local/py-utils/bin/yapf",
"python.linting.banditPath": "/usr/local/py-utils/bin/bandit",
"python.linting.flake8Path": "/usr/local/py-utils/bin/flake8",
"python.linting.mypyPath": "/usr/local/py-utils/bin/mypy",
"python.linting.pycodestylePath": "/usr/local/py-utils/bin/pycodestyle",
"python.linting.pydocstylePath": "/usr/local/py-utils/bin/pydocstyle",
"python.linting.pylintPath": "/usr/local/py-utils/bin/pylint",
"python.testing.pytestPath": "/usr/local/py-utils/bin/pytest"
"python.linting.pylintPath": "",
"python.testing.pytestPath": "",
"editor.tabSize": 4,
"editor.insertSpaces": false
},
"extensions": [
"mhutchie.git-graph",
"ms-python.python",
"waderyan.gitblame"
],
"postCreateCommand": "/usr/bin/pip3 install -r ${containerWorkspaceFolder}/analysis-master/requirements.txt && /usr/bin/pip3 install --no-cache-dir pylint && /usr/bin/pip3 install pytest"
"postCreateCommand": ""
}

View File

@ -0,0 +1,8 @@
numpy
scipy
scikit-learn
six
pyparsing
pylint
pytest

View File

@ -10,12 +10,12 @@ on:
branches: [ master ]
jobs:
build:
unittest:
runs-on: ubuntu-latest
strategy:
matrix:
python-version: [3.7, 3.8]
python-version: ["3.7", "3.8", "3.9", "3.10"]
env:
working-directory: ./analysis-master/

View File

@ -2,5 +2,7 @@ numpy
scipy
scikit-learn
six
matplotlib
pyparsing
pylint
pytest

View File

@ -5,9 +5,11 @@ 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 Clustering
from tra_analysis import CorrelationTest
from tra_analysis import Fit
from tra_analysis import KNN
from tra_analysis import metrics as m
from tra_analysis import NaiveBayes
from tra_analysis import RandomForest
from tra_analysis import RegressionMetric
@ -26,7 +28,7 @@ x_data_circular = []
y_data_circular = []
y_data_ccu = [1, 3, 7, 14, 21]
y_data_ccd = [1, 5, 7, 8.5, 8.66]
y_data_ccd = [8.66, 8.5, 7, 5, 1]
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]
@ -47,16 +49,25 @@ def test_basicstats():
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
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))]
e = [[(21.346, 7.875), (20.415, 7.808), (29.037, 7.170)], [(28.654, 7.875), (28.654, 7.875), (23.225, 6.287)]]
r = an.Metric().trueskill([[(25, 8.33), (24, 8.25), (32, 7.5)], [(25, 8.33), (25, 8.33), (21, 6.5)]], [1, 0])
i = 0
for group in r:
j = 0
for team in group:
assert abs(team.mu - e[i][j][0]) < 0.001
assert abs(team.sigma - e[i][j][1]) < 0.001
j+=1
i+=1
def test_array():
@ -143,13 +154,8 @@ def test_sort():
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():
@ -231,3 +237,17 @@ def test_equation():
}
for key in list(correctParse.keys()):
assert parser.eval(key) == correctParse[key]
def test_clustering():
normalizer = sklearn.preprocessing.Normalizer()
data = X = np.array([[1, 2], [2, 2], [2, 3], [8, 7], [8, 8], [25, 80]])
assert Clustering.dbscan(data, eps=3, min_samples=2).tolist() == [0, 0, 0, 1, 1, -1]
assert Clustering.dbscan(data, normalizer=normalizer, eps=3, min_samples=2).tolist() == [0, 0, 0, 0, 0, 0]
data = np.array([[1, 1], [2, 1], [1, 0], [4, 7], [3, 5], [3, 6]])
assert Clustering.spectral(data, n_clusters=2, assign_labels='discretize', random_state=0).tolist() == [1, 1, 1, 0, 0, 0]
assert Clustering.spectral(data, normalizer=normalizer, n_clusters=2, assign_labels='discretize', random_state=0).tolist() == [0, 1, 1, 0, 0, 0]

View File

@ -7,10 +7,19 @@
# current benchmark of optimization: 1.33 times faster
# setup:
__version__ = "3.0.2"
__version__ = "3.0.6"
# changelog should be viewed using print(analysis.__changelog__)
__changelog__ = """changelog:
3.0.6:
- added docstrings
3.0.5:
- removed extra submodule imports
- fixed/optimized header
3.0.4:
- removed -_obj imports
3.0.3:
- fixed spelling of deprecate
3.0.2:
- fixed __all__
3.0.1:
@ -58,7 +67,7 @@ __changelog__ = """changelog:
- cycle sort
- cocktail sort
- tested all sorting algorithms with both lists and numpy arrays
- depreciated sort function from Array class
- deprecated sort function from Array class
- added warnings as an import
2.1.4:
- added sort and search functions to Array class
@ -136,7 +145,7 @@ __changelog__ = """changelog:
1.12.4:
- renamed gliko to glicko
1.12.3:
- removed depreciated code
- removed deprecated code
1.12.2:
- removed team first time trueskill instantiation in favor of integration in superscript.py
1.12.1:
@ -248,10 +257,10 @@ __changelog__ = """changelog:
1.0.0:
- removed c_entities,nc_entities,obstacles,objectives from __all__
- applied numba.jit to all functions
- depreciated and removed stdev_z_split
- deprecated 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)
- deprecated and removed all regression functions in favor of future pytorch optimizer
- deprecated 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:
@ -270,8 +279,8 @@ __changelog__ = """changelog:
- refactors
- bugfixes
0.8.0:
- depreciated histo_analysis_old
- depreciated debug
- deprecated histo_analysis_old
- deprecated debug
- altered basic_analysis to take array data instead of filepath
- refactor
- optimization
@ -319,7 +328,7 @@ __changelog__ = """changelog:
0.3.5:
- major bug fixes
- updated historical analysis
- depreciated old historical analysis
- deprecated old historical analysis
0.3.4:
- added __version__, __author__, __all__
- added polynomial regression
@ -357,7 +366,6 @@ __all__ = [
'histo_analysis',
'regression',
'Metric',
'kmeans',
'pca',
'decisiontree',
# all statistics functions left out due to integration in other functions
@ -370,40 +378,39 @@ __all__ = [
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
import sklearn, sklearn.cluster, sklearn.pipeline
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):
"""
Loads csv file into 2D numpy array. Does not check csv file validity.
parameters:
filepath: String path to the csv file
return:
2D numpy array of values stored in csv file
"""
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):
"""
Calculates mean, median, standard deviation, variance, minimum, maximum of a simple set of elements.
parameters:
data: List representing set of unordered elements
return:
Dictionary with (mean, median, standard-deviation, variance, minimum, maximum) as keys and corresponding values
"""
data_t = np.array(data).astype(float)
_mean = mean(data_t)
@ -415,24 +422,43 @@ def basic_stats(data):
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):
"""
Calculates z score of a specific point given mean and standard deviation of data.
parameters:
point: Real value corresponding to a single point of data
mean: Real value corresponding to the mean of the dataset
stdev: Real value corresponding to the standard deviation of the dataset
return:
Real value that is the point's z score
"""
score = (point - mean) / stdev
return score
# expects 2d array, normalizes across all axes
def z_normalize(array, *args):
"""
Applies sklearn.normalize(array, axis = args) on any arraylike parseable by numpy.
parameters:
array: array like structure of reals aka nested indexables
*args: arguments relating to axis normalized against
return:
numpy array of normalized values from ArrayLike input
"""
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):
"""
Calculates the mean and standard deviation of derivatives of (x,y) points. Requires at least 2 points to compute.
parameters:
hist_data: list of real coordinate point data (x, y)
return:
Dictionary with (mean, deviation) as keys to corresponding values
"""
if len(hist_data[0]) > 2:
hist_data = np.array(hist_data)
@ -448,7 +474,15 @@ def histo_analysis(hist_data):
return None
def regression(inputs, outputs, args): # inputs, outputs expects N-D array
"""
Applies specified regression kernels onto input, output data pairs.
parameters:
inputs: List of Reals representing independent variable values of each point
outputs: List of Reals representing dependent variable values of each point
args: List of Strings from values (lin, log, exp, ply, sig)
return:
Dictionary with keys (lin, log, exp, ply, sig) as keys to correspondiong regression models
"""
X = np.array(inputs)
y = np.array(outputs)
@ -552,13 +586,39 @@ def regression(inputs, outputs, args): # inputs, outputs expects N-D array
return regressions
class Metric:
"""
The metric class wraps the metrics models. Call without instantiation as Metric.<method>(...)
"""
def elo(self, starting_score, opposing_score, observed, N, K):
"""
Calculates an elo adjusted ELO score given a player's current score, opponent's score, and outcome of match.
reference: https://en.wikipedia.org/wiki/Elo_rating_system
parameters:
starting_score: Real value representing player's ELO score before a match
opposing_score: Real value representing opponent's score before the match
observed: Array of Real values representing multiple sequential match outcomes against the same opponent. 1 for match win, 0.5 for tie, 0 for loss.
N: Real value representing the normal or mean score expected (usually 1200)
K: R eal value representing a system constant, determines how quickly players will change scores (usually 24)
return:
Real value representing the player's new ELO score
"""
return Elo.calculate(starting_score, opposing_score, observed, N, K)
def glicko2(self, starting_score, starting_rd, starting_vol, opposing_score, opposing_rd, observations):
"""
Calculates an adjusted Glicko-2 score given a player's current score, multiple opponent's score, and outcome of several matches.
reference: http://www.glicko.net/glicko/glicko2.pdf
parameters:
starting_score: Real value representing the player's Glicko-2 score
starting_rd: Real value representing the player's RD
starting_vol: Real value representing the player's volatility
opposing_score: List of Real values representing multiple opponent's Glicko-2 scores
opposing_rd: List of Real values representing multiple opponent's RD
opposing_vol: List of Real values representing multiple opponent's volatility
observations: List of Real values representing the outcome of several matches, where each match's opponent corresponds with the opposing_score, opposing_rd, opposing_vol values of the same indesx. Outcomes can be a score, presuming greater score is better.
return:
Tuple of 3 Real values representing the player's new score, rd, and vol
"""
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)
@ -566,7 +626,15 @@ class Metric:
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)]]
"""
Calculates the score changes for multiple teams playing in a single match accoding to the trueskill algorithm.
reference: https://trueskill.org/
parameters:
teams_data: List of List of Tuples of 2 Real values representing multiple player ratings. List of teams, which is a List of players. Each player rating is a Tuple of 2 Real values (mu, sigma).
observations: List of Real values representing the match outcome. Each value in the List is the score corresponding to the team at the same index in teams_data.
return:
List of List of Tuples of 2 Real values representing new player ratings. Same structure as teams_data.
"""
team_ratings = []
for team in teams_data:
@ -602,23 +670,31 @@ 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):
"""
Performs a principle component analysis on the input data.
reference: https://scikit-learn.org/stable/modules/generated/sklearn.decomposition.PCA.html
parameters:
data: Arraylike of Reals representing the set of data to perform PCA on
* : refer to reference for usage, parameters follow same usage
return:
Arraylike of Reals representing the set of data that has had PCA performed. The dimensionality of the Arraylike may be smaller or equal.
"""
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
"""
Generates a decision tree classifier fitted to the given data.
reference: https://scikit-learn.org/stable/modules/generated/sklearn.tree.DecisionTreeClassifier.html
parameters:
data: List of values representing each data point of multiple axes
labels: List of values represeing the labels corresponding to the same index at data
* : refer to reference for usage, parameters follow same usage
return:
DecisionTreeClassifier model and corresponding classification accuracy metrics
"""
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)

View File

@ -4,9 +4,11 @@
# this should be imported as a python module using 'from tra_analysis import Array'
# setup:
__version__ = "1.0.3"
__version__ = "1.0.4"
__changelog__ = """changelog:
1.0.4:
- fixed spelling of deprecate
1.0.3:
- fixed __all__
1.0.2:
@ -135,8 +137,8 @@ class Array(): # tests on nd arrays independent of basic_stats
return Array(np.transpose(self.array))
def sort(self, array): # depreciated
warnings.warn("Array.sort has been depreciated in favor of Sort")
def sort(self, array): # deprecated
warnings.warn("Array.sort has been deprecated in favor of Sort")
array_length = len(array)
if array_length <= 1:
return array

View File

@ -4,9 +4,11 @@
# this should be imported as a python module using 'from tra_analysis import ClassificationMetric'
# setup:
__version__ = "1.0.1"
__version__ = "1.0.2"
__changelog__ = """changelog:
1.0.2:
- optimized imports
1.0.1:
- fixed __all__
1.0.0:
@ -22,7 +24,6 @@ __all__ = [
]
import sklearn
from sklearn import metrics
class ClassificationMetric():

View File

@ -0,0 +1,63 @@
# Titan Robotics Team 2022: Clustering submodule
# Written by Arthur Lu
# Notes:
# this should be imported as a python module using 'from tra_analysis import Clustering'
# setup:
__version__ = "2.0.2"
# changelog should be viewed using print(analysis.__changelog__)
__changelog__ = """changelog:
2.0.2:
- generalized optional args to **kwargs
2.0.1:
- added normalization preprocessing to clustering, expects instance of sklearn.preprocessing.Normalizer()
2.0.0:
- added dbscan clustering algo
- added spectral clustering algo
1.0.0:
- created this submodule
- copied kmeans clustering from Analysis
"""
__author__ = (
"Arthur Lu <learthurgo@gmail.com>",
)
__all__ = [
"kmeans",
"dbscan",
"spectral",
]
import sklearn
def kmeans(data, normalizer = None, **kwargs):
if normalizer != None:
data = normalizer.transform(data)
kernel = sklearn.cluster.KMeans(**kwargs)
kernel.fit(data)
predictions = kernel.predict(data)
centers = kernel.cluster_centers_
return centers, predictions
def dbscan(data, normalizer=None, **kwargs):
if normalizer != None:
data = normalizer.transform(data)
model = sklearn.cluster.DBSCAN(**kwargs).fit(data)
return model.labels_
def spectral(data, normalizer=None, **kwargs):
if normalizer != None:
data = normalizer.transform(data)
model = sklearn.cluster.SpectralClustering(**kwargs).fit(data)
return model.labels_

View File

@ -4,9 +4,13 @@
# this should be imported as a python module using 'from tra_analysis import CorrelationTest'
# setup:
__version__ = "1.0.1"
__version__ = "1.0.3"
__changelog__ = """changelog:
1.0.3:
- generalized optional args to **kwargs
1.0.2:
- optimized imports
1.0.1:
- fixed __all__
1.0.0:
@ -29,7 +33,6 @@ __all__ = [
]
import scipy
from scipy import stats
def anova_oneway(*args): #expects arrays of samples
@ -41,9 +44,9 @@ 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'):
def spearman(a, b = None, **kwargs):
results = scipy.stats.spearmanr(a, b = b, axis = axis, nan_policy = nan_policy)
results = scipy.stats.spearmanr(a, b = b, **kwargs)
return {"r-value": results[0], "p-value": results[1]}
def point_biserial(x, y):
@ -51,17 +54,17 @@ 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'):
def kendall(x, y, **kwargs):
results = scipy.stats.kendalltau(x, y, initial_lexsort = initial_lexsort, nan_policy = nan_policy, method = method)
results = scipy.stats.kendalltau(x, y, **kwargs)
return {"tau": results[0], "p-value": results[1]}
def kendall_weighted(x, y, rank = True, weigher = None, additive = True):
def kendall_weighted(x, y, **kwargs):
results = scipy.stats.weightedtau(x, y, rank = rank, weigher = weigher, additive = additive)
results = scipy.stats.weightedtau(x, y, **kwargs)
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):
def mgc(x, y, **kwargs):
results = scipy.stats.multiscale_graphcorr(x, y, compute_distance = compute_distance, reps = reps, workers = workers, is_twosamp = is_twosamp, random_state = random_state)
results = scipy.stats.multiscale_graphcorr(x, y, **kwargs)
return {"k-value": results[0], "p-value": results[1], "data": results[2]} # unsure if MGC test returns a k value

View File

@ -1,41 +0,0 @@
# 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

View File

@ -4,9 +4,13 @@
# this should be imported as a python module using 'from tra_analysis import KNN'
# setup:
__version__ = "1.0.0"
__version__ = "1.0.2"
__changelog__ = """changelog:
1.0.2:
- generalized optional args to **kwargs
1.0.1:
- optimized imports
1.0.0:
- ported analysis.KNN() here
- removed classness
@ -23,22 +27,21 @@ __all__ = [
]
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
def knn_classifier(data, labels, n_neighbors = 5, test_size = 0.3, **kwargs): #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 = sklearn.neighbors.KNeighborsClassifier(n_neighbors = n_neighbors, **kwargs)
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):
def knn_regressor(data, outputs, n_neighbors = 5, test_size = 0.3, **kwargs):
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 = sklearn.neighbors.KNeighborsRegressor(n_neighbors = n_neighbors, **kwargs)
model.fit(data_train, outputs_train)
predictions = model.predict(data_test)

View File

@ -1,25 +0,0 @@
# 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)

View File

@ -4,9 +4,13 @@
# this should be imported as a python module using 'from tra_analysis import NaiveBayes'
# setup:
__version__ = "1.0.0"
__version__ = "1.0.2"
__changelog__ = """changelog:
1.0.2:
- generalized optional args to **kwargs
1.0.1:
- optimized imports
1.0.0:
- ported analysis.NaiveBayes() here
- removed classness
@ -18,46 +22,45 @@ __author__ = (
__all__ = [
'gaussian',
'multinomial'
'multinomial',
'bernoulli',
'complement'
'complement',
]
import sklearn
from sklearn import model_selection, naive_bayes
from . import ClassificationMetric, RegressionMetric
from . import ClassificationMetric
def gaussian(data, labels, test_size = 0.3, priors = None, var_smoothing = 1e-09):
def gaussian(data, labels, test_size = 0.3, **kwargs):
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 = sklearn.naive_bayes.GaussianNB(**kwargs)
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):
def multinomial(data, labels, test_size = 0.3, **kwargs):
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 = sklearn.naive_bayes.MultinomialNB(**kwargs)
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):
def bernoulli(data, labels, test_size = 0.3, **kwargs):
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 = sklearn.naive_bayes.BernoulliNB(**kwargs)
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):
def complement(data, labels, test_size = 0.3, **kwargs):
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 = sklearn.naive_bayes.ComplementNB(**kwargs)
model.fit(data_train, labels_train)
predictions = model.predict(data_test)

View File

@ -1,43 +0,0 @@
# 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)

View File

@ -4,9 +4,14 @@
# this should be imported as a python module using 'from tra_analysis import RandomForest'
# setup:
__version__ = "1.0.1"
__version__ = "1.0.3"
__changelog__ = """changelog:
1.0.3:
- updated RandomForestClassifier and RandomForestRegressor parameters to match sklearn v 1.0.2
- changed default values for kwargs to rely on sklearn
1.0.2:
- optimized imports
1.0.1:
- fixed __all__
1.0.0:
@ -23,23 +28,22 @@ __all__ = [
"random_forest_regressor",
]
import sklearn
from sklearn import ensemble, model_selection
import sklearn, sklearn.ensemble, sklearn.naive_bayes
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):
def random_forest_classifier(data, labels, test_size, n_estimators, **kwargs):
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 = sklearn.ensemble.RandomForestClassifier(n_estimators = n_estimators, **kwargs)
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):
def random_forest_regressor(data, outputs, test_size, n_estimators, **kwargs):
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 = sklearn.ensemble.RandomForestRegressor(n_estimators = n_estimators, **kwargs)
kernel.fit(data_train, outputs_train)
predictions = kernel.predict(data_test)

View File

@ -1,25 +0,0 @@
# 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)

View File

@ -4,9 +4,11 @@
# this should be imported as a python module using 'from tra_analysis import RegressionMetric'
# setup:
__version__ = "1.0.0"
__version__ = "1.0.1"
__changelog__ = """changelog:
1.0.1:
- optimized imports
1.0.0:
- ported analysis.RegressionMetric() here
"""
@ -21,7 +23,6 @@ __all__ = [
import numpy as np
import sklearn
from sklearn import metrics
class RegressionMetric():

View File

@ -4,9 +4,11 @@
# this should be imported as a python module using 'from tra_analysis import SVM'
# setup:
__version__ = "1.0.2"
__version__ = "1.0.3"
__changelog__ = """changelog:
1.0.3:
- optimized imports
1.0.2:
- fixed __all__
1.0.1:
@ -30,7 +32,6 @@ __all__ = [
]
import sklearn
from sklearn import svm
from . import ClassificationMetric, RegressionMetric
class CustomKernel:

View File

@ -16,7 +16,7 @@ __changelog__ = """changelog:
__author__ = (
"Arthur Lu <learthurgo@gmail.com>",
"James Pan <zpan@imsa.edu>"
"James Pan <zpan@imsa.edu>",
)
__all__ = [

View File

@ -1,391 +0,0 @@
# 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)

View File

@ -4,9 +4,11 @@
# this should be imported as a python module using 'from tra_analysis import StatisticalTest'
# setup:
__version__ = "1.0.2"
__version__ = "1.0.3"
__changelog__ = """changelog:
1.0.3:
- optimized imports
1.0.2:
- added tukey_multicomparison
- fixed styling
@ -61,7 +63,6 @@ __all__ = [
import numpy as np
import scipy
from scipy import stats, interpolate
def ttest_onesample(a, popmean, axis = 0, nan_policy = 'propagate'):
@ -279,9 +280,9 @@ def get_tukeyQcrit(k, df, alpha=0.05):
cv001 = c[:, 2::2]
if alpha == 0.05:
intp = interpolate.interp1d(crows, cv005[:,k-2])
intp = scipy.interpolate.interp1d(crows, cv005[:,k-2])
elif alpha == 0.01:
intp = interpolate.interp1d(crows, cv001[:,k-2])
intp = scipy.interpolate.interp1d(crows, cv001[:,k-2])
else:
raise ValueError('only implemented for alpha equal to 0.01 and 0.05')
return intp(df)

View File

@ -1,170 +0,0 @@
# 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]}

View File

@ -7,10 +7,17 @@
# current benchmark of optimization: 1.33 times faster
# setup:
__version__ = "3.0.0"
__version__ = "4.0.0-dev"
# changelog should be viewed using print(analysis.__changelog__)
__changelog__ = """changelog:
4.0.0:
- deprecated all *_obj.py compatibility modules
- deprecated titanlearn.py
- deprecated visualization.py
- removed matplotlib from requirements
- removed extra submodule imports in Analysis
- added typehinting, docstrings for each function
3.0.0:
- incremented version to release 3.0.0
3.0.0-rc2:
@ -40,6 +47,7 @@ __all__ = [
"Analysis",
"Array",
"ClassificationMetric",
"Clustering",
"CorrelationTest",
"Expression",
"Fit",
@ -53,9 +61,9 @@ __all__ = [
]
from . import Analysis as Analysis
from . import Analysis as analysis
from .Array import Array
from .ClassificationMetric import ClassificationMetric
from . import Clustering
from . import CorrelationTest
from .equation import Expression
from . import Fit

View File

@ -0,0 +1,24 @@
# Titan Robotics Team 2022: Metrics submodule
# Written by Arthur Lu
# Notes:
# this should be imported as a python module using 'from tra_analysis import metrics'
# setup:
__version__ = "1.0.0"
__changelog__ = """changelog:
1.0.0:
- implemented elo, glicko2, trueskill
"""
__author__ = (
"Arthur Lu <learthurgo@gmail.com>",
)
__all__ = {
"Expression"
}
from . import elo
from . import glicko2
from . import trueskill

View File

@ -1,222 +0,0 @@
# Titan Robotics Team 2022: CUDA-based Regressions Module
# Not actively maintained, may be removed in future release
# Written by Arthur Lu & Jacob Levine
# Notes:
# this module has been automatically inegrated into analysis.py, and should be callable as a class from the package
# this module is cuda-optimized (as appropriate) and vectorized (except for one small part)
# setup:
__version__ = "0.0.4"
# changelog should be viewed using print(analysis.regression.__changelog__)
__changelog__ = """
0.0.4:
- bug fixes
- fixed changelog
0.0.3:
- bug fixes
0.0.2:
-Added more parameters to log, exponential, polynomial
-Added SigmoidalRegKernelArthur, because Arthur apparently needs
to train the scaling and shifting of sigmoids
0.0.1:
-initial release, with linear, log, exponential, polynomial, and sigmoid kernels
-already vectorized (except for polynomial generation) and CUDA-optimized
"""
__author__ = (
"Jacob Levine <jlevine@imsa.edu>",
"Arthur Lu <learthurgo@gmail.com>",
)
__all__ = [
'factorial',
'take_all_pwrs',
'num_poly_terms',
'set_device',
'LinearRegKernel',
'SigmoidalRegKernel',
'LogRegKernel',
'PolyRegKernel',
'ExpRegKernel',
'SigmoidalRegKernelArthur',
'SGDTrain',
'CustomTrain',
'CircleFit'
]
import torch
global device
device = "cuda:0" if torch.cuda.is_available() else "cpu"
#todo: document completely
def set_device(self, new_device):
device=new_device
class LinearRegKernel():
parameters= []
weights=None
bias=None
def __init__(self, num_vars):
self.weights=torch.rand(num_vars, requires_grad=True, device=device)
self.bias=torch.rand(1, requires_grad=True, device=device)
self.parameters=[self.weights,self.bias]
def forward(self,mtx):
long_bias=self.bias.repeat([1,mtx.size()[1]])
return torch.matmul(self.weights,mtx)+long_bias
class SigmoidalRegKernel():
parameters= []
weights=None
bias=None
sigmoid=torch.nn.Sigmoid()
def __init__(self, num_vars):
self.weights=torch.rand(num_vars, requires_grad=True, device=device)
self.bias=torch.rand(1, requires_grad=True, device=device)
self.parameters=[self.weights,self.bias]
def forward(self,mtx):
long_bias=self.bias.repeat([1,mtx.size()[1]])
return self.sigmoid(torch.matmul(self.weights,mtx)+long_bias)
class SigmoidalRegKernelArthur():
parameters= []
weights=None
in_bias=None
scal_mult=None
out_bias=None
sigmoid=torch.nn.Sigmoid()
def __init__(self, num_vars):
self.weights=torch.rand(num_vars, requires_grad=True, device=device)
self.in_bias=torch.rand(1, requires_grad=True, device=device)
self.scal_mult=torch.rand(1, requires_grad=True, device=device)
self.out_bias=torch.rand(1, requires_grad=True, device=device)
self.parameters=[self.weights,self.in_bias, self.scal_mult, self.out_bias]
def forward(self,mtx):
long_in_bias=self.in_bias.repeat([1,mtx.size()[1]])
long_out_bias=self.out_bias.repeat([1,mtx.size()[1]])
return (self.scal_mult*self.sigmoid(torch.matmul(self.weights,mtx)+long_in_bias))+long_out_bias
class LogRegKernel():
parameters= []
weights=None
in_bias=None
scal_mult=None
out_bias=None
def __init__(self, num_vars):
self.weights=torch.rand(num_vars, requires_grad=True, device=device)
self.in_bias=torch.rand(1, requires_grad=True, device=device)
self.scal_mult=torch.rand(1, requires_grad=True, device=device)
self.out_bias=torch.rand(1, requires_grad=True, device=device)
self.parameters=[self.weights,self.in_bias, self.scal_mult, self.out_bias]
def forward(self,mtx):
long_in_bias=self.in_bias.repeat([1,mtx.size()[1]])
long_out_bias=self.out_bias.repeat([1,mtx.size()[1]])
return (self.scal_mult*torch.log(torch.matmul(self.weights,mtx)+long_in_bias))+long_out_bias
class ExpRegKernel():
parameters= []
weights=None
in_bias=None
scal_mult=None
out_bias=None
def __init__(self, num_vars):
self.weights=torch.rand(num_vars, requires_grad=True, device=device)
self.in_bias=torch.rand(1, requires_grad=True, device=device)
self.scal_mult=torch.rand(1, requires_grad=True, device=device)
self.out_bias=torch.rand(1, requires_grad=True, device=device)
self.parameters=[self.weights,self.in_bias, self.scal_mult, self.out_bias]
def forward(self,mtx):
long_in_bias=self.in_bias.repeat([1,mtx.size()[1]])
long_out_bias=self.out_bias.repeat([1,mtx.size()[1]])
return (self.scal_mult*torch.exp(torch.matmul(self.weights,mtx)+long_in_bias))+long_out_bias
class PolyRegKernel():
parameters= []
weights=None
bias=None
power=None
def __init__(self, num_vars, power):
self.power=power
num_terms=self.num_poly_terms(num_vars, power)
self.weights=torch.rand(num_terms, requires_grad=True, device=device)
self.bias=torch.rand(1, requires_grad=True, device=device)
self.parameters=[self.weights,self.bias]
def num_poly_terms(self,num_vars, power):
if power == 0:
return 0
return int(self.factorial(num_vars+power-1) / self.factorial(power) / self.factorial(num_vars-1)) + self.num_poly_terms(num_vars, power-1)
def factorial(self,n):
if n==0:
return 1
else:
return n*self.factorial(n-1)
def take_all_pwrs(self, vec, pwr):
#todo: vectorize (kinda)
combins=torch.combinations(vec, r=pwr, with_replacement=True)
out=torch.ones(combins.size()[0]).to(device).to(torch.float)
for i in torch.t(combins).to(device).to(torch.float):
out *= i
if pwr == 1:
return out
else:
return torch.cat((out,self.take_all_pwrs(vec, pwr-1)))
def forward(self,mtx):
#TODO: Vectorize the last part
cols=[]
for i in torch.t(mtx):
cols.append(self.take_all_pwrs(i,self.power))
new_mtx=torch.t(torch.stack(cols))
long_bias=self.bias.repeat([1,mtx.size()[1]])
return torch.matmul(self.weights,new_mtx)+long_bias
def SGDTrain(self, kernel, data, ground, loss=torch.nn.MSELoss(), iterations=1000, learning_rate=.1, return_losses=False):
optim=torch.optim.SGD(kernel.parameters, lr=learning_rate)
data_cuda=data.to(device)
ground_cuda=ground.to(device)
if (return_losses):
losses=[]
for i in range(iterations):
with torch.set_grad_enabled(True):
optim.zero_grad()
pred=kernel.forward(data_cuda)
ls=loss(pred,ground_cuda)
losses.append(ls.item())
ls.backward()
optim.step()
return [kernel,losses]
else:
for i in range(iterations):
with torch.set_grad_enabled(True):
optim.zero_grad()
pred=kernel.forward(data_cuda)
ls=loss(pred,ground_cuda)
ls.backward()
optim.step()
return kernel
def CustomTrain(self, kernel, optim, data, ground, loss=torch.nn.MSELoss(), iterations=1000, return_losses=False):
data_cuda=data.to(device)
ground_cuda=ground.to(device)
if (return_losses):
losses=[]
for i in range(iterations):
with torch.set_grad_enabled(True):
optim.zero_grad()
pred=kernel.forward(data)
ls=loss(pred,ground)
losses.append(ls.item())
ls.backward()
optim.step()
return [kernel,losses]
else:
for i in range(iterations):
with torch.set_grad_enabled(True):
optim.zero_grad()
pred=kernel.forward(data_cuda)
ls=loss(pred,ground_cuda)
ls.backward()
optim.step()
return kernel

View File

@ -1,122 +0,0 @@
# Titan Robotics Team 2022: ML Module
# Written by Arthur Lu & Jacob Levine
# Notes:
# this should be imported as a python module using 'import titanlearn'
# this should be included in the local directory or environment variable
# this module is optimized for multhreaded computing
# this module learns from its mistakes far faster than 2022's captains
# setup:
__version__ = "1.1.1"
#changelog should be viewed using print(analysis.__changelog__)
__changelog__ = """changelog:
1.1.1:
- removed matplotlib import
- removed graphloss()
1.1.0:
- added net, dataset, dataloader, and stdtrain template definitions
- added graphloss function
1.0.1:
- added clear functions
1.0.0:
- complete rewrite planned
- depreciated 1.0.0.xxx versions
- added simple training loop
0.0.x:
-added generation of ANNS, basic SGD training
"""
__author__ = (
"Arthur Lu <arthurlu@ttic.edu>,"
"Jacob Levine <jlevine@ttic.edu>,"
)
__all__ = [
'clear',
'net',
'dataset',
'dataloader',
'train',
'stdtrainer',
]
import torch
from os import system, name
import numpy as np
def clear():
if name == 'nt':
_ = system('cls')
else:
_ = system('clear')
class net(torch.nn.Module): #template for standard neural net
def __init__(self):
super(Net, self).__init__()
def forward(self, input):
pass
class dataset(torch.utils.data.Dataset): #template for standard dataset
def __init__(self):
super(torch.utils.data.Dataset).__init__()
def __getitem__(self, index):
pass
def __len__(self):
pass
def dataloader(dataset, batch_size, num_workers, shuffle = True):
return torch.utils.data.DataLoader(dataset, batch_size=batch_size, shuffle=shuffle, num_workers=num_workers)
def train(device, net, epochs, trainloader, optimizer, criterion): #expects standard dataloader, whch returns (inputs, labels)
dataset_len = trainloader.dataset.__len__()
iter_count = 0
running_loss = 0
running_loss_list = []
for epoch in range(epochs): # loop over the dataset multiple times
for i, data in enumerate(trainloader, 0):
inputs = data[0].to(device)
labels = data[1].to(device)
optimizer.zero_grad()
outputs = net(inputs)
loss = criterion(outputs, labels.to(torch.float))
loss.backward()
optimizer.step()
# monitoring steps below
iter_count += 1
running_loss += loss.item()
running_loss_list.append(running_loss)
clear()
print("training on: " + device)
print("iteration: " + str(i) + "/" + str(int(dataset_len / trainloader.batch_size)) + " | " + "epoch: " + str(epoch) + "/" + str(epochs))
print("current batch loss: " + str(loss.item))
print("running loss: " + str(running_loss / iter_count))
return net, running_loss_list
print("finished training")
def stdtrainer(net, criterion, optimizer, dataloader, epochs, batch_size):
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
net = net.to(device)
criterion = criterion.to(device)
optimizer = optimizer.to(device)
trainloader = dataloader
return train(device, net, epochs, trainloader, optimizer, criterion)

View File

@ -1,58 +0,0 @@
# Titan Robotics Team 2022: Visualization Module
# Written by Arthur Lu & Jacob Levine
# Notes:
# this should be imported as a python module using 'import visualization'
# this should be included in the local directory or environment variable
# fancy
# setup:
__version__ = "0.0.1"
#changelog should be viewed using print(analysis.__changelog__)
__changelog__ = """changelog:
0.0.1:
- added graphhistogram function as a fragment of visualize_pit.py
0.0.0:
- created visualization.py
- added graphloss()
- added imports
"""
__author__ = (
"Arthur Lu <arthurlu@ttic.edu>,"
"Jacob Levine <jlevine@ttic.edu>,"
)
__all__ = [
'graphloss',
]
import matplotlib.pyplot as plt
import numpy as np
def graphloss(losses):
x = range(0, len(losses))
plt.plot(x, losses)
plt.show()
def graphhistogram(data, figsize, sharey = True): # expects library with key as variable and contents as occurances
fig, ax = plt.subplots(1, len(data), sharey=sharey, figsize=figsize)
i = 0
for variable in data:
ax[i].hist(data[variable])
ax[i].invert_xaxis()
ax[i].set_xlabel('Variable')
ax[i].set_ylabel('Frequency')
ax[i].set_title(variable)
plt.yticks(np.arange(len(data[variable])))
i+=1
plt.show()