fix: issue #55

Signed-off-by: Dev Singh <dev@devksingh.com>

.devcontainer/devcontainer.json

@@ -21,7 +21,8 @@
 	},
 	"extensions": [
 		"mhutchie.git-graph",
-		"donjayamanne.jupyter",
+		"ms-python.python",
+		"waderyan.gitblame"
 	],
-	"postCreateCommand": "pip install -r analysis-master/requirements.txt"
+	"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"
 }

.gitattributes

@@ -1,2 +1,4 @@
 # Auto detect text files and perform LF normalization
-* text=auto
+* text=auto eol=lf
+*.{cmd,[cC][mM][dD]} text eol=crlf
+*.{bat,[bB][aA][tT]} text eol=crlf

.github/workflows/publish-analysis.yml

@@ -4,8 +4,9 @@
 name: Upload Analysis Package
 
 on:
-  release:
-    types: [published, edited]
+  push:
+    tags:
+      - 'v*'
 jobs:
   deploy:
 
@@ -34,3 +35,23 @@ jobs:
         user: __token__
         password: ${{ secrets.PYPI_TOKEN }}
         packages_dir: analysis-master/dist/
+    - name: Create Release
+      id: create_release
+      uses: actions/create-release@v1
+      env:
+        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+      with:
+        tag_name: ${{ github.ref }}
+        release_name: Release ${{ github.ref }}
+        body: See PyPI
+        draft: false
+        prerelease: false
+    - name: Upload Release Asset
+      id: upload-release-asset 
+      uses: actions/upload-release-asset@v1
+      env:
+        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+      with:
+        upload_url: ${{ steps.create_release.outputs.upload_url }} 
+        asset_name: ${{ github.ref }}
+        asset_content_type: application/octet-stream

.gitignore

@@ -31,9 +31,11 @@ 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
+analysis-master/dist
+data-analysis/config/

LICENSE

@@ -1,6 +1,6 @@
 BSD 3-Clause License
 
-Copyright (c) 2020, Titan Robotics FRC 2022
+Copyright (c) 2020, Titan Scouting
 All rights reserved.
 
 Redistribution and use in source and binary forms, with or without

MAINTAINERS

@@ -1,3 +1,3 @@
 Arthur Lu <learthurgo@gmail.com>
 Jacob Levine <jacoblevine18@gmail.com>
-Dev Singh <dev@devksingh.com>
+Dev Singh <dev@devksingh.com>

README.md

@@ -1,5 +1,102 @@
-# red-alliance-analysis
+# Red Alliance Analysis · ![GitHub release (latest by date)](https://img.shields.io/github/v/release/titanscout2022/red-alliance-analysis)
+
 Titan Robotics 2022 Strategy Team Repository for Data Analysis Tools. Included with these tools are the backend data analysis engine formatted as a python package, associated binaries for the analysis package, and premade scripts that can be pulled directly from this repository and will integrate with other Red Alliance applications to quickly deploy FRC scouting tools.
 
-# Installing 
-`pip install tra_analysis`
+---
+
+# `tra-analysis`
+
+`tra-analysis` is a higher level package for data processing and analysis. It is a python library that combines popular data science tools like numpy, scipy, and sklearn along with other tools to create an easy-to-use data analysis engine. tra-analysis includes analysis in all ranges of complexity from basic statistics like mean, median, mode to complex kernel based classifiers and allows user to more quickly deploy these algorithms. The package also includes performance metrics for score based applications including elo, glicko2, and trueskill ranking systems.
+
+At the core of the tra-analysis package is the modularity of each analytical tool. The package encapsulates the setup code for the included data science tools. For example, there are many packages that allow users to generate many different types of regressions. With the tra-analysis package, one function can be called to generate many regressions and sort them by accuracy.
+
+## Prerequisites
+---
+
+* Python >= 3.6
+* Pip which can be installed by running\
+`curl https://bootstrap.pypa.io/get-pip.py -o get-pip.py`\
+`python get-pip.py`\
+after installing python, or with a package manager on linux. Refer to the [pip installation instructions](https://pip.pypa.io/en/stable/installing/) for more information.
+
+## Installing
+---
+
+#### Standard Platforms
+
+For the latest version of tra-analysis, run `pip install tra-analysis` or `pip install tra_analysis`. The requirements for tra-analysis should be automatically installed.
+
+#### Exotic Platforms (Android)
+
+[Termux](https://termux.com/) is recommended for a linux environemnt on Android. Consult the [documentation](https://titanscouting.github.io/analysis/general/installation#exotic-platforms-android) for advice on installing the prerequisites. After installing the prerequisites, the package should be installed normally with `pip install tra-analysis` or `pip install tra_analysis`. 
+
+## Use
+
+---
+
+tra-analysis operates like any other python package. Consult the [documentation](https://titanscouting.github.io/analysis/tra_analysis/) for more information.
+
+## Supported Platforms
+
+---
+
+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)
+* ARM64 (Tested on Broadcom BCM2836 SoC, Broadcom BCM2711 SoC)
+
+The following OSes have been tested to be working:
+* Linux Kernel 3.16, 4.4, 4.15, 4.19, 5.4
+	* Ubuntu 16.04, 18.04, 20.04
+	* Debian (and Debian derivaives) Jessie, Buster
+* Windows 7, 10
+
+The following python versions are supported:
+* python 3.6 (not tested)
+* python 3.7
+* python 3.8
+
+---
+
+# `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.
+
+# 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)

SECURITY.md

@@ -0,0 +1,6 @@
+# Security Policy
+
+
+## Reporting a Vulnerability
+
+Please email `titanscout2022@gmail.com` to report a vulnerability.

analysis-master/setup.py

@@ -8,7 +8,7 @@ with open("requirements.txt", 'r') as file:
 
 setuptools.setup(
 	name="tra_analysis",
-	version="2.0.2",
+	version="2.1.0",
 	author="The Titan Scouting Team",
 	author_email="titanscout2022@gmail.com",
 	description="Analysis package developed by Titan Scouting for The Red Alliance",
@@ -17,7 +17,7 @@ setuptools.setup(
 	url="https://github.com/titanscout2022/tr2022-strategy",
 	packages=setuptools.find_packages(),
 	install_requires=requirements,
-	license = "GNU General Public License v3.0",
+	license = "BSD 3-Clause License",
 	classifiers=[
 		"Programming Language :: Python :: 3",
 		"Operating System :: OS Independent",

analysis-master/test_analysis.py

@@ -1,8 +1,11 @@
 from tra_analysis import analysis as an
 from tra_analysis import metrics
+from tra_analysis import fits
 
 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]
@@ -28,4 +31,5 @@ def test_():
 	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 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)

analysis-master/tra_analysis/.ipynb_checkpoints/equation-checkpoint.ipynb

@@ -0,0 +1,35 @@
+{
+ "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
+}

analysis-master/tra_analysis/analysis.py

@@ -7,13 +7,24 @@
 #    current benchmark of optimization: 1.33 times faster
 # setup:
 
-__version__ = "2.0.2"
+__version__ = "2.3.1"
 
 # changelog should be viewed using print(analysis.__changelog__)
 __changelog__ = """changelog:
-	2.0.2:
-		- rename analysis imports to tra_analysis for PyPI publishing
-	1.2.2.000:
+	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
@@ -29,25 +40,25 @@ __changelog__ = """changelog:
 		- tested all sorting algorithms with both lists and numpy arrays
 		- depreciated sort function from Array class
 		- added warnings as an import
-	1.2.1.004:
+	2.1.4:
 		- added sort and search functions to Array class
-	1.2.1.003:
+	2.1.3:
 		- changed output of basic_stats and histo_analysis to libraries
 		- fixed __all__
-	1.2.1.002:
+	2.1.2:
 		- renamed ArrayTest class to Array
-	1.2.1.001:
+	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
-	1.2.1.000:
+	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
-	1.2.0.006:
+	2.0.6:
 		- renamed func functions in regression to lin, log, exp, and sig 
-	1.2.0.005:
+	2.0.5:
 		- moved random_forrest_regressor and random_forrest_classifier to RandomForrest class
 		- renamed Metrics to Metric
 		- renamed RegressionMetrics to RegressionMetric
@@ -55,166 +66,166 @@ __changelog__ = """changelog:
 		- renamed CorrelationTests to CorrelationTest
 		- renamed StatisticalTests to StatisticalTest
 		- reflected rafactoring to all mentions of above classes/functions
-	1.2.0.004:
+	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
-	1.2.0.003:
+	2.0.3:
 		- bug fixes with CorrelationTests and StatisticalTests
 		- moved glicko2 and trueskill to the metrics subpackage
 		- moved elo to a new metrics subpackage
-	1.2.0.002:
+	2.0.2:
 		- fixed docs
-	1.2.0.001:
+	2.0.1:
 		- fixed docs
-	1.2.0.000:
+	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
-	1.1.13.009:
+	1.13.9:
 		- moved elo, glicko2, trueskill functions under class Metrics
-	1.1.13.008:
+	1.13.8:
 		- moved Glicko2 to a seperate package
-	1.1.13.007:
+	1.13.7:
 		- fixed bug with trueskill
-	1.1.13.006:
+	1.13.6:
 		- cleaned up imports
-	1.1.13.005:
+	1.13.5:
 		- cleaned up package
-	1.1.13.004:
+	1.13.4:
 		- small fixes to regression to improve performance
-	1.1.13.003:
+	1.13.3:
 		- filtered nans from regression
-	1.1.13.002:
+	1.13.2:
 		- removed torch requirement, and moved Regression back to regression.py
-	1.1.13.001:
+	1.13.1:
 		- bug fix with linear regression not returning a proper value
 		- cleaned up regression
 		- fixed bug with polynomial regressions
-	1.1.13.000:
+	1.13.0:
 		- fixed all regressions to now properly work
-	1.1.12.006:
+	1.12.6:
 		- fixed bg with a division by zero in histo_analysis
-	1.1.12.005:
+	1.12.5:
 		- fixed numba issues by removing numba  from elo, glicko2 and trueskill
-	1.1.12.004:
+	1.12.4:
 		- renamed gliko to glicko
-	1.1.12.003:
+	1.12.3:
 		- removed depreciated code
-	1.1.12.002:
+	1.12.2:
 		- removed team first time trueskill instantiation in favor of integration in superscript.py
-	1.1.12.001:
+	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
-	1.1.12.000:
+	1.12.0:
 		- temporarily fixed polynomial regressions by using sklearn's PolynomialFeatures
-	1.1.11.010:
+	1.11.010:
 		- alphabeticaly ordered import lists
-	1.1.11.009:
+	1.11.9:
 		- bug fixes
-	1.1.11.008:
+	1.11.8:
 		- bug fixes
-	1.1.11.007:
+	1.11.7:
 		- bug fixes
-	1.1.11.006:
+	1.11.6:
 		- tested min and max
 		- bug fixes 
-	1.1.11.005:
+	1.11.5:
 		- added min and max in basic_stats
-	1.1.11.004:
+	1.11.4:
 		- bug fixes
-	1.1.11.003:
+	1.11.3:
 		- bug fixes
-	1.1.11.002:
+	1.11.2:
 		- consolidated metrics
 		- fixed __all__
-	1.1.11.001:
+	1.11.1:
 		- added test/train split to RandomForestClassifier and RandomForestRegressor
-	1.1.11.000:
+	1.11.0:
 		- added RandomForestClassifier and RandomForestRegressor
 		- note: untested
-	1.1.10.000:
+	1.10.0:
 		- added numba.jit to remaining functions
-	1.1.9.002:
+	1.9.2:
 		- kernelized PCA and KNN
-	1.1.9.001:
+	1.9.1:
 		- fixed bugs with SVM and NaiveBayes
-	1.1.9.000:
+	1.9.0:
 		- added SVM class, subclasses, and functions
 		- note: untested
-	1.1.8.000:
+	1.8.0:
 		- added NaiveBayes classification engine
 		- note: untested
-	1.1.7.000:
+	1.7.0:
 		- added knn()
 		- added confusion matrix to decisiontree()
-	1.1.6.002:
+	1.6.2:
 		- changed layout of __changelog to be vscode friendly
-	1.1.6.001:
+	1.6.1:
 		- added additional hyperparameters to decisiontree()
-	1.1.6.000:
+	1.6.0:
 		- fixed __version__
 		- fixed __all__ order
 		- added decisiontree()
-	1.1.5.003:
+	1.5.3:
 		- added pca
-	1.1.5.002:
+	1.5.2:
 		- reduced import list
 		- added kmeans clustering engine
-	1.1.5.001:
+	1.5.1:
 		- simplified regression by using .to(device)
-	1.1.5.000:
+	1.5.0:
 		- added polynomial regression to regression(); untested
-	1.1.4.000:
+	1.4.0:
 		- added trueskill()
-	1.1.3.002:
+	1.3.2:
 		- renamed regression class to Regression, regression_engine() to regression gliko2_engine class to Gliko2
-	1.1.3.001:
+	1.3.1:
 		- changed glicko2() to return tuple instead of array
-	1.1.3.000:
+	1.3.0:
 		- added glicko2_engine class and glicko()
 		- verified glicko2() accuracy
-	1.1.2.003:
+	1.2.3:
 		- fixed elo()
-	1.1.2.002:
+	1.2.2:
 		- added elo()
 		- elo() has bugs to be fixed
-	1.1.2.001:
+	1.2.1:
 		- readded regrression import
-	1.1.2.000:
+	1.2.0:
 		- integrated regression.py as regression class
 		- removed regression import
 		- fixed metadata for regression class
 		- fixed metadata for analysis class
-	1.1.1.001:
+	1.1.1:
 		- regression_engine() bug fixes, now actaully regresses
-	1.1.1.000:
+	1.1.0:
 		- added regression_engine()
 		- added all regressions except polynomial
-	1.1.0.007:
+	1.0.7:
 		- updated _init_device()
-	1.1.0.006:
+	1.0.6:
 		- removed useless try statements
-	1.1.0.005:
+	1.0.5:
 		- removed impossible outcomes
-	1.1.0.004:
+	1.0.4:
 		- added performance metrics (r^2, mse, rms)
-	1.1.0.003:
+	1.0.3:
 		- resolved nopython mode for mean, median, stdev, variance
-	1.1.0.002:
+	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
-	1.1.0.001:
+	1.0.1:
 		- removed from sklearn import * to resolve uneeded wildcard imports
-	1.1.0.000:
+	1.0.0:
 		- removed c_entities,nc_entities,obstacles,objectives from __all__
 		- applied numba.jit to all functions
 		- depreciated and removed stdev_z_split
@@ -223,93 +234,93 @@ __changelog__ = """changelog:
 		- 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
-	1.0.9.000:
+	0.9.0:
 		- refactored
 		- numpyed everything
 		- removed stats in favor of numpy functions
-	1.0.8.005:
+	0.8.5:
 		- minor fixes
-	1.0.8.004:
+	0.8.4:
 		- removed a few unused dependencies
-	1.0.8.003:
+	0.8.3:
 		- added p_value function
-	1.0.8.002:
-		- updated __all__ correctly to contain changes made in v 1.0.8.000 and v 1.0.8.001
-	1.0.8.001:
+	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
-	1.0.8.000:
+	0.8.0:
 		- depreciated histo_analysis_old
 		- depreciated debug
 		- altered basic_analysis to take array data instead of filepath
 		- refactor
 		- optimization
-	1.0.7.002:
+	0.7.2:
 		- bug fixes
-	1.0.7.001:
+	0.7.1:
 		- bug fixes
-	1.0.7.000:
+	0.7.0:
 		- added tanh_regression (logistical regression)
 		- bug fixes
-	1.0.6.005:
+	0.6.5:
 		- added z_normalize function to normalize dataset
 		- bug fixes
-	1.0.6.004:
+	0.6.4:
 		- bug fixes
-	1.0.6.003:
+	0.6.3:
 		- bug fixes
-	1.0.6.002:
+	0.6.2:
 		- bug fixes
-	1.0.6.001:
+	0.6.1:
 		- corrected __all__ to contain all of the functions
-	1.0.6.000:
+	0.6.0:
 		- added calc_overfit, which calculates two measures of overfit, error and performance
 		- added calculating overfit to optimize_regression
-	1.0.5.000:
+	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
-	1.0.4.002:
+	0.4.2:
 		- added __changelog__
 		- updated debug function with log and exponential regressions
-	1.0.4.001:
+	0.4.1:
 		- added log regressions
 		- added exponential regressions
 		- added log_regression and exp_regression to __all__
-	1.0.3.008:
+	0.3.8:
 		- added debug function to further consolidate functions
-	1.0.3.007:
+	0.3.7:
 		- added builtin benchmark function
 		- added builtin random (linear) data generation function
 		- added device initialization (_init_device)
-	1.0.3.006:
+	0.3.6:
 		- reorganized the imports list to be in alphabetical order
 		- added search and regurgitate functions to c_entities, nc_entities, obstacles, objectives
-	1.0.3.005:
+	0.3.5:
 		- major bug fixes
 		- updated historical analysis
 		- depreciated old historical analysis
-	1.0.3.004:
+	0.3.4:
 		- added __version__, __author__, __all__
 		- added polynomial regression
 		- added root mean squared function
 		- added r squared function
-	1.0.3.003:
+	0.3.3:
 		- bug fixes
 		- added c_entities
-	1.0.3.002:
+	0.3.2:
 		- bug fixes
 		- added nc_entities, obstacles, objectives
 		- consolidated statistics.py to analysis.py
-	1.0.3.001:
+	0.3.1:
 		- compiled 1d, column, and row basic stats into basic stats function
-	1.0.3.000:
+	0.3.0:
 		- added historical analysis function
-	1.0.2.xxx:
+	0.2.x:
 		- added z score test
-	1.0.1.xxx:
+	0.1.x:
 		- major bug fixes
-	1.0.0.xxx:
+	0.0.x:
 		- added loading csv
 		- added 1d, column, row basic stats
 """
@@ -344,7 +355,7 @@ __all__ = [
 
 # now back to your regularly scheduled programming:
 
-# imports (now in alphabetical order! v 1.0.3.006):
+# imports (now in alphabetical order! v 0.3.006):
 
 import csv
 from tra_analysis.metrics import elo as Elo
@@ -424,7 +435,7 @@ def regression(inputs, outputs, args): # inputs, outputs expects N-D array
 	X = np.array(inputs)
 	y = np.array(outputs)
 
-	regressions = []
+	regressions = {}
 
 	if 'lin' in args: # formula: ax + b
 
@@ -437,7 +448,7 @@ def regression(inputs, outputs, args): # inputs, outputs expects N-D array
 			popt, pcov = scipy.optimize.curve_fit(lin, X, y)
 
 			coeffs = popt.flatten().tolist()
-			regressions.append(str(coeffs[0]) + "*x+" + str(coeffs[1]))
+			regressions["lin"] = (str(coeffs[0]) + "*x+" + str(coeffs[1]))
 
 		except Exception as e:
 
@@ -454,7 +465,7 @@ def regression(inputs, outputs, args): # inputs, outputs expects N-D array
 			popt, pcov = scipy.optimize.curve_fit(log, X, y)
 
 			coeffs = popt.flatten().tolist()
-			regressions.append(str(coeffs[0]) + "*log(" + str(coeffs[1]) + "*(x+" + str(coeffs[2]) + "))+" + str(coeffs[3]))
+			regressions["log"] = (str(coeffs[0]) + "*log(" + str(coeffs[1]) + "*(x+" + str(coeffs[2]) + "))+" + str(coeffs[3]))
 
 		except Exception as e:
 			
@@ -471,7 +482,7 @@ def regression(inputs, outputs, args): # inputs, outputs expects N-D array
 			popt, pcov = scipy.optimize.curve_fit(exp, X, y)
 
 			coeffs = popt.flatten().tolist()
-			regressions.append(str(coeffs[0]) + "*e^(" + str(coeffs[1]) + "*(x+" + str(coeffs[2]) + "))+" + str(coeffs[3]))
+			regressions["exp"] = (str(coeffs[0]) + "*e^(" + str(coeffs[1]) + "*(x+" + str(coeffs[2]) + "))+" + str(coeffs[3]))
 
 		except Exception as e:
 
@@ -482,7 +493,7 @@ def regression(inputs, outputs, args): # inputs, outputs expects N-D array
 		inputs = np.array([inputs])
 		outputs = np.array([outputs])
 
-		plys = []
+		plys = {}
 		limit = len(outputs[0])
 
 		for i in range(2, limit):
@@ -500,9 +511,9 @@ def regression(inputs, outputs, args): # inputs, outputs expects N-D array
 			for param in params:
 				temp += "(" + str(param) + "*x^" + str(counter) + ")"
 				counter += 1
-			plys.append(temp)
+			plys["x^" + str(i)] = (temp)
 
-		regressions.append(plys)
+		regressions["ply"] = (plys)
 
 	if 'sig' in args: # formula: a tanh (b(x + c)) + d
 
@@ -515,7 +526,7 @@ def regression(inputs, outputs, args): # inputs, outputs expects N-D array
 			popt, pcov = scipy.optimize.curve_fit(sig, X, y)
 
 			coeffs = popt.flatten().tolist()
-			regressions.append(str(coeffs[0]) + "*tanh(" + str(coeffs[1]) + "*(x+" + str(coeffs[2]) + "))+" + str(coeffs[3]))
+			regressions["sig"] = (str(coeffs[0]) + "*tanh(" + str(coeffs[1]) + "*(x+" + str(coeffs[2]) + "))+" + str(coeffs[3]))
 
 		except Exception as e:
 		   
@@ -642,7 +653,7 @@ def decisiontree(data, labels, test_size = 0.3, criterion = "gini", splitter = "
 
 class KNN:
 
-	def knn_classifier(self, data, labels, test_size = 0.3, algorithm='auto', leaf_size=30, metric='minkowski', metric_params=None, n_jobs=None, n_neighbors=5, p=2, weights='uniform'): #expects *2d data and 1d labels post-scaling
+	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()
@@ -651,7 +662,7 @@ class KNN:
 
 		return model, ClassificationMetric(predictions, labels_test)
 
-	def knn_regressor(self, data, outputs, test_size, n_neighbors = 5, weights = "uniform", algorithm = "auto", leaf_size = 30, p = 2, metric = "minkowski", metric_params = None, n_jobs = None):
+	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)
@@ -754,9 +765,9 @@ class SVM:
 
 		return RegressionMetric(predictions, test_outputs)
 
-class RandomForrest:
+class RandomForest:
 
-	def random_forest_classifier(self, data, labels, test_size, n_estimators="warn", 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(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)
@@ -765,7 +776,7 @@ class RandomForrest:
 
 		return kernel, ClassificationMetric(predictions, labels_test)
 
-	def random_forest_regressor(self, data, outputs, test_size, n_estimators="warn", 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(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)
@@ -779,7 +790,7 @@ 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]}
+		return {"f-value": results[0], "p-value": results[1]}
 
 	def pearson(self, x, y):
 
@@ -978,81 +989,112 @@ class StatisticalTest:
 		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): # expects arrays that are size normalized
+	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)
 
-		return np.mean([*args], axis = 0)
+	def elementwise_median(self, *args, axis = 0):
 
-	def elementwise_median(self, *args):
+		if len(*args) == 0:
+			return np.median(self.array, axis = axis)
+		else:
+			return np.median([*args], axis = axis)
 
-		return np.median([*args], axis = 0)
+	def elementwise_stdev(self, *args, axis = 0):
 
-	def elementwise_stdev(self, *args):
+		if len(*args) == 0:
+			return np.std(self.array, axis = axis)
+		else:
+			return np.std([*args], axis = axis)
 
-		return np.std([*args], axis = 0)
+	def elementwise_variance(self, *args, axis = 0):
 
-	def elementwise_variance(self, *args):
+		if len(*args) == 0:
+			return np.var(self.array, axis = axis)
+		else:
+			return np.var([*args], axis = axis)
 
-		return np.var([*args], axis = 0)
+	def elementwise_npmin(self, *args, axis = 0):
 
-	def elementwise_npmin(self, *args):
+		if len(*args) == 0:
+			return np.amin(self.array, axis = axis)
+		else:
+			return np.amin([*args], axis = axis)
 
-		return np.amin([*args], axis = 0)
+	def elementwise_npmax(self, *args, axis = 0):
 
-	def elementwise_npmax(self, *args):
+		if len(*args) == 0:
+			return np.amax(self.array, axis = axis)
+		else:
+			return np.amax([*args], axis = axis)
 
-		return np.amax([*args], axis = 0)
+	def elementwise_stats(self, *args, axis = 0):
 
-	def elementwise_stats(self, *args):
-
-		_mean = self.elementwise_mean(*args)
-		_median = self.elementwise_median(*args)
-		_stdev = self.elementwise_stdev(*args)
-		_variance = self.elementwise_variance(*args)
-		_min = self.elementwise_npmin(*args)
-		_max = self.elementwise_npmax(*args)
+		_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, *args):
+	def __add__(self, other):
 
-		temp = np.array([])
+		return self.array + other.array
 
-		for a in args:
-			temp += a
+	def __sub__(self, other):
+
+		return self.array - other.array
+
+	def __neg__(self):
 		
-		return temp
+		return -self.array
 
-	def mul(self, *args):
+	def __abs__(self):
 
-		temp = np.array([])
+		return abs(self.array)
 
-		for a in args:
-			temp *= a
-		
-		return temp
+	def __invert__(self):
 
-	def neg(self, array):
-		
-		return -array
+		return 1/self.array
 
-	def inv(self, array):
+	def __mul__(self, other):
 
-		return 1/array
+		return self.array.dot(other.array)
 
-	def dot(self, a, b):
+	def __rmul__(self, other):
 
-		return np.dot(a, b)
+		return self.array.dot(other.array)
 
-	def cross(self, a, b):
+	def cross(self, other):
 
-		return np.cross(a, b)
+		return np.cross(self.array, other.array)
 
 	def sort(self, array): # depreciated
 		warnings.warn("Array.sort has been depreciated in favor of Sort")

analysis-master/tra_analysis/fits.py

@@ -0,0 +1,85 @@
+# Titan Robotics Team 2022: CPU fitting models
+# Written by Dev Singh
+# Notes:
+#   this module is cuda-optimized (as appropriate) and vectorized (except for one small part)
+# setup:
+
+__version__ = "0.0.1"
+
+# changelog should be viewed using print(analysis.fits.__changelog__)
+__changelog__ = """changelog:
+	0.0.1:
+		- initial release, add circle fitting with LSC
+"""
+
+__author__ = (
+	"Dev Singh <dev@devksingh.com>"
+)
+
+__all__ = [
+	'CircleFit'
+]
+
+import numpy as np
+
+class CircleFit:
+	"""Class to fit data to a circle using the Least Square Circle (LSC) method"""
+	# For more information on the LSC method, see: 
+	# http://www.dtcenter.org/sites/default/files/community-code/met/docs/write-ups/circle_fit.pdf
+	def __init__(self, x, y, xy=None):
+		self.ournp = np #todo: implement cupy correctly
+		if type(x) == list:
+			x = np.array(x)
+		if type(y) == list:
+			y = np.array(y)
+		if type(xy) == list:
+			xy = np.array(xy)
+		if xy != None: 
+			self.coords = xy
+		else: 
+			# following block combines x and y into one array if not already done
+			self.coords = self.ournp.vstack(([x.T], [y.T])).T
+	def calc_R(x, y, xc, yc):
+		"""Returns distance between center and point"""
+		return self.ournp.sqrt((x-xc)**2 + (y-yc)**2)
+	def f(c, x, y):
+		"""Returns distance between point and circle at c"""
+		Ri = calc_R(x, y, *c)
+		return Ri - Ri.mean()
+	def LSC(self):
+		"""Fits given data to a circle and returns the center, radius, and variance"""
+		x = self.coords[:, 0]
+		y = self.coords[:, 1]
+		# guessing at a center
+		x_m = self.ournp.mean(x)
+		y_m = self.ournp.mean(y)
+
+		# calculation of the reduced coordinates
+		u = x - x_m
+		v = y - y_m
+
+		# linear system defining the center (uc, vc) in reduced coordinates:
+		#    Suu * uc +  Suv * vc = (Suuu + Suvv)/2
+		#    Suv * uc +  Svv * vc = (Suuv + Svvv)/2
+		Suv  = self.ournp.sum(u*v)
+		Suu  = self.ournp.sum(u**2)
+		Svv  = self.ournp.sum(v**2)
+		Suuv = self.ournp.sum(u**2 * v)
+		Suvv = self.ournp.sum(u * v**2)
+		Suuu = self.ournp.sum(u**3)
+		Svvv = self.ournp.sum(v**3)
+
+		# Solving the linear system
+		A = self.ournp.array([ [ Suu, Suv ], [Suv, Svv]])
+		B = self.ournp.array([ Suuu + Suvv, Svvv + Suuv ])/2.0
+		uc, vc = self.ournp.linalg.solve(A, B)
+
+		xc_1 = x_m + uc
+		yc_1 = y_m + vc
+
+		# Calculate the distances from center (xc_1, yc_1)
+		Ri_1     = self.ournp.sqrt((x-xc_1)**2 + (y-yc_1)**2)
+		R_1      = self.ournp.mean(Ri_1)
+		# calculate residual error
+		residu_1 = self.ournp.sum((Ri_1-R_1)**2)
+		return (xc_1, yc_1, R_1, residu_1)

analysis-master/tra_analysis/regression.py

@@ -1,31 +1,32 @@
 # 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 and vectorized (except for one small part)
+#   this module is cuda-optimized (as appropriate) and vectorized (except for one small part)
 # setup:
 
-__version__ = "1.0.0.004"
+__version__ = "0.0.4"
 
 # changelog should be viewed using print(analysis.regression.__changelog__)
 __changelog__ = """
-	1.0.0.004:
+	0.0.4:
 		- bug fixes
 		- fixed changelog
-	1.0.0.003:
+	0.0.3:
 		- bug fixes
-	1.0.0.002:
+	0.0.2:
 		-Added more parameters to log, exponential, polynomial
 		-Added SigmoidalRegKernelArthur, because Arthur apparently needs
 		to train the scaling and shifting of sigmoids
-	1.0.0.001:
+	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>"
+	"Arthur Lu <learthurgo@gmail.com>",
 )
 
 __all__ = [
@@ -40,14 +41,15 @@ __all__ = [
 	'ExpRegKernel',
 	'SigmoidalRegKernelArthur',
 	'SGDTrain',
-	'CustomTrain'
+	'CustomTrain',
+	'CircleFit'
 ]
 
 import torch
 
 global device
 
-device = "cuda:0" if torch.torch.cuda.is_available() else "cpu"
+device = "cuda:0" if torch.cuda.is_available() else "cpu"
 
 #todo: document completely
 
@@ -217,4 +219,4 @@ def CustomTrain(self, kernel, optim, data, ground, loss=torch.nn.MSELoss(), iter
 				ls=loss(pred,ground_cuda)
 				ls.backward()
 				optim.step()
-		return kernel
+		return kernel

analysis-master/tra_analysis/titanlearn.py

@@ -7,23 +7,23 @@
 #    this module learns from its mistakes far faster than 2022's captains
 # setup:
 
-__version__ = "2.0.1.001"
+__version__ = "1.1.1"
 
 #changelog should be viewed using print(analysis.__changelog__)
 __changelog__ = """changelog:
-	2.0.1.001:
+	1.1.1:
 		- removed matplotlib import
 		- removed graphloss()
-	2.0.1.000:
+	1.1.0:
 		- added net, dataset, dataloader, and stdtrain template definitions
 		- added graphloss function
-	2.0.0.001:
+	1.0.1:
 		- added clear functions
-	2.0.0.000:
+	1.0.0:
 		- complete rewrite planned
 		- depreciated 1.0.0.xxx versions
 		- added simple training loop
-	1.0.0.xxx:
+	0.0.x:
 		-added generation of ANNS, basic SGD training
 """
 

analysis-master/tra_analysis/visualization.py

@@ -6,13 +6,13 @@
 #    fancy
 # setup:
 
-__version__ = "1.0.0.001"
+__version__ = "0.0.1"
 
 #changelog should be viewed using print(analysis.__changelog__)
 __changelog__ = """changelog:
-	1.0.0.001:
+	0.0.1:
 		- added graphhistogram function as a fragment of visualize_pit.py
-	1.0.0.000:
+	0.0.0:
 		- created visualization.py
 		- added graphloss()
 		- added imports

data-analysis/config.json

@@ -1,4 +1,5 @@
 {
+	"max-threads": 0.5,
 	"team": "",
 	"competition": "",
 	"key":{

data-analysis/requirements.txt

@@ -1,4 +1,4 @@
 requests
 pymongo
 pandas
-dnspython
+tra-analysis

data-analysis/superscript.py

@@ -3,19 +3,27 @@
 # Notes:
 # setup:
 
-__version__ = "0.0.6.002"
+__version__ = "0.8.2"
 
 # changelog should be viewed using print(analysis.__changelog__)
 __changelog__ = """changelog:
-	0.0.6.003:
-		- rename analysis imports to tra_analysis for PyPI publishing
-	0.0.6.002:
+	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
-	0.0.6.001:
+	0.6.1:
 		- bug fixes with analysis.Metric() calls
 		- modified metric functions to use config.json defined default values
-	0.0.6.000:
+	0.6.0:
 		- removed main function
 		- changed load_config function
 		- added save_config function
@@ -26,66 +34,66 @@ __changelog__ = """changelog:
 		- renamed metricsloop to metricloop
 		- split push to database functions amon push_match, push_metric, push_pit
 		- moved
-	0.0.5.002:
+	0.5.2:
 		- made changes due to refactoring of analysis
-	0.0.5.001:
+	0.5.1:
 		- text fixes
 		- removed matplotlib requirement
-	0.0.5.000:
+	0.5.0:
 		- improved user interface
-	0.0.4.002:
+	0.4.2:
 		- removed unessasary code
-	0.0.4.001:
+	0.4.1:
 		- fixed bug where X range for regression was determined before sanitization
 		- better sanitized data
-	0.0.4.000:
+	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 
-	0.0.3.000:
+	0.3.0:
 		- added analysis to pit data
-	0.0.2.001:
+	0.2.1:
 		- minor stability patches
 		- implemented db syncing for timestamps
 		- fixed bugs
-	0.0.2.000:
+	0.2.0:
 		- finalized testing and small fixes
-	0.0.1.004:
+	0.1.4:
 		- finished metrics implement, trueskill is bugged
-	0.0.1.003:
+	0.1.3:
 		- working
-	0.0.1.002:
+	0.1.2:
 		- started implement of metrics
-	0.0.1.001:
+	0.1.1:
 		- cleaned up imports
-	0.0.1.000:
+	0.1.0:
 		- tested working, can push to database
-	0.0.0.009:
+	0.0.9:
 		- tested working
 		- prints out stats for the time being, will push to database later
-	0.0.0.008:
+	0.0.8:
 		- added data import
 		- removed tba import
 		- finished main method
-	0.0.0.007:
+	0.0.7:
 		- added load_config
 		- optimized simpleloop for readibility
 		- added __all__ entries
 		- added simplestats engine
 		- pending testing
-	0.0.0.006:
+	0.0.6:
 		- fixes
-	0.0.0.005:
+	0.0.5:
 		- imported pickle
 		- created custom database object
-	0.0.0.004:
+	0.0.4:
 		- fixed simpleloop to actually return a vector
-	0.0.0.003:
+	0.0.3:
 		- added metricsloop which is unfinished
-	0.0.0.002:
+	0.0.2:
 		- added simpleloop which is untested until data is provided
-	0.0.0.001:
+	0.0.1:
 		- created script
 		- added analysis, numba, numpy imports
 """
@@ -114,14 +122,99 @@ __all__ = [
 
 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 = {}
@@ -150,52 +243,86 @@ def get_previous_time(apikey):
 
 	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]
 
-	def simplestats(data, test):
+	global exec_threads
 
-		data = np.array(data)
-		data = data[np.isfinite(data)]
-		ranges = list(range(len(data)))
-
-		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'])
+	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:
-		variable_vector = {}
+
 		for variable in data[team]:
-			test_vector = {}
-			variable_data = data[team][variable]
+
 			if variable in tests:
+
 				for test in tests[variable]:
-					test_vector[test] = simplestats(variable_data, test)
-			else:
-				pass      
-			variable_vector[variable] = test_vector
-		return_vector[team] = variable_vector
+
+					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)
 
@@ -404,4 +531,6 @@ def graph_pit_histogram(apikey, competition, figsize=(80,15)):
 
 		i+=1
 
-	plt.show()
+	plt.show()
+
+main()

data-analysis/test.py

@@ -1,55 +0,0 @@
-import threading
-from multiprocessing import Process, Queue
-import time
-from os import system
-
-class testcls():
-
-	i = 0
-	j = 0
-
-	t1_en = True
-	t2_en = True
-
-	def main(self):
-		t1 = Process(name = "task1", target = self.task1)
-		t2 = Process(name = "task2", target = self.task2)
-		t1.start()
-		t2.start()
-		#print(self.i)
-		#print(self.j)
-		
-	def task1(self):
-		self.i += 1
-		time.sleep(1)
-		if(self.i < 10):
-			t1 = Process(name = "task1", target = self.task1)
-			t1.start()
-
-	def task2(self):
-		self.j -= 1
-		time.sleep(1)
-		if(self.j > -10):
-			t2 = t2 = Process(name = "task2", target = self.task2)
-			t2.start()
-"""
-if __name__ == "__main__":
-
-	tmain = threading.Thread(name = "main", target = main)
-	tmain.start()
-
-	t = 0
-	while(True):
-		system("clear")
-		for thread in threading.enumerate():
-			if thread.getName() != "MainThread":
-				print(thread.getName())
-		print(str(len(threading.enumerate())))
-		print(i)
-		print(j)
-		time.sleep(0.1)
-		t += 1
-		if(t == 100):
-			t1_en = False
-			t2_en = False
-"""

data-analysis/tra.py

@@ -1,91 +0,0 @@
-import json
-import superscript as su
-import threading
-
-__author__ = (
-	"Arthur Lu <learthurgo@gmail.com>",
-)
-
-match = False
-metric = False
-pit = False
-
-match_enable = True
-metric_enable = True
-pit_enable = True
-
-config = {}
-
-def main():
-
-	global match
-	global metric
-	global pit
-
-	global match_enable
-	global metric_enable
-	global pit_enable
-
-	global config
-	config = su.load_config("config.json")
-
-	while(True):
-
-		if match_enable == True and match == False:
-
-			def target():
-
-				apikey = config["key"]["database"]
-				competition = config["competition"]
-				tests = config["statistics"]["match"]
-
-				data = su.load_match(apikey, competition)
-				su.matchloop(apikey, competition, data, tests)
-
-				match = False
-				return
-
-			match = True
-			task = threading.Thread(name = "match", target=target)
-			task.start()
-
-		if metric_enable == True and metric == False:
-			
-			def target():
-
-				apikey = config["key"]["database"]
-				tbakey = config["key"]["tba"]
-				competition = config["competition"]
-				metric = config["statistics"]["metric"]
-
-				timestamp = su.get_previous_time(apikey)
-
-				su.metricloop(tbakey, apikey, competition, timestamp, metric)
-
-				metric = False
-				return
-
-			match = True
-			task = threading.Thread(name = "metric", target=target)
-			task.start()
-
-		if pit_enable == True and pit == False:
-
-			def target():
-
-				apikey = config["key"]["database"]
-				competition = config["competition"]
-				tests = config["statistics"]["pit"]
-
-				data = su.load_pit(apikey, competition)
-				su.pitloop(apikey, competition, data, tests)
-
-				pit = False
-				return
-
-			pit = True
-			task = threading.Thread(name = "pit", target=target)
-			task.start()
-			
-task = threading.Thread(name = "main", target=main)
-task.start()