Merge pull request #85 from titanscouting/analysis-v4

Analysis v4

.devcontainer/Dockerfile

@@ -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

.devcontainer/dev-dockerfile

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

.devcontainer/devcontainer.json

@@ -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": ""
 	}

.devcontainer/requirements.txt

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

.github/workflows/ut-analysis.yml

@@ -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/

analysis-master/requirements.txt

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

analysis-master/test_analysis.py

@@ -9,6 +9,7 @@ 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
@@ -27,7 +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]
@@ -48,16 +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():
 
@@ -143,14 +153,9 @@ def test_sort():
 		assert all(a == b for a, b in zip(sort(test_data_scrambled), test_data_sorted))
 
 def test_statisticaltest():
-	
-	#print(StatisticalTest.tukey_multicomparison([test_data_linear, test_data_linear2, test_data_linear3]))
+
 	assert StatisticalTest.tukey_multicomparison([test_data_linear, test_data_linear2, test_data_linear3]) == \
 		{'group 1 and group 2': [0.32571517201527916, False], 'group 1 and group 3': [0.977145516045838, False], 'group 2 and group 3': [0.6514303440305589, False]}
-	#assert all(np.isclose([i[0] for i in list(StatisticalTest.tukey_multicomparison([test_data_linear, test_data_linear2, test_data_linear3]).values],
-	#	[0.32571517201527916, 0.977145516045838, 0.6514303440305589]))
-	#assert [i[1] for i in StatisticalTest.tukey_multicomparison([test_data_linear, test_data_linear2, test_data_linear3]).values] == \
-	#	[False, False, False]
 
 def test_svm():
 

analysis-master/tra_analysis/Analysis.py

@@ -7,10 +7,15 @@
 #    current benchmark of optimization: 1.33 times faster
 # setup:
 
-__version__ = "3.0.4"
+__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:
@@ -361,7 +366,6 @@ __all__ = [
 	'histo_analysis',
 	'regression',
 	'Metric',
-	'kmeans',
 	'pca',
 	'decisiontree',
 	# all statistics functions left out due to integration in other functions
@@ -374,34 +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 .RegressionMetric import RegressionMetric
-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)
@@ -413,24 +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)
@@ -446,7 +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)
 
@@ -550,13 +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)
@@ -564,7 +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:
@@ -599,24 +669,32 @@ def npmin(data):
 def npmax(data):
 
 	return np.amax(data)
-""" need to decide what to do with this function
-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)

analysis-master/tra_analysis/ClassificationMetric.py

@@ -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():
 

analysis-master/tra_analysis/Clustering.py

@@ -4,10 +4,12 @@
 #    this should be imported as a python module using 'from tra_analysis import Clustering'
 # setup:
 
-__version__ = "2.0.1"
+__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:
@@ -30,32 +32,32 @@ __all__ = [
 
 import sklearn
 
-def kmeans(data, normalizer = None, 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"):
+def kmeans(data, normalizer = None, **kwargs):
 
 	if  normalizer != None:
 		data = normalizer.transform(data)
 
-	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 = sklearn.cluster.KMeans(**kwargs)
 	kernel.fit(data)
 	predictions = kernel.predict(data)
 	centers = kernel.cluster_centers_
 
 	return centers, predictions
 
-def dbscan(data, normalizer=None, eps=0.5, min_samples=5, metric='euclidean', metric_params=None, algorithm='auto', leaf_size=30, p=None, n_jobs=None):
+def dbscan(data, normalizer=None, **kwargs):
 
 	if  normalizer != None:
 		data = normalizer.transform(data)
 
-	model = sklearn.cluster.DBSCAN(eps = eps, min_samples = min_samples, metric = metric, metric_params = metric_params, algorithm = algorithm, leaf_size = leaf_size, p = p, n_jobs = n_jobs).fit(data)
+	model = sklearn.cluster.DBSCAN(**kwargs).fit(data)
 
 	return model.labels_
 
-def spectral(data, normalizer=None, n_clusters=8, eigen_solver=None, n_components=None, random_state=None, n_init=10, gamma=1.0, affinity='rbf', n_neighbors=10, eigen_tol=0.0, assign_labels='kmeans', degree=3, coef0=1, kernel_params=None, n_jobs=None, verbose=False):
+def spectral(data, normalizer=None, **kwargs):
 
 	if  normalizer != None:
 		data = normalizer.transform(data)
 
-	model = sklearn.cluster.SpectralClustering(n_clusters = n_clusters, eigen_solver = eigen_solver, n_components = n_components, random_state = random_state, n_init = n_init, gamma = gamma, affinity = affinity, n_neighbors = n_neighbors, eigen_tol = eigen_tol, assign_labels = assign_labels, degree = degree, coef0 = coef0, kernel_params = kernel_params, n_jobs = n_jobs).fit(data)
+	model = sklearn.cluster.SpectralClustering(**kwargs).fit(data)
 
 	return model.labels_

analysis-master/tra_analysis/CorrelationTest.py

@@ -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

analysis-master/tra_analysis/KNN.py

@@ -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)
 

analysis-master/tra_analysis/NaiveBayes.py

@@ -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)
 

analysis-master/tra_analysis/RandomForest.py

@@ -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)
 

analysis-master/tra_analysis/RegressionMetric.py

@@ -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():
 

analysis-master/tra_analysis/SVM.py

@@ -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:

analysis-master/tra_analysis/Sort.py

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

analysis-master/tra_analysis/StatisticalTest.py

@@ -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)

analysis-master/tra_analysis/__init__.py

@@ -15,6 +15,9 @@ __changelog__ = """changelog:
 		- 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:
@@ -44,6 +47,7 @@ __all__ = [
 	"Analysis",
 	"Array",
 	"ClassificationMetric",
+	"Clustering",
 	"CorrelationTest",
 	"Expression",
 	"Fit",

analysis-master/tra_analysis/metrics/__init__.py

@@ -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