analysis pkg v 1.0.0.11

analysis.py v 1.1.13.009
superscript.py v 0.0.5.002

.devcontainer/Dockerfile

@@ -0,0 +1,2 @@
+FROM python
+WORKDIR ~/

.devcontainer/devcontainer.json

@@ -0,0 +1,26 @@
+{
+    "name": "TRA Analysis Development Environment",
+    "build": {
+		"dockerfile": "Dockerfile",
+    },
+    "settings": { 
+		"terminal.integrated.shell.linux": "/bin/bash",
+		"python.pythonPath": "/usr/local/bin/python",
+		"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"
+	},
+	"extensions": [
+		"mhutchie.git-graph",
+	],
+	"postCreateCommand": "pip install -r analysis-master/analysis-amd64/requirements.txt"
+}

.gitignore

@@ -16,4 +16,9 @@ data analysis/.ipynb_checkpoints/test-checkpoint.ipynb
 .vscode
 data analysis/arthur_pull.ipynb
 data analysis/keys.txt
-data analysis/check_for_new_matches.ipynb
+data analysis/check_for_new_matches.ipynb
+data analysis/test.ipynb
+data analysis/visualize_pit.ipynb
+data analysis/config/keys.config
+analysis-master/analysis/__pycache__/
+data analysis/__pycache__/

analysis-master/analysis-amd64/analysis.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: analysis
-Version: 1.0.0.6
+Version: 1.0.0.11
 Summary: analysis package developed by Titan Scouting for The Red Alliance
 Home-page: https://github.com/titanscout2022/tr2022-strategy
 Author: The Titan Scouting Team

analysis-master/analysis-amd64/analysis.egg-info/SOURCES.txt

@@ -1,6 +1,7 @@
 setup.py
 analysis/__init__.py
 analysis/analysis.py
+analysis/glicko2.py
 analysis/regression.py
 analysis/titanlearn.py
 analysis/trueskill.py
@@ -8,4 +9,5 @@ analysis/visualization.py
 analysis.egg-info/PKG-INFO
 analysis.egg-info/SOURCES.txt
 analysis.egg-info/dependency_links.txt
+analysis.egg-info/requires.txt
 analysis.egg-info/top_level.txt

analysis-master/analysis-amd64/analysis.egg-info/requires.txt

@@ -0,0 +1,6 @@
+numba
+numpy
+scipy
+scikit-learn
+six
+matplotlib

analysis-master/analysis-amd64/analysis/analysis.py

@@ -7,10 +7,26 @@
 #    current benchmark of optimization: 1.33 times faster
 # setup:
 
-__version__ = "1.1.13.001"
+__version__ = "1.1.13.009"
 
 # changelog should be viewed using print(analysis.__changelog__)
 __changelog__ = """changelog:
+    1.1.13.009:
+        - moved elo, glicko2, trueskill functions under class Metrics
+    1.1.13.008:
+        - moved Glicko2 to a seperate package
+    1.1.13.007:
+        - fixed bug with trueskill
+    1.1.13.006:
+        - cleaned up imports
+    1.1.13.005:
+        - cleaned up package
+    1.1.13.004:
+        - small fixes to regression to improve performance
+    1.1.13.003:
+        - filtered nans from regression
+    1.1.13.002:
+        - removed torch requirement, and moved Regression back to regression.py
     1.1.13.001:
         - bug fix with linear regression not returning a proper value
         - cleaned up regression
@@ -239,7 +255,6 @@ __author__ = (
 )
 
 __all__ = [
-    '_init_device',
     'load_csv',
     'basic_stats',
     'z_score',
@@ -260,8 +275,6 @@ __all__ = [
     'SVM',
     'random_forest_classifier',
     'random_forest_regressor',
-    'Regression',
-    'Glicko2',
     # all statistics functions left out due to integration in other functions
 ]
 
@@ -270,27 +283,19 @@ __all__ = [
 # imports (now in alphabetical order! v 1.0.3.006):
 
 import csv
+from analysis import glicko2 as Glicko2
 import numba
 from numba import jit
 import numpy as np
-import math
 import scipy
 from scipy import *
 import sklearn
 from sklearn import *
-import torch
-try:
-    from analysis import trueskill as Trueskill
-except:
-    import trueskill as Trueskill
+from analysis import trueskill as Trueskill
 
 class error(ValueError):
     pass
 
-def _init_device():  # initiates computation device for ANNs
-    device = 'cuda:0' if torch.cuda.is_available() else 'cpu'
-    return device
-
 def load_csv(filepath):
     with open(filepath, newline='') as csvfile:
         file_array = np.array(list(csv.reader(csvfile)))
@@ -349,15 +354,15 @@ def histo_analysis(hist_data):
 
 def regression(inputs, outputs, args): # inputs, outputs expects N-D array 
 
+    X = np.array(inputs)
+    y = np.array(outputs)
+
     regressions = []
 
     if 'lin' in args: # formula: ax + b
 
         try:
 
-            X = np.array(inputs)
-            y = np.array(outputs)
-
             def func(x, a, b):
 
                 return a * x + b
@@ -374,9 +379,6 @@ def regression(inputs, outputs, args): # inputs, outputs expects N-D array
 
         try:
 
-            X = np.array(inputs)
-            y = np.array(outputs)
-
             def func(x, a, b, c, d):
 
                 return a * np.log(b*(x + c)) + d
@@ -391,10 +393,7 @@ def regression(inputs, outputs, args): # inputs, outputs expects N-D array
 
     if 'exp' in args: # formula: a e ^ (b(x + c)) + d
 
-        try:
-
-            X = np.array(inputs)
-            y = np.array(outputs)
+        try:        
 
             def func(x, a, b, c, d):
 
@@ -410,8 +409,8 @@ def regression(inputs, outputs, args): # inputs, outputs expects N-D array
 
     if 'ply' in args: # formula: a + bx^1 + cx^2 + dx^3 + ...
         
-        inputs = [inputs]
-        outputs = [outputs]
+        inputs = np.array([inputs])
+        outputs = np.array([outputs])
 
         plys = []
         limit = len(outputs[0])
@@ -433,10 +432,7 @@ def regression(inputs, outputs, args): # inputs, outputs expects N-D array
 
     if 'sig' in args: # formula: a tanh (b(x + c)) + d
 
-        try:
-
-            X = np.array(inputs)
-            y = np.array(outputs)
+        try:        
 
             def func(x, a, b, c, d):
 
@@ -452,32 +448,34 @@ def regression(inputs, outputs, args): # inputs, outputs expects N-D array
 
     return regressions
 
-def elo(starting_score, opposing_score, observed, N, K):
+class Metrics:
 
-    expected = 1/(1+10**((np.array(opposing_score) - starting_score)/N))
+    def elo(starting_score, opposing_score, observed, N, K):
 
-    return starting_score + K*(np.sum(observed) - np.sum(expected))
+        expected = 1/(1+10**((np.array(opposing_score) - starting_score)/N))
 
-def glicko2(starting_score, starting_rd, starting_vol, opposing_score, opposing_rd, observations):
+        return starting_score + K*(np.sum(observed) - np.sum(expected))
 
-    player = Glicko2(rating = starting_score, rd = starting_rd, vol = starting_vol)
+    def glicko2(starting_score, starting_rd, starting_vol, opposing_score, opposing_rd, observations):
 
-    player.update_player([x for x in opposing_score], [x for x in opposing_rd], observations)
+        player = Glicko2.Glicko2(rating = starting_score, rd = starting_rd, vol = starting_vol)
 
-    return (player.rating, player.rd, player.vol)
+        player.update_player([x for x in opposing_score], [x for x in opposing_rd], observations)
 
-def trueskill(teams_data, observations): # teams_data is array of array of tuples ie. [[(mu, sigma), (mu, sigma), (mu, sigma)], [(mu, sigma), (mu, sigma), (mu, sigma)]]
+        return (player.rating, player.rd, player.vol)
 
-    team_ratings = []
+    def trueskill(teams_data, observations): # teams_data is array of array of tuples ie. [[(mu, sigma), (mu, sigma), (mu, sigma)], [(mu, sigma), (mu, sigma), (mu, sigma)]]
 
-    for team in teams_data:
-        team_temp = []
-        for player in team:
-            player = Trueskill.Rating(player[0], player[1])
-            team_temp.append(player)
-        team_ratings.append(team_temp)
+        team_ratings = []
 
-    return Trueskill.rate(teams_data, observations)
+        for team in teams_data:
+            team_temp = ()
+            for player in team:
+                player = Trueskill.Rating(player[0], player[1])
+                team_temp = team_temp + (player,)
+            team_ratings.append(team_temp)
+
+        return Trueskill.rate(team_ratings, ranks=observations)
 
 class RegressionMetrics():
 
@@ -569,24 +567,25 @@ def decisiontree(data, labels, test_size = 0.3, criterion = "gini", splitter = "
 
     return model, metrics
 
-@jit(forceobj=True)
-def knn_classifier(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
+class KNN:
 
-    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)
+    def knn_classifier(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
 
-    return model, ClassificationMetrics(predictions, labels_test)
+        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)
 
-def knn_regressor(data, outputs, test_size, n_neighbors = 5, weights = "uniform", algorithm = "auto", leaf_size = 30, p = 2, metric = "minkowski", metric_params = None, n_jobs = None):
+        return model, ClassificationMetrics(predictions, labels_test)
 
-    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)
+    def knn_regressor(data, outputs, test_size, n_neighbors = 5, weights = "uniform", algorithm = "auto", leaf_size = 30, p = 2, metric = "minkowski", metric_params = None, n_jobs = None):
 
-    return model, RegressionMetrics(predictions, outputs_test)
+        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, RegressionMetrics(predictions, outputs_test)
 
 class NaiveBayes:
 
@@ -698,322 +697,4 @@ def random_forest_regressor(data, outputs, test_size, n_estimators="warn", crite
     kernel.fit(data_train, outputs_train)
     predictions = kernel.predict(data_test)
 
-    return kernel, RegressionMetrics(predictions, outputs_test)
-
-class Regression:
-
-    # Titan Robotics Team 2022: CUDA-based Regressions Module
-    # 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)
-    # setup:
-
-    __version__ = "1.0.0.003"
-
-    # changelog should be viewed using print(analysis.regression.__changelog__)
-    __changelog__ = """
-    1.0.0.003:
-        - bug fixes
-    1.0.0.002:
-        -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:
-        -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'
-    ]
-
-    global device
-
-    device = "cuda:0" if torch.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
-
-class Glicko2:
-
-    _tau = 0.5
-
-    def getRating(self):
-        return (self.__rating * 173.7178) + 1500 
-
-    def setRating(self, rating):
-        self.__rating = (rating - 1500) / 173.7178
-
-    rating = property(getRating, setRating)
-
-    def getRd(self):
-        return self.__rd * 173.7178
-
-    def setRd(self, rd):
-        self.__rd = rd / 173.7178
-
-    rd = property(getRd, setRd)
-     
-    def __init__(self, rating = 1500, rd = 350, vol = 0.06):
-
-        self.setRating(rating)
-        self.setRd(rd)
-        self.vol = vol
-            
-    def _preRatingRD(self):
-
-        self.__rd = math.sqrt(math.pow(self.__rd, 2) + math.pow(self.vol, 2))
-        
-    def update_player(self, rating_list, RD_list, outcome_list):
-
-        rating_list = [(x - 1500) / 173.7178 for x in rating_list]
-        RD_list = [x / 173.7178 for x in RD_list]
-
-        v = self._v(rating_list, RD_list)
-        self.vol = self._newVol(rating_list, RD_list, outcome_list, v)
-        self._preRatingRD()
-        
-        self.__rd = 1 / math.sqrt((1 / math.pow(self.__rd, 2)) + (1 / v))
-        
-        tempSum = 0
-        for i in range(len(rating_list)):
-            tempSum += self._g(RD_list[i]) * \
-                       (outcome_list[i] - self._E(rating_list[i], RD_list[i]))
-        self.__rating += math.pow(self.__rd, 2) * tempSum
-        
-        
-    def _newVol(self, rating_list, RD_list, outcome_list, v):
-
-        i = 0
-        delta = self._delta(rating_list, RD_list, outcome_list, v)
-        a = math.log(math.pow(self.vol, 2))
-        tau = self._tau
-        x0 = a
-        x1 = 0
-        
-        while x0 != x1:
-            # New iteration, so x(i) becomes x(i-1)
-            x0 = x1
-            d = math.pow(self.__rating, 2) + v + math.exp(x0)
-            h1 = -(x0 - a) / math.pow(tau, 2) - 0.5 * math.exp(x0) \
-            / d + 0.5 * math.exp(x0) * math.pow(delta / d, 2)
-            h2 = -1 / math.pow(tau, 2) - 0.5 * math.exp(x0) * \
-            (math.pow(self.__rating, 2) + v) \
-            / math.pow(d, 2) + 0.5 * math.pow(delta, 2) * math.exp(x0) \
-            * (math.pow(self.__rating, 2) + v - math.exp(x0)) / math.pow(d, 3)
-            x1 = x0 - (h1 / h2)
-
-        return math.exp(x1 / 2)
-        
-    def _delta(self, rating_list, RD_list, outcome_list, v):
-
-        tempSum = 0
-        for i in range(len(rating_list)):
-            tempSum += self._g(RD_list[i]) * (outcome_list[i] - self._E(rating_list[i], RD_list[i]))
-        return v * tempSum
-        
-    def _v(self, rating_list, RD_list):
-
-        tempSum = 0
-        for i in range(len(rating_list)):
-            tempE = self._E(rating_list[i], RD_list[i])
-            tempSum += math.pow(self._g(RD_list[i]), 2) * tempE * (1 - tempE)
-        return 1 / tempSum
-        
-    def _E(self, p2rating, p2RD):
-
-        return 1 / (1 + math.exp(-1 * self._g(p2RD) * \
-                                 (self.__rating - p2rating)))
-        
-    def _g(self, RD):
-
-        return 1 / math.sqrt(1 + 3 * math.pow(RD, 2) / math.pow(math.pi, 2))
-        
-    def did_not_compete(self):
-
-        self._preRatingRD()
+    return kernel, RegressionMetrics(predictions, outputs_test)

analysis-master/analysis-amd64/analysis/glicko2.py

@@ -0,0 +1,99 @@
+import math
+
+class Glicko2:
+    _tau = 0.5
+
+    def getRating(self):
+        return (self.__rating * 173.7178) + 1500 
+
+    def setRating(self, rating):
+        self.__rating = (rating - 1500) / 173.7178
+
+    rating = property(getRating, setRating)
+
+    def getRd(self):
+        return self.__rd * 173.7178
+
+    def setRd(self, rd):
+        self.__rd = rd / 173.7178
+
+    rd = property(getRd, setRd)
+        
+    def __init__(self, rating = 1500, rd = 350, vol = 0.06):
+
+        self.setRating(rating)
+        self.setRd(rd)
+        self.vol = vol
+            
+    def _preRatingRD(self):
+
+        self.__rd = math.sqrt(math.pow(self.__rd, 2) + math.pow(self.vol, 2))
+        
+    def update_player(self, rating_list, RD_list, outcome_list):
+
+        rating_list = [(x - 1500) / 173.7178 for x in rating_list]
+        RD_list = [x / 173.7178 for x in RD_list]
+
+        v = self._v(rating_list, RD_list)
+        self.vol = self._newVol(rating_list, RD_list, outcome_list, v)
+        self._preRatingRD()
+        
+        self.__rd = 1 / math.sqrt((1 / math.pow(self.__rd, 2)) + (1 / v))
+        
+        tempSum = 0
+        for i in range(len(rating_list)):
+            tempSum += self._g(RD_list[i]) * \
+                        (outcome_list[i] - self._E(rating_list[i], RD_list[i]))
+        self.__rating += math.pow(self.__rd, 2) * tempSum
+        
+        
+    def _newVol(self, rating_list, RD_list, outcome_list, v):
+
+        i = 0
+        delta = self._delta(rating_list, RD_list, outcome_list, v)
+        a = math.log(math.pow(self.vol, 2))
+        tau = self._tau
+        x0 = a
+        x1 = 0
+        
+        while x0 != x1:
+            # New iteration, so x(i) becomes x(i-1)
+            x0 = x1
+            d = math.pow(self.__rating, 2) + v + math.exp(x0)
+            h1 = -(x0 - a) / math.pow(tau, 2) - 0.5 * math.exp(x0) \
+            / d + 0.5 * math.exp(x0) * math.pow(delta / d, 2)
+            h2 = -1 / math.pow(tau, 2) - 0.5 * math.exp(x0) * \
+            (math.pow(self.__rating, 2) + v) \
+            / math.pow(d, 2) + 0.5 * math.pow(delta, 2) * math.exp(x0) \
+            * (math.pow(self.__rating, 2) + v - math.exp(x0)) / math.pow(d, 3)
+            x1 = x0 - (h1 / h2)
+
+        return math.exp(x1 / 2)
+        
+    def _delta(self, rating_list, RD_list, outcome_list, v):
+
+        tempSum = 0
+        for i in range(len(rating_list)):
+            tempSum += self._g(RD_list[i]) * (outcome_list[i] - self._E(rating_list[i], RD_list[i]))
+        return v * tempSum
+        
+    def _v(self, rating_list, RD_list):
+
+        tempSum = 0
+        for i in range(len(rating_list)):
+            tempE = self._E(rating_list[i], RD_list[i])
+            tempSum += math.pow(self._g(RD_list[i]), 2) * tempE * (1 - tempE)
+        return 1 / tempSum
+        
+    def _E(self, p2rating, p2RD):
+
+        return 1 / (1 + math.exp(-1 * self._g(p2RD) * \
+                                    (self.__rating - p2rating)))
+        
+    def _g(self, RD):
+
+        return 1 / math.sqrt(1 + 3 * math.pow(RD, 2) / math.pow(math.pi, 2))
+        
+    def did_not_compete(self):
+
+        self._preRatingRD()

analysis-master/analysis-amd64/analysis/regression.py

@@ -1,20 +1,23 @@
 # Titan Robotics Team 2022: CUDA-based Regressions Module
 # Written by Arthur Lu & Jacob Levine
 # Notes:
-#    this should be imported as a python module using 'import regression'
-#    this should be included in the local directory or environment variable
-#    this module is cuda-optimized and vectorized (except for one small part)
+#   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)
 # setup:
 
-__version__ = "1.0.0.002"
+__version__ = "1.0.0.004"
 
-# changelog should be viewed using print(regression.__changelog__)
+# changelog should be viewed using print(analysis.regression.__changelog__)
 __changelog__ = """
+    1.0.0.004:
+        - bug fixes
+        - fixed changelog
+    1.0.0.003:
+        - bug fixes
     1.0.0.002:
         -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:
         -initial release, with linear, log, exponential, polynomial, and sigmoid kernels
         -already vectorized (except for polynomial generation) and CUDA-optimized
@@ -22,6 +25,7 @@ __changelog__ = """
 
 __author__ = (
     "Jacob Levine <jlevine@imsa.edu>",
+    "Arthur Lu <learthurgo@gmail.com>"
 )
 
 __all__ = [
@@ -39,35 +43,15 @@ __all__ = [
     'CustomTrain'
 ]
 
-
-# imports (just one for now):
-
 import torch
 
+global device
+
 device = "cuda:0" if torch.torch.cuda.is_available() else "cpu"
 
 #todo: document completely
 
-def factorial(n):
-    if n==0:
-        return 1
-    else:
-        return n*factorial(n-1)
-def num_poly_terms(num_vars, power):
-    if power == 0:
-        return 0
-    return int(factorial(num_vars+power-1) / factorial(power) / factorial(num_vars-1)) + num_poly_terms(num_vars, power-1)
-
-def take_all_pwrs(vec,pwr):
-    #todo: vectorize (kinda)
-    combins=torch.combinations(vec, r=pwr, with_replacement=True)
-    out=torch.ones(combins.size()[0])
-    for i in torch.t(combins):
-        out *= i
-    return torch.cat(out,take_all_pwrs(vec, pwr-1))
-
-def set_device(new_device):
-    global device
+def set_device(self, new_device):
     device=new_device
 
 class LinearRegKernel():
@@ -154,20 +138,39 @@ class PolyRegKernel():
     power=None
     def __init__(self, num_vars, power):
         self.power=power
-        num_terms=num_poly_terms(num_vars, 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(take_all_pwrs(i,self.power))
+            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(kernel, data, ground, loss=torch.nn.MSELoss(), iterations=1000, learning_rate=.1, return_losses=False):
+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)
@@ -192,7 +195,7 @@ def SGDTrain(kernel, data, ground, loss=torch.nn.MSELoss(), iterations=1000, lea
                 optim.step()
         return kernel
 
-def CustomTrain(kernel, optim, data, ground, loss=torch.nn.MSELoss(), iterations=1000, return_losses=False):
+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):
@@ -214,4 +217,4 @@ def CustomTrain(kernel, optim, data, ground, loss=torch.nn.MSELoss(), iterations
                 ls=loss(pred,ground_cuda)
                 ls.backward()
                 optim.step()
-        return kernel
+        return kernel

analysis-master/analysis-amd64/build.sh

@@ -0,0 +1 @@
+python setup.py sdist bdist_wheel || python3 setup.py sdist bdist_wheel

analysis-master/analysis-amd64/build/lib/analysis/analysis.py

@@ -7,10 +7,26 @@
 #    current benchmark of optimization: 1.33 times faster
 # setup:
 
-__version__ = "1.1.13.001"
+__version__ = "1.1.13.009"
 
 # changelog should be viewed using print(analysis.__changelog__)
 __changelog__ = """changelog:
+    1.1.13.009:
+        - moved elo, glicko2, trueskill functions under class Metrics
+    1.1.13.008:
+        - moved Glicko2 to a seperate package
+    1.1.13.007:
+        - fixed bug with trueskill
+    1.1.13.006:
+        - cleaned up imports
+    1.1.13.005:
+        - cleaned up package
+    1.1.13.004:
+        - small fixes to regression to improve performance
+    1.1.13.003:
+        - filtered nans from regression
+    1.1.13.002:
+        - removed torch requirement, and moved Regression back to regression.py
     1.1.13.001:
         - bug fix with linear regression not returning a proper value
         - cleaned up regression
@@ -239,7 +255,6 @@ __author__ = (
 )
 
 __all__ = [
-    '_init_device',
     'load_csv',
     'basic_stats',
     'z_score',
@@ -260,8 +275,6 @@ __all__ = [
     'SVM',
     'random_forest_classifier',
     'random_forest_regressor',
-    'Regression',
-    'Glicko2',
     # all statistics functions left out due to integration in other functions
 ]
 
@@ -270,27 +283,19 @@ __all__ = [
 # imports (now in alphabetical order! v 1.0.3.006):
 
 import csv
+from analysis import glicko2 as Glicko2
 import numba
 from numba import jit
 import numpy as np
-import math
 import scipy
 from scipy import *
 import sklearn
 from sklearn import *
-import torch
-try:
-    from analysis import trueskill as Trueskill
-except:
-    import trueskill as Trueskill
+from analysis import trueskill as Trueskill
 
 class error(ValueError):
     pass
 
-def _init_device():  # initiates computation device for ANNs
-    device = 'cuda:0' if torch.cuda.is_available() else 'cpu'
-    return device
-
 def load_csv(filepath):
     with open(filepath, newline='') as csvfile:
         file_array = np.array(list(csv.reader(csvfile)))
@@ -349,15 +354,15 @@ def histo_analysis(hist_data):
 
 def regression(inputs, outputs, args): # inputs, outputs expects N-D array 
 
+    X = np.array(inputs)
+    y = np.array(outputs)
+
     regressions = []
 
     if 'lin' in args: # formula: ax + b
 
         try:
 
-            X = np.array(inputs)
-            y = np.array(outputs)
-
             def func(x, a, b):
 
                 return a * x + b
@@ -374,9 +379,6 @@ def regression(inputs, outputs, args): # inputs, outputs expects N-D array
 
         try:
 
-            X = np.array(inputs)
-            y = np.array(outputs)
-
             def func(x, a, b, c, d):
 
                 return a * np.log(b*(x + c)) + d
@@ -391,10 +393,7 @@ def regression(inputs, outputs, args): # inputs, outputs expects N-D array
 
     if 'exp' in args: # formula: a e ^ (b(x + c)) + d
 
-        try:
-
-            X = np.array(inputs)
-            y = np.array(outputs)
+        try:        
 
             def func(x, a, b, c, d):
 
@@ -410,8 +409,8 @@ def regression(inputs, outputs, args): # inputs, outputs expects N-D array
 
     if 'ply' in args: # formula: a + bx^1 + cx^2 + dx^3 + ...
         
-        inputs = [inputs]
-        outputs = [outputs]
+        inputs = np.array([inputs])
+        outputs = np.array([outputs])
 
         plys = []
         limit = len(outputs[0])
@@ -433,10 +432,7 @@ def regression(inputs, outputs, args): # inputs, outputs expects N-D array
 
     if 'sig' in args: # formula: a tanh (b(x + c)) + d
 
-        try:
-
-            X = np.array(inputs)
-            y = np.array(outputs)
+        try:        
 
             def func(x, a, b, c, d):
 
@@ -452,32 +448,34 @@ def regression(inputs, outputs, args): # inputs, outputs expects N-D array
 
     return regressions
 
-def elo(starting_score, opposing_score, observed, N, K):
+class Metrics:
 
-    expected = 1/(1+10**((np.array(opposing_score) - starting_score)/N))
+    def elo(starting_score, opposing_score, observed, N, K):
 
-    return starting_score + K*(np.sum(observed) - np.sum(expected))
+        expected = 1/(1+10**((np.array(opposing_score) - starting_score)/N))
 
-def glicko2(starting_score, starting_rd, starting_vol, opposing_score, opposing_rd, observations):
+        return starting_score + K*(np.sum(observed) - np.sum(expected))
 
-    player = Glicko2(rating = starting_score, rd = starting_rd, vol = starting_vol)
+    def glicko2(starting_score, starting_rd, starting_vol, opposing_score, opposing_rd, observations):
 
-    player.update_player([x for x in opposing_score], [x for x in opposing_rd], observations)
+        player = Glicko2.Glicko2(rating = starting_score, rd = starting_rd, vol = starting_vol)
 
-    return (player.rating, player.rd, player.vol)
+        player.update_player([x for x in opposing_score], [x for x in opposing_rd], observations)
 
-def trueskill(teams_data, observations): # teams_data is array of array of tuples ie. [[(mu, sigma), (mu, sigma), (mu, sigma)], [(mu, sigma), (mu, sigma), (mu, sigma)]]
+        return (player.rating, player.rd, player.vol)
 
-    team_ratings = []
+    def trueskill(teams_data, observations): # teams_data is array of array of tuples ie. [[(mu, sigma), (mu, sigma), (mu, sigma)], [(mu, sigma), (mu, sigma), (mu, sigma)]]
 
-    for team in teams_data:
-        team_temp = []
-        for player in team:
-            player = Trueskill.Rating(player[0], player[1])
-            team_temp.append(player)
-        team_ratings.append(team_temp)
+        team_ratings = []
 
-    return Trueskill.rate(teams_data, observations)
+        for team in teams_data:
+            team_temp = ()
+            for player in team:
+                player = Trueskill.Rating(player[0], player[1])
+                team_temp = team_temp + (player,)
+            team_ratings.append(team_temp)
+
+        return Trueskill.rate(team_ratings, ranks=observations)
 
 class RegressionMetrics():
 
@@ -569,24 +567,25 @@ def decisiontree(data, labels, test_size = 0.3, criterion = "gini", splitter = "
 
     return model, metrics
 
-@jit(forceobj=True)
-def knn_classifier(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
+class KNN:
 
-    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)
+    def knn_classifier(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
 
-    return model, ClassificationMetrics(predictions, labels_test)
+        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)
 
-def knn_regressor(data, outputs, test_size, n_neighbors = 5, weights = "uniform", algorithm = "auto", leaf_size = 30, p = 2, metric = "minkowski", metric_params = None, n_jobs = None):
+        return model, ClassificationMetrics(predictions, labels_test)
 
-    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)
+    def knn_regressor(data, outputs, test_size, n_neighbors = 5, weights = "uniform", algorithm = "auto", leaf_size = 30, p = 2, metric = "minkowski", metric_params = None, n_jobs = None):
 
-    return model, RegressionMetrics(predictions, outputs_test)
+        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, RegressionMetrics(predictions, outputs_test)
 
 class NaiveBayes:
 
@@ -698,322 +697,4 @@ def random_forest_regressor(data, outputs, test_size, n_estimators="warn", crite
     kernel.fit(data_train, outputs_train)
     predictions = kernel.predict(data_test)
 
-    return kernel, RegressionMetrics(predictions, outputs_test)
-
-class Regression:
-
-    # Titan Robotics Team 2022: CUDA-based Regressions Module
-    # 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)
-    # setup:
-
-    __version__ = "1.0.0.003"
-
-    # changelog should be viewed using print(analysis.regression.__changelog__)
-    __changelog__ = """
-    1.0.0.003:
-        - bug fixes
-    1.0.0.002:
-        -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:
-        -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'
-    ]
-
-    global device
-
-    device = "cuda:0" if torch.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
-
-class Glicko2:
-
-    _tau = 0.5
-
-    def getRating(self):
-        return (self.__rating * 173.7178) + 1500 
-
-    def setRating(self, rating):
-        self.__rating = (rating - 1500) / 173.7178
-
-    rating = property(getRating, setRating)
-
-    def getRd(self):
-        return self.__rd * 173.7178
-
-    def setRd(self, rd):
-        self.__rd = rd / 173.7178
-
-    rd = property(getRd, setRd)
-     
-    def __init__(self, rating = 1500, rd = 350, vol = 0.06):
-
-        self.setRating(rating)
-        self.setRd(rd)
-        self.vol = vol
-            
-    def _preRatingRD(self):
-
-        self.__rd = math.sqrt(math.pow(self.__rd, 2) + math.pow(self.vol, 2))
-        
-    def update_player(self, rating_list, RD_list, outcome_list):
-
-        rating_list = [(x - 1500) / 173.7178 for x in rating_list]
-        RD_list = [x / 173.7178 for x in RD_list]
-
-        v = self._v(rating_list, RD_list)
-        self.vol = self._newVol(rating_list, RD_list, outcome_list, v)
-        self._preRatingRD()
-        
-        self.__rd = 1 / math.sqrt((1 / math.pow(self.__rd, 2)) + (1 / v))
-        
-        tempSum = 0
-        for i in range(len(rating_list)):
-            tempSum += self._g(RD_list[i]) * \
-                       (outcome_list[i] - self._E(rating_list[i], RD_list[i]))
-        self.__rating += math.pow(self.__rd, 2) * tempSum
-        
-        
-    def _newVol(self, rating_list, RD_list, outcome_list, v):
-
-        i = 0
-        delta = self._delta(rating_list, RD_list, outcome_list, v)
-        a = math.log(math.pow(self.vol, 2))
-        tau = self._tau
-        x0 = a
-        x1 = 0
-        
-        while x0 != x1:
-            # New iteration, so x(i) becomes x(i-1)
-            x0 = x1
-            d = math.pow(self.__rating, 2) + v + math.exp(x0)
-            h1 = -(x0 - a) / math.pow(tau, 2) - 0.5 * math.exp(x0) \
-            / d + 0.5 * math.exp(x0) * math.pow(delta / d, 2)
-            h2 = -1 / math.pow(tau, 2) - 0.5 * math.exp(x0) * \
-            (math.pow(self.__rating, 2) + v) \
-            / math.pow(d, 2) + 0.5 * math.pow(delta, 2) * math.exp(x0) \
-            * (math.pow(self.__rating, 2) + v - math.exp(x0)) / math.pow(d, 3)
-            x1 = x0 - (h1 / h2)
-
-        return math.exp(x1 / 2)
-        
-    def _delta(self, rating_list, RD_list, outcome_list, v):
-
-        tempSum = 0
-        for i in range(len(rating_list)):
-            tempSum += self._g(RD_list[i]) * (outcome_list[i] - self._E(rating_list[i], RD_list[i]))
-        return v * tempSum
-        
-    def _v(self, rating_list, RD_list):
-
-        tempSum = 0
-        for i in range(len(rating_list)):
-            tempE = self._E(rating_list[i], RD_list[i])
-            tempSum += math.pow(self._g(RD_list[i]), 2) * tempE * (1 - tempE)
-        return 1 / tempSum
-        
-    def _E(self, p2rating, p2RD):
-
-        return 1 / (1 + math.exp(-1 * self._g(p2RD) * \
-                                 (self.__rating - p2rating)))
-        
-    def _g(self, RD):
-
-        return 1 / math.sqrt(1 + 3 * math.pow(RD, 2) / math.pow(math.pi, 2))
-        
-    def did_not_compete(self):
-
-        self._preRatingRD()
+    return kernel, RegressionMetrics(predictions, outputs_test)

analysis-master/analysis-amd64/build/lib/analysis/glicko2.py

@@ -0,0 +1,99 @@
+import math
+
+class Glicko2:
+    _tau = 0.5
+
+    def getRating(self):
+        return (self.__rating * 173.7178) + 1500 
+
+    def setRating(self, rating):
+        self.__rating = (rating - 1500) / 173.7178
+
+    rating = property(getRating, setRating)
+
+    def getRd(self):
+        return self.__rd * 173.7178
+
+    def setRd(self, rd):
+        self.__rd = rd / 173.7178
+
+    rd = property(getRd, setRd)
+        
+    def __init__(self, rating = 1500, rd = 350, vol = 0.06):
+
+        self.setRating(rating)
+        self.setRd(rd)
+        self.vol = vol
+            
+    def _preRatingRD(self):
+
+        self.__rd = math.sqrt(math.pow(self.__rd, 2) + math.pow(self.vol, 2))
+        
+    def update_player(self, rating_list, RD_list, outcome_list):
+
+        rating_list = [(x - 1500) / 173.7178 for x in rating_list]
+        RD_list = [x / 173.7178 for x in RD_list]
+
+        v = self._v(rating_list, RD_list)
+        self.vol = self._newVol(rating_list, RD_list, outcome_list, v)
+        self._preRatingRD()
+        
+        self.__rd = 1 / math.sqrt((1 / math.pow(self.__rd, 2)) + (1 / v))
+        
+        tempSum = 0
+        for i in range(len(rating_list)):
+            tempSum += self._g(RD_list[i]) * \
+                        (outcome_list[i] - self._E(rating_list[i], RD_list[i]))
+        self.__rating += math.pow(self.__rd, 2) * tempSum
+        
+        
+    def _newVol(self, rating_list, RD_list, outcome_list, v):
+
+        i = 0
+        delta = self._delta(rating_list, RD_list, outcome_list, v)
+        a = math.log(math.pow(self.vol, 2))
+        tau = self._tau
+        x0 = a
+        x1 = 0
+        
+        while x0 != x1:
+            # New iteration, so x(i) becomes x(i-1)
+            x0 = x1
+            d = math.pow(self.__rating, 2) + v + math.exp(x0)
+            h1 = -(x0 - a) / math.pow(tau, 2) - 0.5 * math.exp(x0) \
+            / d + 0.5 * math.exp(x0) * math.pow(delta / d, 2)
+            h2 = -1 / math.pow(tau, 2) - 0.5 * math.exp(x0) * \
+            (math.pow(self.__rating, 2) + v) \
+            / math.pow(d, 2) + 0.5 * math.pow(delta, 2) * math.exp(x0) \
+            * (math.pow(self.__rating, 2) + v - math.exp(x0)) / math.pow(d, 3)
+            x1 = x0 - (h1 / h2)
+
+        return math.exp(x1 / 2)
+        
+    def _delta(self, rating_list, RD_list, outcome_list, v):
+
+        tempSum = 0
+        for i in range(len(rating_list)):
+            tempSum += self._g(RD_list[i]) * (outcome_list[i] - self._E(rating_list[i], RD_list[i]))
+        return v * tempSum
+        
+    def _v(self, rating_list, RD_list):
+
+        tempSum = 0
+        for i in range(len(rating_list)):
+            tempE = self._E(rating_list[i], RD_list[i])
+            tempSum += math.pow(self._g(RD_list[i]), 2) * tempE * (1 - tempE)
+        return 1 / tempSum
+        
+    def _E(self, p2rating, p2RD):
+
+        return 1 / (1 + math.exp(-1 * self._g(p2RD) * \
+                                    (self.__rating - p2rating)))
+        
+    def _g(self, RD):
+
+        return 1 / math.sqrt(1 + 3 * math.pow(RD, 2) / math.pow(math.pi, 2))
+        
+    def did_not_compete(self):
+
+        self._preRatingRD()

analysis-master/analysis-amd64/build/lib/analysis/regression.py

@@ -1,20 +1,23 @@
 # Titan Robotics Team 2022: CUDA-based Regressions Module
 # Written by Arthur Lu & Jacob Levine
 # Notes:
-#    this should be imported as a python module using 'import regression'
-#    this should be included in the local directory or environment variable
-#    this module is cuda-optimized and vectorized (except for one small part)
+#   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)
 # setup:
 
-__version__ = "1.0.0.002"
+__version__ = "1.0.0.004"
 
-# changelog should be viewed using print(regression.__changelog__)
+# changelog should be viewed using print(analysis.regression.__changelog__)
 __changelog__ = """
+    1.0.0.004:
+        - bug fixes
+        - fixed changelog
+    1.0.0.003:
+        - bug fixes
     1.0.0.002:
         -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:
         -initial release, with linear, log, exponential, polynomial, and sigmoid kernels
         -already vectorized (except for polynomial generation) and CUDA-optimized
@@ -22,6 +25,7 @@ __changelog__ = """
 
 __author__ = (
     "Jacob Levine <jlevine@imsa.edu>",
+    "Arthur Lu <learthurgo@gmail.com>"
 )
 
 __all__ = [
@@ -39,35 +43,15 @@ __all__ = [
     'CustomTrain'
 ]
 
-
-# imports (just one for now):
-
 import torch
 
+global device
+
 device = "cuda:0" if torch.torch.cuda.is_available() else "cpu"
 
 #todo: document completely
 
-def factorial(n):
-    if n==0:
-        return 1
-    else:
-        return n*factorial(n-1)
-def num_poly_terms(num_vars, power):
-    if power == 0:
-        return 0
-    return int(factorial(num_vars+power-1) / factorial(power) / factorial(num_vars-1)) + num_poly_terms(num_vars, power-1)
-
-def take_all_pwrs(vec,pwr):
-    #todo: vectorize (kinda)
-    combins=torch.combinations(vec, r=pwr, with_replacement=True)
-    out=torch.ones(combins.size()[0])
-    for i in torch.t(combins):
-        out *= i
-    return torch.cat(out,take_all_pwrs(vec, pwr-1))
-
-def set_device(new_device):
-    global device
+def set_device(self, new_device):
     device=new_device
 
 class LinearRegKernel():
@@ -154,20 +138,39 @@ class PolyRegKernel():
     power=None
     def __init__(self, num_vars, power):
         self.power=power
-        num_terms=num_poly_terms(num_vars, 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(take_all_pwrs(i,self.power))
+            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(kernel, data, ground, loss=torch.nn.MSELoss(), iterations=1000, learning_rate=.1, return_losses=False):
+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)
@@ -192,7 +195,7 @@ def SGDTrain(kernel, data, ground, loss=torch.nn.MSELoss(), iterations=1000, lea
                 optim.step()
         return kernel
 
-def CustomTrain(kernel, optim, data, ground, loss=torch.nn.MSELoss(), iterations=1000, return_losses=False):
+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):
@@ -214,4 +217,4 @@ def CustomTrain(kernel, optim, data, ground, loss=torch.nn.MSELoss(), iterations
                 ls=loss(pred,ground_cuda)
                 ls.backward()
                 optim.step()
-        return kernel
+        return kernel

analysis-master/analysis-amd64/docker/Dockerfile

@@ -0,0 +1,5 @@
+FROM python
+WORKDIR ~/
+COPY ./ ./
+RUN pip install -r requirements.txt
+CMD ["bash"]

analysis-master/analysis-amd64/docker/start-docker.sh

@@ -0,0 +1,3 @@
+cd ..
+docker build -t tra-analysis-amd64-dev -f docker/Dockerfile .
+docker run -it tra-analysis-amd64-dev

analysis-master/analysis-amd64/requirements.txt

@@ -0,0 +1,6 @@
+numba
+numpy
+scipy
+scikit-learn
+six
+matplotlib

analysis-master/analysis-amd64/setup.py

@@ -1,8 +1,14 @@
 import setuptools
 
+requirements = []
+
+with open("requirements.txt", 'r') as file:
+    for line in file:
+        requirements.append(line)
+
 setuptools.setup(
-    name="analysis", # Replace with your own username
-    version="1.0.0.006",
+    name="analysis",
+    version="1.0.0.011",
     author="The Titan Scouting Team",
     author_email="titanscout2022@gmail.com",
     description="analysis package developed by Titan Scouting for The Red Alliance",
@@ -10,6 +16,7 @@ setuptools.setup(
     long_description_content_type="text/markdown",
     url="https://github.com/titanscout2022/tr2022-strategy",
     packages=setuptools.find_packages(),
+    install_requires=requirements,
     license = "GNU General Public License v3.0",
     classifiers=[
         "Programming Language :: Python :: 3",

analysis-master/analysis-arm64/docker/start-docker.sh

@@ -0,0 +1,3 @@
+cd ..
+docker build -t tra-analysis-amd64-dev -f docker/Dockerfile .
+docker run -it tra-analysis-amd64-dev

analysis-master/build.sh

@@ -1 +0,0 @@
-python3 setup.py sdist bdist_wheel

data analysis/config.csv

@@ -1,6 +0,0 @@
-2020ilch
-balls-blocked,basic_stats,historical_analysis,regression_linear,regression_logarithmic,regression_exponential,regression_polynomial,regression_sigmoidal
-balls-collected,basic_stats,historical_analysis,regression_linear,regression_logarithmic,regression_exponential,regression_polynomial,regression_sigmoidal
-balls-lower,basic_stats,historical_analysis,regression_linear,regression_logarithmic,regression_exponential,regression_polynomial,regression_sigmoidal
-balls-started,basic_stats,historical_analyss,regression_linear,regression_logarithmic,regression_exponential,regression_polynomial,regression_sigmoidal
-balls-upper,basic_stats,historical_analysis,regression_linear,regression_logarithmic,regression_exponential,regression_polynomial,regression_sigmoidal

data analysis/config/competition.config

@@ -0,0 +1 @@
+2020ilch

data analysis/config/stats.config

@@ -0,0 +1,14 @@
+balls-blocked,basic_stats,historical_analysis,regression_linear,regression_logarithmic,regression_exponential,regression_polynomial,regression_sigmoidal
+balls-collected,basic_stats,historical_analysis,regression_linear,regression_logarithmic,regression_exponential,regression_polynomial,regression_sigmoidal
+balls-lower-teleop,basic_stats,historical_analysis,regression_linear,regression_logarithmic,regression_exponential,regression_polynomial,regression_sigmoidal
+balls-lower-auto,basic_stats,historical_analysis,regression_linear,regression_logarithmic,regression_exponential,regression_polynomial,regression_sigmoidal
+balls-started,basic_stats,historical_analyss,regression_linear,regression_logarithmic,regression_exponential,regression_polynomial,regression_sigmoidal
+balls-upper-teleop,basic_stats,historical_analysis,regression_linear,regression_logarithmic,regression_exponential,regression_polynomial,regression_sigmoidal
+balls-upper-auto,basic_stats,historical_analysis,regression_linear,regression_logarithmic,regression_exponential,regression_polynomial,regression_sigmoidal
+wheel-mechanism
+low-balls
+high-balls
+wheel-success
+strategic-focus
+climb-mechanism
+attitude

data analysis/data.py

@@ -8,7 +8,7 @@ def pull_new_tba_matches(apikey, competition, cutoff):
     x=requests.get("https://www.thebluealliance.com/api/v3/event/"+competition+"/matches/simple", headers={"X-TBA-Auth_Key":api_key})
     out = []
     for i in x.json():
-        if (i["actual_time"]-cutoff >= 0 and i["comp_level"] == "qm"):
+        if (i["actual_time"] != None and i["actual_time"]-cutoff >= 0 and i["comp_level"] == "qm"):
             out.append({"match" : i['match_number'], "blue" : list(map(lambda x: int(x[3:]), i['alliances']['blue']['team_keys'])), "red" : list(map(lambda x: int(x[3:]), i['alliances']['red']['team_keys'])), "winner": i["winning_alliance"]})
     return out
 
@@ -21,6 +21,13 @@ def get_team_match_data(apikey, competition, team_num):
         out[i['match']] = i['data']
     return pd.DataFrame(out)
 
+def get_team_pit_data(apikey, competition, team_num):
+    client = pymongo.MongoClient(apikey)
+    db = client.data_scouting
+    mdata = db.pitdata
+    out = {}
+    return mdata.find_one({"competition" : competition, "team_scouted": team_num})["data"]
+
 def get_team_metrics_data(apikey, competition, team_num):
     client = pymongo.MongoClient(apikey)
     db = client.data_processing
@@ -38,7 +45,7 @@ def unkeyify_2l(layered_dict):
         out[i] = list(map(lambda x: x[1], add))
     return out
 
-def get_data_formatted(apikey, competition):
+def get_match_data_formatted(apikey, competition):
     client = pymongo.MongoClient(apikey)
     db = client.data_scouting
     mdata = db.teamlist
@@ -51,6 +58,19 @@ def get_data_formatted(apikey, competition):
             pass
     return out
 
+def get_pit_data_formatted(apikey, competition):
+    client = pymongo.MongoClient(apikey)
+    db = client.data_scouting
+    mdata = db.teamlist
+    x=mdata.find_one({"competition":competition})
+    out = {}
+    for i in x:
+        try:
+            out[int(i)] = get_team_pit_data(apikey, competition, int(i))
+        except:
+            pass
+    return out
+
 def push_team_tests_data(apikey, competition, team_num, data, dbname = "data_processing", colname = "team_tests"):
     client = pymongo.MongoClient(apikey)
     db = client[dbname]
@@ -63,6 +83,12 @@ def push_team_metrics_data(apikey, competition, team_num, data, dbname = "data_p
     mdata = db[colname]
     mdata.replace_one({"competition" : competition, "team": team_num}, {"_id": competition+str(team_num)+"am", "competition" : competition, "team" : team_num, "metrics" : data}, True)
 
+def push_team_pit_data(apikey, competition, variable, data, dbname = "data_processing", colname = "team_pit"):
+    client = pymongo.MongoClient(apikey)
+    db = client[dbname]
+    mdata = db[colname]
+    mdata.replace_one({"competition" : competition, "variable": variable}, {"competition" : competition, "variable" : variable, "data" : data}, True)
+
 def get_analysis_flags(apikey, flag):
     client = pymongo.MongoClient(apikey)
     db = client.data_processing

data analysis/get_team_rankings.py

@@ -0,0 +1,59 @@
+import data as d
+from analysis import analysis as an
+import pymongo
+import operator
+
+def load_config(file):
+    config_vector = {}
+    file = an.load_csv(file)
+    for line in file[1:]:
+        config_vector[line[0]] = line[1:]
+
+    return (file[0][0], config_vector)
+
+def get_metrics_processed_formatted(apikey, competition):
+    client = pymongo.MongoClient(apikey)
+    db = client.data_scouting
+    mdata = db.teamlist
+    x=mdata.find_one({"competition":competition})
+    out = {}
+    for i in x:
+        try:
+            out[int(i)] = d.get_team_metrics_data(apikey, competition, int(i))
+        except:
+            pass
+    return out
+
+def main():
+
+    apikey = an.load_csv("keys.txt")[0][0]
+    tbakey = an.load_csv("keys.txt")[1][0]
+
+    competition, config = load_config("config.csv")
+
+    metrics = get_metrics_processed_formatted(apikey, competition)
+
+    elo = {}
+    gl2 = {}
+
+    for team in metrics:
+
+        elo[team] = metrics[team]["metrics"]["elo"]["score"]
+        gl2[team] = metrics[team]["metrics"]["gl2"]["score"]
+
+    elo = {k: v for k, v in sorted(elo.items(), key=lambda item: item[1])}
+    gl2 = {k: v for k, v in sorted(gl2.items(), key=lambda item: item[1])}
+
+    for team in elo:
+
+        print("teams sorted by elo:")
+        print("" + str(team) + " | " + str(elo[team]))
+
+    print("*"*25)
+
+    for team in gl2:
+
+        print("teams sorted by glicko2:")
+        print("" + str(team) + " | " + str(gl2[team]))
+
+main()

data analysis/requirements.txt

@@ -0,0 +1,4 @@
+requests
+pymongo
+pandas
+dnspython

data analysis/superscript.py

@@ -3,10 +3,29 @@
 # Notes:
 # setup:
 
-__version__ = "0.0.2.001"
+__version__ = "0.0.5.002"
 
 # changelog should be viewed using print(analysis.__changelog__)
 __changelog__ = """changelog:
+    0.0.5.002:
+        - made changes due to refactoring of analysis
+    0.0.5.001:
+        - text fixes
+        - removed matplotlib requirement
+    0.0.5.000:
+        - improved user interface
+    0.0.4.002:
+        - removed unessasary code
+    0.0.4.001:
+        - fixed bug where X range for regression was determined before sanitization
+        - better sanitized data
+    0.0.4.000:
+        - 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:
+        - added analysis to pit data
     0.0.2.001:
         - minor stability patches
         - implemented db syncing for timestamps
@@ -69,6 +88,9 @@ __all__ = [
 
 from analysis import analysis as an
 import data as d
+import numpy as np
+from os import system, name
+from pathlib import Path
 import time
 import warnings
 
@@ -77,16 +99,16 @@ def main():
     while(True):
 
         current_time = time.time()
-        print("time: " + str(current_time))
+        print("[OK] time: " + str(current_time))
 
-        print(" loading config")
-        competition, config = load_config("config.csv")
-        print(" config loaded")
+        start = time.time()
+        config = load_config(Path("config/stats.config"))
+        competition = an.load_csv(Path("config/competition.config"))[0][0]
+        print("[OK] configs loaded")
 
-        print(" loading database keys")
-        apikey = an.load_csv("keys.txt")[0][0]
-        tbakey = an.load_csv("keys.txt")[1][0]
-        print(" loaded keys")
+        apikey = an.load_csv(Path("config/keys.config"))[0][0]
+        tbakey = an.load_csv(Path("config/keys.config"))[1][0]
+        print("[OK] loaded keys")
 
         previous_time = d.get_analysis_flags(apikey, "latest_update")
 
@@ -99,33 +121,55 @@ def main():
 
             previous_time = previous_time["latest_update"]
 
-        print(" analysis backtimed to: " + str(previous_time))
+        print("[OK] analysis backtimed to: " + str(previous_time))
 
-        print(" loading data")
-        data = d.get_data_formatted(apikey, competition)
-        print(" loaded data")
+        print("[OK] loading data")
+        start = time.time()
+        data = d.get_match_data_formatted(apikey, competition)
+        pit_data = d.pit = d.get_pit_data_formatted(apikey, competition)
+        print("[OK] loaded data in " + str(time.time() - start) + " seconds")
 
-        print(" running tests")
+        print("[OK] running tests")
+        start = time.time()
         results = simpleloop(data, config)
-        print(" finished tests")
+        print("[OK] finished tests in " + str(time.time() - start) + " seconds")
 
-        print(" running metrics")
-        metrics = metricsloop(tbakey, apikey, competition, previous_time)
-        print(" finished metrics")
+        print("[OK] running metrics")
+        start = time.time()
+        metricsloop(tbakey, apikey, competition, previous_time)
+        print("[OK] finished metrics in " + str(time.time() - start) + " seconds")
+
+        print("[OK] running pit analysis")
+        start = time.time()
+        pit = pitloop(pit_data, config)
+        print("[OK] finished pit analysis in " + str(time.time() - start) + " seconds")
 
         d.set_analysis_flags(apikey, "latest_update", {"latest_update":current_time})
         
-        print(" pushing to database")
-        push_to_database(apikey, competition, results, metrics)
-        print(" pushed to database")
+        print("[OK] pushing to database")
+        start = time.time()
+        push_to_database(apikey, competition, results, pit)
+        print("[OK] pushed to database in " + str(time.time() - start) + " seconds")
+
+        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 = {}
     file = an.load_csv(file)
-    for line in file[1:]:
+    for line in file:
         config_vector[line[0]] = line[1:]
 
-    return (file[0][0], config_vector)
+    return config_vector
 
 def simpleloop(data, tests): # expects 3D array with [Team][Variable][Match]
 
@@ -147,36 +191,40 @@ def simpleloop(data, tests): # expects 3D array with [Team][Variable][Match]
 
 def simplestats(data, test):
 
+    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([list(range(len(data))), data])
+        return an.histo_analysis([ranges, data])
 
     if(test == "regression_linear"):
-        return an.regression(list(range(len(data))), data, ['lin'])
+        return an.regression(ranges, data, ['lin'])
 
     if(test == "regression_logarithmic"):
-        return an.regression(list(range(len(data))), data, ['log'])
+        return an.regression(ranges, data, ['log'])
 
     if(test == "regression_exponential"):
-        return an.regression(list(range(len(data))), data, ['exp'])
+        return an.regression(ranges, data, ['exp'])
 
     if(test == "regression_polynomial"):
-        return an.regression(list(range(len(data))), data, ['ply'])
+        return an.regression(ranges, data, ['ply'])
 
     if(test == "regression_sigmoidal"):
-        return an.regression(list(range(len(data))), data, ['sig'])
+        return an.regression(ranges, data, ['sig'])
 
-def push_to_database(apikey, competition, results, metrics):
+def push_to_database(apikey, competition, results, pit):
 
     for team in results:
 
         d.push_team_tests_data(apikey, competition, team, results[team])
 
-    for team in metrics:
+    for variable in pit:
 
-        d.push_team_metrics_data(apikey, competition, team, metrics[team])
+        d.push_team_pit_data(apikey, competition, variable, pit[variable])
 
 def metricsloop(tbakey, apikey, competition, timestamp): # listener based metrics update
 
@@ -185,8 +233,6 @@ def metricsloop(tbakey, apikey, competition, timestamp): # listener based metric
 
     matches = d.pull_new_tba_matches(tbakey, competition, timestamp)
 
-    return_vector = {}
-
     red = {}
     blu = {}
 
@@ -194,7 +240,7 @@ def metricsloop(tbakey, apikey, competition, timestamp): # listener based metric
 
         red = load_metrics(apikey, competition, match, "red")
         blu = load_metrics(apikey, competition, match, "blue")
-
+ 
         elo_red_total = 0
         elo_blu_total = 0
 
@@ -242,11 +288,11 @@ def metricsloop(tbakey, apikey, competition, timestamp): # listener based metric
 
             observations = {"red": 0.5, "blu": 0.5}
 
-        red_elo_delta = an.elo(red_elo["score"], blu_elo["score"], observations["red"], elo_N, elo_K) - red_elo["score"]
-        blu_elo_delta = an.elo(blu_elo["score"], red_elo["score"], observations["blu"], elo_N, elo_K) - blu_elo["score"]
+        red_elo_delta = an.Metrics.elo(red_elo["score"], blu_elo["score"], observations["red"], elo_N, elo_K) - red_elo["score"]
+        blu_elo_delta = an.Metrics.elo(blu_elo["score"], red_elo["score"], observations["blu"], elo_N, elo_K) - blu_elo["score"]
 
-        new_red_gl2_score, new_red_gl2_rd, new_red_gl2_vol = an.glicko2(red_gl2["score"], red_gl2["rd"], red_gl2["vol"], [blu_gl2["score"]], [blu_gl2["rd"]], [observations["red"], observations["blu"]])
-        new_blu_gl2_score, new_blu_gl2_rd, new_blu_gl2_vol = an.glicko2(blu_gl2["score"], blu_gl2["rd"], blu_gl2["vol"], [red_gl2["score"]], [red_gl2["rd"]], [observations["blu"], observations["red"]])
+        new_red_gl2_score, new_red_gl2_rd, new_red_gl2_vol = an.Metrics.glicko2(red_gl2["score"], red_gl2["rd"], red_gl2["vol"], [blu_gl2["score"]], [blu_gl2["rd"]], [observations["red"], observations["blu"]])
+        new_blu_gl2_score, new_blu_gl2_rd, new_blu_gl2_vol = an.Metrics.glicko2(blu_gl2["score"], blu_gl2["rd"], blu_gl2["vol"], [red_gl2["score"]], [red_gl2["rd"]], [observations["blu"], observations["red"]])
 
         red_gl2_delta = {"score": new_red_gl2_score - red_gl2["score"], "rd": new_red_gl2_rd - red_gl2["rd"], "vol": new_red_gl2_vol - red_gl2["vol"]}
         blu_gl2_delta = {"score": new_blu_gl2_score - blu_gl2["score"], "rd": new_blu_gl2_rd - blu_gl2["rd"], "vol": new_blu_gl2_vol - blu_gl2["vol"]}
@@ -267,36 +313,13 @@ def metricsloop(tbakey, apikey, competition, timestamp): # listener based metric
             blu[team]["gl2"]["rd"] = blu[team]["gl2"]["rd"] + blu_gl2_delta["rd"]
             blu[team]["gl2"]["vol"] = blu[team]["gl2"]["vol"] + blu_gl2_delta["vol"]
 
-        """ not functional for now
-        red_trueskill = []
-        blu_trueskill = []
+        temp_vector = {}
+        temp_vector.update(red)
+        temp_vector.update(blu)
 
-        red_ts_team_lookup = []
-        blu_ts_team_lookup = []
+        for team in temp_vector:
 
-        for team in red:
-
-            red_trueskill.append((red[team]["ts"]["mu"], red[team]["ts"]["sigma"]))
-            red_ts_team_lookup.append(team)
-
-        for team in blu:
-
-            blu_trueskill.append((blu[team]["ts"]["mu"], blu[team]["ts"]["sigma"]))
-            blu_ts_team_lookup.append(team)
-
-        print(red_trueskill)
-        print(blu_trueskill)
-
-        results = an.trueskill([red_trueskill, blu_trueskill], [observations["red"], observations["blu"]])
-
-        print(results)
-
-        """
-
-    return_vector.update(red)
-    return_vector.update(blu)
-
-    return return_vector
+            d.push_team_metrics_data(apikey, competition, team, temp_vector[team])
 
 def load_metrics(apikey, competition, match, group_name):
 
@@ -312,21 +335,34 @@ def load_metrics(apikey, competition, match, group_name):
             gl2 = {"score": 1500, "rd": 250, "vol": 0.06}
             ts = {"mu": 25, "sigma": 25/3}
 
-            d.push_team_metrics_data(apikey, competition, team, {"elo":elo, "gliko2":gl2,"trueskill":ts})
+            #d.push_team_metrics_data(apikey, competition, team, {"elo":elo, "gl2":gl2,"trueskill":ts})
 
             group[team] = {"elo": elo, "gl2": gl2, "ts": ts}
 
         else:
 
             metrics = db_data["metrics"]
+
             elo = metrics["elo"]
-            gl2 = metrics["gliko2"]
-            ts = metrics["trueskill"]
+            gl2 = metrics["gl2"]
+            ts = metrics["ts"]
 
             group[team] = {"elo": elo, "gl2": gl2, "ts": ts}
 
     return group
 
+def pitloop(pit, tests):
+
+    return_vector = {}
+    for team in pit:
+        for variable in pit[team]:
+            if(variable in tests):
+                if(not variable in return_vector):
+                    return_vector[variable] = []
+                return_vector[variable].append(pit[team][variable])
+
+    return return_vector
+
 main()
 
 """

data analysis/visualize_pit.py

@@ -0,0 +1,59 @@
+# To add a new cell, type '# %%'
+# To add a new markdown cell, type '# %% [markdown]'
+# %%
+import matplotlib.pyplot as plt
+import data as d
+import pymongo
+
+
+# %%
+def get_pit_variable_data(apikey, competition):
+    client = pymongo.MongoClient(apikey)
+    db = client.data_processing
+    mdata = db.team_pit
+    out = {}
+    return mdata.find()
+
+
+# %%
+def get_pit_variable_formatted(apikey, competition):
+    temp = get_pit_variable_data(apikey, competition)
+    out = {}
+    for i in temp:
+        out[i["variable"]] = i["data"]
+    return out
+
+
+# %%
+pit = get_pit_variable_formatted("mongodb+srv://api-user-new:titanscout2022@2022-scouting-4vfuu.mongodb.net/test?authSource=admin&replicaSet=2022-scouting-shard-0&readPreference=primary&appname=MongoDB%20Compass&ssl=true", "2020ilch")
+
+
+# %%
+import matplotlib.pyplot as plt
+import numpy as np
+
+
+# %%
+fig, ax = plt.subplots(1, len(pit), sharey=True, figsize=(80,15))
+
+i = 0
+
+for variable in pit:
+
+    ax[i].hist(pit[variable])
+    ax[i].invert_xaxis()
+
+    ax[i].set_xlabel('')
+    ax[i].set_ylabel('Frequency')
+    ax[i].set_title(variable)
+
+    plt.yticks(np.arange(len(pit[variable])))
+
+    i+=1
+
+plt.show()
+
+
+# %%
+
+