analysis.py v 1.1.13.006

regression.py v 1.0.0.003
analysis pkg v 1.0.0.8

.gitignore

@@ -17,3 +17,5 @@ data analysis/.ipynb_checkpoints/test-checkpoint.ipynb
 data analysis/arthur_pull.ipynb
 data analysis/keys.txt
 data analysis/check_for_new_matches.ipynb
+data analysis/test.ipynb
+data analysis/visualize_pit.ipynb

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

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: analysis
-Version: 1.0.0.6
+Version: 1.0.0.8
 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.egg-info/SOURCES.txt

@@ -8,4 +8,5 @@ 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.egg-info/requires.txt

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

analysis-master/analysis/analysis.py

@@ -7,10 +7,20 @@
 #    current benchmark of optimization: 1.33 times faster
 # setup:
 
-__version__ = "1.1.13.001"
+__version__ = "1.1.13.006"
 
 # changelog should be viewed using print(analysis.__changelog__)
 __changelog__ = """changelog:
+    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 +249,6 @@ __author__ = (
 )
 
 __all__ = [
-    '_init_device',
     'load_csv',
     'basic_stats',
     'z_score',
@@ -260,7 +269,6 @@ __all__ = [
     'SVM',
     'random_forest_classifier',
     'random_forest_regressor',
-    'Regression',
     'Glicko2',
     # all statistics functions left out due to integration in other functions
 ]
@@ -273,24 +281,15 @@ import csv
 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
 
 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 +348,15 @@ 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 +373,6 @@ 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
@@ -393,9 +389,6 @@ 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.exp(b*(x + c)) + d
@@ -410,8 +403,8 @@ 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])
@@ -435,9 +428,6 @@ 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.tanh(b*(x + c)) + d
@@ -700,225 +690,6 @@ def random_forest_regressor(data, outputs, test_size, n_estimators="warn", crite
 
     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

analysis-master/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 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):

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

@@ -7,10 +7,20 @@
 #    current benchmark of optimization: 1.33 times faster
 # setup:
 
-__version__ = "1.1.13.001"
+__version__ = "1.1.13.006"
 
 # changelog should be viewed using print(analysis.__changelog__)
 __changelog__ = """changelog:
+    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 +249,6 @@ __author__ = (
 )
 
 __all__ = [
-    '_init_device',
     'load_csv',
     'basic_stats',
     'z_score',
@@ -260,7 +269,6 @@ __all__ = [
     'SVM',
     'random_forest_classifier',
     'random_forest_regressor',
-    'Regression',
     'Glicko2',
     # all statistics functions left out due to integration in other functions
 ]
@@ -273,24 +281,15 @@ import csv
 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
 
 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 +348,15 @@ 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 +373,6 @@ 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
@@ -393,9 +389,6 @@ 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.exp(b*(x + c)) + d
@@ -410,8 +403,8 @@ 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])
@@ -435,9 +428,6 @@ 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.tanh(b*(x + c)) + d
@@ -700,225 +690,6 @@ def random_forest_regressor(data, outputs, test_size, n_estimators="warn", crite
 
     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

analysis-master/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 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):

analysis-master/setup.py

@@ -2,7 +2,7 @@ import setuptools
 
 setuptools.setup(
     name="analysis", # Replace with your own username
-    version="1.0.0.006",
+    version="1.0.0.008",
     author="The Titan Scouting Team",
     author_email="titanscout2022@gmail.com",
     description="analysis package developed by Titan Scouting for The Red Alliance",
@@ -10,6 +10,14 @@ setuptools.setup(
     long_description_content_type="text/markdown",
     url="https://github.com/titanscout2022/tr2022-strategy",
     packages=setuptools.find_packages(),
+    install_requires=[
+        "numba",
+        "numpy",
+        "scipy",
+        "scikit-learn",
+        "six",
+        "matplotlib"
+    ],
     license = "GNU General Public License v3.0",
     classifiers=[
         "Programming Language :: Python :: 3",

data analysis/config.csv

@@ -1,6 +1,15 @@
 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-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,basic_stats,historical_analysis,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/superscript.py

@@ -3,10 +3,22 @@
 # Notes:
 # setup:
 
-__version__ = "0.0.2.001"
+__version__ = "0.0.4.002"
 
 # changelog should be viewed using print(analysis.__changelog__)
 __changelog__ = """changelog:
+    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 +81,8 @@ __all__ = [
 
 from analysis import analysis as an
 import data as d
+import numpy as np
+import matplotlib.pyplot as plt
 import time
 import warnings
 
@@ -102,7 +116,8 @@ def main():
         print(" analysis backtimed to: " + str(previous_time))
 
         print(" loading data")
-        data = d.get_data_formatted(apikey, competition)
+        data = d.get_match_data_formatted(apikey, competition)
+        pit_data = d.pit = d.get_pit_data_formatted(apikey, competition)
         print(" loaded data")
 
         print(" running tests")
@@ -110,13 +125,17 @@ def main():
         print(" finished tests")
 
         print(" running metrics")
-        metrics = metricsloop(tbakey, apikey, competition, previous_time)
+        metricsloop(tbakey, apikey, competition, previous_time)
         print(" finished metrics")
 
+        print(" running pit analysis")
+        pit = pitloop(pit_data, config)
+        print(" finished pit analysis")
+
         d.set_analysis_flags(apikey, "latest_update", {"latest_update":current_time})
         
         print(" pushing to database")
-        push_to_database(apikey, competition, results, metrics)
+        push_to_database(apikey, competition, results, pit)
         print(" pushed to database")
 
 def load_config(file):
@@ -147,36 +166,40 @@ 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 +208,6 @@ def metricsloop(tbakey, apikey, competition, timestamp): # listener based metric
 
     matches = d.pull_new_tba_matches(tbakey, competition, timestamp)
 
-    return_vector = {}
-
     red = {}
     blu = {}
 
@@ -267,36 +288,13 @@ 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 +310,34 @@ 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()
+
+
+# %%
+
+