Merge branch 'master' of https://github.com/PerryXDeng/wheatyeeters

hypotheses_modeling/KerasRegressions.py

@@ -49,7 +49,7 @@ def time_series_sigmoid_classification(X, Y, k, n0, x_columns, y_columns):
   return model.get_weights()
 
 
-def time_series_sigmoid_classification(X, Y, k, n0, x_columns, y_columns):
+def time_series_dnn_classification(X, Y, k, n0, x_columns, y_columns):
   inp = X[x_columns]
   out = Y[y_columns]
   col = "day"
@@ -86,7 +86,7 @@ def time_series_sigmoid_classification(X, Y, k, n0, x_columns, y_columns):
   y = np.array(y)
   model = tf.keras.Sequential([
     tf.keras.layers.Flatten(input_shape=input_shape),
-    tf.keras.layers.Dense(32),
+    tf.keras.layers.Dense(32, activation=tf.nn.softmax),
     tf.keras.layers.Dense(output_shape, activation=tf.nn.softmax)
   ])
   model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy', 'categorical_accuracy'])
@@ -94,3 +94,95 @@ def time_series_sigmoid_classification(X, Y, k, n0, x_columns, y_columns):
   loss, accuracy = model.evaluate(x, y)
   print(loss, accuracy)
   return model.get_weights()
+
+def time_series_linear_regression(X, Y, k, n0, x_columns, y_columns):
+  inp = X[x_columns]
+  out = Y[y_columns]
+  col = "day"
+  x = []
+  y = []
+  input_shape = 0
+  output_shape = 0
+  for player in Y["playerID"].unique():
+    XPlayer = inp[inp["playerID"] == player]
+    YPlayer = out[out["playerID"] == player]
+    for day in YPlayer[col][n0 - 1:]:
+      prev = day - k
+      xprev = XPlayer[XPlayer[col] == prev].drop(columns=[col]).to_numpy()
+      if xprev.shape[0] != 1:
+        continue
+      else:
+        xprev = xprev[0, :]
+      yt = YPlayer[YPlayer[col] == day].drop(columns=[col]).to_numpy()[0, :]
+      if input_shape == 0:
+        input_shape = xprev.shape[0]
+      else:
+        if input_shape != xprev.shape[0]:
+          print("INCONSISTENT INPUT DIMENSION")
+          exit(2)
+      if input_shape == 0:
+        output_shape = yt.shape[0]
+      else:
+        if output_shape != yt.shape[0]:
+          print("INCONSISTENT OUTPUT DIMENSION")
+          exit(2)
+      x.append(xprev)
+      y.append(yt)
+  x = np.array(x)
+  y = np.array(y)
+  model = tf.keras.Sequential([
+    tf.keras.layers.Flatten(input_shape=input_shape),
+    tf.keras.layers.Dense(output_shape)
+  ])
+  model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy', 'categorical_accuracy'])
+  model.fit(x, y, epochs=100)
+  loss, accuracy = model.evaluate(x, y)
+  print(loss, accuracy)
+  return model.get_weights()
+
+
+def time_series_dnn_regressions(X, Y, k, n0, x_columns, y_columns):
+  inp = X[x_columns]
+  out = Y[y_columns]
+  col = "day"
+  x = []
+  y = []
+  input_shape = 0
+  output_shape = 0
+  for player in Y["playerID"].unique():
+    XPlayer = inp[inp["playerID"] == player]
+    YPlayer = out[out["playerID"] == player]
+    for day in YPlayer[col][n0 - 1:]:
+      prev = day - k
+      xprev = XPlayer[XPlayer[col] == prev].drop(columns=[col]).to_numpy()
+      if xprev.shape[0] != 1:
+        continue
+      else:
+        xprev = xprev[0, :]
+      yt = YPlayer[YPlayer[col] == day].drop(columns=[col]).to_numpy()[0, :]
+      if input_shape == 0:
+        input_shape = xprev.shape[0]
+      else:
+        if input_shape != xprev.shape[0]:
+          print("INCONSISTENT INPUT DIMENSION")
+          exit(2)
+      if input_shape == 0:
+        output_shape = yt.shape[0]
+      else:
+        if output_shape != yt.shape[0]:
+          print("INCONSISTENT OUTPUT DIMENSION")
+          exit(2)
+      x.append(xprev)
+      y.append(yt)
+  x = np.array(x)
+  y = np.array(y)
+  model = tf.keras.Sequential([
+    tf.keras.layers.Flatten(input_shape=input_shape),
+    tf.keras.layers.Dense(32, activation=tf.nn.softmax),
+    tf.keras.layers.Dense(output_shape)
+  ])
+  model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy', 'categorical_accuracy'])
+  model.fit(x, y, epochs=100)
+  loss, accuracy = model.evaluate(x, y)
+  print(loss, accuracy)
+  return model.get_weights()

hypotheses_modeling/hypotheses.txt

@@ -21,8 +21,15 @@ Team:
 
     5.
 
+
+Individual:
+    Player 1 - fatigue + day / soreness
+        lr - 0.24677741789096985
+        pr - 0.32119826926167405
+
 Perry:
 7 day moving average team workload - normalized team fatigue: 0.0006
 21 day moving average team workload - normalized team fatigue: 0.0024
 normalized team fatigue - game day performance: 0.0696
 normalized team fatigue - paper smoothed workload fatigue: 0.0324
+

hypotheses_modeling/team_regressions.py

@@ -1,4 +1,6 @@
 from sklearn import linear_model
+from sklearn.preprocessing import PolynomialFeatures
+import numpy as np
 import pandas as pd
 from sklearn.metrics import mean_squared_error, r2_score
 
@@ -34,6 +36,7 @@ def k_days_into_future_regression(X, y, k, n0):
 
 
 def standard_lr(x, y):
+  # Standard linear regression formula, gives back params and r2
   regr = linear_model.LinearRegression()
   regr.fit(x, y)
   predictions = regr.predict(x)
@@ -42,19 +45,27 @@ def standard_lr(x, y):
   return regr.intercept_, regr.coef_, r2, mse
 
 
-def main():
-  # fatigueSums = pd.read_csv("fatigue_total_sum.csv")
-  # workMovingAverage21 = pd.read_csv("21DaySlidingWorkAverage.csv", index_col=0)
-  # print(k_days_into_future_regression(workMovingAverage21, fatigueSums, 0, 21))
+def poly_regression(x, y, degree):
+  # Polynomial regression with nth degree, gives back rmse and r2
+  polynomial_features = PolynomialFeatures(degree=degree)
+  x_poly = polynomial_features.fit_transform(x)
+
+  model = linear_model.LinearRegression()
+  model.fit(x_poly, y)
+  y_poly_pred = model.predict(x_poly)
 
+  rmse = np.sqrt(mean_squared_error(y, y_poly_pred))
+  r2 = r2_score(y, y_poly_pred)
+  return rmse, r2
 
-  wellness = pd.read_csv("../data_preparation/cleaned/time_series_normalized_wellness_menstruation.csv")
 
-  wellness = wellness.fillna(0)
-  x = wellness[['normSoreness', 'TimeSinceAugFirst']]
-  y = wellness['normFatigue']
-  print(wellness.isnull().sum())
+def main():
+  player = pd.read_csv("../data_preparation/cleaned/personal.csv", index_col=0)
+  player = player[player['playerID'] == 1]
+  x = player[['fatigueNorm', 'day']]
+  y = player['sorenessNorm']
   print(standard_lr(x, y))
+  print(poly_regression(x, y, 5))
 
 
 if __name__ == "__main__":