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

hypotheses_modeling/ryan_regressions.txt

@@ -0,0 +1,56 @@
+Player 9 for acuteChronicRatio
+(1.5543991777375237, array([-0.13902363, -0.0050734 ]), 0.43833525766886916, 0.0008867324974165428)
+(0.48957502323211444, 0.5699208996736808)
+
+Player 11 for acuteChronicRatio
+(1.3258336437888891, array([ 0.00685405, -0.00203877]), 0.11479264860906191, 0.00096573215060248)
+(0.4626369870793939, 0.44423100028132423)
+
+Player 9 for sleepQuality
+(5.334340148618029, array([ 1.02125114, -0.00432071]), 0.6539555377710119, 0.0012466268315319546)
+(0.597372726628557, 0.7193845945200593)
+
+Player 12 for sleepQuality
+(3.584632145668627, array([0.41485048, 0.00088306]), 0.34499328173976607, 0.0006803191826778461)
+(0.4600451787749952, 0.4227561697627662)
+
+Player 3 for soreness
+(3.2022109874813864, array([ 4.19185564e-01, -1.39780603e-04]), 0.4252210971285296, 0.0006688273367686844)
+(0.4674558844267985, 0.468022382169041)
+
+Player 7 for soreness
+(3.077085467389001, array([4.26722267e-01, 5.78941104e-05]), 0.39740866670470376, 0.0007515523424419748)
+(0.49988907759269197, 0.4324080355741665)
+
+Player 9 for soreness
+(5.246967544538162, array([ 0.71359643, -0.00715268]), 0.5944763974272957, 0.0019117577400940124)
+(0.7765705044770445, 0.637614880294574)
+
+Player 3 for sorenessNorm
+(0.12141700921277873, array([ 0.58776641, -0.00068588]), 0.36954097046558354, 0.0017457549720592538)
+(0.7372571250720799, 0.443920566690573)
+
+Player 9 for sleepQualityNorm
+(0.08976795719049747, array([ 7.62990183e-01, -4.56901189e-04]), 0.5858342550214043, 0.0005114756024138036)
+(0.40337948626285336, 0.6267479812123391)
+
+Player 12 for sleepQualityNorm
+(0.0030010445831953553, array([ 5.97640029e-01, -1.59341568e-05]), 0.3568843263232311, 0.00117522635306064)
+(0.6154637522814207, 0.4127840710858218)
+
+Player 3 for BestOutOfMyselfAbsolutely
+(0.5591113560131244, array([-0.06273135,  0.00144052]), 0.19693367374327753, 0.00034431962962114574)
+(0.29946330051959735, 0.4074811906349808)
+
+Player 9 for BestOutOfMyselfAbsolutely
+(0.6212790914046262, array([ 0.23297634, -0.00209794]), 0.49210290965481174, 0.0002682490835151878)
+(0.2897694328560262, 0.5496315964616945)
+
+Player 3 for BestOutOfMyselfUnknown
+(0.45258982162191874, array([ 0.0601493 , -0.00149072]), 0.20252316026232742, 0.0003459027048924739)
+(0.2980996120964688, 0.41962026820540466)
+
+Player 9 for BestOutOfMyselfUnknown
+(0.34069195794958324, array([-0.22074479,  0.00217018]), 0.4646199842752917, 0.0003011772648087732)
+(0.3048702214016301, 0.5319467359793901)
+

hypotheses_modeling/team_regressions.py

@@ -60,12 +60,24 @@ def poly_regression(x, y, degree):
 
 
 def main():
+  file = open("ryan_regressions.txt", 'w')
   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))
+
+  for name, value in player.iteritems():
+    if name == "day":
+      continue
+
+    for j in range(1, 17):
+      ply = player[player['playerID'] == j]
+      x = ply[['fatigueNorm', 'day']]
+      y = ply[name]
+
+      lr = standard_lr(x, y)
+      poly = poly_regression(x, y, 3)
+      if .9 > lr[2] > .4 or .9 > poly[1] > .4:
+        file.write("Player {} for {}\n".format(j, name))
+        file.write("{}\n".format(lr))
+        file.write("{}\n\n".format(poly))
 
 
 if __name__ == "__main__":

run_all_regressions.py

@@ -0,0 +1,102 @@
+from sklearn import linear_model
+import pandas as pd
+from sklearn.metrics import mean_squared_error, r2_score
+from matplotlib import pyplot as plt
+import numpy as np
+from sklearn.preprocessing import PolynomialFeatures
+
+
+def k_days_into_future_regression(X, y, k, n0):
+  """
+  linear regression that returns the fitted weights as well as metrics
+  :param X: x timeseries dataframe (very clean, no unamed columns), multidimensional rows
+  :param y: y timeseries dataframe (very clean, no unamed columns), scalar rows
+  :param k: days predicting in advance
+  :param n0: ignoring the first n0 days
+  :return: intercept, slopes, correlation, mean squared error
+  """
+  col = "TimeSinceAugFirst"
+  inp = []
+  out = []
+  for day in y[col][n0 - 1:]:
+    prev = day - k
+    xprev = X[X[col] == prev].drop(columns=[col]).to_numpy()
+    if xprev.shape[0] != 1:
+      continue
+    else:
+      xprev = xprev[0, :]
+    yt = y[y[col] == day].drop(columns=[col]).to_numpy()[0, :]
+    inp.append(xprev)
+    out.append(yt)
+  regr = linear_model.LinearRegression()
+  regr.fit(inp, out)
+  predictions = regr.predict(inp)
+  mse = mean_squared_error(out, predictions)/(len(out) - 2)
+  r2 = r2_score(out, predictions)
+  return regr.intercept_, regr.coef_, r2, mse
+
+
+def standard_lr(x, y):
+  x = x.reshape(-1, 1)
+  y = y.reshape(-1, 1)
+  regr = linear_model.LinearRegression()
+  regr.fit(x, y)
+  predictions = regr.predict(x)
+  mse = mean_squared_error(y, predictions) / (len(y) - 2)
+  r2 = r2_score(y, predictions)
+  return regr.intercept_, regr.coef_, r2, mse
+
+
+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.fist_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
+
+
+def run_all_linears():
+
+    # Reads in the neccessary csv file
+    df = pd.read_csv('data_preparation/cleaned/time_series_normalized_wellness_menstruation.csv')
+    regr = linear_model.LinearRegression()
+    for i in range(4, 11):
+        for j in range(1, 11 - i):
+            mat = df[[df.columns[i], df.columns[i + j]]].values
+            regr.intercept_, regr.coef_, r2, mse = standard_lr(mat[:, 0], mat[:, 1])
+            plt.figure(figsize=(6, 6))
+            plt.xlabel(df.columns[i])
+            plt.ylabel(df.columns[i + j])
+            plt.title('r2: ' + str(r2))
+            plt.scatter(mat[:, 0], mat[:, 1])
+            plt.savefig('wellness_linear_regressions/' + df.columns[i] + '_vs_' + df.columns[i + j] + '.png')
+            plt.close()
+
+
+def run_all_polynomials():
+    # Reads in the neccessary csv file
+    df = pd.read_csv('data_preparation/cleaned/time_series_normalized_wellness_menstruation.csv')
+    regr = linear_model.LinearRegression()
+    for i in range(4, 11):
+        for j in range(1, 11 - i):
+            mat = df[[df.columns[i], df.columns[i + j]]].values
+            for d in range(2, 5):
+                rmse, r2 = poly_regression(mat[:, 0], mat[:, 1], d)
+                plt.figure(figsize=(6, 6))
+                plt.xlabel(df.columns[i])
+                plt.ylabel(df.columns[i + j])
+                plt.title('r2: ' + str(r2) + 'degree: ' + str(d))
+                plt.scatter(mat[:, 0], mat[:, 1])
+                plt.savefig('wellness_poly_regressions/' + df.columns[i] + '_vs_' + df.columns[i + j] + '_' + str(d) + '_degree.png')
+                print(df.columns[i] + '_vs_' + df.columns[i + j] + '_degree_' + str(d) + '_r2=' + str(r2) + '_rmse=' + str(rmse))
+                plt.close()
+
+
+run_all_linears()
+run_all_polynomials()

wellness_poly_regressions/wellness_poly_regression_desc.csv

@@ -0,0 +1,64 @@
+xVal, yVal, degree, r2, rmse
+normSoreness, normFatigue, 2, 0.16854967429853518, 0.9033575013918365
+normSoreness, normFatigue, 3, 0.17006015472626201, 0.9025365719486311
+normSoreness, normFatigue, 4, 0.17055326322782471, 0.9022684111987103
+normSoreness, normDesire, 2, 0.09702753580052226, 0.9408536578361171
+normSoreness, normDesire, 3, 0.09735543680398395, 0.940682813827439
+normSoreness, normDesire, 4, 0.10223585110043043, 0.9381363274157384
+normSoreness, normIrritability, 2, 0.032418630567133566, 0.9819871762899308
+normSoreness, normIrritability, 3, 0.03261787177694686, 0.9818860672812905
+normSoreness, normIrritability, 4, 0.034543628328234544, 0.980908265725734
+normSoreness, normSleepHours, 2, 0.0011338446969086924, 0.9780197919269892
+normSoreness, normSleepHours, 3, 0.001843402686714568, 0.9776723554666978
+normSoreness, normSleepHours, 4, 0.0020137564689429732, 0.9775889230219283
+normSoreness, normSleepQuality, 2, 0.019594649756118798, 0.981995418492479
+normSoreness, normSleepQuality, 3, 0.01986261536093159, 0.9818612092191729
+normSoreness, normSleepQuality, 4, 0.020514330099920652, 0.9815347244646507
+normSoreness, MenstruationNumber, 2, 0.00044841702343612067, 0.3486519499940022
+normSoreness, MenstruationNumber, 3, 0.000554110484162873, 0.3486335161252519
+normSoreness, MenstruationNumber, 4, 0.0005547900767390868, 0.3486333975951783
+normFatigue, normDesire, 2, 0.17044223675854964, 0.9017956586323999
+normFatigue, normDesire, 3, 0.17050241420665846, 0.9017629491888505
+normFatigue, normDesire, 4, 0.1708742559722647, 0.9015608083271118
+normFatigue, normIrritability, 2, 0.09218025965334886, 0.9511781793201747
+normFatigue, normIrritability, 3, 0.09220971365139041, 0.9511627488188138
+normFatigue, normIrritability, 4, 0.09233746191827452, 0.9510958205482378
+normFatigue, normSleepHours, 2, 0.037395679724302355, 0.9601031570708193
+normFatigue, normSleepHours, 3, 0.037684532627811795, 0.9599590950784357
+normFatigue, normSleepHours, 4, 0.038112628469872734, 0.9597455475331765
+normFatigue, normSleepQuality, 2, 0.1420596292108267, 0.9186184788560888
+normFatigue, normSleepQuality, 3, 0.14230117332089598, 0.9184891560556917
+normFatigue, normSleepQuality, 4, 0.14342854510375913, 0.9178853198307455
+normFatigue, MenstruationNumber, 2, 0.00027452223877810766, 0.3486822766525199
+normFatigue, MenstruationNumber, 3, 0.00027698344816373677, 0.3486818474443827
+normFatigue, MenstruationNumber, 4, 0.0004451365239876992, 0.3486525221263516
+normDesire, normIrritability, 2, 0.11666322360262527, 0.9382643679754818
+normDesire, normIrritability, 3, 0.1260690807253083, 0.9332556331480653
+normDesire, normIrritability, 4, 0.12620943541142648, 0.9331806889744677
+normDesire, normSleepHours, 2, 0.00026365971406716593, 0.9784457112843362
+normDesire, normSleepHours, 3, 0.000703037710309995, 0.9782306772075785
+normDesire, normSleepHours, 4, 0.0016808528069790496, 0.9777519592356363
+normDesire, normSleepQuality, 2, 0.03521627084735923, 0.974140524703551
+normDesire, normSleepQuality, 3, 0.03910728572266642, 0.9721741644763685
+normDesire, normSleepQuality, 4, 0.03919352657097985, 0.9721305368139393
+normDesire, MenstruationNumber, 2, 0.00025365769743490585, 0.3486859151802862
+normDesire, MenstruationNumber, 3, 0.001084296589686895, 0.34854103229587113
+normDesire, MenstruationNumber, 4, 0.001167671735395226, 0.34852648639092143
+normIrritability, normSleepHours, 2, 0.0054773031348056556, 0.9758910701062076
+normIrritability, normSleepHours, 3, 0.005760770582335373, 0.9757519817442735
+normIrritability, normSleepHours, 4, 0.00604160923489816, 0.9756141636933635
+normIrritability, normSleepQuality, 2, 0.0571290005694004, 0.9630143625256148
+normIrritability, normSleepQuality, 3, 0.06372152915693075, 0.9596417716991388
+normIrritability, normSleepQuality, 4, 0.06372236804314457, 0.9596413417894175
+normIrritability, MenstruationNumber, 2, 3.478074077056803e-05, 0.34872408242930736
+normIrritability, MenstruationNumber, 3, 0.00021136235215735155, 0.3486932908687858
+normIrritability, MenstruationNumber, 4, 0.00045263232822978505, 0.34865121482644773
+normSleepHours, normSleepQuality, 2, 0.11537381813541336, 0.9327956662582828
+normSleepHours, normSleepQuality, 3, 0.1264879229963617, 0.9269175012315237
+normSleepHours, normSleepQuality, 4, 0.12825670781561405, 0.9259785626300854
+normSleepHours, MenstruationNumber, 2, 0.00028226050221602517, 0.3486809271817931
+normSleepHours, MenstruationNumber, 3, 0.0003063947730116423, 0.3486767183884638
+normSleepHours, MenstruationNumber, 4, 0.00036532726929028314, 0.3486664408933668
+normSleepQuality, MenstruationNumber, 2, 0.00028132986323747833, 0.3486810894755954
+normSleepQuality, MenstruationNumber, 3, 0.00028142151526955317, 0.3486810734924333
+normSleepQuality, MenstruationNumber, 4, 0.00032000171402246647, 0.34867434544156367