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

5 years ago · 93db9a57da
--- a/data_exploration/wellness_cluster_test.py
+++ b/data_exploration/wellness_cluster_test.py
@ -0,0 +1,25 @@
 import sklearn.cluster as cluster
 import pandas as pd
 from matplotlib import pyplot as plt


 def find_kmeans(mat, k, first, second):
    km = cluster.KMeans(n_clusters=k)
    km.fit(mat)

    # Plot sse against k
    plt.figure(figsize=(6, 6))
    plt.xlabel('Metric: ' + first)
    plt.ylabel('Metric: ' + second)
    plt.scatter(mat[:, 0], mat[:, 1], c=km.labels_, cmap='rainbow')
    plt.show()


 # Read csv in
 df = pd.read_csv('../data_preparation/cleaned/time_series_normalized_wellness_menstruation.csv')

 # Specify what things you want
 df = df[["normFatigue", "normSleepQuality"]]

 # values, num clusters, axis labelsg
 find_kmeans(df.values, 2, "normFatigue", "normSleepQuality")
--- a/data_preparation/cleaned/expSmoothWorkAndFatigueData.csv
+++ b/data_preparation/cleaned/expSmoothWorkAndFatigueData.csv
@ -1,4 +1,4 @@
 "","day","totalWork","averageWorkLoad","smoothedWork","smoothedFatigueData"
 "","TimeSinceAugFirst","totalWork","averageWorkLoad","smoothedWork","smoothedFatigueData"
 "1",0,4855,255.526315789474,4855,0.734457489003587
 "2",1,1380,138,5921.8864123285,1.17226558337237
 "3",2,6030,231.923076923077,11569.9661032971,1.37713723445689
--- a/data_preparation/cleaned/time_series_normalized_wellness_menstruation.csv
+++ b/data_preparation/cleaned/time_series_normalized_wellness_menstruation.csv
--- a/data_preparation/cleaned/time_series_notnormalized_with_0Nan_rpe.csv
+++ b/data_preparation/cleaned/time_series_notnormalized_with_0Nan_rpe.csv
@ -36,8 +36,8 @@
 34,34,34,2018-07-17,4,1,Skills,60.0,5.0,300.0,300.0,107.1,309.11,0.35,7.0,8.0,,0,0,1,0,0,0,0,0,0,0,0,1,350
 35,35,35,2018-07-17,5,1,Skills,60.0,5.0,300.0,300.0,42.9,100.71,0.43,9.0,9.0,,0,0,1,0,0,0,0,0,0,0,0,1,350
 36,36,36,2018-07-17,6,1,Speed,30.0,3.0,90.0,370.0,52.9,333.5,0.16,0.0,0.0,,0,0,0,0,0,0,1,0,0,0,0,1,350
 37,37,37,2018-07-17,6,1,Conditioning,35.0,8.0,280.0,0.0,0.0,0.0,0.0,0.0,0.0,,0,0,0,1,0,0,0,0,0,0,0,1,350
 38,38,38,2018-07-17,7,1,Skills,75.0,6.0,450.0,450.0,205.7,401.79,0.51,0.0,0.0,,0,0,1,0,0,0,0,0,0,0,0,1,350
 37,37,37,2018-07-17,6,1,Conditioning,35.0,8.0,280.0,0.0,0.0,0.0,0.0,0.0,0.0,,0,0,0,1,0,0,0,0,0,0,0,1,350
 39,39,39,2018-07-17,10,1,Skills,60.0,4.0,240.0,240.0,79.3,298.57,0.27,0.0,0.0,,0,0,1,0,0,0,0,0,0,0,0,1,350
 40,40,40,2018-07-17,11,1,Skills,90.0,5.0,450.0,450.0,210.0,391.36,0.54,9.0,9.0,Absolutely,0,0,1,0,0,0,0,0,0,1,0,0,350
 41,41,41,2018-07-17,13,1,Skills,90.0,6.0,540.0,540.0,268.6,309.25,0.87,0.0,0.0,Not at all,0,0,1,0,0,0,0,0,1,0,0,0,350
--- a/data_preparation/time_series.py
+++ b/data_preparation/time_series.py
@ -30,4 +30,4 @@ def normalize_time_series(path, filename, start):


 start = start_end_times("data/rpe.csv")
 normalize_time_series("data/games_ranked.csv", "games_ranked.csv", start)
 normalize_time_series("cleaned/normalizedWellness.csv", "normalizedWellness.csv", start)
--- a/findings/data_plot.py
+++ b/findings/data_plot.py
@ -0,0 +1,13 @@
 from matplotlib import pyplot as plt
 import pandas as pd


 def plot_xy(x, y):
    plt.scatter(x, y)
    plt.xlabel(x.name)
    plt.ylabel(y.name)
    plt.show()


 wellness = pd.read_csv('../data_preparation/data/wellness.csv')
 plot_xy(wellness['Fatigue'], wellness['SleepHours'])
--- a/findings/r2correlation.txt
+++ b/findings/r2correlation.txt
--- a/hypotheses_modeling/21DaySlidingWorkAverage.csv
+++ b/hypotheses_modeling/21DaySlidingWorkAverage.csv
@ -0,0 +1,336 @@
 "","TimeSinceAugFirst","slidingWorkAverage"
 "1",20,5563.95
 "2",21,5895.66666666667
 "3",22,6307.42857142857
 "4",23,6331.71428571429
 "5",24,6458.52380952381
 "6",25,6752.33333333333
 "7",26,6767.33333333333
 "8",27,6766.61904761905
 "9",28,6738.42857142857
 "10",29,6798.66666666667
 "11",30,6811.38095238095
 "12",31,6813.7619047619
 "13",32,6881.85714285714
 "14",33,6840.42857142857
 "15",34,6834.71428571429
 "16",35,6788.47619047619
 "17",36,6711.09523809524
 "18",37,6720.61904761905
 "19",38,6781.33333333333
 "20",39,6495.04761904762
 "21",40,6617.90476190476
 "22",41,6578.85714285714
 "23",42,6122.66666666667
 "24",43,5613.04761904762
 "25",44,5671
 "26",45,5383.2380952381
 "27",46,4878.52380952381
 "28",47,4872.90476190476
 "29",48,4874.33333333333
 "30",49,4910.85714285714
 "31",50,4796.80952380952
 "32",51,4867.42857142857
 "33",52,5067.90476190476
 "34",53,5234.04761904762
 "35",54,5216.19047619048
 "36",55,5235.47619047619
 "37",56,5313.09523809524
 "38",57,5416.90476190476
 "39",58,5454.90476190476
 "40",59,5578.47619047619
 "41",60,5850.80952380952
 "42",61,5744.38095238095
 "43",62,5768.66666666667
 "44",63,6210.71428571429
 "45",64,6592.95238095238
 "46",65,6613.90476190476
 "47",66,6986.7619047619
 "48",67,7557.09523809524
 "49",68,7567.71428571429
 "50",69,7583.42857142857
 "51",70,7640.33333333333
 "52",71,7712.38095238095
 "53",72,7741.19047619048
 "54",73,7612.85714285714
 "55",74,7466
 "56",75,7487.42857142857
 "57",76,7480.28571428571
 "58",77,7064.61904761905
 "59",78,6618.42857142857
 "60",79,6647.38095238095
 "61",80,6575.95238095238
 "62",81,5935.85714285714
 "63",82,6326.33333333333
 "64",83,7005.38095238095
 "65",84,6509.52380952381
 "66",85,6314.66666666667
 "67",86,6331
 "68",87,5901.95238095238
 "69",88,5370.85714285714
 "70",89,5633.80952380952
 "71",90,5935.52380952381
 "72",91,5317.66666666667
 "73",92,4865.38095238095
 "74",93,4682.7619047619
 "75",94,4640.61904761905
 "76",95,4585.61904761905
 "77",96,4604.66666666667
 "78",97,4592.52380952381
 "79",98,5018.95238095238
 "80",99,5509.19047619048
 "81",100,5545.38095238095
 "82",101,5570.52380952381
 "83",102,6642.42857142857
 "84",103,6281.95238095238
 "85",104,5579.19047619048
 "86",105,6177.7619047619
 "87",106,6478.2380952381
 "88",107,6441.33333333333
 "89",108,7018.95238095238
 "90",109,7771.09523809524
 "91",110,7487.42857142857
 "92",111,7168.57142857143
 "93",112,7570.95238095238
 "94",113,7856.38095238095
 "95",114,7973.7619047619
 "96",115,7617.33333333333
 "97",116,7176.85714285714
 "98",117,7260.66666666667
 "99",118,7479.2380952381
 "100",119,7162.33333333333
 "101",120,6722.57142857143
 "102",121,6734.71428571429
 "103",122,6630
 "104",123,6050.57142857143
 "105",124,6004.14285714286
 "106",125,6003.57142857143
 "107",126,5477.38095238095
 "108",127,4982.38095238095
 "109",128,4995.71428571429
 "110",129,4822.14285714286
 "111",130,4590
 "112",131,4634.28571428571
 "113",132,4634.28571428571
 "114",133,4787.61904761905
 "115",134,4950.19047619048
 "116",135,5018.52380952381
 "117",136,5628.90476190476
 "118",137,6380.04761904762
 "119",138,6255.7619047619
 "120",139,6037.19047619048
 "121",140,6435.90476190476
 "122",141,6408.04761904762
 "123",142,6788.90476190476
 "124",143,6869.19047619048
 "125",144,6356.95238095238
 "126",145,6463.14285714286
 "127",146,6653.61904761905
 "128",147,6511.71428571429
 "129",148,6512.95238095238
 "130",149,6397.71428571429
 "131",150,6617.2380952381
 "132",151,6094.85714285714
 "133",152,6766.28571428571
 "134",153,6873.19047619048
 "135",154,6273.19047619048
 "136",155,6500.61904761905
 "137",156,6401.80952380952
 "138",157,6452.2380952381
 "139",158,6449.42857142857
 "140",159,6518
 "141",160,6518
 "142",161,6399.7619047619
 "143",162,6653.19047619048
 "144",163,6260.19047619048
 "145",164,6179.2380952381
 "146",165,6804.2380952381
 "147",166,6751.14285714286
 "148",167,6560.66666666667
 "149",168,6990.90476190476
 "150",169,6975.14285714286
 "151",170,6970.14285714286
 "152",171,6734.80952380952
 "153",172,6583.04761904762
 "154",173,6174.2380952381
 "155",174,6067.33333333333
 "156",175,6419.2380952381
 "157",176,6005.47619047619
 "158",177,5965.57142857143
 "159",178,5539.04761904762
 "160",179,5201.80952380952
 "161",180,5306
 "162",181,5357.33333333333
 "163",182,4840.19047619048
 "164",183,4516.04761904762
 "165",184,4437.38095238095
 "166",185,4148.19047619048
 "167",186,3595.90476190476
 "168",187,3589
 "169",188,3614.71428571429
 "170",189,3615.90476190476
 "171",190,4194.09523809524
 "172",191,4347.19047619048
 "173",192,4576.33333333333
 "174",193,5244.28571428571
 "175",194,4937.38095238095
 "176",195,4937.38095238095
 "177",196,5191.42857142857
 "178",197,5533.57142857143
 "179",198,5683.71428571429
 "180",199,5955.38095238095
 "181",200,6318.57142857143
 "182",201,6214.85714285714
 "183",202,6167.80952380952
 "184",203,6524.47619047619
 "185",204,6826.14285714286
 "186",205,6846.95238095238
 "187",206,6975.66666666667
 "188",207,7325.80952380952
 "189",208,7488.04761904762
 "190",209,7584.71428571429
 "191",210,7458.04761904762
 "192",211,6931.52380952381
 "193",212,6847.33333333333
 "194",213,6665.90476190476
 "195",214,6637.09523809524
 "196",215,6637.09523809524
 "197",216,6637.09523809524
 "198",217,6707.80952380952
 "199",218,6657.04761904762
 "200",219,6630.80952380952
 "201",220,6465.09523809524
 "202",221,5746.7619047619
 "203",222,5677.71428571429
 "204",223,5673.42857142857
 "205",224,6052.2380952381
 "206",225,6061.28571428571
 "207",226,6100.90476190476
 "208",227,6407.80952380952
 "209",228,6582.80952380952
 "210",229,6400.09523809524
 "211",230,6277.71428571429
 "212",231,5974.61904761905
 "213",232,6039.85714285714
 "214",233,6138.61904761905
 "215",234,5793.95238095238
 "216",235,5185.61904761905
 "217",236,5185.61904761905
 "218",237,5185.61904761905
 "219",238,5011.33333333333
 "220",239,4762.33333333333
 "221",240,4749.28571428571
 "222",241,4999.7619047619
 "223",242,5391.90476190476
 "224",243,5391.90476190476
 "225",244,5391.90476190476
 "226",245,5236.42857142857
 "227",246,5204.09523809524
 "228",247,5067.57142857143
 "229",248,4865.90476190476
 "230",249,4221.85714285714
 "231",250,4196.14285714286
 "232",251,4287.33333333333
 "233",252,4549.61904761905
 "234",253,4529.61904761905
 "235",254,4321.95238095238
 "236",255,4376.2380952381
 "237",256,4534.95238095238
 "238",257,4642.28571428571
 "239",258,4867.95238095238
 "240",259,4410.66666666667
 "241",260,4181.7619047619
 "242",261,4132
 "243",262,3547.95238095238
 "244",263,3165.57142857143
 "245",264,3537.19047619048
 "246",265,3752.71428571429
 "247",266,3212
 "248",267,3017.04761904762
 "249",268,3013.47619047619
 "250",269,2987.04761904762
 "251",270,3462.28571428571
 "252",271,3469.42857142857
 "253",272,3391.09523809524
 "254",273,3847.14285714286
 "255",274,4045.71428571429
 "256",275,4249.85714285714
 "257",276,4280.47619047619
 "258",277,4291.42857142857
 "259",278,4184.09523809524
 "260",279,3958.42857142857
 "261",280,4075.47619047619
 "262",281,4352.66666666667
 "263",282,4394.80952380952
 "264",283,4441.95238095238
 "265",284,4476.2380952381
 "266",285,4435.66666666667
 "267",286,4468.14285714286
 "268",287,4414.09523809524
 "269",288,4349
 "270",289,4450.19047619048
 "271",290,4178.04761904762
 "272",291,3862.09523809524
 "273",292,3881.38095238095
 "274",293,3871.38095238095
 "275",294,3611.19047619048
 "276",295,3662.61904761905
 "277",296,3575.85714285714
 "278",297,3918.2380952381
 "279",298,4170.2380952381
 "280",299,4170.2380952381
 "281",300,4170.2380952381
 "282",301,4577.85714285714
 "283",302,4423.38095238095
 "284",303,4388.38095238095
 "285",304,4756.47619047619
 "286",305,4869.19047619048
 "287",306,4538.14285714286
 "288",307,4290.14285714286
 "289",308,4433.2380952381
 "290",309,4762.28571428571
 "291",310,4642.71428571429
 "292",311,4739.61904761905
 "293",312,4890.19047619048
 "294",313,4977.90476190476
 "295",314,5076.2380952381
 "296",315,4817.2380952381
 "297",316,4391.52380952381
 "298",317,4344.14285714286
 "299",318,4162.71428571429
 "300",319,4213.19047619048
 "301",320,4247.85714285714
 "302",321,4270.42857142857
 "303",322,4225.42857142857
 "304",323,4455.19047619048
 "305",324,4327.80952380952
 "306",325,4272.80952380952
 "307",326,4688.19047619048
 "308",327,4688.19047619048
 "309",328,4688.19047619048
 "310",329,5210.80952380952
 "311",330,5324.14285714286
 "312",331,5318.71428571429
 "313",332,5487.85714285714
 "314",333,5625.85714285714
 "315",334,5602.42857142857
 "316",335,5535.52380952381
 "317",336,5745.47619047619
 "318",337,6030.2380952381
 "319",338,5963.57142857143
 "320",339,5825
 "321",340,5540.95238095238
 "322",341,5506.28571428571
 "323",342,5496.09523809524
 "324",343,5394.66666666667
 "325",344,5061.95238095238
 "326",345,5061.2380952381
 "327",346,4868.61904761905
 "328",347,4190.04761904762
 "329",348,4192.90476190476
 "330",349,4192.90476190476
 "331",350,3631.2380952381
 "332",351,3369.09523809524
 "333",352,3366.2380952381
 "334",353,3131.38095238095
 "335",354,2723.52380952381
--- a/hypotheses_modeling/KerasRegressions.py
+++ b/hypotheses_modeling/KerasRegressions.py
@ -0,0 +1,188 @@
 import tensorflow as tf
 import pandas as pd
 import numpy as np


 def time_series_sigmoid_classification(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, activation=tf.nn.softmax)
  ])
  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_classification(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, activation=tf.nn.softmax)
  ])
  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_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()
--- a/hypotheses_modeling/fatigue_total_sum.csv
+++ b/hypotheses_modeling/fatigue_total_sum.csv
@ -0,0 +1,355 @@
 TimeSinceAugFirst,fatigueSum
 0,0.734457489003587
 1,0.485175472200728
 2,0.280474592899874
 3,0.852899672028512
 4,0.067718127997734
 5,0.387261248267282
 6,0.466815138124766
 7,0.763731947890889
 8,0.685512083480377
 9,0.895108656027463
 10,-0.061861871122328
 11,0.296321907390904
 12,0.623117762114496
 13,0.753829250795893
 14,0.217870344211225
 15,0.53926849046086
 16,0.734843942472552
 17,0.308469121871186
 18,0.167041135359123
 19,0.746267880340515
 20,0.622788652776368
 21,0.214320156058007
 22,0.050827857843934
 23,0.294246790332209
 24,0.186808624194322
 25,0.552767197321023
 26,0.78454170658556
 27,0.779419550851109
 28,0.798357373731036
 29,0.323129040463109
 30,0.145143808515553
 31,0.68487764162657
 32,0.539874793771553
 33,0.36321009791783
 34,0.489148204465833
 35,0.413236542977807
 36,0.395011893731417
 37,0.156837050771386
 38,-0.285558218459401
 39,-0.349698539921412
 40,-0.558765836143965
 41,0.785941194779244
 42,0.260825136166886
 43,0.175173324395181
 44,0.548662507988438
 45,0.252321231106257
 46,0.742763716938104
 47,0.529872511137736
 48,0.37042402851138
 49,0.162733394153363
 50,0.357107946620677
 51,0.012983087373205
 52,-0.038997965254495
 53,0.241085179931302
 54,0.27305103057282
 55,0.501283454971351
 56,0.352131554149897
 57,0.510308182531921
 58,0.408416961411701
 59,-0.38225962517156
 60,0.111784933841739
 61,0.610578265741467
 62,0.563836579606691
 63,0.387038159139884
 64,0.17691474265164
 65,-0.158440974403251
 66,-0.127808846886789
 67,0.16767510337051
 68,0.232412554117885
 69,-0.034039586741236
 70,0.369219132420847
 71,0.055166081100634
 72,-0.15914007575716
 73,-0.143815705049808
 74,0.309931292450968
 75,0.481718700637843
 76,0.542695985663472
 77,-0.592609862606928
 78,-0.087871760090222
 79,0.323133612277408
 80,0.145926738048549
 81,0.266068498675575
 82,0.112895006227449
 83,0.11774653805839
 84,0.289982558620813
 85,0.156268777724842
 86,0.336960194430492
 87,0.211568516622687
 88,0.405654888856629
 89,-0.080651094767532
 90,-0.989503212930113
 91,-0.618589483268202
 92,-0.106354633315225
 93,-0.036704167015262
 94,-0.199061758628498
 95,-0.165391404949047
 96,0.465559713151923
 97,0.553712364147757
 98,0.10718598664192
 99,-0.176520319237606
 100,-0.012471746839114
 101,0.009238546030446
 102,0.031210965670768
 103,0.306981488185374
 104,0.326512806301329
 105,0.389789945787445
 106,0.163338392510265
 107,0.43041006311016
 108,0.064529621280754
 109,-0.056642839331862
 110,0.360810616073057
 111,0.674486235636005
 112,0.203177618350165
 113,0.016482187327924
 114,0.645937951499796
 115,-0.635636762766677
 116,0.054267298726349
 117,0.197678247905769
 118,-0.037744729883124
 119,0.510184386241254
 120,0.456725618316876
 121,0.36942720222611
 122,-0.305694272607688
 123,-1.09191169102099
 124,-0.726910533417431
 125,-0.43884728739089
 126,0.029939288546349
 127,-0.061371102729405
 128,-0.245528132438078
 129,0.009470765956943
 130,-0.341784370603988
 131,-0.049919365357729
 132,0.097143172058972
 133,-0.011342193521127
 134,0.080421703207904
 135,-0.129004417719117
 136,-0.270859696160466
 137,-0.708904646451948
 138,-0.229009026264089
 139,-0.181424438959781
 140,-0.026564683920245
 141,0.219065484118407
 142,-0.530439085926495
 143,-0.739993065212586
 144,-0.078144247328314
 145,0.281806254987051
 146,0.106323312617401
 147,0.461051503524687
 148,-0.194960844877302
 149,-1.0323471479209
 150,-0.221708749633043
 151,-0.146094771209489
 152,-0.769845305708576
 153,-0.006930021908459
 154,-0.104647283728296
 155,-0.012381788872799
 156,-0.19121232166827
 157,-0.671529527201817
 158,-0.616394224498445
 159,-0.073943182938408
 160,0.057147640203543
 161,-0.346330630873381
 162,-0.08655944015928
 163,-0.408202837238968
 164,-1.28901633269902
 165,-1.06200969217439
 166,-0.239078707352407
 167,-0.069592861351456
 168,-0.47050097438462
 169,-1.02350760409975
 170,-0.382414735756562
 171,-0.091983676112389
 172,0.016194125135445
 173,0.208557925296051
 174,0.382631435594289
 175,0.054618860565352
 176,0.392539314443691
 177,0.407308177079325
 178,0.5361087576086
 179,-0.559118537823889
 180,-0.041279425806623
 181,-0.811977779328337
 182,-0.673110139192779
 183,-0.647190032646896
 184,-0.264055759125838
 185,0.2137206708926
 186,0.169532929678205
 187,0.572823128029248
 188,0.504138498108557
 189,-0.025148663593221
 190,0.243256165168842
 191,-0.028600242158836
 192,-0.470973085298726
 193,-0.404980167324132
 194,0.192687307444004
 195,0.249123463461409
 196,-0.094501395021819
 197,0.330171642369123
 198,0.303808916345168
 199,-0.225895188174485
 200,-0.337185144362268
 201,0.184560773992318
 202,0.105945063048639
 203,-0.268263490373093
 204,-0.630585558331497
 205,-0.458206840787744
 206,-0.498158052976791
 207,-0.029702307826457
 208,-0.067979765277485
 209,-0.656925656525055
 210,-0.457529274865099
 211,-0.271352185811345
 212,-1.11655632791675
 213,-0.611166931446556
 214,-0.610527376526797
 215,0.034382530133085
 216,-0.141318464945944
 217,0.004511261469066
 218,-0.164492395019851
 219,-0.056862211997474
 220,0.010261586762043
 221,0.101082024613018
 222,0.372300796539504
 223,-0.145874961700409
 224,0.060726106209981
 225,-0.371059412216481
 226,-0.370670092221636
 227,0.083119527458891
 228,-0.058338986929759
 229,0.3362958277405
 230,0.519265121699177
 231,0.169683826619216
 232,0.077486840441911
 233,-0.474364612134558
 234,-0.247702269140266
 235,-0.659595488129965
 236,0.262402593762269
 237,-0.277905669965979
 238,-0.073857678558781
 239,0.053602846962544
 240,-0.606205677585295
 241,-0.624053318548306
 242,-0.605867224210048
 243,-0.252954297674564
 244,-0.101338569851228
 245,0.133299355850543
 246,0.416469635541468
 247,-0.48865392999333
 248,0.145411566109825
 250,-0.727338523179393
 251,0.124104120321982
 252,0.276748683294634
 253,0.793381770905604
 254,0.643063414197272
 255,1.04989185847975
 256,0.164337667404437
 257,0.158175420900341
 258,-0.376784412957032
 259,-1.13446825563484
 260,-0.682110266582935
 261,0.03890579636218
 262,0.250705347616431
 263,0.63083548881295
 264,-0.381185476545982
 265,-2.09473205252048
 266,-1.08423548600842
 267,-1.00435109992827
 268,-0.96922353115861
 269,-0.845113477539493
 270,-0.542326267460438
 271,-0.154289023678556
 272,-0.47818347594847
 273,-0.306186227227698
 274,0.130165587788887
 275,-0.534607431666707
 276,-0.024108562029165
 277,0.441356603857835
 278,0.835974252393425
 279,0.504743612581526
 280,0.608084130261808
 281,0.354286698358717
 282,0.149098455139156
 283,0.362866649040982
 284,0.585107099551978
 285,-0.238849557858286
 286,-1.29316205044401
 287,-0.514971003845922
 288,-0.130605271784348
 289,0.054601023159174
 290,0.712654053152515
 291,0.345411091599797
 292,0.590827647093801
 293,0.226175565336716
 294,0.066456432118622
 295,-0.244109627769699
 296,-0.668607818640876
 297,-0.892753779097629
 298,-0.864450623997139
 299,-0.052629105168991
 300,0.097879540271865
 301,0.068861223343318
 302,0.201303180551096
 303,-0.343311264954187
 304,-0.149597988654366
 305,0.1591975667215
 306,-0.128030046827757
 307,-0.881761347390814
 308,0.110911445153907
 309,-0.059481544970226
 310,0.248261046579106
 311,0.217829171777561
 312,-0.168769117743194
 313,-0.734302536254684
 314,-1.23366692589506
 315,-0.425009478665031
 316,-0.236956665438271
 317,-0.135287941133465
 318,-0.214676104364952
 319,-0.246512442890127
 320,0.020016985976053
 321,-0.561102012471304
 322,-0.258337553328078
 323,-0.360201383670261
 324,-0.676758179307032
 325,-1.22326716932596
 326,-0.552498077877283
 327,-0.05938292421172
 328,-0.230174146084735
 329,-0.178125732975686
 330,-0.782218150988738
 331,-0.902771605320945
 332,-0.83417758585907
 333,-0.623742294718358
 334,0.029100211618237
 335,-0.276998463243979
 336,-0.495616972912957
 337,-0.16842928848014
 338,-0.215205592767
 339,-0.400929404850442
 340,0.001421286489176
 341,0.247646162510804
 342,-0.019832667817069
 343,0.41449646066539
 344,0.305217583351337
 345,0.260375893221019
 346,0.643585606257478
 347,0.587502564497385
 348,0.933368991653645
 349,0.562934043178896
 350,0.582213233197938
 351,0.550560856980579
 352,0.598280595137412
 353,0.739698209165581
 354,0.066689402177346
--- a/hypotheses_modeling/hypotheses.txt
+++ b/hypotheses_modeling/hypotheses.txt
@ -0,0 +1,28 @@
 Team:
    1.
    x - normFatigue, TimeSince
    y - normSoreness
    r2 - 0.16830803694995466

    2.
    x - normFatigue, TimeSince
    y - normDesire
    r2 - 0.1722466278587138

    3.
    x - normFatigue, TimeSince
    y - normIrritability
    r2 - 0.09563459728506452

    4.
    x - normSleepHours, TimeSince
    y - normSleepQualiyt
    r2 - 0.09717095676693188

    5.

 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
--- a/hypotheses_modeling/slidingWorkAverageSevenDay.csv
+++ b/hypotheses_modeling/slidingWorkAverageSevenDay.csv
@ -0,0 +1,350 @@
 "","TimeSinceAugFirst","slidingWorkAverage"
 "1",6,3340
 "2",7,4662.14285714286
 "3",8,5407.85714285714
 "4",9,5460.71428571429
 "5",10,5780.71428571429
 "6",11,6050
 "7",12,6225.71428571429
 "8",13,6240.71428571429
 "9",14,6057.14285714286
 "10",15,6055.71428571429
 "11",16,6022.71428571429
 "12",17,6087
 "13",18,6871.28571428571
 "14",19,6693.42857142857
 "15",20,6793.42857142857
 "16",21,6967.71428571429
 "17",22,7458.71428571429
 "18",23,7511.71428571429
 "19",24,7507.85714285714
 "20",25,7335.71428571429
 "21",26,7382.85714285714
 "22",27,7265.71428571429
 "23",28,7190.42857142857
 "24",29,6881.57142857143
 "25",30,6899.71428571429
 "26",31,6846.42857142857
 "27",32,6438.57142857143
 "28",33,6445
 "29",34,6445
 "30",35,6207.28571428571
 "31",36,5793
 "32",37,5750.42857142857
 "33",38,5989.71428571429
 "34",39,5710.85714285714
 "35",40,6025.85714285714
 "36",41,6025.85714285714
 "37",42,4970.28571428571
 "38",43,4164.57142857143
 "39",44,4362.85714285714
 "40",45,3313.57142857143
 "41",46,2486.14285714286
 "42",47,2147.85714285714
 "43",48,2152.14285714286
 "44",49,3555
 "45",50,4432.85714285714
 "46",51,4489
 "47",52,5900.42857142857
 "48",53,7505.14285714286
 "49",54,7474.85714285714
 "50",55,7528.42857142857
 "51",56,7414
 "52",57,7653.28571428571
 "53",58,7512.85714285714
 "54",59,7521.42857142857
 "55",60,7561.14285714286
 "56",61,7610.42857142857
 "57",62,7625.42857142857
 "58",63,7663.14285714286
 "59",64,7692.71428571429
 "60",65,7839.85714285714
 "61",66,7538.42857142857
 "62",67,7605
 "63",68,7617.85714285714
 "64",69,7596.42857142857
 "65",70,7843.85714285714
 "66",71,7791.14285714286
 "67",72,7870.85714285714
 "68",73,7778.71428571429
 "69",74,7231.85714285714
 "70",75,7234
 "71",76,7219
 "72",77,5686.85714285714
 "73",78,4371.42857142857
 "74",79,4231.42857142857
 "75",80,4410.71428571429
 "76",81,2970.71428571429
 "77",82,4127.14285714286
 "78",83,6200.71428571429
 "79",84,5997.85714285714
 "80",85,6781.42857142857
 "81",86,6890.71428571429
 "82",87,5516.42857142857
 "83",88,5910
 "84",89,5540.28571428571
 "85",90,4386.85714285714
 "86",91,4268.28571428571
 "87",92,3443.28571428571
 "88",93,2926.14285714286
 "89",94,3994.71428571429
 "90",95,4876.14285714286
 "91",96,4146.57142857143
 "92",97,3190
 "93",98,4790.71428571429
 "94",99,6302.85714285714
 "95",100,6819.28571428571
 "96",101,7200.42857142857
 "97",102,9141.14285714286
 "98",103,9159
 "99",104,9160.71428571429
 "100",105,9474.28571428571
 "101",106,9688.57142857143
 "102",107,9578.57142857143
 "103",108,9861.71428571429
 "104",109,9296
 "105",110,9156.71428571429
 "106",111,9155
 "107",112,8447.85714285714
 "108",113,7577.71428571429
 "109",114,7523.42857142857
 "110",115,5789.85714285714
 "111",116,3093.42857142857
 "112",117,3466.28571428571
 "113",118,4122
 "114",119,3564.85714285714
 "115",120,2901.42857142857
 "116",121,3102.14285714286
 "117",122,4238.42857142857
 "118",123,5762.28571428571
 "119",124,5389.42857142857
 "120",125,4733.71428571429
 "121",126,4419.42857142857
 "122",127,4468
 "123",128,4361.57142857143
 "124",129,4438.14285714286
 "125",130,4914.28571428571
 "126",131,5047.14285714286
 "127",132,5047.14285714286
 "128",133,6378.57142857143
 "129",134,7481.14285714286
 "130",135,7591.85714285714
 "131",136,8210.14285714286
 "132",137,8463.57142857143
 "133",138,8330.71428571429
 "134",139,8330.71428571429
 "135",140,8509.71428571429
 "136",141,7275
 "137",142,8413.28571428571
 "138",143,7959.28571428571
 "139",144,5693
 "140",145,6011.57142857143
 "141",146,6583
 "142",147,4646.85714285714
 "143",148,4782.71428571429
 "144",149,3188
 "145",150,3682.28571428571
 "146",151,4128
 "147",152,5956.57142857143
 "148",153,5705.85714285714
 "149",154,5663
 "150",155,7444.14285714286
 "151",156,7604.14285714286
 "152",157,7715.14285714286
 "153",158,9527.28571428571
 "154",159,7585.85714285714
 "155",160,7265.14285714286
 "156",161,8889.42857142857
 "157",162,7732.71428571429
 "158",163,7988.42857142857
 "159",164,7140.28571428571
 "160",165,6757.42857142857
 "161",166,6711
 "162",167,6711
 "163",168,6420.28571428571
 "164",169,5748.57142857143
 "165",170,5317.85714285714
 "166",171,5349
 "167",172,3464.42857142857
 "168",173,4225.85714285714
 "169",174,4225.85714285714
 "170",175,3948
 "171",176,4535.14285714286
 "172",177,4590.42857142857
 "173",178,4127.85714285714
 "174",179,5383.57142857143
 "175",180,4981.14285714286
 "176",181,5135.14285714286
 "177",182,4152.28571428571
 "178",183,3264.42857142857
 "179",184,3403.85714285714
 "180",185,2967.71428571429
 "181",186,1939.71428571429
 "182",187,1560
 "183",188,1483.14285714286
 "184",189,2747.42857142857
 "185",190,4782.71428571429
 "186",191,5047.28571428571
 "187",192,6633.42857142857
 "188",193,8409.57142857143
 "189",194,8271
 "190",195,8193.85714285714
 "191",196,8674.57142857143
 "192",197,8553.57142857143
 "193",198,8600
 "194",199,8265
 "195",200,8606.42857142857
 "196",201,8813.57142857143
 "197",202,8826.42857142857
 "198",203,8151.42857142857
 "199",204,7142.14285714286
 "200",205,6893.57142857143
 "201",206,6028.57142857143
 "202",207,4961.42857142857
 "203",208,5379.57142857143
 "204",209,5733.85714285714
 "205",210,5548.14285714286
 "206",211,5098.85714285714
 "207",212,5048.42857142857
 "208",213,5704.14285714286
 "209",214,6343.42857142857
 "210",215,5718.14285714286
 "211",216,5351
 "212",217,6423.85714285714
 "213",218,7730.14285714286
 "214",219,7950.42857142857
 "215",220,7662.57142857143
 "216",221,5935.42857142857
 "217",222,5935.42857142857
 "218",223,5935.42857142857
 "219",224,6184.71428571429
 "220",225,5354.85714285714
 "221",226,5303.85714285714
 "222",227,5856.71428571429
 "223",228,7469.57142857143
 "224",229,7546.71428571429
 "225",230,7546.71428571429
 "226",231,5315.28571428571
 "227",232,5034.57142857143
 "228",233,5161.57142857143
 "229",234,3862.57142857143
 "230",235,2151.85714285714
 "231",236,2074.71428571429
 "232",237,2074.71428571429
 "233",238,3534
 "234",239,3897.57142857143
 "235",240,3782.42857142857
 "236",241,5280
 "237",242,6554.28571428571
 "238",243,6554.28571428571
 "239",244,6554.28571428571
 "240",245,6860
 "241",246,6680.14285714286
 "242",247,6258.71428571429
 "243",248,5455.14285714286
 "244",249,3959.42857142857
 "245",250,3959.42857142857
 "246",251,4233
 "247",252,3254.85714285714
 "248",253,3011.14285714286
 "249",254,2924.71428571429
 "250",255,2393.57142857143
 "251",256,3091.14285714286
 "252",257,3413.14285714286
 "253",258,3816.57142857143
 "254",259,3117.14285714286
 "255",260,2854
 "256",261,3212.57142857143
 "257",262,2795.14285714286
 "258",263,2446.14285714286
 "259",264,3239
 "260",265,3208.57142857143
 "261",266,3264
 "262",267,3186
 "263",268,2903.14285714286
 "264",269,3772.42857142857
 "265",270,4849.57142857143
 "266",271,3756.14285714286
 "267",272,3148.14285714286
 "268",273,5160.28571428571
 "269",274,6097.14285714286
 "270",275,6633.85714285714
 "271",276,6273.85714285714
 "272",277,5578.57142857143
 "273",278,5557.14285714286
 "274",279,5518.57142857143
 "275",280,3802.14285714286
 "276",281,3774.85714285714
 "277",282,3647.42857142857
 "278",283,3279.57142857143
 "279",284,3000.57142857143
 "280",285,3993.71428571429
 "281",286,4737.71428571429
 "282",287,4279.85714285714
 "283",288,3175
 "284",289,3069.28571428571
 "285",290,2980.71428571429
 "286",291,3007.14285714286
 "287",292,2093.28571428571
 "288",293,1357.85714285714
 "289",294,2751.57142857143
 "290",295,4038
 "291",296,4010.85714285714
 "292",297,5494.42857142857
 "293",298,6503
 "294",299,6423.71428571429
 "295",300,6415.14285714286
 "296",301,6702.14285714286
 "297",302,6057.14285714286
 "298",303,6085
 "299",304,5794.28571428571
 "300",305,5097.42857142857
 "301",306,5097.42857142857
 "302",307,5097.42857142857
 "303",308,3846
 "304",309,4191.71428571429
 "305",310,3832.28571428571
 "306",311,2930.14285714286
 "307",312,3070.14285714286
 "308",313,3412.57142857143
 "309",314,3716.14285714286
 "310",315,3903.57142857143
 "311",316,2925.71428571429
 "312",317,3115.14285714286
 "313",318,3763.71428571429
 "314",319,4472
 "315",320,4233.57142857143
 "316",321,3997.71428571429
 "317",322,4926.71428571429
 "318",323,6248.14285714286
 "319",324,6036
 "320",325,6124.57142857143
 "321",326,6522.42857142857
 "322",327,6418.42857142857
 "323",328,6350.71428571429
 "324",329,6802.14285714286
 "325",330,6798.57142857143
 "326",331,6805
 "327",332,6575.28571428571
 "328",333,5883.14285714286
 "329",334,6155.28571428571
 "330",335,6258.14285714286
 "331",336,5507.57142857143
 "332",337,5044
 "333",338,5049.71428571429
 "334",339,4775.14285714286
 "335",340,4217.28571428571
 "336",341,3945.14285714286
 "337",342,3879.42857142857
 "338",343,3874.28571428571
 "339",344,3343.28571428571
 "340",345,3329
 "341",346,3255.42857142857
 "342",347,2469.71428571429
 "343",348,2478.28571428571
 "344",349,2441.14285714286
 "345",350,1511.85714285714
 "346",351,1720
 "347",352,1720
 "348",353,1363.57142857143
 "349",354,1483.57142857143
--- a/hypotheses_modeling/team_regressions.py
+++ b/hypotheses_modeling/team_regressions.py
@ -0,0 +1,61 @@
 from sklearn import linear_model
 import pandas as pd
 from sklearn.metrics import mean_squared_error, r2_score


 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):
  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 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))


  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())
  print(standard_lr(x, y))


 if __name__ == "__main__":
  main()
--- a/hypotheses_modeling/time_series_days_ranked.csv
+++ b/hypotheses_modeling/time_series_days_ranked.csv
@ -0,0 +1,18 @@
 ,TimeSinceAugFirst,DailyElo
 0,121,0.0
 1,122,-3.714599999999998
 2,178,0.04346000000000028
 3,179,2.1916710000000013
 4,180,0.0
 5,255,0.0
 6,256,0.0
 7,257,-2.520374784999996
 8,263,-2.0880156214999985
 9,264,-1.7032140593500005
 10,284,-0.6130256153877235
 11,285,2.620463284090865
 12,311,-2.076954630427971
 13,312,1.0960590427574828
 14,313,1.8954531384817344
 15,353,-0.2940921753664384
 16,354,-1.8646829578297937