发家致富靠AI：使用keras预测NBA比赛赚钱，回报率136%

  import os  
  import numpy as np  
  from tqdm import tqdm  
  from pymongo import MongoClient  
  bookies = {  
      "44":"Betfair",  
      "16":"bet365",  
      "18":"Pinnacle",  
      "5":"Unibet"  
  }  
  client = MongoClient()  
  db = client.nba  
  games = db.games  
    
  seasons = [f"002{str(i).zfill(2)}" for i in range(8, 20)]  
  # load the samples into memory  
  x, y = [], []  
  def normalize_sample(nparr):  
      for feature in range(nparr.shape[-1]): # iterate over the features  
          f = np.nan_to_num(nparr[:, :, feature])  
          nparr[:, :, feature] = (f-f.min())/(f.max()-f.min())  
      return nparr  
    
  for season in seasons:  
      for filename in tqdm(os.listdir(f"samples/{season}")[120:]):  
          if ".npy" in filename:  
              game = list(games.find({"GAME_ID":filename.strip(".npy"), "bet365":{"$exists":"True"}}))  
              if not game:  
                  continue  
              game = game[0]  
              closing_odds = 1/float(game["bet365"].split()[1].split("v")[0])  
              home_win = int(game["HOME"] == game["WINNER"])  
              sample = np.load(f"samples/{season}/{filename}")  
              x.append((normalize_sample(sample), closing_odds))  
              y.append(home_win)  
  x = np.array(x)  
  y = np.array(y)  
    
  import random  
  print(x.shape, y.shape)  
  diff = len(y)//2 - np.count_nonzero(y == 0)  
  for i in tqdm(range(diff)):  
      while True:  
              a = random.randint(1, len(y)-1)  
              if y[a] == 1:  
                  x = np.delete(x, a, 0)  
                  y = np.delete(y, a, 0)  
                  break  
  print(len(x), len(y))

from keras import backend as K  
from keras.models import Model  
from keras.models import Sequential  
from keras.layers import Input, Dense, Dropout, Conv2D, Flatten, Activation, concatenate  
from keras.optimizers import Adam  
  
c = 0.6  
def decorrelation_loss(neuron):  
    def loss(y_actual, y_predicted):  
          return K.mean(  
                  K.square(y_actual-y_predicted) - c * K.square(y_predicted - neuron))  
      return loss  
    
  # split the two input streams  
  box_scores_train, odds_train = map(list, zip(*x_train))  
  box_scores_test, odds_test = map(list, zip(*x_test))  
    
  # box model turns stats into a vector  
  box_model = Sequential()  
  shape = box_scores_train[0].shape  
  print(shape)  
  box_model.add(Conv2D(filters=32, kernel_size=(1, 8), input_shape=shape,  
                   data_format="channels_first", activation="relu"))  
  box_model.add(Flatten())  
    
  box_input = Input(shape=shape)  
  box_encoded = box_model(box_input)  
    
  odds_input = Input(shape=(1,), dtype="float32") #(opening or closing weight)  
  merged = concatenate([odds_input, box_encoded])  
  output = Dense(32, activation="relu")(merged)  
  output = Dropout(0.5)(output)  
  output = Dense(8, activation="relu")(output)  
  output = Dropout(0.5)(output)  
  signal = Dense(1, activation="sigmoid")(output)  
    
  opt = Adam(lr=0.0001)  
  nba_model = Model(inputs=[box_input, odds_input], outputs=signal)  
  print(nba_model.summary())  
    
  nba_model.compile(optimizer=opt,  
                    #loss="binary_crossentropy",  
                loss=decorrelation_loss(odds_input), # Call the loss function with the selected layer  
                metrics=['accuracy'])  
  nba_model.fit([box_scores_train, odds_train], y_train,  
                batch_size=16,validation_data=([box_scores_test, odds_test], y_test), verbose=1,epochs=20)