Keras 利用sklearn的ROC-AUC建立评价函数详解

# 利用sklearn自建评价函数
from sklearn.model_selection import train_test_split
from sklearn.metrics import roc_auc_score
from keras.callbacks import Callback

class RocAucEvaluation(Callback):
 def __init__(self, validation_data=(), interval=1):
 super(Callback, self).__init__()
 self.interval = interval
 self.x_val,self.y_val = validation_data
 def on_epoch_end(self, epoch, log={}):
 if epoch % self.interval == 0:
  y_pred = self.model.predict(self.x_val, verbose=0)
  score = roc_auc_score(self.y_val, y_pred)
  print('n ROC_AUC - epoch:%d - score:%.6f n' % (epoch+1, score))

x_train,y_train,x_label,y_label = train_test_split(train_feature, train_label, train_size=0.95, random_state=233)
RocAuc = RocAucEvaluation(validation_data=(y_train,y_label), interval=1)

hist = model.fit(x_train, x_label, batch_size=batch_size, epochs=epochs, validation_data=(y_train, y_label), callbacks=[RocAuc], verbose=2)

import tensorflow as tf
from sklearn.metrics import roc_auc_score

def auroc(y_true, y_pred):
 return tf.py_func(roc_auc_score, (y_true, y_pred), tf.double)
# Build Model...
model.compile(loss='categorical_crossentropy', optimizer='adam',metrics=['accuracy', auroc])

def auc(y_true, y_pred):
 auc = tf.metrics.auc(y_true, y_pred)[1]
 K.get_session().run(tf.local_variables_initializer())
 return auc

def create_model_nn(in_dim,layer_size=200):
 model = Sequential()
 model.add(Dense(layer_size,input_dim=in_dim, kernel_initializer='normal'))
 model.add(BatchNormalization())
 model.add(Activation('relu'))
 model.add(Dropout(0.3))
 for i in range(2):
 model.add(Dense(layer_size))
 model.add(BatchNormalization())
 model.add(Activation('relu'))
 model.add(Dropout(0.3))
 model.add(Dense(1, activation='sigmoid'))
 adam = optimizers.Adam(lr=0.01)
 model.compile(optimizer=adam,loss='binary_crossentropy',metrics = [auc]) 
 return model
####cv train
folds = StratifiedKFold(n_splits=5, shuffle=False, random_state=15)
oof = np.zeros(len(df_train))
predictions = np.zeros(len(df_test))
for fold_, (trn_idx, val_idx) in enumerate(folds.split(df_train.values, target2.values)):
 print("fold n°{}".format(fold_))
 X_train = df_train.iloc[trn_idx][features]
 y_train = target2.iloc[trn_idx]
 X_valid = df_train.iloc[val_idx][features]
 y_valid = target2.iloc[val_idx]
 model_nn = create_model_nn(X_train.shape[1])
 callback = EarlyStopping(monitor="val_auc", patience=50, verbose=0, mode='max')
 history = model_nn.fit(X_train, y_train, validation_data = (X_valid ,y_valid),epochs=1000,batch_size=64,verbose=0,callbacks=[callback])
 print('n Validation Max score : {}'.format(np.max(history.history['val_auc'])))
 predictions += model_nn.predict(df_test[features]).ravel()/folds.n_splits