feature_names = get_feature_names(linear_feature_columns +
dnn_feature_columns)
# 3.generate input data for model
# train, test = train_test_split(data, test_size=0.2)
train = data
train_model_input = {name: train[name] for name in feature_names}
test_model_input = {name: test[name] for name in feature_names}
# 4.Define Model,train,predict and evaluate
model = FLEN(linear_feature_columns,
dnn_feature_columns,
task='binary',
dnn_dropout=dropout,
dnn_use_bn=True)
model.compile(optimizer, "binary_crossentropy", metrics=METRICS)
log_dir = prefix_dir + 'flen_' + data_type + '_' + str(epochs)
if not os.path.exists(log_dir): # 如果路径不存在
os.makedirs(log_dir)
logs = tf.keras.callbacks.TensorBoard(log_dir=log_dir, histogram_freq=1)
history = model.fit(train_model_input,
train[target].values,
batch_size=256,
epochs=epochs,
verbose=2,
validation_split=0.2,
callbacks=[logs])
pred_ans = model.predict(test_model_input, batch_size=256)
linear_feature_columns = fixlen_feature_columns
feature_names = get_feature_names(linear_feature_columns +
dnn_feature_columns)
# 3.generate input data for model
train, test = train_test_split(data, test_size=0.2)
train_model_input = {name: train[name] for name in feature_names}
test_model_input = {name: test[name] for name in feature_names}
# 4.Define Model,train,predict and evaluate
model = FLEN(linear_feature_columns, dnn_feature_columns, task='binary')
model.compile(
"adam",
"binary_crossentropy",
metrics=['binary_crossentropy'],
)
history = model.fit(
train_model_input,
train[target].values,
batch_size=256,
epochs=10,
verbose=2,
validation_split=0.2,
)
pred_ans = model.predict(test_model_input, batch_size=256)
print("test LogLoss", round(log_loss(test[target].values, pred_ans), 4))
print("test AUC", round(roc_auc_score(test[target].values, pred_ans), 4))