def main():
hidden_unit = 64
batch_size = 32
learning_rate = 0.001
epochs = 50
with open('../Din/dataset/dataset.pkl', 'rb') as f:
train_set = np.array(pickle.load(f))
test_set = pickle.load(f)
cate_list = pickle.load(f)
user_count, item_count, cate_count, max_sl = pickle.load(f)
train_user, train_item, train_hist, train_sl, train_y = input_data(
train_set, max_sl)
# Tensorboard
current_time = datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
log_dir = 'logs/' + current_time
tensorboard = tf.keras.callbacks.TensorBoard(log_dir=log_dir,
histogram_freq=1,
write_graph=True,
write_grads=False,
write_images=True,
embeddings_freq=0,
embeddings_layer_names=None,
embeddings_metadata=None,
embeddings_data=None,
update_freq=500)
# model checkpoint
check_path = 'save/wide_deep_weights.epoch_{epoch:04d}.val_loss_{val_loss:.4f}.ckpt'
checkpoint = tf.keras.callbacks.ModelCheckpoint(check_path,
save_weights_only=True,
verbose=1,
period=1)
model = WideDeep(user_count, item_count, cate_count, cate_list,
hidden_unit)
model.summary()
optimizer = tf.keras.optimizers.Adam(learning_rate=learning_rate)
model.compile(loss=tf.keras.losses.binary_crossentropy,
optimizer=optimizer,
metrics=[tf.keras.metrics.AUC()])
model.fit([train_user, train_item, train_hist, train_sl],
train_y,
epochs=epochs,
batch_size=batch_size,
validation_split=0.1,
callbacks=[tensorboard, checkpoint])
model.compile(loss=tf.keras.losses.binary_crossentropy,
optimizer=tf.keras.optimizers.Adam(learning_rate=learning_rate),
metrics=METRICS)
# ---------早停法 -----
early_stopping = tf.keras.callbacks.EarlyStopping(monitor='val_auc',
verbose=1,
patience=10,
mode='max',
restore_best_weights=True)
model.fit(
train_X,
train_y,
epochs=epochs,
# callbacks=[early_stopping, checkpoint],
batch_size=batch_size,
validation_split=0.1,
validation_data=(val_X, val_y),
# class_weight={0:1, 1:3}, # 样本均衡
)
print('test AUC: %f' % model.evaluate(test_X, test_y)[1])
# ------------- model evaluation in test dataset ----
train_predictions_weighted = model.predict(train_X, batch_size=batch_size)
test_predictions_weighted = model.predict(test_X, batch_size=batch_size)
# ------------- confusion matrix
from sklearn.metrics import confusion_matrix, roc_curve
import matplotlib.pyplot as plt
test_size=test_size)
train_X, train_y = train
test_X, test_y = test
# ============================Build Model==========================
model = WideDeep(feature_columns,
hidden_units=hidden_units,
dnn_dropout=dnn_dropout)
model.summary()
# ============================model checkpoint======================
# check_path = '../save/wide_deep_weights.epoch_{epoch:04d}.val_loss_{val_loss:.4f}.ckpt'
# checkpoint = tf.keras.callbacks.ModelCheckpoint(check_path, save_weights_only=True,
# verbose=1, period=5)
# ============================Compile============================
model.compile(loss=binary_crossentropy,
optimizer=Adam(learning_rate=learning_rate),
metrics=[AUC()])
# ==============================Fit==============================
model.fit(
train_X,
train_y,
epochs=epochs,
callbacks=[
EarlyStopping(monitor='val_loss',
patience=1,
restore_best_weights=True)
], # checkpoint
batch_size=batch_size,
validation_split=0.1)
# ===========================Test==============================
print('test AUC: %f' % model.evaluate(test_X, test_y)[1])
input_mms = MinMaxScaler(feature_range=(0, 1))
deep_input_feats.iloc[:, [i]] = input_mms.fit_transform(
deep_input_feats.iloc[:, [i]])
deep_input.append(wide_features.values)
my_callbacks = [
EarlyStopping(monitor='loss',
min_delta=1e-5,
patience=3,
verbose=1,
mode='min')
]
model.fit(x=deep_input,
y=final_tags,
batch_size=64,
epochs=100,
verbose=1,
callbacks=my_callbacks)
pred = model.predict(deep_input, batch_size=2**14)
pred_real = target_mms.inverse_transform(pred)
s0, s1 = 0, 0
for i, x in enumerate(pred_real):
if pred[i] > 0:
s1 += 1
print(deep_features.iloc[i, 0], deep_features.iloc[i, -1],
final_tags[i], pred[i])
else:
s0 += 1
# ========================== Create dataset =======================
feature_columns, train, test = create_criteo_dataset(file=file,
embed_dim=embed_dim,
read_part=read_part,
sample_num=sample_num,
test_size=test_size)
train_X, train_y = train
test_X, test_y = test
# ============================Build Model==========================
model = WideDeep(feature_columns, hidden_units=hidden_units, dnn_dropout=dnn_dropout)
model.summary()
# ============================model checkpoint======================
# check_path = '../save/wide_deep_weights.epoch_{epoch:04d}.val_loss_{val_loss:.4f}.ckpt'
# checkpoint = tf.keras.callbacks.ModelCheckpoint(check_path, save_weights_only=True,
# verbose=1, period=5)
# ============================Compile============================
model.compile(loss=binary_crossentropy, optimizer=Adam(learning_rate=learning_rate),
metrics=[AUC()])
# ==============================Fit==============================
model.fit(
train_X,
train_y,
epochs=epochs,
# callbacks=[checkpoint],
batch_size=batch_size,
validation_split=0.1
)
# ===========================Test==============================
print('test AUC: %f' % model.evaluate(test_X, test_y)[1])