def build_model(features_dict, vocabularies):
model = DCN(
features_dict=features_dict,
vocabularies=vocabularies,
num_cross_layers=FLAGS.num_cross_layers,
num_deep_layers=FLAGS.num_deep_layers,
deep_layer_size=FLAGS.deep_layer_size,
model_structure=FLAGS.model_structure,
embedding_dim=FLAGS.embedding_dim,
projection_dim=FLAGS.projection_dim,
l2_penalty=FLAGS.l2_penalty,
)
return model
def main(learning_rate, epochs, hidden_units):
"""
feature_columns is a list and contains two dict：
- dense_features: {feat: dense_feature_name}
- sparse_features: {feat: sparse_feature_name, feat_num: the number of this feature,
embed_dim: the embedding dimension of this feature }
train_X: [dense_train_X, sparse_train_X]
test_X: [dense_test_X, sparse_test_X]
"""
feature_columns, train_X, test_X, train_y, test_y = create_dataset()
# ============================Build Model==========================
model = DCN(feature_columns, hidden_units)
model.summary()
# =============================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/dcn_weights.epoch_{epoch:04d}.val_loss_{val_loss:.4f}.ckpt'
checkpoint = tf.keras.callbacks.ModelCheckpoint(check_path, save_weights_only=True,
verbose=1, period=4)
# =========================Compile============================
model.compile(loss=binary_crossentropy, optimizer=Adam(learning_rate=learning_rate),
metrics=[AUC()])
# ===========================Fit==============================
model.fit(
train_X,
train_y,
epochs=epochs,
callbacks=[tensorboard, checkpoint],
batch_size=128,
validation_split=0.2
)
# ===========================Test==============================
print('test AUC: %f' % model.evaluate(test_X, test_y)[1])
dnn_dropout = 0.5
hidden_units = [256, 128, 64]
learning_rate = 0.001
batch_size = 4096
epochs = 10
# ========================== 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 = DCN(feature_columns, hidden_units, dnn_dropout=dnn_dropout)
model.summary()
# ============================model checkpoint======================
# check_path = 'save/dcn_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=[
def run_DCN():
dcn = DCN.DCN(field_size, feature_sizes, batch_size=32 * 8, verbose=True, use_cuda=True,
weight_decay=0.00002, use_inner_product=True, n_epochs=num_epoch)
if online = False:
dcn.fit(Xi_train, Xv_train, y_train, Xi_test, Xv_test, y_test, ealry_stopping=True,refit=True)
import tensorflow as tf
from tensorflow.keras import losses, optimizers
from sklearn.metrics import accuracy_score
if __name__ == '__main__':
file = 'E:\\PycharmProjects\\推荐算法\\data\\train.txt'
test_size = 0.4
hidden_units = [256, 128, 64]
feature_columns, (X_train, y_train), (X_test,
y_test) = create_criteo_dataset(
file, test_size=test_size)
model = DCN(feature_columns,
hidden_units,
1,
activation='relu',
layer_num=6)
optimizer = optimizers.SGD(0.01)
train_dataset = tf.data.Dataset.from_tensor_slices((X_train, y_train))
train_dataset = train_dataset.batch(32).prefetch(
tf.data.experimental.AUTOTUNE)
# model.compile(optimizer='sgd', loss='binary_crossentropy', metrics=['accuracy'])
# model.fit(train_dataset, epochs=100)
# logloss, auc = model.evaluate(X_test, y_test)
# print('logloss {}\nAUC {}'.format(round(logloss,2), round(auc,2)))
# model.summary()
summary_writer = tf.summary.create_file_writer(
dnn_dropout = 0.5
hidden_units = [256, 128, 64]
learning_rate = 0.001
batch_size = 512
epochs = 5
# ========================== 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 = DCN(feature_columns, hidden_units, dnn_dropout)
model.summary()
# ============================model checkpoint======================
# check_path = 'save/dcn_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=[tensorboard, checkpoint],
mean = data[feat].mean()
std = data[feat].std()
data[feat] = (data[feat] - mean) / (std + 1e-12)
# print(data.shape)
# print(data.head())
train, valid = train_test_split(data, test_size=0.1, random_state=42)
# print(train.shape) # (540000, 40)
# print(valid.shape) # (60000, 40)
train_dataset = TensorDataset(
torch.LongTensor(train[sparse_features].values),
torch.FloatTensor(train[dense_features].values),
torch.FloatTensor(train['label'].values))
train_loader = DataLoader(dataset=train_dataset,
batch_size=args.train_batch_size,
shuffle=True)
valid_dataset = TensorDataset(
torch.LongTensor(valid[sparse_features].values),
torch.FloatTensor(valid[dense_features].values),
torch.FloatTensor(valid['label'].values))
valid_loader = DataLoader(dataset=valid_dataset,
batch_size=args.eval_batch_size,
shuffle=False)
cat_fea_unique = [data[f].nunique() for f in sparse_features]
model = DCN(cat_fea_unique, num_fea_size=len(dense_features))
train_model(model)