file = '../dataset/Criteo/train.txt'
read_part = True
sample_num = 100000
test_size = 0.2
embed_dim = 8
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 = NFM(feature_columns, hidden_units, dropout_rate=dnn_dropout)
model.summary()
# ============================model checkpoint======================
# check_path = 'save/nfm_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==============================
# Author : junchaoli
# File : train.py
'''
from model import CCPM
from utils import create_criteo_dataset
import tensorflow as tf
from tensorflow.keras import optimizers, losses
from sklearn.metrics import accuracy_score
if __name__ == '__main__':
file_path = 'E:\\PycharmProjects\\推荐算法\\data\\train.txt'
feature_columns, (X_train,
y_train), (X_test,
y_test) = create_criteo_dataset(file_path,
test_size=0.2)
hidden_units = [128]
dropout = 0.2
filters = [4, 4]
kernel_width = [6, 5]
model = CCPM(feature_columns,
hidden_units,
dropout=dropout,
filters=filters,
kernel_width=kernel_width)
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)
'''
from model import AutoInt
from utils import create_criteo_dataset
import numpy as np
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 = 0.1
hidden_units = [256, 128, 64]
feature_columns, (X_train, y_train), (X_test,
y_test) = create_criteo_dataset(
file, test_size=test_size)
model = AutoInt(feature_columns,
hidden_units,
dnn_dropout=0.2,
n_heads=4,
head_dim=16,
att_dropout=0.2)
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)
summary_writer = tf.summary.create_file_writer(
'E:\\PycharmProjects\\tensorboard')
from utils import create_criteo_dataset
import tensorflow as tf
from tensorflow.keras import optimizers, losses, metrics
from sklearn.metrics import accuracy_score
import argparse
parser = argparse.ArgumentParser(description='命令行参数')
parser.add_argument('-k', type=int, help='v_dim', default=8)
parser.add_argument('-w_reg', type=float, help='w正则', default=1e-4)
parser.add_argument('-v_reg', type=float, help='v正则', default=1e-4)
args=parser.parse_args()
if __name__ == '__main__':
file_path = 'train.txt'
(X_train, y_train), (X_test, y_test) = create_criteo_dataset(file_path, test_size=0.5)
k = args.k
w_reg = args.w_reg
v_reg = args.v_reg
model = FM(k, w_reg, v_reg)
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='rmsprop',loss='binary_crossentropy',metrics=['accuracy'])
# model.fit(train_dataset, epochs=200)
# print(model.evaluate(X_test, y_test))
# model.summary()
summary_writer = tf.summary.create_file_writer('E:\\PycharmProjects\\tensorboard')
from sklearn.metrics import confusion_matrix, roc_curve
import matplotlib.pyplot as plt
import seaborn as sns
file = './criteo_sampled_data.csv'
read_part = True
sample_num = 100000
test_size = 0.2
k = 32
learning_rate = 0.001
batch_size = 500
epochs = 100
feature_columns, train, test, val = create_criteo_dataset(
file=file, read_part=read_part, sample_num=sample_num, test_size=test_size)
train_X, train_y = train
test_X, test_y = test
val_X, val_y = val
model = FM(feature_columns=feature_columns, k=k)
model.summary()
early_stopping = tf.keras.callbacks.EarlyStopping(monitor='val_auc',
verbose=1,
patience=10,
mode='max',
restore_best_weights=True)
model.compile(loss=tf.keras.losses.binary_crossentropy,
optimizer=tf.keras.optimizers.Adam(lr=learning_rate),
# Author : junchaoli
# File : train.py
'''
from model import DCN
from utils import create_criteo_dataset
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('E:\\PycharmProjects\\tensorboard')
for i in range(100):
# -*- encoding: utf-8 -*- ''' @File : data_test.py @Time : 2020/09/13 16:34:13 @Author : Peng He @Version : 1.0 @Contact : [email protected] @IDE : Visual Studio Code @License : (C)Copyright 2020, CUG @Desc : None ''' from utils import create_criteo_dataset # here put the import lib if __name__ == "__main__": feature_columns, (train_X, train_Y), ( test_X, test_Y ) = create_criteo_dataset( 'D:/data/Chrome-Download/198459_438654_bundle_archive/train_1m.txt') print(feature_columns)
