def plot_nfm():
# 读取数据
data, dense_features, sparse_features = read_criteo_data()
dense_features = dense_features[:3]
sparse_features = sparse_features[:2]
# 将特征分组，分成linear部分和dnn部分(根据实际场景进行选择)，并将分组之后的特征做标记（使用DenseFeat, SparseFeat）
linear_feature_columns = [
SparseFeat(feat, vocabulary_size=data[feat].nunique(), embedding_dim=4)
for i, feat in enumerate(sparse_features)
] + [DenseFeat(
feat,
1,
) for feat in dense_features]
dnn_feature_columns = [
SparseFeat(feat, vocabulary_size=data[feat].nunique(), embedding_dim=4)
for i, feat in enumerate(sparse_features)
] + [DenseFeat(
feat,
1,
) for feat in dense_features]
# 构建NFM模型
history = NFM(linear_feature_columns, dnn_feature_columns)
keras.utils.plot_model(history, to_file="./imgs/NFM.png", show_shapes=True)
def plot_dien():
"""读取数据"""
samples_data = pd.read_csv("data/movie_sample.txt", sep="\t", header=None)
samples_data.columns = [
"user_id", "gender", "age", "hist_movie_id", "hist_len", "movie_id",
"movie_type_id", "label"
]
"""数据集"""
X = samples_data[[
"user_id", "gender", "age", "hist_movie_id", "hist_len", "movie_id",
"movie_type_id"
]]
y = samples_data["label"]
"""特征封装"""
feature_columns = [
SparseFeat('user_id',
max(samples_data["user_id"]) + 1,
embedding_dim=8),
SparseFeat('gender', max(samples_data["gender"]) + 1, embedding_dim=8),
SparseFeat('age', max(samples_data["age"]) + 1, embedding_dim=8),
SparseFeat('movie_id',
max(samples_data["movie_id"]) + 1,
embedding_dim=8),
SparseFeat('movie_type_id',
max(samples_data["movie_type_id"]) + 1,
embedding_dim=8),
DenseFeat('hist_len', 1)
]
feature_columns += [
VarLenSparseFeat('hist_movie_id',
vocabulary_size=max(samples_data["movie_id"]) + 1,
embedding_dim=8,
maxlen=50)
]
feature_columns += [
VarLenSparseFeat('neg_hist_movie_id',
vocabulary_size=max(samples_data["movie_id"]) + 1,
embedding_dim=8,
maxlen=50)
]
# 行为特征列表，表示的是基础特征
behavior_feature_list = ['movie_id']
# 行为序列特征
behavior_seq_feature_list = ['hist_movie_id']
# 负采样序列特征
neg_seq_feature_list = ['neg_hist_movie_id']
"""构建DIN模型"""
history = DIEN(feature_columns,
behavior_feature_list,
behavior_seq_feature_list,
neg_seq_feature_list,
use_neg_sample=True)
keras.utils.plot_model(history,
to_file="./imgs/DIEN.png",
show_shapes=True)
def plot_ncf():
# 读取数据，NCF使用的特征只有user_id和item_id
rnames = ['user_id', 'movie_id', 'rating', 'timestamp']
data = pd.read_csv('./data/ml-1m/ratings.dat',
sep='::',
engine='python',
names=rnames)
lbe = LabelEncoder()
data['user_id'] = lbe.fit_transform(data['user_id'])
data['movie_id'] = lbe.fit_transform(data['movie_id'])
dnn_feature_columns = [
SparseFeat('user_id', data['user_id'].nunique(), 8),
SparseFeat('movie_id', data['movie_id'].nunique(), 8)
]
# 构建FM模型
history = NCF(dnn_feature_columns)
keras.utils.plot_model(history, to_file="./imgs/NCF.png", show_shapes=True)
def plot_din():
# 读取数据
samples_data = pd.read_csv("./data/movie_sample.txt",
sep="\t",
header=None)
samples_data.columns = [
"user_id", "gender", "age", "hist_movie_id", "hist_len", "movie_id",
"movie_type_id", "label"
]
feature_columns = [
SparseFeat('user_id',
max(samples_data["user_id"]) + 1,
embedding_dim=8),
SparseFeat('gender', max(samples_data["gender"]) + 1, embedding_dim=8),
SparseFeat('age', max(samples_data["age"]) + 1, embedding_dim=8),
SparseFeat('movie_id',
max(samples_data["movie_id"]) + 1,
embedding_dim=8),
SparseFeat('movie_type_id',
max(samples_data["movie_type_id"]) + 1,
embedding_dim=8),
DenseFeat('hist_len', 1)
]
feature_columns += [
VarLenSparseFeat('hist_movie_id',
vocabulary_size=max(samples_data["movie_id"]) + 1,
embedding_dim=8,
maxlen=50)
]
# 行为特征列表，表示的是基础特征
behavior_feature_list = ['movie_id']
# 行为序列特征
behavior_seq_feature_list = ['hist_movie_id']
history = DIN(feature_columns, behavior_feature_list,
behavior_seq_feature_list)
keras.utils.plot_model(history, to_file="./imgs/DIN.png", show_shapes=True)
def plot_pnn():
data, dense_features, sparse_features = read_criteo_data()
dense_features = dense_features[:3]
sparse_features = sparse_features[:3]
# 将特征分组，分成linear部分和dnn部分(根据实际场景进行选择)，并将分组之后的特征做标记（使用DenseFeat, SparseFeat）
dnn_feature_columns = [
SparseFeat(feat, vocabulary_size=data[feat].nunique(), embedding_dim=4)
for feat in sparse_features
] + [DenseFeat(
feat,
1,
) for feat in dense_features]
# 构建DeepCrossing模型
history = PNN(dnn_feature_columns)
keras.utils.plot_model(history, to_file="./imgs/PNN.png", show_shapes=True)
if __name__ == "__main__":
# 读取数据
data = pd.read_csv('../data/criteo_sample.txt')
# 划分dense和sparse特征
columns = data.columns.values
dense_features = [feat for feat in columns if 'I' in feat]
sparse_features = [feat for feat in columns if 'C' in feat]
# 简单的数据预处理
train_data = data_process(data, dense_features, sparse_features)
train_data['label'] = data['label']
# 将特征分组，分成linear部分和dnn部分(根据实际场景进行选择)，并将分组之后的特征做标记（使用DenseFeat, SparseFeat）
linear_feature_columns = [
SparseFeat(feat, vocabulary_size=data[feat].nunique(), embedding_dim=4)
for i, feat in enumerate(sparse_features)
] + [DenseFeat(
feat,
1,
) for feat in dense_features]
dnn_feature_columns = [
SparseFeat(feat, vocabulary_size=data[feat].nunique(), embedding_dim=4)
for i, feat in enumerate(sparse_features)
] + [DenseFeat(
feat,
1,
) for feat in dense_features]
# 构建xDeepFM模型
"""构建DIEN模型的输入格式"""
# 这里和DIN相比， 会多出负采样的一列历史行为
X_train = {"user_id": np.array(X["user_id"]), \
"gender": np.array(X["gender"]), \
"age": np.array(X["age"]), \
"hist_movie_id": np.array([[int(i) for i in l.split(',')] for l in X["hist_movie_id"]]), \
"neg_hist_movie_id": np.array([[int(i) for i in l.split(',')] for l in X["neg_hist_movie_id"]]), \
"hist_len": np.array(X["hist_len"]), \
"movie_id": np.array(X["movie_id"]), \
"movie_type_id": np.array(X["movie_type_id"])}
y_train = np.array(y)
"""特征封装"""
feature_columns = [SparseFeat('user_id', max(samples_data["user_id"])+1, embedding_dim=8),
SparseFeat('gender', max(samples_data["gender"])+1, embedding_dim=8),
SparseFeat('age', max(samples_data["age"])+1, embedding_dim=8),
SparseFeat('movie_id', max(samples_data["movie_id"])+1, embedding_dim=8),
SparseFeat('movie_type_id', max(samples_data["movie_type_id"])+1, embedding_dim=8),
DenseFeat('hist_len', 1)]
feature_columns += [VarLenSparseFeat('hist_movie_id', vocabulary_size=max(samples_data["movie_id"])+1, embedding_dim=8, maxlen=50)]
feature_columns += [VarLenSparseFeat('neg_hist_movie_id', vocabulary_size=max(samples_data["movie_id"])+1, embedding_dim=8, maxlen=50)]
# 行为特征列表，表示的是基础特征
behavior_feature_list = ['movie_id']
# 行为序列特征
behavior_seq_feature_list = ['hist_movie_id']
# 负采样序列特征
neg_seq_feature_list = ['neg_hist_movie_id']
if __name__ == "__main__":
# 读取数据
data = pd.read_csv('./data/criteo_sample.txt')
# 划分dense和sparse特征
columns = data.columns.values
dense_features = [feat for feat in columns if 'I' in feat]
sparse_features = [feat for feat in columns if 'C' in feat]
# 简单的数据预处理
train_data = data_process(data, dense_features, sparse_features)
train_data['label'] = data['label']
# 将特征分组，分成linear部分和dnn部分(根据实际场景进行选择)，并将分组之后的特征做标记（使用DenseFeat, SparseFeat）
linear_feature_columns = [SparseFeat(feat, vocabulary_size=data[feat].nunique(),embedding_dim=4)
for i,feat in enumerate(sparse_features)] + [DenseFeat(feat, 1,)
for feat in dense_features]
dnn_feature_columns = [SparseFeat(feat, vocabulary_size=data[feat].nunique(),embedding_dim=4)
for i,feat in enumerate(sparse_features)] + [DenseFeat(feat, 1,)
for feat in dense_features]
# 构建DCN模型
history = DCN(linear_feature_columns, dnn_feature_columns)
history.summary()
history.compile(optimizer="adam",
loss="binary_crossentropy",
metrics=["binary_crossentropy", tf.keras.metrics.AUC(name='auc')])
# 将输入数据转化成字典的形式输入
return model
if __name__ == "__main__":
# 读取数据，NCF使用的特征只有user_id和item_id
rnames = ['user_id','movie_id','rating','timestamp']
data = pd.read_csv('./data/ml-1m/ratings.dat', sep='::', engine='python', names=rnames)
lbe = LabelEncoder()
data['user_id'] = lbe.fit_transform(data['user_id'])
data['movie_id'] = lbe.fit_transform(data['movie_id'])
train_data = data[['user_id', 'movie_id']]
train_data['label'] = data['rating']
dnn_feature_columns = [SparseFeat('user_id', train_data['user_id'].nunique(), 8),
SparseFeat('movie_id', train_data['movie_id'].nunique(), 8)]
# 构建FM模型
history = NCF(dnn_feature_columns)
history.summary()
# 因为数据目前只有用户点击的数据，没有用户未点击的movie，所以这里不能用于做ctr预估
# 如果需要做ctr预估需要给用户点击和未点击的movie打标签，这里就先预测用户评分
history.compile(optimizer="adam", loss="mse", metrics=['mae'])
# 将输入数据转化成字典的形式输入
# 将数据转换成字典的形式，用于Input()层对应
train_model_input = {name: train_data[name] for name in ['user_id', 'movie_id', 'label']}
# 模型训练
history.fit(train_model_input, train_data['label'].values,