DeepCTR：易用可扩展的深度学习点击率预测算法包

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
import pandas as pd
from sklearn.metrics import log_loss, roc_auc_score
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder, MinMaxScaler

from deepctr.models import DeepFM
from deepctr.feature_column import SparseFeat, DenseFeat, get_feature_names

if __name__ == "__main__":
    data = pd.read_csv('./criteo_sample.txt')

    sparse_features = ['C' + str(i) for i in range(1, 27)]
    dense_features = ['I' + str(i) for i in range(1, 14)]

    data[sparse_features] = data[sparse_features].fillna('-1', )
    data[dense_features] = data[dense_features].fillna(0, )
    target = ['label']

    # 1.Label Encoding for sparse features,and do simple Transformation for dense features
    for feat in sparse_features:
        lbe = LabelEncoder()
        data[feat] = lbe.fit_transform(data[feat])
    mms = MinMaxScaler(feature_range=(0, 1))
    data[dense_features] = mms.fit_transform(data[dense_features])

    # 2.count #unique features for each sparse field,and record dense feature field name

    fixlen_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 = fixlen_feature_columns
    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, random_state=2018)
    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 = DeepFM(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))

1
2
3
4
5
fm_input = Concatenate(axis=1)(embed_list)#将输入拼接成FM层需要的shape
deep_input = Flatten()(fm_input)#将输入拼接成Deep网络需要的shape
fm_out = FM()(fm_input)#调用FM组件
deep_out = DNN(dnn_hidden_units, dnn_activation, l2_reg_dnn, dnn_dropout,dnn_use_bn, seed)(deep_input)#调用Deep网络组件
deep_logit = Dense(1, use_bias=False, activation=None)(deep_out)

1
2
pip install deepctr[cpu]#CPU版本
pip install deepctr[gpu]#GPU版本