【推荐系统】TensorFlow实现FM特征分解机

如果需要完整代码可以关注下方公众号，后台回复“代码”即可获取，阿光期待着您的光临~

文章目录

• ​​导库​​
• ​​FM特征组合层​​
• ​​定义FM模型​​
• ​​读取数据​​
• ​​划分数据集​​
• ​​构建模型​​
• ​​训练模型​​

2021人工智能领域新星创作者，带你从入门到精通，该博客每天更新，逐渐完善推荐系统各个知识体系的文章，帮助大家更高效学习。

导库

from tensorflow.keras import *
from tensorflow.keras.layers import *
from tensorflow.keras.models import *
from tensorflow.keras.callbacks import *
import tensorflow.keras.backend as K

from sklearn.model_selection import train_test_split
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder
from sklearn.datasets import load_breast_cancer

from tqdm import tqdm

import pandas as pd
import numpy as np

FM特征组合层

# FM 特征组合层
class crossLayer(layers.Layer):
    def __init__(self, input_dim, output_dim=10, **kwargs):
        super(crossLayer, self).__init__(**kwargs)

        self.input_dim = input_dim
        self.output_dim = output_dim

        self.kernel = self.add_weight(name='kernel',
                                      shape=(self.input_dim, self.output_dim),
                                      initializer='glorot_uniform',
                                      trainable=True)

    def call(self, x):
        a = K.pow(K.dot(x, self.kernel), 2)
        b = K.dot(K.pow(x, 2), K.pow(self.kernel, 2))
        return 0.5 * K.mean(a - b, 1, keepdims=True)

定义FM模型

# 定义FM模型
def FM(feature_dim):
    inputs = Input(shape=(feature_dim,))

    # 一阶特征
    linear = Dense(units=1,
                   kernel_regularizer=regularizers.l2(0.01),
                   bias_regularizer=regularizers.l2(0.01))(inputs)

    # 二阶特征
    cross = crossLayer(feature_dim)(inputs)
    add = Add()([linear, cross])

    pred = Dense(units=1, activation="sigmoid")(add)
    model = Model(inputs=inputs, outputs=pred)

    model.summary()
    model.compile(loss='binary_crossentropy',
                  optimizer=optimizers.Adam(),
                  metrics=['binary_accuracy'])

    return model

读取数据

# 读取数据
print('loading data...')
X, y = load_breast_cancer(return_X_y = True)

划分数据集

# 划分数据集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=2021)

构建模型

# 构建模型
model = FM(X.shape[1])

训练模型

# 训练模型
model.fit(X_train, y_train, epochs=10, batch_size=128, validation_data=(X_test, y_test))