推荐系统实战之排序层- Embedding+MLP

embedding+MLP用一句话总结就是：对于类别特征，先利用 Embedding 层进行特征稠密化，再利用 Stacking 层连接其他特征，输入 MLP 的多层结构，最后用 Scoring 层预估结果。

具体步骤为：

1. 将分类特征embedding，转为N维的稠密向量。

2. 数值特征不做处理。

3. 将embedding后的向量和数值向量进行concat操作，也就是Stacking层

4. 输入MLP层，全连接充分交叉，中间层输出为128维，使用RELU激活函数（维度和激活函数根据具体项目按照经验调节）。

5. 输出为1维向量，使用sigmoid激活函数。

预测电影评分实战代码如下，代码见EmbeddingMLP.py：

import tensorflow as tf

# Training samples path, change to your local path
training_samples_file_path = tf.keras.utils.get_file("trainingSamples.csv",
                                                     "file:///Users/xxx/workspace/SparrowRecSys/src/main"
                                                     "/resources/webroot/sampledata/trainingSamples.csv")
# Test samples path, change to your local path
test_samples_file_path = tf.keras.utils.get_file("testSamples.csv",
                                                 "file:///Users/xxx/workspace/SparrowRecSys/src/main"
                                                 "/resources/webroot/sampledata/testSamples.csv")


# load sample as tf dataset
def get_dataset(file_path):
    dataset = tf.data.experimental.make_csv_dataset(
        file_path,
        batch_size=12,
        label_name='label',
        na_value="0",
        num_epochs=1,
        ignore_errors=True)
    return dataset


# split as test dataset and training dataset
train_dataset = get_dataset(training_samples_file_path)
test_dataset = get_dataset(test_samples_file_path)

# genre features vocabulary
genre_vocab = ['Film-Noir', 'Action', 'Adventure', 'Horror', 'Romance', 'War', 'Comedy', 'Western', 'Documentary',
               'Sci-Fi', 'Drama', 'Thriller',
               'Crime', 'Fantasy', 'Animation', 'IMAX', 'Mystery', 'Children', 'Musical']

GENRE_FEATURES = {
    'userGenre1': genre_vocab,
    'userGenre2': genre_vocab,
    'userGenre3': genre_vocab,
    'userGenre4': genre_vocab,
    'userGenre5': genre_vocab,
    'movieGenre1': genre_vocab,
    'movieGenre2': genre_vocab,
    'movieGenre3': genre_vocab
}

# all categorical features
categorical_columns = []
for feature, vocab in GENRE_FEATURES.items():
    cat_col = tf.feature_column.categorical_column_with_vocabulary_list(
        key=feature, vocabulary_list=vocab)
    emb_col = tf.feature_column.embedding_column(cat_col, 10)
    categorical_columns.append(emb_col)
# movie id embedding feature
movie_col = tf.feature_column.categorical_column_with_identity(key='movieId', num_buckets=1001)
movie_emb_col = tf.feature_column.embedding_column(movie_col, 10)
categorical_columns.append(movie_emb_col)

# user id embedding feature
user_col = tf.feature_column.categorical_column_with_identity(key='userId', num_buckets=30001)
user_emb_col = tf.feature_column.embedding_column(user_col, 10)
categorical_columns.append(user_emb_col)

# all numerical features
numerical_columns = [tf.feature_column.numeric_column('releaseYear'),
                     tf.feature_column.numeric_column('movieRatingCount'),
                     tf.feature_column.numeric_column('movieAvgRating'),
                     tf.feature_column.numeric_column('movieRatingStddev'),
                     tf.feature_column.numeric_column('userRatingCount'),
                     tf.feature_column.numeric_column('userAvgRating'),
                     tf.feature_column.numeric_column('userRatingStddev')]

# embedding + MLP model architecture
model = tf.keras.Sequential([
    tf.keras.layers.DenseFeatures(numerical_columns + categorical_columns),
    tf.keras.layers.Dense(128, activation='relu'),
    tf.keras.layers.Dense(128, activation='relu'),
    tf.keras.layers.Dense(1, activation='sigmoid'),
])

# compile the model, set loss function, optimizer and evaluation metrics
model.compile(
    loss='binary_crossentropy',
    optimizer='adam',
    metrics=['accuracy', tf.keras.metrics.AUC(curve='ROC'), tf.keras.metrics.AUC(curve='PR')])

# train the model
model.fit(train_dataset, epochs=5)

# evaluate the model
test_loss, test_accuracy, test_roc_auc, test_pr_auc = model.evaluate(test_dataset)
print('\n\nTest Loss {}, Test Accuracy {}, Test ROC AUC {}, Test PR AUC {}'.format(test_loss, test_accuracy,
                                                                                   test_roc_auc, test_pr_auc))

# print some predict results
predictions = model.predict(test_dataset)
for prediction, goodRating in zip(predictions[:12], list(test_dataset)[0][1][:12]):
    print("Predicted good rating: {:.2%}".format(prediction[0]),
          " | Actual rating label: ",
          ("Good Rating" if bool(goodRating) else "Bad Rating"))