基于卷积神经网络的电视节目推荐_基于卷积神经网络cnn的电影推荐系统

本文使用文本卷积神经网络，并使用自己的电视节目数据集完成电影推荐的任务。 

本文在参考了 https://blog.csdn.net/chengcheng1394/article/details/78820529 的基础上，采用自己的数据集对代码进行修改，终于运行出来了！不过对于神经网络是如何搭建的，具体实现原理还是不是很懂的!

需要安装TensorFlow1.0，Python3.5 

模型设计：图片来自https://blog.csdn.net/chengcheng1394/article/details/78820529

跟上图不同的是，本文采用的数据集没有用户属性中的性别，年龄和职业编号，仅有用户号。

电影id和用户id以及评分数据都不需要进行转换，但电影名称和节目类型的数据需要将其转为对应的数字，不然没法处理。 

文本卷积神经网络的图如下， 

图片来自Kim Yoon的论文：Convolutional Neural Networks for Sentence Classification

http://www.wildml.com/2015/11/understanding-convolutional-neural-networks-for-nlp/

# -*- coding: utf-8 -*-
 
import pandas as pd
from sklearn.model_selection import train_test_split
import numpy as np
from collections import Counter
import tensorflow as tf
 
import os
import pickle
from tensorflow.python.ops import math_ops
from urllib.request import urlretrieve
from os.path import isfile, isdir
from tqdm import tqdm
 
 
def load_data():
    """
    Load Dataset from File
    """
    
    os.chdir('E:/广电大数据营销推荐项目案例/数据清洗/电视节目信息数据预处理')
    
    
    
#    #    #读取User数据
    users = pd.read_table('./wordsbag/dataprocess/data/week/mydata/data1_users.csv', sep=',', header='infer', engine = 'python')
    users_orig = users.values
  
    #读取Movie数据集
    #    movies_title = ['MovieID', 'Title', 'Genres']
    movies = pd.read_table('./wordsbag/dataprocess/data/week/mydata/data1_tv.csv', sep=',', header='infer', engine = 'python')
    movies = movies.filter(regex='program_id|program_title|genres_good')
    movies_orig = movies.values
    
    #电影类型转数字字典
    genres_set = set()
    for val in movies['genres_good'].str.split('/'):
        genres_set.update(val)
    
    genres_set.add('<PAD>')
    genres2int = {val:ii for ii, val in enumerate(genres_set)}
    
    #将电影类型转成等长数字列表，长度是18
    genres_count = 18
    genres_map = {val:[genres2int[row] for row in val.split('/')] for ii,val in enumerate(set(movies['genres_good']))}
    
    for key in genres_map:
        for cnt in range(genres_count - len(genres_map[key])):
            genres_map[key].insert(len(genres_map[key]) + cnt,genres2int['<PAD>'])
    
    movies['genres_good'] = movies['genres_good'].map(genres_map)
    
    #电影Title转数字字典
    title_set = set()
    for val in movies['program_title'].str.split():
        title_set.update(val)
    
    title_set.add('<PAD>')
    title2int = {val:ii for ii, val in enumerate(title_set)}
    
    #将电影Title转成等长数字列表，长度是15
    title_count = 15
    title_map = {val:[title2int[row] for row in val.split()] for ii,val in enumerate(set(movies['program_title']))}
    
    for key in title_map:
        for cnt in range(title_count - len(title_map[key])):
            title_map[key].insert(len(title_map[key]) + cnt,title2int['<PAD>'])
    
    movies['program_title'] = movies['program_title'].map(title_map)
    
    
    #读取评分数据集，评分为1-10分
    ratings = pd.read_table('./wordsbag/dataprocess/data/week/mydata/data1_ratings.csv', sep=',', header='infer', engine = 'python')
    ratings = ratings.filter(regex='user_id|program_id|rating')
    
    #合并表
    data = pd.merge(ratings,movies)
    
    #将数据分成X和y两张表
    target_fields = ['rating']
    features_pd, targets_pd = data.drop(target_fields, axis=1), data[target_fields]
    
    features = features_pd.values
    targets_values = targets_pd.values
 
 
      
    return title_count, title_set, genres_count, genres2int, features, targets_values, ratings, users, movies, data, movies_orig,users_orig
 
 
title_count, title_set, genres_count,  genres2int, features, targets_values, ratings, users, movies, data, movies_orig,users_orig= load_data()
 
pickle.dump((title_count, title_set, genres_count, genres2int, features, targets_values, ratings, movies, data, movies_orig,users_orig), open('./wordsbag/dataprocess/data/week/mydata/preprocess.p', 'wb'))
 
 
 
# 预处理后
 
#users.head()
 
movies.head()
 
movies.values[0]
 
title_count, title_set, genres_count, genres2int, features, targets_values, ratings,  movies, data, movies_orig,users_orig = pickle.load(open('./wordsbag/dataprocess/data/week/mydata/preprocess.p', mode='rb'))
 
 
import tensorflow as tf
import os
import pickle
 
def save_params(params):
    """
    Save parameters to file
    """
    pickle.dump(params, open('./wordsbag/dataprocess/data/week/mydata/params.p', 'wb'))
 
 
def load_params():
    """
    Load parameters from file
    """
    return pickle.load(open('./wordsbag/dataprocess/data/week/mydata/params.p', mode='rb'))
 
 
# 编码实现
    
#嵌入矩阵的维度
embed_dim = 32
#用户ID个数
uid_max = max(features.take(0,1)) + 1 # 1966+1=1967
print(uid_max)
 
#电影ID个数
movie_id_max = max(features.take(1,1)) + 1 # 995+1 = 996
print(movie_id_max)
#电影类型个数
movie_categories_max = max(genres2int.values()) + 1 # 104为什么有这么多重复的个数
print(movie_categories_max)
#电影名单词个数
movie_title_max = len(title_set) # 501+1=502
print(movie_title_max)
 
#对电影类型嵌入向量做加和操作的标志，考虑过使用mean做平均，但是没实现mean
combiner = "sum"
 
#电影名长度
sentences_size = title_count # = 15
#文本卷积滑动窗口，分别滑动2, 3, 4, 5个单词
window_sizes = {2, 3, 4, 5}
#文本卷积核数量
filter_num = 8
 
#电影ID转下标的字典，数据集中电影ID跟下标不一致，比如第5行的数据电影ID不一定是5
movieid2idx = {val[0]:i for i, val in enumerate(movies.values)}
print(movieid2idx)
 
 
 
# 超参
# Number of Epochs
num_epochs = 5
# Batch Size
batch_size = 256
 
dropout_keep = 0.5
# Learning Rate
learning_rate = 0.0001
# Show stats for every n number of batches
show_every_n_batches = 20
 
save_dir = './wordsbag/dataprocess/data/week/mydata/save2'
 
 
 
# 输入
def get_inputs():
    uid = tf.placeholder(tf.int32, [None, 1], name="uid")
    
    movie_id = tf.placeholder(tf.int32, [None, 1], name="movie_id")
    movie_categories = tf.placeholder(tf.int32, [None, 18], name="movie_categories")
    movie_titles = tf.placeholder(tf.int32, [None, 15], name="movie_titles")
    
    targets = tf.placeholder(tf.int32, [None, 1], name="targets")
    LearningRate = tf.placeholder(tf.float32, name = "LearningRate")
    dropout_keep_prob = tf.placeholder(tf.float32, name = "dropout_keep_prob")
    return uid, movie_id, movie_categories, movie_titles, targets, LearningRate, dropout_keep_prob
 
 
# 构建神经网络
def get_user_embedding(uid):
    with tf.name_scope("user_embedding"):
        uid_embed_matrix = tf.Variable(tf.random_uniform([uid_max, embed_dim], -1, 1), name = "uid_embed_matrix")
        uid_embed_layer = tf.nn.embedding_lookup(uid_embed_matrix, uid, name = "uid_embed_layer")
    return uid_embed_layer
 
 
#将User的嵌入矩阵一起全连接生成User的特征
def get_user_feature_layer(uid_embed_layer):
    with tf.name_scope("user_fc"):
        #第一层全连接
        uid_fc_layer = tf.layers.dense(uid_embed_layer, embed_dim, name = "uid_fc_layer", activation=tf.nn.relu)
        
        #第二层全连接
        user_combine_layer = tf.concat([uid_fc_layer], 2)  #(?, 1, 128)
        user_combine_layer = tf.contrib.layers.fully_connected(user_combine_layer, 200, tf.tanh)  #(?, 1, 200)
    
        user_combine_layer_flat = tf.reshape(user_combine_layer, [-1, 200])
    return user_combine_layer, user_combine_layer_flat
 
 
 
#定义Movie ID的嵌入矩阵
 
def get_movie_id_embed_layer(movie_id):
    with tf.name_scope("movie_embedding"):
        movie_id_embed_matrix = tf.Variable(tf.random_uniform([movie_id_max, embed_dim], -1, 1), name = "movie_id_embed_matrix")
        movie_id_embed_layer = tf.nn.embedding_lookup(movie_id_embed_matrix, movie_id, name = "movie_id_embed_layer")
    return movie_id_embed_layer
 
 
#对电影类型的多个嵌入向量做加和
def get_movie_categories_layers(movie_categories):
    with tf.name_scope("movie_categories_layers"):
        movie_categories_embed_matrix = tf.Variable(tf.random_uniform([movie_categories_max, embed_dim], -1, 1), name = "movie_categories_embed_matrix")
        movie_categories_embed_layer = tf.nn.embedding_lookup(movie_categories_embed_matrix, movie_categories, name = "movie_categories_embed_layer")
        if combiner == "sum":
            movie_categories_embed_layer = tf.reduce_sum(movie_categories_embed_layer, axis=1, keep_dims=True)
    #     elif combiner == "mean":
    return movie_categories_embed_layer
 
# Movie Title的文本卷积网络实现
 
def get_movie_cnn_layer(movie_titles):
    #从嵌入矩阵中得到电影名对应的各个单词的嵌入向量
    with tf.name_scope("movie_embedding"):
        movie_title_embed_matrix = tf.Variable(tf.random_uniform([movie_title_max, embed_dim], -1, 1), name = "movie_title_embed_matrix")
        movie_title_embed_layer = tf.nn.embedding_lookup(movie_title_embed_matrix, movie_titles, name = "movie_title_embed_layer")
        movie_title_embed_layer_expand = tf.expand_dims(movie_title_embed_layer, -1)
    
    #对文本嵌入层使用不同尺寸的卷积核做卷积和最大池化
    pool_layer_lst = []
    for window_size in window_sizes:
        with tf.name_scope("movie_txt_conv_maxpool_{}".format(window_size)):
            filter_weights = tf.Variable(tf.truncated_normal([window_size, embed_dim, 1, filter_num],stddev=0.1),name = "filter_weights")
            filter_bias = tf.Variable(tf.constant(0.1, shape=[filter_num]), name="filter_bias")
            
            conv_layer = tf.nn.conv2d(movie_title_embed_layer_expand, filter_weights, [1,1,1,1], padding="VALID", name="conv_layer")
            relu_layer = tf.nn.relu(tf.nn.bias_add(conv_layer,filter_bias), name ="relu_layer")
            
            maxpool_layer = tf.nn.max_pool(relu_layer, [1,sentences_size - window_size + 1 ,1,1], [1,1,1,1], padding="VALID", name="maxpool_layer")
            pool_layer_lst.append(maxpool_layer)
 
    #Dropout层
    with tf.name_scope("pool_dropout"):
        pool_layer = tf.concat(pool_layer_lst, 3, name ="pool_layer")
        max_num = len(window_sizes) * filter_num
        pool_layer_flat = tf.reshape(pool_layer , [-1, 1, max_num], name = "pool_layer_flat")
    
        dropout_layer = tf.nn.dropout(pool_layer_flat, dropout_keep_prob, name = "dropout_layer")
    return pool_layer_flat, dropout_layer
 
# 将Movie的各个层一起做全连接
def get_movie_feature_layer(movie_id_embed_layer, movie_categories_embed_layer, dropout_layer):
    with tf.name_scope("movie_fc"):
        #第一层全连接
        movie_id_fc_layer = tf.layers.dense(movie_id_embed_layer, embed_dim, name = "movie_id_fc_layer", activation=tf.nn.relu)
        movie_categories_fc_layer = tf.layers.dense(movie_categories_embed_layer, embed_dim, name = "movie_categories_fc_layer", activation=tf.nn.relu)
    
        #第二层全连接
        movie_combine_layer = tf.concat([movie_id_fc_layer, movie_categories_fc_layer, dropout_layer], 2)  #(?, 1, 96)
        movie_combine_layer = tf.contrib.layers.fully_connected(movie_combine_layer, 200, tf.tanh)  #(?, 1, 200)
    
        movie_combine_layer_flat = tf.reshape(movie_combine_layer, [-1, 200])
    return movie_combine_layer, movie_combine_layer_flat 
 
 
 
#构建计算图
tf.reset_default_graph()
train_graph = tf.Graph()
with train_graph.as_default():
    #获取输入占位符
    uid, movie_id, movie_categories, movie_titles, targets, lr, dropout_keep_prob = get_inputs()
    #获取User的4个嵌入向量
    uid_embed_layer = get_user_embedding(uid)
    #得到用户特征
    user_combine_layer, user_combine_layer_flat = get_user_feature_layer(uid_embed_layer)
    #获取电影ID的嵌入向量
    movie_id_embed_layer = get_movie_id_embed_layer(movie_id)
    #获取电影类型的嵌入向量
    movie_categories_embed_layer = get_movie_categories_layers(movie_categories)
    #获取电影名的特征向量
    pool_layer_flat, dropout_layer = get_movie_cnn_layer(movie_titles)
    #得到电影特征
    movie_combine_layer, movie_combine_layer_flat = get_movie_feature_layer(movie_id_embed_layer, 
                                                                                movie_categories_embed_layer, 
                                                                                dropout_layer)
    #计算出评分，要注意两个不同的方案，inference的名字（name值）是不一样的，后面做推荐时要根据name取得tensor
    with tf.name_scope("inference"):
        #将用户特征和电影特征作为输入，经过全连接，输出一个值的方案
        #简单的将用户特征和电影特征做矩阵乘法得到一个预测评分
        inference = tf.reduce_sum(user_combine_layer_flat * movie_combine_layer_flat, axis=1)
        inference = tf.expand_dims(inference, axis=1)
 
    with tf.name_scope("loss"):
        # MSE损失，将计算值回归到评分
        cost = tf.losses.mean_squared_error(targets, inference )
        loss = tf.reduce_mean(cost)
    # 优化损失 
#     train_op = tf.train.AdamOptimizer(lr).minimize(loss)  #cost
    global_step = tf.Variable(0, name="global_step", trainable=False)
    optimizer = tf.train.AdamOptimizer(lr)
    gradients = optimizer.compute_gradients(loss)  #cost
    train_op = optimizer.apply_gradients(gradients, global_step=global_step)
    
    
# 取得batch
def get_batches(Xs, ys, batch_size):
    for start in range(0, len(Xs), batch_size):
        end = min(start + batch_size, len(Xs))
        yield Xs[start:end], ys[start:end]
        
 
 
       
# 训练网络
#%matplotlib inline
#%config InlineBackend.figure_format = 'retina'
import matplotlib.pyplot as plt
import time
import datetime
 
losses = {'train':[], 'test':[]}
 
 
with tf.Session(graph=train_graph) as sess:
    
    #搜集数据给tensorBoard用
    # Keep track of gradient values and sparsity
    grad_summaries = []
    for g, v in gradients:
        if g is not None:
            grad_hist_summary = tf.summary.histogram("{}/grad/hist".format(v.name.replace(':', '_')), g)
            sparsity_summary = tf.summary.scalar("{}/grad/sparsity".format(v.name.replace(':', '_')), tf.nn.zero_fraction(g))
            grad_summaries.append(grad_hist_summary)
            grad_summaries.append(sparsity_summary)
    grad_summaries_merged = tf.summary.merge(grad_summaries)
        
    # Output directory for models and summaries
    timestamp = str(int(time.time()))
    out_dir = os.path.abspath(os.path.join(os.path.curdir, "runs", timestamp))
    print("Writing to {}\n".format(out_dir))
     
    # Summaries for loss and accuracy
    loss_summary = tf.summary.scalar("loss", loss)
 
    # Train Summaries
    train_summary_op = tf.summary.merge([loss_summary, grad_summaries_merged])
    train_summary_dir = os.path.join(out_dir, "summaries", "train")
    train_summary_writer = tf.summary.FileWriter(train_summary_dir, sess.graph)
 
    # Inference summaries
    inference_summary_op = tf.summary.merge([loss_summary])
    inference_summary_dir = os.path.join(out_dir, "summaries", "inference")
    inference_summary_writer = tf.summary.FileWriter(inference_summary_dir, sess.graph)
 
    sess.run(tf.global_variables_initializer())
    saver = tf.train.Saver()
    for epoch_i in range(num_epochs):
        
        #将数据集分成训练集和测试集，随机种子不固定
        train_X,test_X, train_y, test_y = train_test_split(features,  
                                                           targets_values,  
                                                           test_size = 0.2,  
                                                           random_state = 0)  
        
        train_batches = get_batches(train_X, train_y, batch_size)
        test_batches = get_batches(test_X, test_y, batch_size)
    
        #训练的迭代，保存训练损失
        for batch_i in range(len(train_X) // batch_size):
            x, y = next(train_batches)
 
            categories = np.zeros([batch_size, 18])
            for i in range(batch_size):
                categories[i] = x.take(3,1)[i]
#                categories[i] = x.take(6,1)[i]
 
            titles = np.zeros([batch_size, sentences_size])
            for i in range(batch_size):
                titles[i] = x.take(2,1)[i]
 
            feed = {
                uid: np.reshape(x.take(0,1), [batch_size, 1]),
                
                movie_id: np.reshape(x.take(1,1), [batch_size, 1]),
                movie_categories: categories,  #x.take(3,1)
                movie_titles: titles,  #x.take(2,1)
                
                targets: np.reshape(y, [batch_size, 1]),
                dropout_keep_prob: dropout_keep, #dropout_keep
                lr: learning_rate}
 
            step, train_loss, summaries, _ = sess.run([global_step, loss, train_summary_op, train_op], feed)  #cost
            losses['train'].append(train_loss)
            train_summary_writer.add_summary(summaries, step)  #
            
            # Show every <show_every_n_batches> batches
            if (epoch_i * (len(train_X) // batch_size) + batch_i) % show_every_n_batches == 0:
                time_str = datetime.datetime.now().isoformat()
                print('{}: Epoch {:>3} Batch {:>4}/{}   train_loss = {:.3f}'.format(
                    time_str,
                    epoch_i,
                    batch_i,
                    (len(train_X) // batch_size),
                    train_loss))
                
        #使用测试数据的迭代
        for batch_i  in range(len(test_X) // batch_size):
            x, y = next(test_batches)
            
            categories = np.zeros([batch_size, 18])
            for i in range(batch_size):
                categories[i] = x.take(3,1)[i]     #x.take(3,1)中的3要根据自己的数据去做修改
 
            titles = np.zeros([batch_size, sentences_size])
            for i in range(batch_size):
                titles[i] = x.take(2,1)[i]    #x.take(2,1)中的2要根据自己的数据去做修改
 
            feed = {
                uid: np.reshape(x.take(0,1), [batch_size, 1]),
                
                movie_id: np.reshape(x.take(1,1), [batch_size, 1]),
                movie_categories: categories,  #x.take(3,1)
                movie_titles: titles,  #x.take(2,1)
                
                targets: np.reshape(y, [batch_size, 1]),
                dropout_keep_prob: 1,
                lr: learning_rate}
            
            step, test_loss, summaries = sess.run([global_step, loss, inference_summary_op], feed)  #cost
 
            #保存测试损失
            losses['test'].append(test_loss)
            inference_summary_writer.add_summary(summaries, step)  #
 
            time_str = datetime.datetime.now().isoformat()
            if (epoch_i * (len(test_X) // batch_size) + batch_i) % show_every_n_batches == 0:
                print('{}: Epoch {:>3} Batch {:>4}/{}   test_loss = {:.3f}'.format(
                    time_str,
                    epoch_i,
                    batch_i,
                    (len(test_X) // batch_size),
                    test_loss))
 
    # Save Model
    saver.save(sess, save_dir)  #, global_step=epoch_i
    print('Model Trained and Saved')
 
# 保存参数
save_params((save_dir))
 
load_dir = load_params()
 
 
# 显示训练Loss
plt.plot(losses['train'], label='Training loss')
plt.legend()
_ = plt.ylim()
 
# 显示测试Loss
plt.plot(losses['test'], label='Test loss')
plt.legend()
_ = plt.ylim()
 
 
 
 
# 获取Tensors
def get_tensors(loaded_graph):
 
    uid = loaded_graph.get_tensor_by_name("uid:0")
    
    movie_id = loaded_graph.get_tensor_by_name("movie_id:0")
    movie_categories = loaded_graph.get_tensor_by_name("movie_categories:0")
    movie_titles = loaded_graph.get_tensor_by_name("movie_titles:0")
    
    targets = loaded_graph.get_tensor_by_name("targets:0")
    dropout_keep_prob = loaded_graph.get_tensor_by_name("dropout_keep_prob:0")
    lr = loaded_graph.get_tensor_by_name("LearningRate:0")
    #两种不同计算预测评分的方案使用不同的name获取tensor inference
#     inference = loaded_graph.get_tensor_by_name("inference/inference/BiasAdd:0")
    inference = loaded_graph.get_tensor_by_name("inference/ExpandDims:0") # 之前是MatMul:0 因为inference代码修改了 这里也要修改 感谢网友 @清歌 指出问题
    movie_combine_layer_flat = loaded_graph.get_tensor_by_name("movie_fc/Reshape:0")
    user_combine_layer_flat = loaded_graph.get_tensor_by_name("user_fc/Reshape:0")
    return uid, movie_id, movie_categories, movie_titles, targets, lr, dropout_keep_prob, inference, movie_combine_layer_flat, user_combine_layer_flat
 
 
 
#指定用户和电影进行评分
def rating_movie(user_id_val, movie_id_val):
    loaded_graph = tf.Graph()  #
    with tf.Session(graph=loaded_graph) as sess:  #
        # Load saved model
        loader = tf.train.import_meta_graph(load_dir + '.meta')
        loader.restore(sess, load_dir)
    
        # Get Tensors from loaded model
        uid, movie_id, movie_categories, movie_titles, targets, lr, dropout_keep_prob, inference,_, __ = get_tensors(loaded_graph)  #loaded_graph
    
        categories = np.zeros([1, 18])
        categories[0] = movies.values[movieid2idx[movie_id_val]][2]
    
        titles = np.zeros([1, sentences_size])
        titles[0] = movies.values[movieid2idx[movie_id_val]][1]
    
        feed = {
              uid: np.reshape(users.values[user_id_val-1][0], [1, 1]),
 
              movie_id: np.reshape(movies.values[movieid2idx[movie_id_val]][0], [1, 1]),
              movie_categories: categories,  #x.take(6,1)
              movie_titles: titles,  #x.take(5,1)
              dropout_keep_prob: 1}
    
        # Get Prediction
        inference_val = sess.run([inference], feed)  
    
        return (inference_val) 
    
rating_movie(23, 1)    
 
 
 
#生成Movie特征矩阵
loaded_graph = tf.Graph()  #
movie_matrics = []
with tf.Session(graph=loaded_graph) as sess:  #
    # Load saved model
    loader = tf.train.import_meta_graph(load_dir + '.meta')
    loader.restore(sess, load_dir)
 
    # Get Tensors from loaded model
    uid, movie_id, movie_categories, movie_titles, targets, lr, dropout_keep_prob, _, movie_combine_layer_flat, __ = get_tensors(loaded_graph)  #loaded_graph
 
    for item in movies.values:
        categories = np.zeros([1, 18])
        categories[0] = item.take(2)
 
        titles = np.zeros([1, sentences_size])
        titles[0] = item.take(1)
 
        feed = {
            movie_id: np.reshape(item.take(0), [1, 1]),
            movie_categories: categories,  #x.take(3,1)
            movie_titles: titles,  #x.take(2,1)
            dropout_keep_prob: 1}
 
        movie_combine_layer_flat_val = sess.run([movie_combine_layer_flat], feed)  
        movie_matrics.append(movie_combine_layer_flat_val)
 
pickle.dump((np.array(movie_matrics).reshape(-1, 200)), open('movie_matrics.p', 'wb'))
movie_matrics = pickle.load(open('movie_matrics.p', mode='rb'))
 
#生成User特征矩阵
loaded_graph = tf.Graph()  #
users_matrics = []
with tf.Session(graph=loaded_graph) as sess:  #
    # Load saved model
    loader = tf.train.import_meta_graph(load_dir + '.meta')
    loader.restore(sess, load_dir)
 
    # Get Tensors from loaded model
    uid, movie_id, movie_categories, movie_titles, targets, lr, dropout_keep_prob, _, __,user_combine_layer_flat = get_tensors(loaded_graph)  #loaded_graph
 
    for item in users.values:
 
        feed = {
            uid: np.reshape(item.take(0), [1, 1]),
            dropout_keep_prob: 1}
 
        user_combine_layer_flat_val = sess.run([user_combine_layer_flat], feed)  
        users_matrics.append(user_combine_layer_flat_val)
 
pickle.dump((np.array(users_matrics).reshape(-1, 200)), open('./wordsbag/dataprocess/data/week/mydata/users_matrics.p', 'wb'))
users_matrics = pickle.load(open('./wordsbag/dataprocess/data/week/mydata/users_matrics.p', mode='rb'))
 
 
users_matrics = pickle.load(open('./wordsbag/dataprocess/data/week/mydata/users_matrics.p', mode='rb'))
 
#
#
def recommend_same_type_movie(movie_id_val, top_k = 20):
    
    loaded_graph = tf.Graph()  #
    with tf.Session(graph=loaded_graph) as sess:  #
        # Load saved model
        loader = tf.train.import_meta_graph(load_dir + '.meta')
        loader.restore(sess, load_dir)
        
        norm_movie_matrics = tf.sqrt(tf.reduce_sum(tf.square(movie_matrics), 1, keep_dims=True))
        normalized_movie_matrics = movie_matrics / norm_movie_matrics
 
        #推荐同类型的电影
        probs_embeddings = (movie_matrics[movieid2idx[movie_id_val]]).reshape([1, 200])
        probs_similarity = tf.matmul(probs_embeddings, tf.transpose(normalized_movie_matrics))
        sim = (probs_similarity.eval())
    #     results = (-sim[0]).argsort()[0:top_k]
    #     print(results)
        
        print("您看的电影是：{}".format(movies_orig[movieid2idx[movie_id_val]]))
        print("以下是给您的推荐：")
        p = np.squeeze(sim)
        p[np.argsort(p)[:-top_k]] = 0
        p = p / np.sum(p)
        results = set()
        while len(results) != 10:
            c = np.random.choice(501, 1, p=p)[0]
            results.add(c)
        for val in (results):
            print(val)
            print(movies_orig[val])
        
        return results
    
recommend_same_type_movie(20, 10)
 
 
 
 
 
 
 

调用recommend_your_favorite_movie(用户收看过的节目id，推荐个数N） ，可以输入和用户收看节目标签类似的节目。

recommend_your_favorite_movie(20, 10)

运行结果如下： 

您看的电影是：[20 '欢乐颂' '剧情 / 爱情']
以下是给您的推荐：
257
[401 '生活启示录' '剧情 / 爱情']
193
[275 '朋友圈' '剧情 / 爱情']
262
[409 '平凡岁月' '剧情 / 爱情']
426
[770 '公主夜游记' '剧情 / 爱情']
460
[867 '观音山' '剧情 / 爱情']
46
[75 '人间至味是清欢' '剧情 / 爱情']
303
[498 '上海滩' '剧情 / 爱情']
16
[20 '欢乐颂' '剧情 / 爱情']
308
[505 '逆光飞翔' '剧情 / 爱情']
86
[134 '向幸福出发' '剧情 / 爱情']

基于深度学习的推荐算法研究，路漫漫其修远兮。。。。