recommend.py

import numpy as np
import pandas  as pd

header = ['user_id', 'item_id', 'rating', 'timestamp']
df = pd.read_csv('ml-100k/u.data', sep='\t', names=header)
n_users = df.user_id.unique().shape[0]
n_items = df.item_id.unique().shape[0]
print('Number of users = ' + str(n_users) + ' | Number of movies = ' + str(n_items))
#你可以使用scikit-learn库将数据集分割成测试和训练。Cross_validation.train_test_split
#根据测试样本的比例（test_size），本例中是0.25，来将数据混洗并分割成两个数据集
from sklearn import model_selection  as ms
train_data, test_data = ms.train_test_split(df, test_size=0.25)
#Create two user-item matrices, one for training and another for testing
train_data_matrix = np.zeros((n_users, n_items))
for line in train_data.itertuples():
    train_data_matrix[line[1]-1, line[2]-1] = line[3] 
test_data_matrix = np.zeros((n_users, n_items))
for line in test_data.itertuples():
    test_data_matrix[line[1]-1, line[2]-1] = line[3]
    
from sklearn.metrics.pairwise import pairwise_distances
user_similarity = pairwise_distances(train_data_matrix, metric='cosine')
item_similarity = pairwise_distances(train_data_matrix.T, metric='cosine')
print(user_similarity)

def predict(ratings, similarity, type='user'):
    #ratings.mean(axis=1) 按行求平均值
    if type == 'user':
        mean_user_rating = ratings.mean(axis=1)
        #You use np.newaxis so that mean_user_rating has same format as ratings
        ratings_diff = (ratings - mean_user_rating[:, np.newaxis]) 
        pred = mean_user_rating[:, np.newaxis] + similarity.dot(ratings_diff) / np.array([np.abs(similarity).sum(axis=1)]).T
    elif type == 'item':
        pred = ratings.dot(similarity) / np.array([np.abs(similarity).sum(axis=1)])     
    return pred
    
item_prediction = predict(train_data_matrix, item_similarity, type='item')
user_prediction = predict(train_data_matrix, user_similarity, type='user')