##ml_1m数据集下载地址:
http://files.grouplens.org/datasets/movielens/
##基于用户的协同过滤
import numpy as np
import pandas as pd
file = "ml-1m/ratings.dat"
header = ["uid","iid","rating"]
dtype = {
"uid" :np.int32,"iid":np.int32,"rating":np.float32}
data = pd.read_csv(file,sep="::",usecols=range(3),names=header,dtype=dtype)
# print(data)
#构建透视表,找到用户与电影之间的评分关系
rating_matrix = data.pivot_table(index=["uid"],columns=["iid"],values="rating")
# print(rating_matrix)
#计算相似度 .corr():计算两列之间的pearson相似度
similar = rating_matrix.T.corr