商业分析python实战（二）：电影智能推荐

import pandas as pd
import numpy as np
import matplotlib
import matplotlib.pyplot as plt
import math
import operator
from sklearn import model_selection as ms

#step1:获取数据
print("#step1:获取数据")
datafile = pd.read_csv('dataMovieLense.csv')
#print(datafile.head(10))

#step2:数据探索分析
print("#step2:数据探索分析")
datafile.info()#数据基本信息
datafile.score.isna().sum()#数据缺失值数量
datafile = datafile.dropna(axis=0)#删除存在缺失值的行
datafile.loc[datafile['score'] > 5]#存在异常值
datafile = datafile.drop(datafile[datafile.score >5].index)#删除异常值
#print(datafile.shape)#输出数据维数
datafile_trans = pd.pivot(datafile, index='user', columns='movie', values='score')#将movie中的电影名转换为列名
#print(datafile_trans.head())
datafile_trans.describe()
df_index = datafile_trans.index
df_columns = datafile_trans.columns
datafile_trans = datafile_trans.fillna(0).to_numpy() 

#step3:构建智能推荐模型
print("#step3:构建智能推荐模型")
from sklearn.metrics.pairwise import cosine_similarity
item_similarity = cosine_similarity(datafile_trans.T)#电影间的相似度矩阵
pd.DataFrame(item_similarity,index=df_columns,columns = df_columns).head()

class ItemCf():

    ########获得初始化数据,字典格式
    def __init__(self,data):
        data_dic = {}
        #self.itemSim = dict()
        for line in data.itertuples():
            if not line[1] in data_dic.keys():
                
                data_dic[line[1]]={line[2]:line[3]}
            else:
                data_dic[line[1]][line[2]]=line[3]
        self.data = data_dic
        self.ItemSimilarity()
        
    def ItemSimilarity(self):
        self.itemSim = dict()
        movie_popular = dict() #item_user_count{item: likeCount} the number of users who like the item
        count = dict() #count{i:{j:value}} the number of users who both like item i and j
        for user,movies in self.data.items():
            for movie in movies:
                if movie not in movie_popular:
                    movie_popular[movie] = 0
                movie_popular[movie] += 1
        movie_count = len(movie_popular)
        print('Total movies: %d'% movie_count)

        for user,movies in self.data.items():
            for m1 in movies:
                for m2 in movies:
                    if m1 == m2:
                        continue
                    self.itemSim.setdefault(m1,{})
                    self.itemSim[m1].setdefault(m2,0)
                    self.itemSim[m1][m2] += 1/math.log(1+len(movies))
        print('Build co-rated users matrix success!')

        for m1,related_movies in self.itemSim.items():
            for m2,count in related_movies.items():
                if movie_popular[m1] == 0 or movie_popular[m2] == 0:
                    movie_sim_matrix[m1][m2] = 0
                else:
                    self.itemSim[m1][m2] = count / math.sqrt(movie_popular[m1]*movie_popular[m2])
        print('Calculate movie similarity matrix success!')

        max_w = 0
        for m1,related_movies in self.itemSim.items():
            for m2,_ in related_movies.items():
                if self.itemSim[m1][m2] > max_w:
                    max_w = self.itemSim[m1][m2]
        for m1,related_movies in self.itemSim.items():
            for m2,_ in related_movies.items():
                self.itemSim[m1][m2] = self.itemSim[m1][m2]/max_w

    def Recomand(self,user,n_sim_movie=10,n_rec_movie=5):
        K = n_sim_movie
        N = n_rec_movie
        rank = {}
        watched_movies = self.data[user]
        for movie,rating in watched_movies.items():
            for related_movie,w in sorted(self.itemSim[movie].items(),key=operator.itemgetter(1),reverse=True)[:K]:
                if related_movie in watched_movies:
                    continue
                rank.setdefault(related_movie,0)
                rank[related_movie] += w*float(rating)
        return sorted(rank.items(),key=operator.itemgetter(1),reverse=True)[0:N]

if __name__=='__main__':
    
    datafile['user']=datafile['user'].astype(str)
    print(datafile.head())
    itemCf=ItemCf(data=datafile)
    recommandList=itemCf.Recomand('1.0',20,10)
    print('用户1.0的推荐结果为：' + str(recommandList))