数据集请点赞收藏关注后评论区留言并且私信博主要

本例中使用得是著名得电影数据集MovieLens-100数据集

MoviesLens数据集是实现和测试电影推荐最常用得数据集之一，包含943个用户为精选得1682部电影给出得100000个电影评分

主要文件如下1:u.data 2:u.item 3:u.user

1：查看用户/电影排名信息得代码如下

importpandas as pdheads=['user_id','item_id','rating','timestamp']ratings=pd.read_csv(r'u.data',sep='\t',names=heads)print(ratings)print("用户数量",len(ratings))

2：查看导入的电影数据表

代码如下

importpandas as pdu_cols=['user_id','age','sex','occupation','zip_code']users=pd.read_csv(r'u.data',sep='|',names=u_cols,encoding='latin-1')print(users)r_cols=['user_id','movie_id','rating','unix_timestamp']ratings=pd.read_csv(r'u.data',sep='\t',names=r_cols,encoding='latin-1')print(ratings)m_cols=['movie_id','title','release_data','video_release_data','imdb_url']movies=pd.read_csv(r'u.item',sep='|',names=m_cols,usecols=range(5),encoding='latin-1')print(movies)

3：用协同过滤推荐算法进行电影推荐

误差评估如下

全部代码如下

importpandas as pdimportnumpy as npfrom sklearn.metrics.pairwise import pairwise_distancesnp.set_printoptions(suppress=True)# 取消科学计数法输出pd.set_option('display.max_rows', None) # 展示所有行pd.set_option('display.max_columns', None) # 展示所有列def predict(scoredata,similarity,type='user'):#基于物品得推荐if type=='item':predt_mat=scoredata.dot(similarity)/np.array([np.abs(similarity).sum(axis=1)])elif type=='user':#计算用户评分值 减少用户评分高低习惯影响user_meanscorse=scoredata.mean(axis=1)score_diff=(scoredata-user_meanscorse.reshape(-1,1))predt_mat=user_meanscorse.reshape(-1,1)+similarity.dot(score_diff)/np.array([np.abs(similarity).sum(axis=1)]).Treturn predt_mat#读取数据print('step 1 读取数据')r_cols=['user_id','movie_id','rating','unix_timestamp']scoredata=pd.read_csv(r'u.data',sep='\t',names=r_cols,encoding='latin-1')print('数据形状',scoredata.shape)#生成用户-物品评分矩阵print('step2 生成 用户物品评分矩阵')n_users=943n_items=1682data_matrix=np.zeros((n_users,n_items))for line in range(np.shape(scoredata)[0]):row=scoredata['user_id'][line]-1col=scoredata['movie_id'][line]-1score=scoredata['rating'][line]data_matrix[row,col]=scoreprint('用户物品矩阵形状',data_matrix.shape)#计算相似度print('step3 计算相似度')user_similaritry=pairwise_distances(data_matrix,metric='cosine')item_similarity=pairwise_distances(data_matrix.T,metric='cosine')print('user similarity',user_similaritry.shape)print('item similartity',item_similarity.shape)#进行相似度进行预测print('step4 预测')user_prediction=predict(data_matrix,user_similaritry,type='user')item_perdiction=predict(data_matrix,item_similarity,type='item')#显示推荐结果print('step 5 显示推荐结果')print('----------------')print('ubcf预测形状',user_prediction.shape)print('real answer\n',data_matrix[:5,5])print('预测结果\n',user_prediction)print('ibcf预测形状',item_perdiction.shape)print('real answer\n',data_matrix[:5,:5])print('预测结果\n',item_perdiction)#性能评估print('step 6 性能评估')from sklearn.metrics import mean_squared_errorfrom math import sqrtdef rmse(predct,realNum):predct=predct[realNum.nonzero()].flatten()realNum=realNum[realNum.nonzero()].flatten()return sqrt(mean_squared_error(predct,realNum))print('u-base mse=',str(rmse(user_prediction,data_matrix)))print('m-based mse=',str(rmse(item_perdiction,data_matrix)))

数据集请点赞收藏关注后私信博主要