import osimport pandas as pd
import numpy as npDATA_PATH = "./datasets/ml-latest-small/ratings.csv"dtype = {"userId": np.int32, "movieId": np.int32, "rating": np.float32}# 加载数据，我们只用前三列数据，分别是用户ID，电影ID，已经用户对电影的对应评分ratings = pd.read_csv(data_path, dtype=dtype, usecols=range(3))# 透视表，将电影ID转换为列名称，转换成为一个User-Movie的评分矩阵ratings_matrix = ratings.pivot_table(index=["userId"], columns=["movieId"],values="rating")#计算用户之间相似度user_similar = ratings_matrix.T.corr()

# 1. 找出uid用户的相似用户similar_users = user_similar[1].drop([1]).dropna()# 相似用户筛选规则：正相关的用户similar_users = similar_users.where(similar_users>0).dropna()# 2. 从用户1的近邻相似用户中筛选出对物品1有评分记录的近邻用户ids = set(ratings_matrix[1].dropna().index)&set(similar_users.index)
finally_similar_users = similar_users.ix[list(1)]# 3. 结合uid用户与其近邻用户的相似度预测uid用户对iid物品的评分numerator = 0    # 评分预测公式的分子部分的值
denominator = 0    # 评分预测公式的分母部分的值
for sim_uid, similarity in finally_similar_users.iteritems():# 近邻用户的评分数据sim_user_rated_movies = ratings_matrix.ix[sim_uid].dropna()# 近邻用户对iid物品的评分sim_user_rating_for_item = sim_user_rated_movies[1]# 计算分子的值numerator += similarity * sim_user_rating_for_item# 计算分母的值denominator += similarity# 4 计算预测的评分值predict_rating = numerator/denominator
print("预测出用户<%d>对电影<%d>的评分：%0.2f" % (1, 1, predict_rating))

def predict(uid, iid, ratings_matrix, user_similar):
    '''
    预测给定用户对给定物品的评分值
    :param uid: 用户ID
    :param iid: 物品ID
    :param ratings_matrix: 用户-物品评分矩阵
    :param user_similar: 用户两两相似度矩阵
    :return: 预测的评分值
    '''print("开始预测用户<%d>对电影<%d>的评分..."%(uid, iid))# 1. 找出uid用户的相似用户similar_users = user_similar[uid].drop([uid]).dropna()# 相似用户筛选规则：正相关的用户similar_users = similar_users.where(similar_users>0).dropna()if similar_users.empty is True:raise Exception("用户<%d>没有相似的用户" % uid)# 2. 从uid用户的近邻相似用户中筛选出对iid物品有评分记录的近邻用户ids = set(ratings_matrix[iid].dropna().index)&set(similar_users.index)finally_similar_users = similar_users.ix[list(ids)]# 3. 结合uid用户与其近邻用户的相似度预测uid用户对iid物品的评分numerator = 0    # 评分预测公式的分子部分的值denominator = 0    # 评分预测公式的分母部分的值for sim_uid, similarity in finally_similar_users.iteritems():# 近邻用户的评分数据sim_user_rated_movies = ratings_matrix.ix[sim_uid].dropna()# 近邻用户对iid物品的评分sim_user_rating_for_item = sim_user_rated_movies[iid]# 计算分子的值numerator += similarity * sim_user_rating_for_item# 计算分母的值denominator += similarity# 计算预测的评分值并返回predict_rating = numerator/denominatorprint("预测出用户<%d>对电影<%d>的评分：%0.2f" % (uid, iid, predict_rating))return round(predict_rating, 2)

def predict_all(uid, ratings_matrix, user_similar):
    '''
    预测全部评分
    :param uid: 用户id
    :param ratings_matrix: 用户-物品打分矩阵
    :param user_similar: 用户两两间的相似度
    :return: 生成器，逐个返回预测评分
    '''# 准备要预测的物品的id列表item_ids = ratings_matrix.columns# 逐个预测for iid in item_ids:try:rating = predict(uid, iid, ratings_matrix, user_similar)except Exception as e:print(e)else:yield uid, iid, rating
if __name__ == '__main__':for i in predict_all(1, ratings_matrix, user_similar):pass

def top_k_rs_result(k):results = predict_all(1, ratings_matrix, user_similar)return sorted(results, key=lambda x: x[2], reverse=True)[:k]
if __name__ == '__main__':from pprint import pprintresult = top_k_rs_result(20)pprint(result)

import osimport pandas as pd
import numpy as npDATA_PATH = "./datasets/ml-latest-small/ratings.csv"dtype = {"userId": np.int32, "movieId": np.int32, "rating": np.float32}# 加载数据，我们只用前三列数据，分别是用户ID，电影ID，已经用户对电影的对应评分ratings = pd.read_csv(data_path, dtype=dtype, usecols=range(3))# 透视表，将电影ID转换为列名称，转换成为一个User-Movie的评分矩阵ratings_matrix = ratings.pivot_table(index=["userId"], columns=["movieId"],values="rating")#计算用户之间相似度item_similar = ratings_matrix.corr()

# 1. 找出iid物品的相似物品similar_items = item_similar[1].drop([1]).dropna()# 相似物品筛选规则：正相关的物品similar_items = similar_items.where(similar_items>0).dropna()# 2. 从iid物品的近邻相似物品中筛选出uid用户评分过的物品ids = set(ratings_matrix.ix[1].dropna().index)&set(similar_items.index)
finally_similar_items = similar_items.ix[list(ids)]# 3. 结合iid物品与其相似物品的相似度和uid用户对其相似物品的评分，预测uid对iid的评分numerator = 0    # 评分预测公式的分子部分的值
denominator = 0    # 评分预测公式的分母部分的值
for sim_iid, similarity in finally_similar_items.iteritems():# 近邻物品的评分数据sim_item_rated_movies = ratings_matrix[sim_iid].dropna()# 1用户对相似物品物品的评分sim_item_rating_from_user = sim_item_rated_movies[1]# 计算分子的值numerator += similarity * sim_item_rating_from_user# 计算分母的值denominator += similarity# 计算预测的评分值并返回predict_rating = sum_up/sum_down
print("预测出用户<%d>对电影<%d>的评分：%0.2f" % (uid, iid, predict_rating))

def predict(uid, iid, ratings_matrix, user_similar):
    '''
    预测给定用户对给定物品的评分值
    :param uid: 用户ID
    :param iid: 物品ID
    :param ratings_matrix: 用户-物品评分矩阵
    :param user_similar: 用户两两相似度矩阵
    :return: 预测的评分值
    '''print("开始预测用户<%d>对电影<%d>的评分..."%(uid, iid))# 1. 找出uid用户的相似用户similar_users = user_similar[uid].drop([uid]).dropna()# 相似用户筛选规则：正相关的用户similar_users = similar_users.where(similar_users>0).dropna()if similar_users.empty is True:raise Exception("用户<%d>没有相似的用户" % uid)# 2. 从uid用户的近邻相似用户中筛选出对iid物品有评分记录的近邻用户ids = set(ratings_matrix[iid].dropna().index)&set(similar_users.index)finally_similar_users = similar_users.ix[list(ids)]# 3. 结合uid用户与其近邻用户的相似度预测uid用户对iid物品的评分numerator = 0    # 评分预测公式的分子部分的值denominator = 0    # 评分预测公式的分母部分的值for sim_uid, similarity in finally_similar_users.iteritems():# 近邻用户的评分数据sim_user_rated_movies = ratings_matrix.ix[sim_uid].dropna()# 近邻用户对iid物品的评分sim_user_rating_for_item = sim_user_rated_movies[iid]# 计算分子的值numerator += similarity * sim_user_rating_for_item# 计算分母的值denominator += similarity# 计算预测的评分值并返回predict_rating = numerator/denominatorprint("预测出用户<%d>对电影<%d>的评分：%0.2f" % (uid, iid, predict_rating))return round(predict_rating, 2)

def predict_all(uid, ratings_matrix, item_similar):
    '''
    预测全部评分
    :param uid: 用户id
    :param ratings_matrix: 用户-物品打分矩阵
    :param item_similar: 物品两两间的相似度
    :return: 生成器，逐个返回预测评分
    '''# 准备要预测的物品的id列表item_ids = ratings_matrix.columns# 逐个预测for iid in item_ids:try:rating = predict(uid, iid, ratings_matrix, item_similar)except Exception as e:print(e)else:yield uid, iid, ratingif __name__ == '__main__':for i in predict_all(1, ratings_matrix, item_similar):pass

def top_k_rs_result(k):results = predict_all(1, ratings_matrix, item_similar)return sorted(results, key=lambda x: x[2], reverse=True)[:k]
if __name__ == '__main__':from pprint import pprintresult = top_k_rs_result(20)pprint(result)