电影推荐_亲和性分析_规则提取(数据挖掘入门与实践-实验6)

#数据导入 import os import pandas as pdall_ratings=pd.read_csv("ml-100k/u.data", delimiter="\t", header=None, names=["UserID", "MovieID", "Rating", "Datetime"]) all_ratings["Datatime"]=pd.to_datetime(all_ratings["Datetime"], unit='s') all_ratings=all_ratings[["UserID", "MovieID", "Rating", "Datatime"]] #all_ratings[:5]#是否电影喜爱特征添加 all_ratings["Favorable"]=all_ratings["Rating"]>3 #all_ratings[:15]#UserID<=200的数据截取 ratings_200=all_ratings[all_ratings["UserID"].isin(range(200))] #print(ratings_200)#用户喜爱电影提取 favorable_ratings = ratings_200[ratings_200["Favorable"]] #print(favorable_ratings) favorable_reviews_by_users=dict((k, frozenset(v.values)) for k, v in favorable_ratings.groupby("UserID")["MovieID"]) #print(favorable_reviews_by_users)#最受欢迎电影提取 nums_favorable_by_movie=ratings_200[["MovieID", "Favorable"]].groupby("MovieID").sum() #nums_favorable_by_movie.sort_values("Favorable", ascending=False)[:5]####################Aprior算法#频繁集字典 frequent_itemsets = {}#最小支持度 min_support=50#备选项集生成 frequent_itemsets[1]=dict((frozenset((movie_id,)),row["Favorable"]) for movie_id,row in nums_favorable_by_movie.iterrows() if row["Favorable"]>min_support) #print(frequent_itemsets[1])#备选集检测 from collections import defaultdict def find_frequent_itemsets(favorable_reviews_by_users,k_l_itemsets, min_support):counts=defaultdict(int)for user,reviews in favorable_reviews_by_users.items():for itemset in k_l_itemsets:if itemset.issubset(reviews):for other_reviewed_movie in reviews - itemset: current_superset = itemset | frozenset((other_reviewed_movie,)) counts[current_superset] += 1return dict([(itemset, frequency) for itemset, frequency in counts.items() if frequency >= min_support])#循环创建，运行Apriori import sys for k in range(2, 20): cur_frequent_itemsets = find_frequent_itemsets(favorable_reviews_by_users, frequent_itemsets[k-1], min_support) frequent_itemsets[k] = cur_frequent_itemsets#检测频繁集项数if len(cur_frequent_itemsets) == 0: #print("Did not find any frequent itemsets of length {}". format(k)) sys.stdout.flush() breakelse: #print("I found {} frequent itemsets of length {}".format(len(cur_frequent_itemsets), k)) sys.stdout.flush()del frequent_itemsets[1]#规则生成 candidate_rules = [] for itemset_length, itemset_counts in frequent_itemsets.items(): for itemset in itemset_counts.keys(): for conclusion in itemset: premise = itemset - set((conclusion,)) candidate_rules.append((premise, conclusion)) candidate_rules[:5]#规则置信度计算 correct_counts = defaultdict(int) incorrect_counts = defaultdict(int)for user, reviews in favorable_reviews_by_users.items(): for candidate_rule in candidate_rules: premise, conclusion = candidate_ruleif premise.issubset(reviews):if conclusion in reviews: correct_counts[candidate_rule] += 1 else: incorrect_counts[candidate_rule] += 1rule_confidence = {candidate_rule: correct_counts[candidate_rule] / float(correct_counts[candidate_rule] + incorrect_counts[candidate_rule]) for candidate_rule in candidate_rules}from operator import itemgetter sorted_confidence = sorted(rule_confidence.items(), key=itemgetter(1), reverse=True) for index in range(5): #print("Rule #{0}".format(index + 1)) (premise, conclusion) = sorted_confidence[index][0]#print("Rule: If a person recommends {0} they will also recommend {1}".format(premise, conclusion)) #print(" - Confidence: {0:.3f}".format(rule_confidence[(premise, conclusion)])) #print("")#ml-100k/u.item #u.items数据加载 movie_name_data = pd.read_csv("ml-100k/u.item", delimiter="|",header=None, encoding = "mac-roman") movie_name_data.columns = ["MovieID", "Title", "Release Date", "Video Release", "IMDB", "<UNK>", "Action", "Adventure", "Animation", "Children's", "Comedy", "Crime", "Documentary", "Drama", "Fantasy", "Film-Noir", "Horror", "Musical", "Mystery", "Romance", "Sci-Fi", "Thriller", "War", "Western"]def get_movie_name(movie_id):title_object = movie_name_data[movie_name_data["MovieID"] ==movie_id]["Title"]title = title_object.values[0]return titlefor index in range(5): #print("Rule #{0}".format(index + 1)) (premise, conclusion) = sorted_confidence[index][0] premise_names = ", ".join(get_movie_name(idx) for idx in premise) conclusion_name = get_movie_name(conclusion) #print("Rule: If a person recommends {0} they will also recommend {1}".format(premise_names, conclusion_name)) #print(" - Confidence: {0:.3f}".format(rule_confidence[(premise, conclusion)])) #print("")#training && testtest_dataset = all_ratings[~all_ratings['UserID'].isin(range(200))] test_favorable = test_dataset[test_dataset["Favorable"]] test_favorable_by_users = dict((k, frozenset(v.values)) for k, v in test_favorable.groupby("UserID")["MovieID"])correct_counts = defaultdict(int) incorrect_counts = defaultdict(int) for user, reviews in test_favorable_by_users.items(): for candidate_rule in candidate_rules: premise, conclusion = candidate_rule if premise.issubset(reviews): if conclusion in reviews: correct_counts[candidate_rule] += 1 else: incorrect_counts[candidate_rule] += 1test_confidence = {candidate_rule: correct_counts[candidate_rule] / float(correct_counts[candidate_rule] + incorrect_counts [candidate_rule]) for candidate_rule in rule_confidence}for index in range(5): #print("Rule #{0}".format(index + 1)) (premise, conclusion) = sorted_confidence[index][0] premise_names = ", ".join(get_movie_name(idx) for idx in premise) conclusion_name = get_movie_name(conclusion) #print("Rule: If a person recommends {0} they will also recommend {1}".format(premise_names, conclusion_name)) #print(" - Train Confidence: {0:.3f}".format(rule_confidence.get((premise, conclusion), -1))) #print(" - Test Confidence: {0:.3f}".format(test_confidence.get((premise, conclusion), -1))) #print("")

总结

以上是生活随笔为你收集整理的电影推荐_亲和性分析_规则提取(数据挖掘入门与实践-实验6)的全部内容，希望文章能够帮你解决所遇到的问题。

如果觉得生活随笔网站内容还不错，欢迎将生活随笔推荐给好友。