嘤~本节代码比着书上的源码看了一遍并加上了自己的理解注释，但并没有运行成功，因为他运行警告，我还不会改错
亲和力分析：从频繁出现的商品中选取共同出现额商品组成频繁项集，生成关联规则
import os
import pandas as pd
import sys
#数据读取
ratings_filename = "D:\\python27\\study\\code\\Chapter4\\ml-1M\\ratings.dat"
#数据规范化
all_ratings = pd.read_csv(ratings_filename, delimiter="\t", header=None, names = ["UserID", "MovieID", "Rating", "Datetime"])
all_ratings["Datetime"] = pd.to_datetime(all_ratings['Datetime'],unit='s')
all_ratings[:5]
all_ratings["Favorable"] = all_ratings["Rating"] > 3
all_ratings[10:15]
#选取部分数据
ratings = all_ratings[all_ratings['UserID'].isin(range(200))] #取前200名用户的打分数据
favorable_ratings = ratings[ratings["Favorable"]] # 只包括用户喜欢电影的数据行
favorable_ratings[:5]
favorable_reviews_by_users = dict((k, frozenset(v.values)) for k, v in favorable_ratings.groupby("UserID")["MovieID"])#知道每个用户各喜欢哪个些电影
len(favorable_reviews_by_users)
num_favorable_by_movie = ratings[["MovieID", "Favorable"]].groupby("MovieID").sum()#知道某个电影的影迷有多少
num_favorable_by_movie.sort("Favorable", ascending=False)[:5]#查看最受欢迎的五部电影
frequent_itemsets = {} # 以项集长度为字典的键
min_support = 50 #最小支持度
#为每一部电影生成只包含它自己的项集，检测它是否够频繁
frequent_itemsets[1] = dict((frozenset((movie_id,)), row["Favorable"])
for movie_id, row in num_favorable_by_movie.iterrows()
if row["Favorable"] > min_support)
from collections import defaultdict
#接收新发现的频繁项集，创建超集，检测频繁程度
def find_frequent_itemsets(favorable_reviews_by_users, k_1_itemsets, min_support):
counts = defaultdict(int)
for user, reviews in favorable_reviews_by_users.items():
for itemset in k_1_itemsets:
if itemset.issubset(reviews):
for other_reviewed_movie in reviews - itemset:
current_superset = itemset | frozenset((other_reviewed_movie,))
counts[current_superset] += 1
return dict([(itemset, frequency) for itemset, frequency in counts.items() if frequency >= min_support])
print("There are {} movies with more than {} favorable reviews".format(len(frequent_itemsets[1]), min_support))
sys.stdout.flush()
for k in range(2, 20):
cur_frequent_itemsets = find_frequent_itemsets(favorable_reviews_by_users, frequent_itemsets[k-1],
min_support)
if len(cur_frequent_itemsets) == 0:
print("Did not find any frequent itemsets of length {}".format(k))
sys.stdout.flush()
break
else:
print("I found {} frequent itemsets of length {}".format(len(cur_frequent_itemsets), k))
#print(cur_frequent_itemsets)
sys.stdout.flush()
frequent_itemsets[k] = cur_frequent_itemsets
del frequent_itemsets[1]#删除只有一个元素的项集
print("Found a total of {0} frequent itemsets".format(sum(len(itemsets) for itemsets in frequent_itemsets.values())))
#抽取关联规则
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))
print("There are {} candidate rules".format(len(candidate_rules)))
print(candidate_rules[:5]) #查看前五条规则
correct_counts = defaultdict(int) #规则应验
incorrect_counts = defaultdict(int) #规则不适用
for user, reviews in favorable_reviews_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] += 1
#计算每条规则的置信度
rule_confidence = {candidate_rule: correct_counts[candidate_rule] / float(correct_counts[candidate_rule] + incorrect_counts[candidate_rule])
for candidate_rule in candidate_rules}
min_confidence = 0.9
rule_confidence = {rule: confidence for rule, confidence in rule_confidence.items() if confidence > min_confidence}
print(len(rule_confidence))
#输出置信度最高的前五条规则
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("")
movie_name_filename = "D:\\python27\\study\\code\\Chapter4\\ml-1M\\movies.dat"
movie_name_data = pd.read_csv(movie_name_filename, 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"]