数据挖掘-商品购买记录-商品推荐_亲和度分析

# coding: utf-8
import numpy as np
dataset_filename="affinity_dataset.txt"
#加载数据文件
dataset=np.loadtxt(dataset_filename)
'''
数据结果:
array([[ 0.,  0.,  1.,  1.,  1.],
[ 1.,  1.,  0.,  1.,  0.]
])
'''
#一行表示一个用户对五个商品的购买情况,1表示买了，0表示没买
n_samples,n_features=dataset.shape
print("{0} samples in total with {1} features".format(n_samples,n_features))

#定义特征名集合
features=["bread","milk","cheese","apple","banana"]

#目标一 ， 找出以下规则:要找出用户购买了apple, 那他也可能购买banana
# 前提：计算规则的支持度和置信度
#支持度:数据集中规则应验的次数.
#置信度: 符合给定条件的所有规则里，跟当前规则结论一致的比例有多少.

#首先, 有多少行有这条规则的前提条件
num_apple_purchases=0
for sample in dataset:
if sample[3]==1:
num_apple_purchases+=1
print("{0} people bought apples".format(num_apple_purchases))

#下面可以计算这条规则的应验数和无效数
rule_valid=0.0
rule_invalid=0
for sample in dataset:
if sample[3]==1:
if sample[4]==1:
rule_valid+=1
else:
rule_invalid+=1
print("{0} cases of the rule being valid".format(rule_valid))
print("{0} cases of the rule being invalid".format(rule_invalid))

#支持度
support=rule_valid
#置信度
confidence=rule_valid/num_apple_purchases
print("the support is {0} and the confidence is {1:.3f}".format(support, confidence))

################################################################
#有了上面的案例，用于理解支持度和置信度
#下面开始所有的规则的支持度和置信度的计算

from collections import defaultdict
#数据格式采用字典：{ 键(前提,结论), 值(数值)}
valid_rules=defaultdict(int)    #每条规则的支持度
invalid_rules=defaultdict(int)  #每条规则的无效数
#数据格式采用字典：{ 键(前提), 值(数值)}
num_rule_occurances=defaultdict(float)   #规则条件出现的次数

for sample in dataset:
# premise 前提条件
for premise in range(n_features):
if sample[premise] ==0: continue    #这个商品没有购买，则表示这个前提不成立,跳过循环
num_rule_occurances[premise]+=1.0     #出现了一次前提条件
for conclusion in range(n_features):   #计算它的支持度和无效数
if premise==conclusion:
continue
if sample[conclusion]==1:
valid_rules[(premise,conclusion)]+=1
else:
invalid_rules[(premise,conclusion)]+=1

support=valid_rules
confidence=defaultdict(float)
for premise,conclusion in valid_rules.keys():
confidence[(premise,conclusion)]=valid_rules[(premise,conclusion)]/num_rule_occurances[premise]
#下面将结果输出一下
for premise, conclusion in confidence:
#求出规则前提条件商品名
premise_name=features[premise]
#求出规则条件的结论对应的商品名
conclusion_name=features[conclusion]
print("Rule: if a person buys {0} they will also buy {1}".format(premise_name,conclusion_name))
print(" this rule's support is :{0}".format( support[(premise,conclusion)]     )  )
print(" this rule's confidence is :{0}".format( confidence[(premise,conclusion)]     )  )
print("")

'''
将输出部分定义成一个函数
premise: 前提 的索引
conclusion: 结论的索引
support: 支持度字典
confidence: 置信度字典
features: 特征数组
'''
def print_rule( premise,conclusion,support,confidence,features):
#求出规则前提条件商品名
premise_name=features[premise]
#求出规则条件的结论对应的商品名
conclusion_name=features[conclusion]
print("Rule: if a person buys {0} they will also buy {1}".format(premise_name,conclusion_name))
print(" this rule's support is :{0}".format( support[(premise,conclusion)]     )  )
print(" this rule's confidence is :{0}".format( confidence[(premise,conclusion)]     )  )
print("")

#调用上面的函数，输出计算好的规则的支持度和置信度,比如，买了milk后又买apple的支持度和置信度
premise=1
conclusion=3
print_rule(premise,conclusion,support,confidence,features)

###################################################################################
'''
下面对支持度进行排序
'''
#先排序输出
from pprint import pprint
pprint(list(support.items()))
#排好序后存到字典中
from operator import itemgetter
#                根据支持度的值排序
sorted_support=sorted(support.items(), key=itemgetter(1),reverse=True)
#输出前三名
for index in range(5):
print("Rule #{0}".format(index+1))
(premise,conclusion)=sorted_support[index][0]   #取出键
print_rule( premise, conclusion, support,confidence,features)
'''
下面对信任度进行排序
'''
#先排序输出
pprint(list(confidence.items()))
#排好序后存到字典中
#                根据信任度的值排序
sorted_confidence=sorted(confidence.items(), key=itemgetter(1),reverse=True)
#输出前三名
for index in range(5):
print("Rule #{0}".format(index+1))
(premise,conclusion)=sorted_confidence[index][0]   #取出键
print_rule( premise, conclusion, support,confidence,features)