数据挖掘 —支持度和置信度的用法

# 面包,牛奶,奶酪,苹果,香蕉
from collections import OrderedDict
import numpy as np 
from pyexcel_xls import get_data
from pyexcel_xls import save_data
xls_data = get_data(r"777.xls")
features = ["bread", "milk", "cheese", "apples", "bananas"]

# print (xls_data['Sheet1'])
lis =xls_data['Sheet1']
X= np.array(lis)
n_samples,n_features=X.shape  # 获取行数
print(n_samples)
print(n_features)
# print(X)
# 统计买苹果的人数
num_apple_purchaes =0
for  sample  in X:
    if sample[3]==1:
        num_apple_purchaes +=1
print("{0} people bought Apples".format(num_apple_purchaes))
from collections import defaultdict

valid_rules =defaultdict(int)         # 接受应验次数
invalid_rules =defaultdict(int)       # 接受不应验次数
num_occurences =defaultdict(int)       # 接受出现次数



for sample in X:                                 #对每一行进行循环
    for premise in range(n_features):            #对每列进行循环
        if sample[premise] == 0: continue        #判断该行的某一列列元素是否位0，即是否购买，若为0，跳出本轮循环，测试下一列
        
        num_occurences[premise] += 1             #记录有购买的一列 sample[premise]
        for conclusion in range(n_features):     #当读取到某一列有购买后，再次循环每一列的值
            if premise == conclusion:            #排除相同的一列，若循环到同一列，则跳出循环，比较下一列
                continue
            if sample[conclusion] == 1:          #当sample[conclusion] 的值为1时，满足了当顾客购买前一件商品时也买了这种商品
                
                valid_rules[(premise, conclusion)] += 1  #记录下该规则出现的次数
            else:
                
                invalid_rules[(premise, conclusion)] += 1  #当不满足时即 sample[conclusion]=0 时，记录下不满足该规则的次数
support = valid_rules                               #支持度=规则出现的次数
confidence = defaultdict(float)                     #强制将置信度转为浮点型
for premise, conclusion in valid_rules.keys():
    confidence[(premise, conclusion)] = valid_rules[(premise, conclusion)] / num_occurences[premise] #计算某一规则的置信度，并将其存在字典confidence中

    
    
for premise, conclusion in confidence:     #根据字典的两个参数来取值
    premise_name = features[premise]       #我们之前定义了features列表，它的每一列都对应数组的每一列，即商品名称
    conclusion_name = features[conclusion] #商品名称
 
    print("Rule: 如果顾客购买 {0} 那么他可能同时购买 {1}".format(premise_name, conclusion_name))
    print(" - Confidence: {0:.3f}".format(confidence[(premise, conclusion)]))
    print(" - Support: {0}".format(support[(premise, conclusion)]))
    print("")

25
5
18 people bought Apples
Rule: 如果顾客购买 bread 那么他可能同时购买 milk
 - Confidence: 0.533
 - Support: 8

Rule: 如果顾客购买 milk 那么他可能同时购买 cheese
 - Confidence: 0.222
 - Support: 2

Rule: 如果顾客购买 apples 那么他可能同时购买 cheese
 - Confidence: 0.333
 - Support: 6

Rule: 如果顾客购买 milk 那么他可能同时购买 apples
 - Confidence: 0.444
 - Support: 4

Rule: 如果顾客购买 bread 那么他可能同时购买 apples
 - Confidence: 0.667
 - Support: 10

Rule: 如果顾客购买 apples 那么他可能同时购买 bread
 - Confidence: 0.556
 - Support: 10

Rule: 如果顾客购买 apples 那么他可能同时购买 bananas
 - Confidence: 0.611
 - Support: 11

Rule: 如果顾客购买 apples 那么他可能同时购买 milk
 - Confidence: 0.222
 - Support: 4

Rule: 如果顾客购买 milk 那么他可能同时购买 bananas
 - Confidence: 0.556
 - Support: 5

Rule: 如果顾客购买 cheese 那么他可能同时购买 bananas
 - Confidence: 0.556
 - Support: 5

Rule: 如果顾客购买 cheese 那么他可能同时购买 bread
 - Confidence: 0.556
 - Support: 5

Rule: 如果顾客购买 cheese 那么他可能同时购买 apples
 - Confidence: 0.667
 - Support: 6

Rule: 如果顾客购买 cheese 那么他可能同时购买 milk
 - Confidence: 0.222
 - Support: 2

Rule: 如果顾客购买 bananas 那么他可能同时购买 apples
 - Confidence: 0.647
 - Support: 11

Rule: 如果顾客购买 bread 那么他可能同时购买 bananas
 - Confidence: 0.467
 - Support: 7

Rule: 如果顾客购买 bananas 那么他可能同时购买 cheese
 - Confidence: 0.294
 - Support: 5

Rule: 如果顾客购买 milk 那么他可能同时购买 bread
 - Confidence: 0.889
 - Support: 8

Rule: 如果顾客购买 bananas 那么他可能同时购买 milk
 - Confidence: 0.294
 - Support: 5

Rule: 如果顾客购买 bread 那么他可能同时购买 cheese
 - Confidence: 0.333
 - Support: 5

Rule: 如果顾客购买 bananas 那么他可能同时购买 bread
 - Confidence: 0.412
 - Support: 7