数据挖掘学习相关

一直以来对机器学习，数据挖掘这块挺感兴趣，最近有时间就买了本《python数据挖掘入门与实践》，这篇文章主要贴一些书里面的代码，和我自己的一些理解与注释，供以后复习查看

商品推荐：

#coding=utf-8
#如果开头不声明保存编码的格式是什么，那么它会默认使用ASKII码保存文件，这时如果你的代码中有中文就会出错了，即使你的中文是包含在注释里面的。所以加上中文注释很重要。

import numpy as np
from collections import defaultdict

def calS(X , n_feature):
    valid_rules = defaultdict(int)             #规则应验
    invalid_rules = defaultdict(int)            #规则无效
    num_occurances = defaultdict(int)            #条件相同的规则数量

    for sample in X:
        for premise in range(5):                    #这一段主要统计在某一水果出现的情况下其他水果出现的次数
            if sample[premise] == 0:                 #如果没有，就直接跳过
                continue
            num_occurances[premise] += 1
            for conclusion in range(n_features):         #统计在该水果出现的情况下其他水果也出现， 就加一
                if premise == conclusion:
                    continue
                if sample[conclusion] == 1:
                    valid_rules[(premise , conclusion)] += 1
                else:
                    invalid_rules[(premise , conclusion)] += 1

    support = valid_rules                      #支持度就是规则应验的次数

    confidence = defaultdict(float)            #计算置信度
    for premise , conclusion in valid_rules.keys():
        rule = (premise , conclusion)
        confidence[rule] = float(valid_rules[rule]) / num_occurances[premise]   #切记前面要转为float型

    return support , confidence


def print_rule(premise , conclusion , support , confidence , features):        #用于打印输出
    premise_name = features[premise]
    conclusion_name = features[conclusion]
    print ("Rule: If a person buys {0} they will also buy {1} ".format(premise_name , conclusion_name))
    print (" - Support: {0} ".format(support[(premise,conclusion)]))
    print("-Confidence:{0:.6f}".format(confidence[(premise, conclusion)]))


if __name__ == '__main__':
    dataset_filename = "affinity_dataset.txt"
    X = np.loadtxt(dataset_filename)
    n_sample, n_features = X.shape
    print (n_features)
    print (X[:5])  # 前五次交易顾客都买了？
    premise = 1
    conclusion = 3
    support, confidence = calS(X, n_features)
    features = ['bread' , 'cow' , 'cheese' , 'apple' , 'banana']
    print (support)
    print (confidence)
    print_rule(premise , conclusion , support , confidence , features)

    from operator import itemgetter
    sorted_support = sorted(support.items() , key = itemgetter(1) , reverse=True)

    for index in range(5):                             #输出支持度前五的
        print ("Rule #{0}".format(index + 1))
        premise , conclusion = sorted_support[index][0]
        print_rule(premise , conclusion , support , confidence , features )

    sorted_confidence = sorted(confidence.items(), key=itemgetter(1), reverse=True)
    for index in range(5):                             #输出置信度前五的
        print ("Rule #{0}".format(index + 1))
        premise , conclusion = sorted_confidence[index][0]
        print_rule(premise , conclusion , support , confidence , features )