数据挖掘（Python）——利用sklearn进行数据挖掘，实现算法：svm、knn、C5.0、NaiveBayes

<span style="line-height: 18px; font-family: Consolas, 'Courier New', Courier, mono, serif; background-color: rgb(255, 255, 255);">说明：下面程序将利用python中的sklearn包根据用户流失前的行为，对用户的流失进行预测</span>

数据格式：lost表示是否流失，其他变量为用户的行为变量，下面是部分数据

import xlrdimport stringimport sklearnfrom sklearn import svmfrom sklearn import neighborsfrom sklearn import clusterfrom sklearn import treefrom sklearn import naive_bayes import numpy as np#--------数据加载开始--------------def data_import(filepath): data=xlrd.open_workbook(filepath) table=data.sheet_by_index(0) nrows=table.nrows ncols=table.ncols result=[] result.append(table.row_values(0)) for i in range(1,nrows):     result_0=[]     for j in range(0,ncols):                                    result_0=result_0+[table.cell(i,j).value]     result.append(result_0) result=result[1:] return resultfilepath1=r'F:\data_retain.xls'result1=data_import(filepath1)count1=len(result1)target1=[]data1=[]for i in range(0,count1):     data1.append(result1[i][1:])     target1.append(result1[i][0])filepath2=r'F:\data_lost.xls'result2=data_import(filepath2)count2=len(result2)target2=[]data2=[]for i in range(0,count2):     data2.append(result2[i][1:])     target2.append(result2[i][0])data=[]target=[]len_1=10000for i in range(0,len_1):     data.append(data1[i])     target.append(target1[i])len_2=10000for i in range(0,len_2):     data.append(data2[i])     target.append(target2[i])#--------数据加载完毕--------------class machine_learn:    def svm_(self,data,target):        #支持向量机算法预测        svc = svm.SVC(kernel='linear')        svc.fit(data,target)        predict_target=svc.predict(data)        temp0_0=0        temp0_1=0        temp1_0=0        temp1_1=0        for i in range(0,len(target)):            if predict_target[i]==0:                if target[i]==0:                    temp0_0=temp0_0+1                else:                    temp0_1=temp0_1+1            else:                if target[i]==0:                    temp1_0=temp1_0+1                else:                    temp1_1=temp1_1+1        kind_0_precision=temp0_0/(temp0_0+temp0_1)        kind_0_penetration=temp0_0/(temp0_0+temp1_0)        kind_1_precision=temp1_1/(temp1_0+temp1_1)        kind_1_penetration=temp1_1/(temp0_1+temp1_1)        return [[kind_0_precision,kind_0_penetration],[kind_1_precision,kind_1_penetration]]    def knn_(self,data,target):        #最邻近算法算法预测        knn = neighbors.KNeighborsClassifier()        knn.fit(data,target)        predict_target=knn.predict(data)        temp0_0=0        temp0_1=0        temp1_0=0        temp1_1=0        for i in range(0,len(target)):            if predict_target[i]==0:                if target[i]==0:                    temp0_0=temp0_0+1                else:                    temp0_1=temp0_1+1            else:                if target[i]==0:                    temp1_0=temp1_0+1                else:                    temp1_1=temp1_1+1        kind_0_precision=temp0_0/(temp0_0+temp0_1)        kind_0_penetration=temp0_0/(temp0_0+temp1_0)        kind_1_precision=temp1_1/(temp1_0+temp1_1)        kind_1_penetration=temp1_1/(temp0_1+temp1_1)        return [[kind_0_precision,kind_0_penetration],[kind_1_precision,kind_1_penetration]]    def tree_(self,data,target):        #决策树算法预测        tre = tree.DecisionTreeClassifier()        tre.fit(data,target)        predict_target=tre.predict(data)        temp0_0=0        temp0_1=0        temp1_0=0        temp1_1=0        for i in range(0,len(target)):            if predict_target[i]==0:                if target[i]==0:                    temp0_0=temp0_0+1                else:                    temp0_1=temp0_1+1            else:                if target[i]==0:                    temp1_0=temp1_0+1                else:                    temp1_1=temp1_1+1        kind_0_precision=temp0_0/(temp0_0+temp0_1)        kind_0_penetration=temp0_0/(temp0_0+temp1_0)        kind_1_precision=temp1_1/(temp1_0+temp1_1)        kind_1_penetration=temp1_1/(temp0_1+temp1_1)        return [[kind_0_precision,kind_0_penetration],[kind_1_precision,kind_1_penetration]]    def bayes_(self,data,target):        #使用贝叶斯算法预测（GaussianNB）        bayes = naive_bayes.GaussianNB()        bayes.fit(data,target)        predict_target=bayes.predict(data)        temp0_0=0        temp0_1=0        temp1_0=0        temp1_1=0        for i in range(0,len(target)):            if predict_target[i]==0:                if target[i]==0:                    temp0_0=temp0_0+1                else:                    temp0_1=temp0_1+1            else:                if target[i]==0:                    temp1_0=temp1_0+1                else:                    temp1_1=temp1_1+1        kind_0_precision=temp0_0/(temp0_0+temp0_1)        kind_0_penetration=temp0_0/(temp0_0+temp1_0)        kind_1_precision=temp1_1/(temp1_0+temp1_1)        kind_1_penetration=temp1_1/(temp0_1+temp1_1)        return [[kind_0_precision,kind_0_penetration],[kind_1_precision,kind_1_penetration]]a=machine_learn()svm_method=a.svm_(data,target)print ('svm 方法预测，它的准确率可以达到 %f, 覆盖率达到 %f' % (svm_method[1][0],svm_method[1][1]))knn_method=a.knn_(data,target)print ('knn 方法预测，它的准确率可以达到 %f, 覆盖率达到 %f' % (knn_method[1][0],knn_method[1][1]))tree_method=a.tree_(data,target)print ('决策树 方法预测，它的准确率可以达到 %f, 覆盖率达到 %f' % (tree_method[1][0],tree_method[1][1]))bayes_method=a.bayes_(data,target)print ('NaiveBayes 方法预测，它的准确率可以达到 %f, 覆盖率达到 %f' % (bayes_method[1][0],bayes_method[1][1]))

1、当训练样本中，流失用户：留存用户调整为1:1时，决策树模型的前10个规则可以通过覆盖20%的频道用户来定位60%的流失用户

2、<span style="font-family: Arial, Helvetica, sans-serif;">当训练样本中，流失用户：留存用户调整为1:3时，决策树模型的前10个规则可以通过覆盖25.3%的频道用户来定位65.6%的流失用户</span>

<span style="font-family: Arial, Helvetica, sans-serif;"></span><pre name="code" class="python">3、当训练样本中，流失用户：留存用户调整为1:1时，增加部分变量，决策树模型的前10个规则可以通过覆盖15%的频道用户来定位47%的流失用户