sklearn實戰-乳腺癌細胞數據挖掘

https://study.163.com/course/introduction.htm?courseId=1005269003&utm_campaign=commission&utm_source=cp-400000000398149&utm_medium=share

醫藥統計項目聯系QQ：231469242

如果樣本量太小，數據必須做分段化處理，否則會有很多空缺數據，woe效果不能有效發揮

隨機森林結果

iv》0.02的因子在隨機森林結果裏都屬於有效因子，但是隨機森林重要性最強的因子沒有出現在有效iv參數裏，說明這些缺失重要變量沒有做分段處理，數據離散造成。

數據文件

腳本備份

step1_customers_split_goodOrBad.py

# -*- coding: utf-8 -*-
"""
Created on Sun Jan 14 21:45:43 2018

@author  QQ：231469242

把數據源分類為兩個Excel，好客戶Excel數據和壞客戶Excel數據
"""

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

#讀取文件
readFileName="breast_cancer_總.xlsx"

#保存文件
saveFileName_good="result_good.xlsx"
saveFileName_bad="result_bad.xlsx"

#讀取excel
df=pd.read_excel(readFileName)
#帥選數據
df_good=df[df.diagnosis=="B"]
df_bad=df[df.diagnosis=="M"]

#保存數據
df_good.to_excel(saveFileName_good, sheet_name=‘Sheet1‘)
df_bad.to_excel(saveFileName_bad, sheet_name=‘Sheet1‘)

step2_automate_find_informative_variables.py

# -*- coding: utf-8 -*-
"""
Created on Sun Jan 14 22:13:30 2018

@author: QQ:231469242
woe負數，好客戶<壞客戶
woe正數，好客戶>壞客戶
"""

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import os

#創建save文件
newFile=os.mkdir("save/") 

#讀取文件
FileName_good="result_good.xlsx"
FileName_bad="result_bad.xlsx"

#保存文件
saveFileName="result_woe_iv.xlsx"

#讀取excel
df_good=pd.read_excel(FileName_good)
df_bad=pd.read_excel(FileName_bad)

#所有變量列表
list_columns=list(df_good.columns[:-1])

index=0

def Ratio_goodDevideBad(index):
    #第一列字段名（好客戶屬性）
    columnName=list(df_good.columns)[index]

    #第一列好客戶內容和第二列壞客戶內容
    column_goodCustomers=df_good[columnName]
    column_badCustomers=df_bad[columnName]

    #去掉NAN
    num_goodCustomers=column_goodCustomers.dropna()
    #統計數量
    num_goodCustomers=num_goodCustomers.size

    #去掉NAN
    num_badCustomers=column_badCustomers.dropna()
    #統計數量
    num_badCustomers=num_badCustomers.size
    

    #第一列頻率分析
    frenquency_goodCustomers=column_goodCustomers.value_counts()
    #第二列頻率分析
    frenquency_badCustomers=column_badCustomers.value_counts()
   
    #各個元素占比
    ratio_goodCustomers=frenquency_goodCustomers/num_goodCustomers
    ratio_badCustomers=frenquency_badCustomers/num_badCustomers
    #最終好壞比例
    ratio_goodDevideBad=ratio_goodCustomers/ratio_badCustomers
    return (columnName,num_goodCustomers,num_badCustomers,frenquency_goodCustomers,frenquency_badCustomers,ratio_goodCustomers,ratio_badCustomers,ratio_goodDevideBad)

#woe函數,陣列計算
def Woe(ratio_goodDevideBad):
    woe=np.log(ratio_goodDevideBad)
    return woe

‘‘‘    
#iv函數,陣列計算
def Iv(woe):
    iv=(ratio_goodCustomers-ratio_badCustomers)*woe
    return iv
    ‘‘‘

#iv參數評估,參數iv_sum（變量iv總值）
def Iv_estimate(iv_sum):
    #如果iv值大於0.02，為有效因子
    if iv_sum>0.02:
        print("informative")
        return "A"
    #評估能力一般
    else:
        print("not informative")
        return "B"
   
    
‘‘‘
#詳細參數輸出
def Print():
    print ("columnName:",columnName)
    Iv_estimate(iv_sum)
    print("iv_sum",iv_sum)
    #print("",)
    #print("",)
    ‘‘‘
    
#詳細參數保存到excel，save文件裏    
def Write_singleVariable_to_Excel(index):
    #index為變量索引，第一個變量，index=0
    ratio=Ratio_goodDevideBad(index)
    columnName,num_goodCustomers,num_badCustomers,frenquency_goodCustomers,frenquency_badCustomers,ratio_goodCustomers,ratio_badCustomers,ratio_goodDevideBad=ratio[0],ratio[1],ratio[2],ratio[3],ratio[4],ratio[5],ratio[6],ratio[7]

    woe=Woe(ratio_goodDevideBad)
    iv=(ratio_goodCustomers-ratio_badCustomers)*woe
    
    df_woe_iv=pd.DataFrame({"num_goodCustomers":num_goodCustomers,"num_badCustomers":num_badCustomers,"frenquency_goodCustomers":frenquency_goodCustomers,
    "frenquency_badCustomers":frenquency_badCustomers,"ratio_goodCustomers":ratio_goodCustomers,
    "ratio_badCustomers":ratio_badCustomers,"ratio_goodDevideBad":ratio_goodDevideBad,
    "woe":woe,"iv":iv},columns=["num_goodCustomers","num_badCustomers","frenquency_goodCustomers","frenquency_badCustomers",
    "ratio_goodCustomers","ratio_badCustomers","ratio_goodDevideBad","woe","iv"])
    
    
    #sort_values(by=...)用於對指定字段排序
    df_sort=df_woe_iv.sort_values(by=‘iv‘,ascending=False)

    #ratio_badDevideGood數據寫入到result_compare_badDevideGood.xlsx文件
    df_sort.to_excel("save/"+columnName+".xlsx")


    #計算iv總和，評估整體變量
    iv_sum=sum([i for i in iv if np.isnan(i)!=True])

    print ("變量:",columnName)
    #iv參數評估,參數iv_sum（變量iv總值）
    iv_estimate=Iv_estimate(iv_sum)
    print("iv_sum",iv_sum)
    return iv_estimate,columnName



#y\有價值變量列表存儲器
list_Informative_variables=[]


#寫入所有變量參數,保存到excel裏，save文件
for i in range(len(list_columns)):
    status=Write_singleVariable_to_Excel(i)[0]
    columnName=Write_singleVariable_to_Excel(i)[1]
    
    if status=="A":
        list_Informative_variables.append(columnName)

        

　最終得到一部分有效因子，共12個，經過數據分段化處理，會得到更多有效因子。

python風控評分卡建模和風控常識

https://study.163.com/course/introduction.htm?courseId=1005214003&utm_campaign=commission&utm_source=cp-400000000398149&utm_medium=share

sklearn-woe/iv-乳腺癌分類器實戰