性味归经与功能的脚本——3元素

最新推荐文章于 2025-09-07 01:02:55 发布

转载最新推荐文章于 2025-09-07 01:02:55 发布 · 91 阅读

文章标签：

#python #人工智能

本教程通过实战案例介绍如何使用sklearn进行乳腺癌细胞的数据挖掘分析。内容涵盖数据处理、统计检验等方面，利用卡方检验验证性味归经与功能之间的相关性。

sklearn实战-乳腺癌细胞数据挖掘(博客主亲自录制视频教程)

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

censor_xwgj_function.py脚本

需要list_xwgj_function,chi_square两个脚本支持

# -*- coding: utf-8 -*-
"""
Created on Thu Aug 25 10:06:52 2016

审核性味归经与功能的脚本

@author: Administrator
"""

import xlrd,csv
import list_xwgj_function,chi_square
#三元素组合[寒，苦，肝]
thelist_xwgj_function=list_xwgj_function.thelist_xwgj_function
#多元素组合
#thelist_xwgj_function=list_xwgj_function_multiElements.list_xwgj2_function

fileName="性味归经_功能_关系.csv"
excelFilename="中药表.xlsx"
sheetName="Sheet1"
#打开excel数据
excelFile=xlrd.open_workbook(excelFilename)
  
sheet=excelFile.sheet_by_name(sheetName)

#表单行与列
number_rows=sheet.nrows
number_columns=sheet.ncols
#表单内数据
list_sheetData=[]  
#
list_xingWeiFunction_relation=[]


#获取表格数据
def Get_sheetData():
    for row in range(1,number_rows):
        list_sheetData.append(sheet.row_values(row))
    return list_sheetData


list_sheetData=Get_sheetData()



#卡方统计的keyWord1与keyWord2的关系
def Get_single_chiSquare(keyWord1,keyWord2):
    list_a=[]
    a=0
    b=0
    c=0
    d=0
    #统计包含a数量
    for k in range(len(list_sheetData)):
        i=list_sheetData[k]
        if keyWord1[0] in i[0] and keyWord1[1] in i[0] and keyWord1[2] in i[0] and keyWord2 in i[1]:
            a+=1
            list_a.append(k+2)
    
    #统计包含b数量
    for i in list_sheetData:
        if keyWord1[0] in i[0] and keyWord1[1] in i[0] and keyWord1[2] in i[0] and keyWord2 not in i[1]:
            b+=1    


    #统计包含c数量
    for i in list_sheetData:
        if keyWord1[0] not in i[0] or keyWord1[1] not in i[0] or keyWord1[2] not in i[0] and keyWord2 in i[1]:
            c+=1

    #统计包含d数量
    for i in list_sheetData:
        if keyWord1[0] not in i[0] or keyWord1[1] not in i[0] or keyWord1[2] not in i[0] and keyWord2 not in i[1]:
            d+=1
    #print("a:",a)
    #print("b:",b)
    #print("c:",c)
    #print("d:",d)
    k2=chi_square.value_independence(a,b,c,d)
    relation=chi_square.judge_independence(a,b,c,d)
    lis1=[[a,b,c,d],k2,relation,list_a]
    return lis1
    
#计算所有性味的相关性    
def Get_all_chiSquare(thelist_xwgj_function):
    for i in thelist_xwgj_function:
        try:
            keyWord1,keyWord2=i[0],i[1]
            relation=Get_single_chiSquare(keyWord1,keyWord2)
            list1=[i,relation,relation[2]]
            list_xingWeiFunction_relation.append(list1)
        except:
            print("wrong at:",i)
            continue
    return list_xingWeiFunction_relation
    
    
    
def Write_table_to_csv(list1,fileName):
    #对列表格式修改，字符串写入的格式不对
    file=open(fileName,'w',newline='')
    writer1=csv.writer(file)
    writer1.writerows(list1)
    file.close()  

  
list_xingWeiFunction_relation=Get_all_chiSquare(thelist_xwgj_function)  
Write_table_to_csv(list_xingWeiFunction_relation,fileName)

chi_square 脚本

#coding=utf-8

#独立性检验test for independence,也是卡方检验chi_square
#前提条件：a,b,c,d 必须大于5

#2.706是判断标准（90概率），值越大，越有关，值越小，越无关
def value_independence(a,b,c,d):
    if a>=5 and b>=5 and c>=5 and d>=5:
        return ((a+b+c+d)*(a*d-b*c)**2)/float((a+b)*(c+d)*(a+c)*(b+d))

#返回True表示有关
#返回False表示无关
#2.706表示有90%概率
def judge_independence(a,b,c,d):
    num_independence=value_independence(a,b,c,d)
    print("chi_square:",num_independence)
    if num_independence==None:
        print("not suit for chi_square statistics")
        return "wrong"
    if num_independence>2.706:
        print ("there is relationship")
        return True
    if num_independence<=2.706:
        print("there is no relationship")
        return False

list_xwgj_function脚本

# -*- coding: utf-8 -*-
"""
Created on Tue Aug 23 11:38:35 2016
高频率的性味归经和功能相关性分析

算法：卡方

@author: Administrator
"""

import xlrd,csv
excelFilename="性味归经与功能.xlsx"
sheetName="Sheet1"
#打开excel数据
excelFile=xlrd.open_workbook(excelFilename)
  
sheet=excelFile.sheet_by_name(sheetName)

#表单行与列
number_rows=sheet.nrows
number_columns=sheet.ncols

#表格性味归经
list_xwgj=sheet.col_values(0)[1:]
list_xwgj1=[]

#表格性味归经
list_function=sheet.col_values(1)[1:] 
#去除空格
list_function1=[i for i in list_function if i!=""]

#性味归经和功能的组合
list_xwgj_function=[]


def Get_list_xwgj_function():
    for i in list_xwgj1:
        
        for k in list_function1:
            list_xwgj_function.append([i,k])
        
    return list_xwgj_function

#性味归经列表 ，统一格式            
def Get_list_xwgj():
    for i in list_xwgj:
        b=i.split(",")
        list_xwgj1.append(b)
    
    return list_xwgj1
            

            
#性味归经列表，统一格式        
list_xwgj1=Get_list_xwgj()   
        
thelist_xwgj_function=Get_list_xwgj_function()

list_xwgj_function脚本需要性味归经与功能excel