医学数据处理1_ 病人样本去重

前言：

               最近帮某三甲医院做了一些医学数据处理的程序

记录一下

---

一  病人样本去重

      需要：

      

 第三列表格病人的编号，第一列表格病人的数据类型

统计的时候，出现同一个病人有不同的数据类型，按照一定的优先级别，

只保留一类。 

sample	OS	_PATIENT	OS.time
MMRF_2226_1_PB_Whole	0	MMRF_2226	1
MMRF_2226_1_BM_CD138pos	0	MMRF_2226	1
MMRF_2187_1_PB_CD138pos	0	MMRF_2187	1

 

   

# -*- coding: utf-8 -*-
"""
Created on Mon Jul 20 14:10:43 2020

@author: chengxf2
去掉内容重复的
https://www.jb51.net/article/42635.htm
"""

import os
from openpyxl import load_workbook
import numpy as np
from xlrd import open_workbook
import csv
import sys



class RemoveRep:
    
    """
    获取当前目录下面的xls
    Args
       None
    return
       path: 文件路径
    """
    
    def GetPath(self):
        
        root = os.getcwd()
        
        files = os.listdir(root)
        
        for file in files:
            
            pos = file.find("xls")
            
                   
            if pos>1:
                
                path = os.path.abspath(file)
                fileName = os.path.splitext(file)[0]
                print("\n path ",path)
                return path,fileName
        
    
    def __init__(self):
        
        self.m = 0
        self.n = 0
        self.DictItem ={} #表格里面的所有内容
        self.keyList = []
        
    """
    获得优先级别
    Args
       tag1: CD138pos,Whole，WBC
       tag2: PB, BM
    return
       pri:优先级别，3 最高
    """
    def GetPre(self, tag1, tag2):
        
       # print("\n tag1 ",tag1,"\t tg2 ",tag2)
        pri = -1
        
        if tag1 =="CD138pos" and tag2 == "BM":
            pri = 3
        elif tag1 =="CD138pos" and tag2 =="PB":
            pri = 2
        else:
            pri = 1
        return pri
        
        
        
    """
    同一个病人，有重复的资料，只保存一种
    [['CD138pos', 'PB', 3], ['CD3pos', 'PB', 4], ['CD138pos', 'BM', 5]]
    Args
       Items: 重复的列表项
    return
       maxIndex: 选择最优的
    """
    def GetIndex(self, Items):
        
        maxPri = -1 #最优级别的index
        maxIndex = -1 #最优级别的index
        for item in Items:
            tag1 = item[0]
            tag2 = item[1]
            index = item[2]

            
            pri = self.GetPre(tag1, tag2)
            
           # print("\n ","tag1",tag1,"\t tag2 ",tag2, "\t 优先级别: ",pri,"\t index ",index)
            if pri>maxPri:
                maxPri = pri
                maxIndex = index
       # print("\n maxIndex:",maxIndex) 
        return maxIndex
            
            
            
        
        
    """
    去除重复的
    Args
        rows: 行
        head： 头
    return
        retRow: 去重后的列表
    """
    def Merge(self, rows,head):
        
        retRow = []
        retRow.append(head)
        
        Index =[] #需要添加的列表
        #print("head ",head)
        
        
        
        for key in self.DictItem.keys(): #只留一个
            items = self.DictItem[key]
            if len(items)>1: #有重复的
                #print("++++++key +++++",key)
                index = self.GetIndex(items) #多个只预留一个
               # print("item: ",rows[index])
            else:
                #print("\n item ",item[0][2])
                index = items[0][2]
            Index.append(index)
        
        #print(Index)
        
        
        for key in Index:
            item = rows[key] 
            retRow.append(item)
        #print("\n 删除后的表格: \n  ",retRow)
        return retRow
                
                
        
    """
    读取xls
    Args
       path:
           表格路径
           CD138Pos 排在第一优先级
           [BM,CD]
    return
       rows : 表格内容
       head: 表格头
           
    """
    def Readxls(self,path):
        
        rows =[]
        workbook = open_workbook(path)  # 打开xls文件

        
        sh = workbook.sheet_by_index(0)
        
        nrows = sh.nrows
        ncols = sh.ncols
       # print("sheets ",nrows,"\t ncols : ",ncols)
        
        #获取第一行，第一列数据
        #Whead = sh.cell_value(1,1)
     
        
        head = sh.row_values(0)  #从0 开始的


        for i in range(1,nrows): #第一行不读,为头
            
            row_data = sh.row_values(i)
            
            #print("\n row_data ",row_data)

            sample = row_data[0].split("_")
            
            tag1 = sample[4]#CD138pos
            tag2 = sample[3]#PB,BM
            index = i-1 #头不读，所以减去1
            patient = row_data[2] #病人标号
            
            if patient not in self.DictItem.keys():
                self.DictItem[patient]=[[tag1,tag2,index]]
            else: #已经存在了
                curitem = self.DictItem[patient] #当前列表
                newItem = [tag1,tag2,index] #新的条目
                curitem.append(newItem)
                self.DictItem[patient] = curitem

            rows.append(row_data)
        return rows,head
            
            
            
        
            
        
        
        
    """
    保存到csv文件里面
    Arg
    Head: 表格第一行   #head = ['标题列1', '标题列2']
    rows:  表格内容    #rows = [['张三', 80],['李四', 90]] 
    return
    Rows:  文件里面的数据内容
    Head:  [ID,文件名]
    
    """
    def WriteCSV(self,rows, name):
        
         print("\n *****保存文件  ********\n ") #4,60483   
         fileName = name+".csv"
         f= open(fileName,'w', newline='')
         
        # print("\n rows, ",rows)
       
         writer = csv.writer(f)
 
         writer.writerows(rows)
         f.close()
         print("\n *****保存退出  ********\n ") #4,60483   
        
    """
    """
    def Remove(self):
        path,name = self.GetPath()
        print("\n 读取表格 \n ")
        xmlrows,head = self.Readxls(path)
        print("\n 合并表格 \n ")
        rows = self.Merge(xmlrows,head)
        self.WriteCSV(rows,name)
        
move = RemoveRep()
move.Remove()
        

        

---