生物学数据处理——读取数据筛选输出

代码描述

主要就是从两个文件中读取数据，然后根据某列指标进行差异筛选，输出基因id
代码比较简单，可能并不完善，以后有机会继续完善。
学习并分享，共建良好社区文化！

代码原文

# -*- coding: utf-8 -*-
"""
Created on 2021.08.09

@author: logic


"""

import os
import pandas as pd

os.chdir('D:\日常工作\dong')


f1 = open('all_up.txt','w') # 都上调
f2 = open('all_down.txt','w')
f3 = open('1up2down.txt','w')
f4 = open('1down2up.txt','w')


def reader_compare():
    df1 = pd.read_excel('crispr_wt.xlsx',index_col='RefName')
    data1_up = df1[df1['regulation']=='up']
    data1_down = df1[df1['regulation']=='down']
    # print(data_down)
    df2 = pd.read_excel('ox_wt.xlsx',index_col='RefName')
    data2_up = df2[df2['regulation']=='up']
    data2_down = df2[df2['regulation']=='down']
    # print(data2_down.index)
    
    # 同时上调
    for i in data1_up.index:
        if i in data2_up.index:
            f1.write(i+'\n')
            
    # 同时下调
    for j in data1_down.index:
        if j in data2_down.index:
            f2.write(j+'\n')
            
    # 1 up,2 down
    for x in data1_up.index:
        if x in data2_down.index:
            f3.writelines(x+'\n')
            
    # 1 down,2 up
    for y in data1_down.index:
        if y in data2_up.index:
            f4.writelines(y+'\n')
    
        

if __name__ == '__main__' :
    reader_compare()
    
f1.close()
f2.close()
f3.close()
f4.close()