#!/usr/bin/env python
# -*- coding: utf-8 -*-

import os
import sys
import scipy.stats as stats 

in1=sys.argv[1]
ou1=sys.argv[2]

#def trimdata(inputD,outputf): 
def trimdata(inputD):
# inputD 第一列case/control ; 第二列 sample number ; 第三列 sample ID; 输入形式是文本
# outputf 输出形式 文本
    casen=0
    controln=0
    case_T=0
    case_G=0
    case_GT=0
    con_T=0
    con_G=0
    con_GT=0
    patientn=0
    Gn=0
    Tn=0
    GTn=0
#   outc=open(outputf,'w')
    casel=[]
    controll=[]
    with open(inputD,'r') as f:
        fi=f.readlines()
        for fil in fi[1:]:
            filc=fil.strip().split("\t")
            types=filc[0]
            genotyp=filc[2]
            if types == "case":
                casen=casen+1
                if genotyp == "G":
                    case_G=case_G+1
                    Gn=Gn+1
                elif genotyp == "T":
                    case_T=case_T+1
                    Tn=Tn+1
                elif genotyp == "GT":
                    case_GT=case_GT+1
                    con_GT=con_GT+1
            elif types == "control":
                controln=controln+1
                if genotyp == "G":
                    con_G=con_G+1
                    Gn=Gn+1
                                elif genotyp == "T":
                    con_T=con_T+1
                    Tn=Tn+1
                                elif genotyp == "GT":
                    con_GT=con_GT+1
                    GTn=GTn+1
    casel=[case_G,case_T,case_GT]
    controll=[con_G,con_T,con_T]
    r, p=stats.pearsonr(casel,controll)
    conc=str(case_G)+"\t"+str(case_T)+"\t"+str(case_GT)+"\t"+str(con_G)+"\t"+str(con_T)+"\t"+str(con_T)+"\t"+str(p)+"\n"
    return conc
#   outc.write("G\tT\tGT\n")
#   outc.write("case\t"+str(case_G)+"\t"+str(case_T)+"\t"+str(case_GT)+"\n")
#   outc.write("control\t"+str(con_G)+"\t"+str(con_T)+"\t"+str(con_GT)+"\n")

if __name__ == "__main__":
    inputf=in1
    outputf=open(ou1,'w')
    outcon=trimdata(inputf)
    trimdata.write(outcon)