generate_the_excel.py

import pandas as pd
import time
import numpy as np
import re
import multiprocessing as mp
globi=0
df_b=None

def substitute_or_remove_prot_id(data,sub_rem):
    print("inside the problem")
    with open("nombres_sust.txt") as prottosubs:
          index=prottosubs.readline()
          acept=index.split()
          listtosubs={}
          for i in range(0,len(acept)):
            listtosubs[acept[i]]=[]
          while line := prottosubs.readline():
              newline=line.split()
              #print(len(newline))
              for i in range(0,len(newline)):
                  
                  listtosubs[list(listtosubs.keys())[i]].append(newline[i].strip())  
    resub=1
    if re.search("Primary",list(listtosubs.keys())[0]):
           resub=0
    print((resub+1)%2)
    #print(data)
    #data2=data.copy()
    global globi
    if(sub_rem == "s"):
        data["protein_id"].replace(list(listtosubs.values())[(resub+1)%2], list(listtosubs.values())[resub])
    #datacp=data.copy()
    #print(pd.concat([data2,datacp]).drop_duplicates())
    elif(sub_rem == "p"):
        datas= data[data["protein_id"].isin(list(listtosubs.values())[(resub)])==False]
        data= data[data["protein_id"].isin(list(listtosubs.values())[(resub)])==True]
        #print(data[data["protein_id"].isin(list(listtosubs.values())[(resub)])==True])
        #print(datas)
        
        #data.drop_duplicates(subset=['disease_id','protein_sequence'],keep='first',inplace=True)
        data=data.drop_duplicates(keep="first", inplace=False)
        did=data.copy()
        data = data.drop_duplicates(subset=['disease_id', 'protein_sequence'], keep="first", inplace=False)
        did=did[~did.isin(data).all(axis=1)]
        did=did.drop_duplicates()
        #print(pd.concat([did,did2]).drop_duplicates(keep=False))
        print(did)
        datas=pd.concat([datas, did], ignore_index=True)
        data.to_excel('data_principalpurge.xlsx',index=False,columns=data.columns) 
        datas.to_csv('resultados/proteinasDescartadassp_'+ str(globi) +'.csv', index=False) 
    elif(sub_rem == "c"):
        datas= data[data["protein_id"].isin(list(listtosubs.values())[(resub+1)%2])==True]
        data["protein_id"].replace(list(listtosubs.values())[(resub+1)%2], list(listtosubs.values())[resub])
        print("tamaño original: "+str(len(data)))
        dats=data.drop_duplicates(subset=['protein_id','class_id'],keep='first',inplace=False)
        print("Despues de tirar duplicados en id: "+str(len(dats)))
        dats=dats.drop_duplicates(subset=['protein_sequence','class_id'],keep='first',inplace=False)
        print("Despues de tirar duplicados en secuencia: "+str(len(dats)))
        dats.to_excel('clases.xlsx',index=False,columns=data.columns)  
        datas.to_csv('resultados/clasesDescartadas_'+ str(globi) +'.csv', index=False) 
        #pd_diff=pd.concat([data,dats]).drop_duplicates(keep=False)
        #pd_diff.to_excel('data_not_valid.xlsx')
        globi=globi+1 
        data=dats
    else: 
        
        datas= data[data["protein_id"].isin(list(listtosubs.values())[(resub+1)%2])==True]
        data["protein_id"].replace(list(listtosubs.values())[(resub+1)%2], list(listtosubs.values())[resub])
        print("tamaño original: "+str(len(data)))
        dats=data.drop_duplicates(subset=['disease_id','protein_id'],keep='first',inplace=False)
        print("Despues de tirar duplicados en id: "+str(len(dats)))
        dats=dats.drop_duplicates(subset=['disease_id','protein_sequence'],keep='first',inplace=False)
        print("Despues de tirar duplicados en secuencia: "+str(len(dats)))
        dats.to_excel('data_x.xlsx',index=False,columns=data.columns)  
        datas.to_csv('resultados/proteinasDescartadas_'+ str(globi) +'.csv', index=False) 
        #pd_diff=pd.concat([data,dats]).drop_duplicates(keep=False)
        #pd_diff.to_excel('data_not_valid.xlsx')
        globi=globi+1 
        data=dats
        #data.to_excel('data_nervous_genes_2.xlsx')
    return data                


def divide_by_class(data):
    print("inside the problem")
    cl=pd.read_excel("lung_cancer_protein_class.xlsx")
    cl=substitute_or_remove_prot_id(cl,"c")
    cl.to_excel("lung_cancer_protein_class_2.xlsx")
    #data2=data.copy()
    cli=cl.groupby('class_id')
    di=[]
    dd=data[~(data['protein_id'].isin(cl['protein_id']))]
    dd.to_excel("proteinas_sin_clase.xlsx")
    for k,v in cli:
     
      for index,row in v.iterrows():
         di.append(row['protein_id'])
      do=data[data["protein_id"].isin(di)]
      do.to_excel('proteinasClase_'+k+'.xlsx',index=False,columns=data.columns )
      di=[]
    #datacp=data.copy()
    #print(pd.concat([data2,datacp]).drop_duplicates())
    
    return data

def readData(archivoEntrada, enfermedad,archivoDescarte=None):
    data = pd.read_csv(archivoEntrada)
    dataor=data.copy()
    #data.to_excel('data_nervous_genes_2.xlsx')
    data=substitute_or_remove_prot_id(data,"r")
    #data.to_excel("data_nervous_genes_x.xlsx")
    if (enfermedad != ''):
        #datar=substitute_or_remove_prot_id(data,"r")
        #sprint("numero de filas de proteinas descartadas totales principal : "+ str(len(data)-len(datar)))
        
        
        #data = data.loc[data["disease_id"] == enfermedad]
        if(archivoDescarte != None):
          dataB = pd.read_excel(archivoDescarte)
                  
        
          print(len(data))
        #data=substitute_or_remove_prot_id(data,"r")
          dataB=substitute_or_remove_prot_id(dataB,"r")  
        #dataB.to_excel("data_nervous_genes_xf2.xlsx")
        #data.to_excel('data_nervous_genes_2.xlsx')
          filt_data=len(data)
          alz_filt_data=len(dataB)
          print("proteinas descartadas post filtro, principal: " + str(filt_data-len(data)))      
          print("proteinas descartadas post filtro, comun alz: " + str(alz_filt_data-len(dataB)))
          print("tamaño del descarte: "+ str(data[data["protein_id"].isin(dataB["protein_id"])].shape[0]))
          datad=data[(data['protein_id'].isin(dataB['protein_id']))]
          datad.to_excel("drop_data.xlsx")
          data.drop(data[data["protein_id"].isin(dataB["protein_id"])].index,inplace = True)
          data.to_excel(archivoEntrada+"_PostDrop.xlsx")
                          
    #data=substitute_or_remove_prot_id(data,"r")
    sequences = data["protein_sequence"]

    return sequences
def readOData(archivoEntrada, enfermedad):
    data = pd.read_excel(archivoEntrada)
    #data=substitute_or_remove_prot_id(data,"r")
    
    if (enfermedad != ''):
        #datar=substitute_or_remove_prot_id(data,"r")
        #sprint("numero de filas de proteinas descartadas totales principal : "+ str(len(data)-len(datar)))
        
        
        data = data.loc[data["disease_id"] == enfermedad]

        #dataB = pd.read_excel("proteinas_en_comun_Alzheimer.xlsx")
                  
        
        
        #data=substitute_or_remove_prot_id(data,"r")
        #dataB=substitute_or_remove_prot_id(dataB,"r")  
        #dataB.to_excel("proteinas_en_comun_Alzeheimer2.xlsx")
        #data.to_excel('data_nervous_genes_2.xlsx')
        #filt_data=len(data)
        #alz_filt_data=len(dataB)
        #print("proteinas descartadas post filtro, principal: " + str(filt_data-len(data)))      
        #print("proteinas descartadas post filtro, comun alz: " + str(alz_filt_data-len(dataB)))
        #data = data[~((data["disease_id"] == enfermedad) &
        #              (data["protein_id"].isin(dataB["protein_id"])) &
        #              (data["gene_id"].isin(dataB["gene_id"])))]

    sequences = data["protein_sequence"]

    return sequences

def readDataClassDiv(archivoEntrada, enfermedad):
    data = pd.read_excel(archivoEntrada)
    #data=substitute_or_remove_prot_id(data,"r")
    
    if (enfermedad != ''):
        #datar=substitute_or_remove_prot_id(data,"r")
        #sprint("numero de filas de proteinas descartadas totales principal : "+ str(len(data)-len(datar)))
        
        
        data = data.loc[data["disease_id"] == enfermedad]

        #dataB = pd.read_excel("proteinas_en_comun_Alzheimer.xlsx")
                  
        
        
        #data=substitute_or_remove_prot_id(data,"r")
        #dataB=substitute_or_remove_prot_id(dataB,"r")  
        #dataB.to_excel("proteinas_en_comun_Alzeheimer2.xlsx")
        #data.to_excel('data_nervous_genes_2.xlsx')
        #filt_data=len(data)
        #alz_filt_data=len(dataB)
        #print("proteinas descartadas post filtro, principal: " + str(filt_data-len(data)))      
        #print("proteinas descartadas post filtro, comun alz: " + str(alz_filt_data-len(dataB)))
        #data = data[~((data["disease_id"] == enfermedad) &
        #              (data["protein_id"].isin(dataB["protein_id"])) &
        #              (data["gene_id"].isin(dataB["gene_id"])))]

    data=divide_by_class(data)
    sequences = data["protein_sequence"]

    return sequences
def restructure_class(data,ArchivoSalida):
    data=data.groupby(['protein_id','protein_sequence','disease_id']).agg(list)
    print(data)
    #data.drop_duplicates(subset=['protein_id','protein_sequence'],keep='first',inplace=True)
    data.to_excel(ArchivoSalida)
    return data
def readDataRestructure(archivoEntrada, enfermedad,archivoSalida):
    data = pd.read_excel(archivoEntrada)
    print(len(data["protein_id"].unique()))
    data=substitute_or_remove_prot_id(data,"r")
    print(len(data["protein_id"].unique()))
    if (enfermedad != ''):
        #datar=substitute_or_remove_prot_id(data,"r")
        #sprint("numero de filas de proteinas descartadas totales principal : "+ str(len(data)-len(datar)))
        
        
        data = data.loc[data["disease_id"] == enfermedad]

        #dataB = pd.read_excel("proteinas_en_comun_Alzheimer.xlsx")
                  
        
        
        #data=substitute_or_remove_prot_id(data,"r")
        #dataB=substitute_or_remove_prot_id(dataB,"r")  
        #dataB.to_excel("proteinas_en_comun_Alzeheimer2.xlsx")
        #data.to_excel('data_nervous_genes_2.xlsx')
        #filt_data=len(data)
        #alz_filt_data=len(dataB)
        #print("proteinas descartadas post filtro, principal: " + str(filt_data-len(data)))      
        #print("proteinas descartadas post filtro, comun alz: " + str(alz_filt_data-len(dataB)))
        #data = data[~((data["disease_id"] == enfermedad) &
        #              (data["protein_id"].isin(dataB["protein_id"])) &
        #              (data["gene_id"].isin(dataB["gene_id"])))]

    data=restructure_class(data,archivoSalida)
    sequences = data["protein_sequence"]

    return sequences

if __name__=='__main__':
      #data=readData('protein_lung_cancer_C0007131.csv',,'C0007131',)
      data2 = readDataRestructure('treatment_lung_cancer.xlsx','C0007131','data_lung_cancer_treatment.xlsx')
      #data2=data2.to_list()
      datl=data.to_list() 
      #print(len(datl))
      du=[]
      #print(set(data2) - set(datl))      
      get_index_to_delete=[]
      for u in range(0,len(datl)):
         if datl[u] not in data2:
            du.append(datl[u])
         else:
            get_index_to_delete.append(u)   
            #print(str(u)+" Este no deberia estar: "+str(datl[u]))         
      with open("nombres_sust.txt") as prottosubs:
          index=prottosubs.readline()
          accept=index.split()
          listtosubs={}
          for i in range(0,len(accept)):
            listtosubs[acept[i]]=[]
          while line := prottosubs.readline():
              newline=line.split()
              #print(len(newline))
              for i in range(0,len(newline)):
                  
                  listtosubs[list(listtosubs.keys())[i]].append(newline[i].strip())  
      resub=1
      if re.search("Primary",list(listtosubs.keys())[0]):
           resub=0
      dia=[]     
      for y in du:
          dia.append(list(listtosubs.values())[(resub+1)%2][list(listtosubs.values())[resub].index(y)])
                
      #print(dia)