通过熊猫df进行python多处理

Question

python多处理

此脚本创建一个数据框并定义一个对象，然后尝试使用该数据框中的数据制成的对象填充列表。

通过将数据帧分为2部分并在每个部分上进行多处理来实现此目的

没有多处理功能就可以很好地工作，但是当我尝试多处理功能时，即使只有1个进程，部分代码似乎还是会抢先得到执行，而在只应执行一次的情况下也会重复执行

evidence of it running + it printing stuff from the end repeatedly

import random
import pandas as pd
import multiprocessing as mp
import time

class car_term(): #object to go into list 
    def __init__(self, capcode, miles,months , cmprice, fmprice ):
        self.capcode = capcode
        self.months = months
        self.miles = miles
        self.cmprice = cmprice
        self.fmprice = fmprice

df_final = pd.DataFrame({'capcode':[],'months':[],'mileage':[],'cm':[],'fm':[]})

for i in range (200): # making dataframe to get data from
    df_final = df_final.append(pd.DataFrame({'capcode':[i],'months':[random.randint(1, 12)],'mileage':[random.randint(0, 10000)],'cm':[random.randint(5, 700)],'fm':[random.randint(15, 710)]}))


all_deals=[] # this is the list i want to put my objects into
def get_car_terms(data,mdb1,all_deals1):
    all_deals1.append(car_term(mdb1['capcode'][data],mdb1['mileage'][data],mdb1['months'][data],mdb1['cm'][data],mdb1['fm'][data])) # i make the objects with the dataframe like this
all_deals1a=[]   # individual lists for each proccessor

print("yo1")
if __name__ == "__main__":
    print('1')
    if df_final.shape[0] != 0:
        print('2')
        df_final = df_final.reset_index(drop=True)
        print(df_final.head())
        for i in range(int(df_final.shape[0]/4)):

            ############# the problem is the get_car_terms function doesnt run below
            p1 = mp.Process( target = get_car_terms , args =(i+((df_final.shape[0]/4)*1), df_final,all_deals1a)) # each cpu sorts a quater of the dataframe into my objects list


            p1.start()

            time.sleep(10000)
            p1.join()
         #   get_car_terms(i+((df_final.shape[0]/n_cpus)*2), df_final,all_deals1a)


            print(" ppp ")
    all_deals.append(all_deals1a)   # group lists together


print("we did it")
print(len(all_deals))  # this should have 200 of my objects in it... it doesnt
for i in all_deals:
    print(len(i))
    for j in i:
        print(j.miles)