详解pandas apply 并行处理的几种方法

from pandarallel import pandarallel
 
# Initialization
pandarallel.initialize()
 
# Standard pandas apply
df.apply(func)
 
# Parallel apply
df.parallel_apply(func)

# Embarrassingly parallel helper: to make it easy to write readable parallel code and debug it quickly
 
from math import sqrt
from joblib import Parallel, delayed
 
def test():
  start = time.time()
  result1 = Parallel(n_jobs=1)(delayed(sqrt)(i**2) for i in range(10000))
  end = time.time()
  print(end-start)
  result2 = Parallel(n_jobs=8)(delayed(sqrt)(i**2) for i in range(10000))
  end2 = time.time()
  print(end2-end)

import multiprocessing as mp
 
with mp.Pool(mp.cpu_count()) as pool:
  df['newcol'] = pool.map(f, df['col'])
multiprocessing.cpu_count()

import sys
import time
import pandas as pd
import multiprocessing as mp
from joblib import Parallel, delayed
from pandarallel import pandarallel
from tqdm import tqdm, tqdm_notebook
 
 
def get_url_len(url):
  url_list = url.split(".")
  time.sleep(0.01) # 休眠0.01秒
  return len(url_list)
 
def test1(data):
  """
  不进行任何优化
  """
  start = time.time()
  data['len'] = data['url'].apply(get_url_len)
  end = time.time()
  cost_time = end - start
  res = sum(data['len'])
  print("res:{}, cost time:{}".format(res, cost_time))
 
def test_mp(data):
  """
  采用mp优化
  """
  start = time.time()
  with mp.Pool(mp.cpu_count()) as pool:
    data['len'] = pool.map(get_url_len, data['url'])
  end = time.time()
  cost_time = end - start
  res = sum(data['len'])
  print("test_mp \t res:{}, cost time:{}".format(res, cost_time))
 
def test_pandarallel(data):
  """
  采用pandarallel优化
  """
  start = time.time()
  pandarallel.initialize()
  data['len'] = data['url'].parallel_apply(get_url_len)
  end = time.time()
  cost_time = end - start
  res = sum(data['len'])
  print("test_pandarallel \t res:{}, cost time:{}".format(res, cost_time))
 
 
def test_delayed(data):
  """
  采用delayed优化
  """
  def key_func(subset):
    subset["len"] = subset["url"].apply(get_url_len)
    return subset
 
  start = time.time()
  data_grouped = data.groupby(data.index)
  # data_grouped 是一个可迭代的对象，那么就可以使用 tqdm 来可视化进度条
  results = Parallel(n_jobs=8)(delayed(key_func)(group) for name, group in tqdm(data_grouped))
  data = pd.concat(results)
  end = time.time()
  cost_time = end - start
  res = sum(data['len'])
  print("test_delayed \t res:{}, cost time:{}".format(res, cost_time))
 
 
if __name__ == '__main__':
  
  columns = ['title', 'url', 'pub_old', 'pub_new']
  temp = pd.read_csv("./input.csv", names=columns, nrows=10000)
  data = temp
  """
  for i in range(99):
    data = data.append(temp)
  """
  print(len(data))
  """
  test1(data)
  test_mp(data)
  test_pandarallel(data)
  """
  test_delayed(data)