Created
September 15, 2021 10:19
-
-
Save thangarajan8/f2358621beef40e945f825f8aad3b91e to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import pandas as pd | |
import time | |
import numpy as np | |
#http://eforexcel.com/wp/wp-content/uploads/2020/09/5m-Sales-Records.zip | |
df = pd.read_csv("5m Sales Records.csv") | |
def filter1(df): | |
start_time = time.time() | |
for i in df.Country.unique(): | |
df[(df.Country==i)] | |
print(f"Total time {time.time()-start_time}") | |
#90 sec | |
def filter2(df): | |
start_time = time.time() | |
for i in df.Country.unique(): | |
df.loc[(df.Country==i)] | |
print(f"Total time {time.time()-start_time}") | |
#81.4 Sec | |
def filter_numpy(df): | |
start_time = time.time() | |
for i in df.Country.unique(): | |
df.loc[np.in1d(df.Country,i)] | |
print(f"Total time {time.time()-start_time}") | |
filter1(df) | |
filter2(df) | |
filter_numpy(df) | |
#Total time 92.1524384021759 | |
#Total time 97.74113202095032 | |
#Total time 43.44165015220642 | |
#winner is filter_numpy |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment