Created
June 25, 2019 08:35
-
-
Save f-huang/d2a949ecc37ec714e198c45498c0b779 to your computer and use it in GitHub Desktop.
Python function to show progress bar while reading a CSV.
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 math | |
import pandas as pd | |
def read_csv_in_chunks(path, n_lines, **read_params): | |
if 'chunksize' not in read_params or read_params['chunksize'] < 1: | |
read_params['chunksize'] = 80000 | |
chunks = [0] * math.ceil(n_lines / read_params['chunksize']) | |
for i, chunk in enumerate(pd.read_csv(path, **read_params)): | |
percent = min(((i + 1) * read_params['chunksize'] / n_lines) * 100, 100.0) | |
print("#" * int(percent), f"{percent:.2f}%", end='\r', flush=True) | |
chunks[i] = chunk | |
df = pd.concat(chunks, axis=0) | |
del chunks | |
print() | |
return df |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment