Created
May 9, 2024 18:51
-
-
Save pythoninthegrass/d39352309b3becdfd96333707f2e725f 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
#!/usr/bin/env python3 | |
# SOURCE: https://www.youtube.com/watch?v=xtFo1IiZqzM | |
import pandas as pd | |
from pathlib import Path | |
from tqdm import tqdm | |
fn = Path("../csv/anime_dataset/users-score-2023.csv") | |
# TODO: programmatic chunksize calculation | |
chunksize = 5000 # naive amount | |
data = pd.read_csv(fn, chunksize=chunksize) | |
num_rows = sum(1 for _ in data) | |
counter = 0 | |
# results = [] | |
# TODO: test tqdm | |
for chunk in tqdm(data, total=num_rows): | |
chunk.columns = chunk.columns.str.strip().str.replace(' ', '_').str.lower() | |
chunk['username'] = chunk['username'].apply(lambda x: x.strip()) | |
chunk['anime_title'] = chunk['anime_title'].apply(lambda x: x.strip()) | |
chunk.drop(columns=['anime_id'], inplace=True) | |
chunk.rename(columns={'username': 'name', 'anime_title': 'anime', 'rating': 'rating'}, inplace=True) | |
chunk.drop(columns=['user_id'], inplace=True) | |
results = [] # or results = {} or results = set() depending on your needs and performance considerations | |
counter += 1 | |
# results.append(chunk) | |
if counter == 5: | |
break | |
else: | |
progress = counter * chunksize | |
print(f"Progress: {progress}/{num_rows}") | |
# TODO: refactor this to use a single dataframe | |
# results = chunk.groupby('anime')['rating'].agg(['mean', 'size']).sort_values(by='size', ascending=False).head(10) | |
print(results) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment