Created
February 3, 2023 14:52
-
-
Save anandsaha/4db838aeb200ec85779655f53d09c118 to your computer and use it in GitHub Desktop.
This file contains hidden or 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
# Towards homework 1 of XCS224U | |
from multiprocessing import Pool | |
import pandas as pd | |
import spacy | |
from pathlib import Path | |
df = pd.read_csv('books_and_genres.csv') | |
nlp = spacy.load('en_core_web_sm') | |
total_rows = len(df) | |
count = 0 | |
print(df.columns) | |
def func(x): | |
row = df.loc[x] | |
title = row['title'] | |
text = str(row['text']).replace('\n', ' ') | |
file_name = f'corpus/{title}.txt' | |
if Path(file_name).exists(): | |
print(f"Already processed {title} ") | |
return | |
print(f"Processing {title} ") | |
with open(file_name, 'w') as f: | |
sents = [i for i in nlp(title).sents] | |
for s in sents: | |
f.write(s.text) | |
sents = [i for i in nlp(text).sents if i.text.strip() != ""] | |
for s in sents: | |
f.write(f"{s.text}\n") | |
n = 10 | |
with Pool(n) as p: | |
p.map(func, df.index) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment