2024-04-16 18:58:43 +02:00
|
|
|
import pandas as pd
|
|
|
|
|
from sklearn.model_selection import train_test_split
|
|
|
|
|
|
2024-06-11 19:44:30 +02:00
|
|
|
data = pd.read_csv('beer_reviews.csv')
|
2024-04-16 18:58:43 +02:00
|
|
|
|
|
|
|
|
train_data, test_data = train_test_split(data, test_size=0.2, random_state=42)
|
|
|
|
|
|
|
|
|
|
train_data.to_csv('beer_reviews_train.csv', index=False)
|
|
|
|
|
test_data.to_csv('beer_reviews_test.csv', index=False)
|
