ium_495719/data_processing_dvc.py

15 lines
501 B
Python
Raw Normal View History

2024-05-29 21:22:02 +02:00
from sklearn.model_selection import train_test_split
import pandas as pd
import sys
housing_price_dataset = pd.read_csv(sys.argv[1])
housing_price_dataset = pd.get_dummies(housing_price_dataset, columns=['Neighborhood'])
hp_train_test, hp_dev = train_test_split(housing_price_dataset, test_size=0.1)
hp_train, hp_test = train_test_split(hp_train_test, test_size=1000)
hp_train.to_csv('hp_train.csv', index=False)
hp_dev.to_csv('hp_dev.csv', index=False)
hp_test.to_csv('hp_test.csv', index=False)