Update 'process_dataset.py'

This commit is contained in:
Kacper Dudzic 2022-04-02 17:10:11 +02:00
parent 7d80afc9dd
commit 1921a91f6d

View File

@ -14,8 +14,8 @@ lego['piece_count'] = lego['piece_count'].apply(np.int64)
lego['prod_id'] = lego['prod_id'].apply(np.int64) lego['prod_id'] = lego['prod_id'].apply(np.int64)
# wglad, statystyki # wglad, statystyki
print(lego[:10]) print(lego)
print(lego.describe(include='all')[:10]) print(lego.describe(include='all'))
# pierwszy podzial, wydzielamy zbior treningowy # pierwszy podzial, wydzielamy zbior treningowy
lego_train, lego_rem = train_test_split(lego, train_size=0.8, random_state=1) lego_train, lego_rem = train_test_split(lego, train_size=0.8, random_state=1)