44 KiB
44 KiB
In [3]:
import pandas as pd
from sklearn import set_config
set_config(transform_output="pandas")
random_state=9
data_car = pd.read_csv('car_price_prediction.csv', index_col="ID")
data_car
Out[3]:
In [5]:
from src.utils import split_stratified_into_train_val_test
X_train, X_val, X_test, y_train, y_val, y_test = split_stratified_into_train_val_test(
data_car,
stratify_colname="Airbags",
frac_train=0.80,
frac_val=0,
frac_test=0.20,
random_state=random_state,
)
display("X_train", X_train)
display("y_train", y_train)
display("X_test", X_test)
display("y_test", y_test)