getting CatBoostError: Invalid cat_features[6] = 22 value: index must be < 22 but len(x_train.columns) is 23

[javiercoh]

Problem: getting "catBoostError: Invalid cat_features[6] = 22 value: index must be < 22" but len(cat_features) = 23
catboost version:1.2.3
Operating System: Linux 24.01.30
CPU:4 cores, 28 GB RAM, 56 GB disk
GPU:

`
print(x_train.columns)

print(len(x_train.columns)) # this returns 23

categorical_positions = [11,12,13,17,20,21,22]

model = CatBoostRegressor(iterations=100,
loss_function=f'MultiQuantile:alpha={quantile_str}', cat_features=categorical_positions)

model.fit(x_train, y_train)
`

[andrey-khropov]

Can you give more detailed information to reproduce? I cannot reproduce this error.

Here's the code that works without problems for me.

    import numpy as np
    import pandas as pd
    from catboost import CatBoostRegressor

    n_samples = 10
    x_train_dict = {}

    for i in range(23):
        x_train_dict[str(i)] = np.random.random_integers(100, size=n_samples)

    x_train = pd.DataFrame(x_train_dict)
    y_train = np.random.random_sample(n_samples)

    quantile_str = '0.1,0.9'

    print(len(x_train.columns)) # this returns 23
    categorical_positions = [11,12,13,17,20,21,22]

    model = CatBoostRegressor(iterations=100,
    loss_function=f'MultiQuantile:alpha={quantile_str}', cat_features=categorical_positions)

    model.fit(x_train, y_train)