# Код fit.py:

import pandas as pd
from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline
from category_encoders import CatBoostEncoder
from sklearn.preprocessing import StandardScaler, OneHotEncoder
from catboost import CatBoostClassifier
import yaml
import os
import joblib

# обучение модели
def fit_model():
    with open('params.yaml', 'r') as fd:
        params = yaml.safe_load(fd)

    data = pd.read_csv('data/initial_data.csv')

    cat_features = data.select_dtypes(include='object')
    potential_binary_features = cat_features.nunique() == 2

    binary_cat_features = cat_features[potential_binary_features[potential_binary_features].index]
    other_cat_features = cat_features[potential_binary_features[~potential_binary_features].index]
    num_features = data.select_dtypes(['float'])

    preprocessor = ColumnTransformer(
        [
        ('binary', OneHotEncoder(drop=params["one_hot_drop"]), binary_cat_features.columns.tolist()),
        ('cat', CatBoostEncoder(return_df=False), other_cat_features.columns.tolist()),
        ('num', StandardScaler(), num_features.columns.tolist())
        ],
        remainder='drop',
        verbose_feature_names_out=False
    )

    model = CatBoostClassifier(auto_class_weights=params["auto_class_weights"])

    pipeline = Pipeline(
        [
        ('preprocessor', preprocessor),
        ('model', model)
        ]
    )
    pipeline.fit(data, data["target"])

    os.makedirs('models', exist_ok=True)
    with open('models/fitted_model.pkl', 'wb') as fd:
        joblib.dump(pipeline, fd)


if __name__ == '__main__':
    fit_model()

-----

Ошибка полностью:

Traceback (most recent call last):
  File "/home/mle-user/mle_projects/mle-dvc/scripts/fit.py", line 51, in <module>
    fit_model()
  File "/home/mle-user/mle_projects/mle-dvc/scripts/fit.py", line 43, in fit_model
    pipeline.fit(data, data["target"])
  File "/home/mle-user/mle_projects/mle-dvc/.venv_mle-dvc/lib/python3.10/site-packages/sklearn/base.py", line 1351, in wrapper
    return fit_method(estimator, *args, **kwargs)
  File "/home/mle-user/mle_projects/mle-dvc/.venv_mle-dvc/lib/python3.10/site-packages/sklearn/pipeline.py", line 475, in fit
    self._final_estimator.fit(Xt, y, **last_step_params["fit"])
  File "/home/mle-user/mle_projects/mle-dvc/.venv_mle-dvc/lib/python3.10/site-packages/catboost/core.py", line 5100, in fit
    self._fit(X, y, cat_features, text_features, embedding_features, None, sample_weight, None, None, None, None, baseline, use_best_model,
  File "/home/mle-user/mle_projects/mle-dvc/.venv_mle-dvc/lib/python3.10/site-packages/catboost/core.py", line 2303, in _fit
    train_params = self._prepare_train_params(
  File "/home/mle-user/mle_projects/mle-dvc/.venv_mle-dvc/lib/python3.10/site-packages/catboost/core.py", line 2184, in _prepare_train_params
    train_pool = _build_train_pool(X, y, cat_features, text_features, embedding_features, pairs,
  File "/home/mle-user/mle_projects/mle-dvc/.venv_mle-dvc/lib/python3.10/site-packages/catboost/core.py", line 1444, in _build_train_pool
    train_pool = Pool(X, y, cat_features=cat_features, text_features=text_features, embedding_features=embedding_features, pairs=pairs, weight=sample_weight, group_id=group_id,
  File "/home/mle-user/mle_projects/mle-dvc/.venv_mle-dvc/lib/python3.10/site-packages/catboost/core.py", line 793, in __init__
    self._init(data, label, cat_features, text_features, embedding_features, embedding_features_data, pairs, weight,
  File "/home/mle-user/mle_projects/mle-dvc/.venv_mle-dvc/lib/python3.10/site-packages/catboost/core.py", line 1369, in _init
    self._check_label_empty(label)
  File "/home/mle-user/mle_projects/mle-dvc/.venv_mle-dvc/lib/python3.10/site-packages/catboost/core.py", line 905, in _check_label_empty
    raise CatBoostError("Labels variable is empty.")
_catboost.CatBoostError: Labels variable is empty.
ERROR: failed to reproduce 'fit_model': failed to run: python scripts/fit.py, exited with 1