Оценка качества модели catboost

import numpy as np
import pandas as pd
from sklearn.model_selection import KFold
from sklearn.metrics import f1_score

skf=KFold(n_splits=5)
cat_feature=[2,3,4,6, 10,12,13]
print(cat_feature)
#categorical_features_indices = np.where(X.dtypes != np.float)[0]

from catboost import CatBoostClassifier, Pool, cv
import catboost
 
model = CatBoostClassifier(iterations = 100, depth = 2, learning_rate = 0.03, verbose = False)
f1 =[]
print(model)

%%time
for train_index, test_index in skf.split(y):
   X_train = X.iloc[train_index]
   X_test = X.iloc [test_index]
   y_train = y[train_index]
   y_test = y[test_index]
#pool = Pool(data=X, label=y, cat_features=cat_features)
# test_pool = Pool(X_test, cat_features=cat_feature)
   train_pool = Pool(X_train, y_train, cat_features=cat_feature)
   test_pool = Pool(X_test, y_test, cat_features=cat_feature)
   model.fit(train_pool)
   #model.fit(train_pool)
   preds =model.predict(test_pool, prediction_type='Class')
   #def predict(data, prediction_type='Class', ntree_start=0, ntree_end=0, thread_count=-1, verbose=None, task_type='CPU')
   f1.append(f1_score(y_test,preds.flatten()))