def test_fit_data():
pool = Pool(CLOUDNESS_TRAIN_FILE, column_description=CLOUDNESS_CD_FILE)
eval_pool = Pool(CLOUDNESS_TEST_FILE, column_description=CLOUDNESS_CD_FILE)
base_model = CatBoostClassifier(iterations=2,
random_seed=0,
loss_function="MultiClass")
base_model.fit(pool)
baseline = np.array(
base_model.predict(pool, prediction_type='RawFormulaVal'))
eval_baseline = np.array(
base_model.predict(eval_pool, prediction_type='RawFormulaVal'))
eval_pool._set_baseline(eval_baseline)
model = CatBoostClassifier(iterations=2,
random_seed=0,
loss_function="MultiClass")
data = map_cat_features(pool.get_features(),
pool.get_cat_feature_indices())
model.fit(data,
pool.get_label(),
pool.get_cat_feature_indices(),
sample_weight=np.arange(1,
pool.num_row() + 1),
baseline=baseline,
use_best_model=True,
eval_set=eval_pool)
model.save_model(OUTPUT_MODEL_PATH)
return local_canonical_file(OUTPUT_MODEL_PATH)
