def test_export_to_python_after_load():
train_pool = Pool(TRAIN_FILE, column_description=CD_FILE)
test_pool = Pool(TEST_FILE, column_description=CD_FILE)
model = CatBoostClassifier(iterations=40, random_seed=0)
model.fit(train_pool)
pred_model = model.predict(test_pool, prediction_type='RawFormulaVal')
model.save_model(OUTPUT_MODEL_PATH)
model_loaded = CatBoostClassifier()
model_loaded.load_model(OUTPUT_MODEL_PATH)
model_loaded.save_model(OUTPUT_PYTHON_MODEL_PATH,
format="python",
pool=train_pool)
pred_model_loaded = model_loaded.predict(test_pool,
prediction_type='RawFormulaVal')
import sys
import os.path
module_dir = os.path.dirname(OUTPUT_PYTHON_MODEL_PATH)
sys.path.insert(0, module_dir)
from model import apply_catboost_model as apply_catboost_model_from_python
pred_python = []
for test_line in test_pool.get_features():
float_features, cat_features = _split_features(
test_line, train_pool.get_cat_feature_indices(),
test_pool.get_cat_feature_hash_to_string())
pred_python.append(
apply_catboost_model_from_python(float_features, cat_features))
assert _check_data(pred_model, pred_python)
assert _check_data(pred_model_loaded, pred_python)
def test_export_model_with_only_float_features_to_python_from_python():
train_pool = Pool(HIGGS_TRAIN_FILE, column_description=HIGGS_CD_FILE)
test_pool = Pool(HIGGS_TEST_FILE, column_description=HIGGS_CD_FILE)
model = CatBoost({'iterations': 30, 'random_seed': 0})
model.fit(train_pool)
pred_model = model.predict(test_pool, prediction_type='RawFormulaVal')
model.save_model(OUTPUT_PYTHON_MODEL_PATH, format="python")
import sys
import os.path
module_dir = os.path.dirname(OUTPUT_PYTHON_MODEL_PATH)
sys.path.insert(0, module_dir)
from model import apply_catboost_model as apply_catboost_model_from_python
pred_python = []
for float_features in test_pool.get_features():
pred_python.append(apply_catboost_model_from_python(float_features))
assert _check_data(pred_model, pred_python)