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 compare_canonical_models(OUTPUT_MODEL_PATH)
def test_zero_baseline():
pool = Pool(TRAIN_FILE, column_description=CD_FILE)
baseline = np.zeros(pool.num_row())
pool.set_baseline(baseline)
model = CatBoostClassifier(iterations=2, random_seed=0)
model.fit(pool)
model.save_model(OUTPUT_MODEL_PATH)
return compare_canonical_models(OUTPUT_MODEL_PATH)
def test_zero_baseline():
pool = Pool(TRAIN_FILE, column_description=CD_FILE)
baseline = np.zeros(pool.num_row())
pool.set_baseline(baseline)
model = CatBoostClassifier(iterations=2, random_seed=0)
model.fit(pool)
model.save_model(OUTPUT_MODEL_PATH)
return compare_canonical_models(OUTPUT_MODEL_PATH)
def test_non_zero_bazeline():
pool = Pool(CLOUDNESS_TRAIN_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'))
pool.set_baseline(baseline)
model = CatBoostClassifier(iterations=2, random_seed=0)
model.fit(pool)
model.save_model(OUTPUT_MODEL_PATH)
return compare_canonical_models(OUTPUT_MODEL_PATH)
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 compare_canonical_models(OUTPUT_MODEL_PATH)
object_importance = model.get_object_importance(pool, pool_train)
model.eval_metrics()
params = {'iterations': 500, 'depth': 10, 'loss_function': ['RMSE','MAE'], 'logging_level': 'Silent'}
params = {
'iterations' : 500,
'learning_rate': 0.1,
'loss_function': 'RMSE',
'eval_metric': 'R2',
'random_seed': 42,
'logging_level': 'Silent',
'allow_writing_files' : True,
'use_best_model': False
}
train_pool = Pool(X_train, y_train)
train_pool.set_baseline([[int(x)] for x in y_pred_X_train_rd])
validate_pool = Pool(X_test, y_test)
validate_pool.set_baseline([[int(x)] for x in y_pred_X_test_rd])
model = CatBoostRegressor(**params)
model.fit(train_pool, eval_set=validate_pool, plot=True)
best_model_params = params.copy()
best_model_params.update({
'use_best_model': True
})
best_model = CatBoostRegressor(**best_model_params)
best_model.fit(train_pool, eval_set=validate_pool, plot=True);
best_pred2 = best_model.predict(X_test)
best_pred_total = np.round(y_pred_X_test_rd + best_pred1)
ev = eval_metrics(y_test, np.round(model.predict(X_test)))