I am new in python. I am trying to predict the "time_to_failure" for given "acoustic_data" in the test CSV file using catboost algorithm.
def catbostregtest(X_train, y_train): # submission format submission = pd.read_csv('sample_submission.csv', index_col='seg_id') X_test = pd.DataFrame() # prepare test data for seg_id in submission.index: seg = pd.read_csv('test/' + seg_id + '.csv') ch = gen_features(seg['acoustic_data']) X_test = X_test.append(ch, ignore_index=True) # model of choice here model = CatBoostRegressor(iterations=10000, loss_function='MAE', boosting_type='Ordered') model.fit(X_train, y_train) #error line y_hat = model.predict(X_test) #error line # write submission file LSTM submission['time_to_failure'] = y_hat submission.to_csv('submissionCAT.csv') print(model.best_score_) This function "catbostregtest" is giving me error with the errorlog Traceback (most recent call last): File "E:\dir\question.py", line 68, in main() File "E:\dir\question.py", line 65, in main catbostregtest(X_train, y_train) File "E:\dir\question.py", line 50, in catbostregtest model.fit(X_train, y_train) File "C:\Users\xyz\AppData\Local\Continuum\anaconda3\lib\site-packages\catboost\core.py", line 4330, in fit save_snapshot, snapshot_file, snapshot_interval, init_model) File "C:\Users\xyz\AppData\Local\Continuum\anaconda3\lib\site-packages\catboost\core.py", line 1690, in _fit train_params["init_model"] File "C:\Users\xyz\AppData\Local\Continuum\anaconda3\lib\site-packages\catboost\core.py", line 1225, in _train self._object._train(train_pool, test_pool, params, allow_clear_pool, init_model._object if init_model else None) File "_catboost.pyx", line 3870, in _catboost._CatBoost._train File "_catboost.pyx", line 3916, in _catboost._CatBoost._train CatBoostError: c:/goagent/pipelines/buildmaster/catboost.git/catboost/libs/data/quantization.cpp:2424: All features are either constant or ignored. This is gen_features function def gen_features(X): strain = [] strain.append(X.mean()) strain.append(X.std()) strain.append(X.min()) strain.append(X.max()) strain.append(X.kurtosis()) strain.append(X.skew()) strain.append(np.quantile(X,0.01)) strain.append(np.quantile(X,0.05)) strain.append(np.quantile(X,0.95)) strain.append(np.quantile(X,0.99)) strain.append(np.abs(X).max()) strain.append(np.abs(X).mean()) strain.append(np.abs(X).std()) return pd.Series(strain) This function is called from the main function def main(): train1 = pd.read_csv('train.csv', iterator=True, chunksize=150_000, dtype={'acoustic_data': np.int16, 'time_to_failure': np.float64}) X_train = pd.DataFrame() y_train = pd.Series() for df in train1: ch = gen_features(df['acoustic_data']) X_train = X_train.append(ch, ignore_index=True) y_train = y_train.append(pd.Series(df['time_to_failure'].values[-1])) catbostregtest(X_train, y_train) How I can remove the error that occur during making predict from catboost model? How I can remove this error please help. You can download and run the project in spyder ide from this link https://drive.google.com/file/d/1JFsNfE22ef82e-dS0zsZHDE3zGJxnJ_J/view?usp=sharing or https://github.com/princit/catboostAlgorithm -- https://mail.python.org/mailman/listinfo/python-list