results = provider.balance_result(result_cols[0], low, high, step, samples) results = results[result_cols].as_matrix() results = results[:, 0] data = provider.fetch_dataset(data_segment) # results = results * 0.1 # data = data[:10000] # results = results[:10000] count = data.shape[0] [training_data, training_result], \ [validation_data, validation_result], \ [test_data, test_result], \ = provider.balance_dataset([results, data], low, high, step, validation_samples_ratio=0.05, test_samples_ratio=0.05) print(("Total data set size: {}\n" "Training set size: {}\n" "Validation set size: {}\n" "Test set size: {}\n".format(count, training_data.shape[0], validation_data.shape[0], test_data.shape[0]))) print( ("training result max:{} min:{}".format(round(np.max(training_result), 2), round(np.min(training_result)), 2))) model.train([training_data, training_result],
result_cols = ['nextday_close'] provider = Provider(start_date, end_date) model = Model() results = provider.fetch_resultset(result_cols) results = provider.balance_result(result_cols[0], low, high, step, samples) results = results[result_cols].as_matrix() results = results[:, 0] data = provider.fetch_dataset(data_segment) # results = results * 0.1 # data = data[:10000] # results = results[:10000] count = data.shape[0] [training_data, training_result], \ [validation_data, validation_result], \ [test_data, test_result], \ = provider.balance_dataset([results, data], low, high, step, 250, 200) print(("Training set size: {}\n" "Validation set size: {}\n" "Test set size: {}\n".format(training_data.shape[0], validation_data.shape[0], test_data.shape[0]))) model.train([training_data, training_result], [validation_data, validation_result], [test_data, test_result])