def export_predictions(predictions, output_dir) -> None:
exportation_columns = []
for ticker, prediction_data in predictions.items():
actual_prediction, observed_accuracy = prediction_data
exportation_columns.append(
(ticker, actual_prediction, observed_accuracy))
csv_exportation.export_predictions(exportation_columns,
output_dir + path.sep + 'gnb.csv')
def export_predictions(predictions, out_dir) -> None:
exportation_columns = []
for ticker, prediction_data in predictions.items():
actual_prediction, observed_accuracy = prediction_data
actual_prediction = np.argmax(actual_prediction)
if actual_prediction == 1:
prediction_str = "Trend Upward"
else:
prediction_str = "Trend Downward"
exportation_columns.append((ticker, prediction_str, observed_accuracy))
csv_exportation.export_predictions(exportation_columns, out_dir + path.sep + 'ann.csv')
def export_predictions(predictions, output_dir) -> None:
exportation_columns = []
for ticker, prediction_data in predictions.items():
actual_predictions, observed_accuracies = prediction_data
for i in range(len(actual_predictions)):
actual_prediction = actual_predictions[i]
observed_accuracy = observed_accuracies[i]
exportation_columns.append(
(ticker, actual_prediction, observed_accuracy))
csv_exportation.export_predictions(exportation_columns,
output_dir + path.sep + 'svm.csv')
def export_predictions(predictions, output_dir) -> None:
exportation_columns = []
for ticker, prediction_data in predictions.items():
actual_predictions, observed_accuracies = prediction_data
for i in range(len(actual_predictions)):
actual_prediction = actual_predictions[i]
observed_accuracy = observed_accuracies[i]
if actual_prediction == 1:
prediction_str = "Trend Upward"
else:
prediction_str = "Trend Downward"
exportation_columns.append(
(ticker, prediction_str, observed_accuracy))
csv_exportation.export_predictions(
exportation_columns, output_dir + path.sep + 'random_forest.csv')