hookeai.model_architectures.rnn_base_model.predict.prediction

Prediction of recurrent neural network model.

Functions

predict

Make predictions with recurrent neural network model for given dataset.

compute_sample_prediction_loss

Compute loss of sample output features prediction.

Functions

compute_sample_prediction_loss(model, ...[, ...])	Compute loss of sample output features prediction.
data_scaler_transform(model, tensor, ...[, mode])	Perform data scaling operation on features PyTorch tensor.
get_pytorch_loss(loss_type, **kwargs)	Get PyTorch-based loss function.
get_time_series_data_loader(dataset[, ...])	Get time series data set data loader.
load_model_state(model[, model_load_state, ...])	Load model state from file.
make_predictions_subdir(predict_directory)	Create model predictions subdirectory.
predict(dataset, model_directory[, model, ...])	Make predictions with recurrent neural network model for given dataset.
save_sample_predictions(predictions_dir, ...)	Save model prediction results for given sample.
seed_worker(worker_id)	Set workers seed in PyTorch data loaders to preserve reproducibility.
write_prediction_summary_file(...)	Write summary data file for model prediction process.

Classes

GRURNNModel(n_features_in, n_features_out, ...)

Multi-layer gated recurrent unit (GRU) recurrent neural network model.