Man pages for thfuchs/tsRNN
Time Series Forecasting using Recurrent Neural Networks by Keras
| acd | Absolute coverage difference (ACD) |
| baselines | Forecast with baseline models |
| check_acf | Check for autocorrelation |
| cv_arima | Cross validated prediction and evaluation with ARIMA... |
| cv_baselines | Cross validated prediction and evaluation with baseline... |
| dow30 | US index Dow Jones 30 quarterly earnings data from 1990 to... |
| dow30_clean | US index Dow Jones 30 quarterly EBIT from 1990 to 2020,... |
| DT_apple | Quarterly reported EBIT from Apple as data.table object from... |
| fc_arima | Univaritate time series with actual datapoints and ARIMA... |
| fc_baseline | Baseline forecast results (data.table object) by SNAIVE and... |
| keras_rnn | Train Recurrent Neural Network with Keras |
| mape | Mean Absolute Percentage Error (MAPE) |
| mase | Mean Absolute Scaled Error (MASE) |
| parse_tf_version | Parse installed TensorFlow version |
| plot_baselines | Plot Baseline forecasts |
| plot_baselines_samples | Plot cross validated samples of baseline forecasts |
| plot_prediction | Plot time series (incl. forecasts) for single cross... |
| plot_prediction_samples | Plot multiple splits from list with forecast results |
| py_dropout_model | Change dropout rate in recurrent layer or dropout layer of... |
| smape | symmetric Mean Absolute Percentage Error (sMAPE) |
| smis | scaled Mean Interval Score (sMIS) |
| ts_apple | Quarterly reported EBIT from Apple as ts object from 1995 to... |
| ts_nn_preparation | Timeseries data preparation for neural network Keras models |
| ts_normalization | Normalize univariate timeseries |
| tune_keras_rnn_bayesoptim | Automatic cross-validated tuning of recurrent neural networks... |
| tune_keras_rnn_eval | Evaluate (tuned) recurrent neural networks per... |
| tune_keras_rnn_predict | Automatic cross-validated training and prediction process for... |
