plots

neuralhydrology.evaluation.plots.percentile_plot(y: ndarray, y_hat: ndarray, title: str = '') → Tuple[matplotlib.figure.Figure, matplotlib.axes.Axes]

Plot the time series of observed values with 3 specific prediction intervals (i.e.: 25 to 75, 10 to 90, 5 to 95).

Parameters:

  • y (np.ndarray) – Array of observed values.

  • y_hat (np.ndarray) – Array of simulated values, where the last dimension contains the samples for each time step.

  • title (str, optional) – Title of the plot.

Returns:

The percentile plot.

Return type:

Tuple[mpl.figure.Figure, mpl.axes.Axis]

neuralhydrology.evaluation.plots.regression_plot(y: ndarray, y_hat: ndarray, title: str = '') → Tuple[matplotlib.figure.Figure, matplotlib.axes.Axes]

Plot the time series of observed and simulated values.

Parameters:

  • y (np.ndarray) – Array of observed values.

  • y_hat (np.ndarray) – Array of simulated values.

  • title (str, optional) – Title of the plot.

Returns:

The regression plot.

Return type:

Tuple[mpl.figure.Figure, mpl.axes.Axis]

neuralhydrology.evaluation.plots.uncertainty_plot(y: ndarray, y_hat: ndarray, title: str = '') → Tuple[matplotlib.figure.Figure, ndarray]

Plots probability plot alongside a hydrograph with simulation percentiles.

The probability plot itself is analogous to the calibration plot for classification tasks. The plot compares the theoretical percentiles of the estimated conditional distributions (over time) with the respective relative empirical counts. The probability plot is often also referred to as probability integral transform diagram, Q-Q plot, or predictive Q-Q plot.

Parameters:

  • y (np.ndarray) – Array of observed values.

  • y_hat (np.ndarray) – Array of simulated values.

  • title (str, optional) – Title of the plot, by default empty.

Returns:

The uncertainty plot.

Return type:

Tuple[mpl.figure.Figure, np.ndarray]