ContributionsPlotter#

class openstef_models.explainability.ContributionsPlotter[source]#

Bases: object

Visualizations for per-timestep feature contributions.

static plot_heatmap(contributions: TimeSeriesDataset, top_n: int = 10, target_column: str = 'load', bias_column: str = 'bias', *, show_prediction: bool = True) → Figure[source]#

Create an interactive heatmap of feature contributions over time.

X-axis is the prediction datetime, Y-axis shows feature names ranked by mean absolute contribution (most important at top). Color ranges from blue (negative) through white (zero) to red (positive). When show_prediction is True a line plot of the model prediction (sum of contributions + bias) is shown above the heatmap.

Parameters:

  • contributions (TimeSeriesDataset) – Output of predict_contributions().

  • top_n (int) – Number of top features to show (ranked by mean absolute contribution).

  • target_column (str) – Name of the target column to exclude. Default “load”.

  • bias_column (str) – Name of the bias column. Default “bias”.

  • show_prediction (bool) – If True, add a prediction line subplot above the heatmap. Default True.

  • contributions

  • top_n

  • target_column

  • bias_column

  • show_prediction

Returns:

Plotly Figure with a diverging heatmap centered at zero (and optional prediction line).

Return type:

Figure

static plot_waterfall(contributions: TimeSeriesDataset, timestep: int = 0, top_n: int = 10, target_column: str = 'load', bias_column: str = 'bias') → Figure[source]#

Create a waterfall chart decomposing a single timestep’s prediction.

Shows how the bias (base value) is pushed up or down by each feature’s contribution to arrive at the final prediction.

Parameters:

  • contributions (TimeSeriesDataset) – Output of predict_contributions().

  • timestep (int) – Row index (0-based) of the timestep to explain.

  • top_n (int) – Number of top features to show. Remaining features are aggregated into an “other” bar.

  • target_column (str) – Name of the target column to exclude. Default “load”.

  • bias_column (str) – Name of the bias column used as base value. Default “bias”.

  • contributions

  • timestep

  • top_n

  • target_column

  • bias_column

Returns:

Plotly Figure with waterfall chart.

Return type:

Figure

static plot_bar(contributions: TimeSeriesDataset, top_n: int = 10, target_column: str = 'load', bias_column: str = 'bias') → Figure[source]#

Create a horizontal bar chart of mean absolute contributions per feature.

Features are ranked from most to least important (top to bottom).

Parameters:

  • contributions (TimeSeriesDataset) – Output of predict_contributions().

  • top_n (int) – Number of top features to show.

  • target_column (str) – Name of the target column to exclude. Default “load”.

  • bias_column (str) – Name of the bias column to exclude. Default “bias”.

  • contributions

  • top_n

  • target_column

  • bias_column

Returns:

Plotly Figure with horizontal bar chart.

Return type:

Figure