DATASET GET PREDICTION METRICS¶
Computes regression prediction-quality metrics (R², MAE, RMSE, etc.) for selected target columns in a dataset. Use this worker to evaluate model predictions against actuals when both ground-truth and predicted values are present in the same dataset.
When to use¶
Classification: process.
Tagged: error_metrics, mae, model_evaluation, mse, prediction_metrics, r2, regression_evaluation, rmse.
Inputs¶
| Label | ID | Type | Default | Required | Description |
|---|---|---|---|---|---|
| Dataset | dataset_1 | dataset | — | Input dataset containing both predicted and actual values as columns; the worker computes the chosen metric across the specified target columns. | |
| Target Columns | columns | scalar | — | One or more column names from dataset_1 to evaluate; each selected column should represent a prediction/actual pair or a residual series (multi-select, list populated from dataset_1). | |
| Metrics | metrics | select | r | Regression error metric to compute; choose from R² (r2), Mean/Median/Max Absolute Error, Mean/Max Absolute Percentage Error, Sum Squared Error, Mean Squared Error, or Root Mean Squared Error — defaults to ‘r’ (R²). |
Outputs¶
| Label | ID | Type | Description |
|---|---|---|---|
| dataset_drop_columns_output_1 | dataset_drop_columns_output_1 | dataset | Output dataset containing the computed prediction metric value(s) for each selected target column, one row or column per metric result. |
Disciplines¶
- ai_ml.model_selection
- ai_ml.supervised.regression
- data.statistics
Runnable example¶
A runnable example is registered for this worker. Open the example workflow on the d3VIEW canvas: /api/workflow/example?id=dataset_get_prediction_metrics
Auto-generated from transformation schema. Worker id: dataset_get_prediction_metrics. Schema hash: a00ded5f61bc. Hand-curated docs in workerexamples/ override this page when present.