bigframes.bigquery.ml.evaluate#
- bigframes.bigquery.ml.evaluate(model:BaseEstimator|str|Series,input_:DataFrame|DataFrame|str|None=None,*,perform_aggregation:bool|None=None,horizon:int|None=None,confidence_level:float|None=None)→DataFrame[source]#
Evaluates a BigQuery ML model.
See theBigQuery ML EVALUATE function syntaxfor additional reference.
- Parameters:
model (bigframes.ml.base.BaseEstimator orstr) – The model to evaluate.
input (Union[bigframes.pandas.DataFrame,str],optional) – The DataFrame or query to use for evaluation. If not provided, theevaluation data from training is used.
perform_aggregation (bool,optional) – A BOOL value that indicates the level of evaluation for forecastingaccuracy. If you specify TRUE, then the forecasting accuracy is onthe time series level. If you specify FALSE, the forecastingaccuracy is on the timestamp level. The default value is TRUE.
horizon (int,optional) – An INT64 value that specifies the number of forecasted time pointsagainst which the evaluation metrics are computed. The default valueis the horizon value specified in the CREATE MODEL statement for thetime series model, or 1000 if unspecified. When evaluating multipletime series at the same time, this parameter applies to each timeseries.
confidence_level (float,optional) – A FLOAT64 value that specifies the percentage of the future valuesthat fall in the prediction interval. The default value is 0.95. Thevalid input range is
[0,1).
- Returns:
The evaluation results.
- Return type: