log_mmm_evaluation_metrics#

pymc_marketing.mlflow.log_mmm_evaluation_metrics(y_true, y_pred, metrics_to_calculate=None, hdi_prob=0.94, prefix='')[source]#

Log evaluation metrics produced by pymc_marketing.mmm.evaluation.compute_summary_metrics() to MLflow.

Parameters:

y_truenpt.NDArray | pd.Series

The true values of the target variable.

y_prednpt.NDArray | xr.DataArray

The predicted values of the target variable.

metrics_to_calculatelist of str or None, optional

List of metrics to calculate. If None, all available metrics will be calculated. Options include:

r_squared: Bayesian R-squared.

rmse: Root Mean Squared Error.

nrmse: Normalized Root Mean Squared Error.

mae: Mean Absolute Error.

nmae: Normalized Mean Absolute Error.

mape: Mean Absolute Percentage Error.

hdi_probfloat, optional

The probability mass of the highest density interval. Defaults to 0.94.

prefixstr, optional

Prefix to add to the metric names. Defaults to “”.

Examples

Log in-sample evaluation metrics for a PyMC-Marketing MMM model:

import mlflow

from pymc_marketing.mmm import MMM

mmm = MMM(...)
mmm.fit(X, y)

predictions = mmm.sample_posterior_predictive(X)

with mlflow.start_run():
    log_mmm_evaluation_metrics(y, predictions["y"])