econml.validate.EvaluationResults

class econml.validate.EvaluationResults(cal_res: CalibrationEvaluationResults, blp_res: BLPEvaluationResults, qini_res: UpliftEvaluationResults, toc_res: UpliftEvaluationResults)[source]

Bases: object

Results class for combination of all tests.

Parameters:
  • cal_res (CalibrationEvaluationResults object) – Results object for calibration test

  • blp_res (BLPEvaluationResults object) – Results object for BLP test

  • qini_res (UpliftEvaluationResults object) – Results object for QINI test

  • toc_res (UpliftEvaluationResults object) – Results object for TOC test

__init__(cal_res: CalibrationEvaluationResults, blp_res: BLPEvaluationResults, qini_res: UpliftEvaluationResults, toc_res: UpliftEvaluationResults)[source]

Methods

__init__(cal_res, blp_res, qini_res, toc_res)

plot_cal(tmt)

Plot group average treatment effects (GATEs) and predicted GATEs by quantile-based group in validation sample.

plot_qini(tmt[, err_type])

Plot QINI curves.

plot_toc(tmt[, err_type])

Plot TOC curves.

summary()

Construct a dataframe summarizing the results of all 3 tests.

plot_cal(tmt: int)[source]

Plot group average treatment effects (GATEs) and predicted GATEs by quantile-based group in validation sample.

Parameters:

tmt (integer) – Treatment level to plot

Return type:

matplotlib plot with predicted GATE on x-axis and GATE (and 95% CI) on y-axis

plot_qini(tmt: int, err_type: str = None)[source]

Plot QINI curves.

Parameters:
  • tmt (integer) – Treatment level to plot

  • err_type (str) – Type of error to plot. Accepted values are normal (None), two-sided uniform confidence band (‘ucb2’), or 1-sided uniform confidence band (‘ucb1’).

Return type:

matplotlib plot with percentage treated on x-axis and QINI value (and 95% CI) on y-axis

plot_toc(tmt: int, err_type: str = None)[source]

Plot TOC curves.

Parameters:
  • tmt (integer) – Treatment level to plot

  • err_type (str) – Type of error to plot. Accepted values are normal (None), two-sided uniform confidence band (‘ucb2’), or 1-sided uniform confidence band (‘ucb1’).

Return type:

matplotlib plot with percentage treated on x-axis and TOC value (and 95% CI) on y-axis

summary()[source]

Construct a dataframe summarizing the results of all 3 tests.

Parameters:

None

Return type:

pandas dataframe containing summary of all test results