abacusai.feature_drift_summary

Classes

CategoricalRangeViolation	Summary of important range mismatches for a numerical feature discovered by a model monitoring instance
NullViolation	Summary of anomalous null frequencies for a feature discovered by a model monitoring instance
RangeViolation	Summary of important range mismatches for a numerical feature discovered by a model monitoring instance
AbstractApiClass
FeatureDriftSummary	Summary of important model monitoring statistics for features available in a model monitoring instance

Module Contents

class abacusai.feature_drift_summary.CategoricalRangeViolation(client, name=None, mostCommonValues=None, freqOutsideTrainingRange=None)

Bases: abacusai.return_class.AbstractApiClass

Summary of important range mismatches for a numerical feature discovered by a model monitoring instance

Parameters:

• client (ApiClient) – An authenticated API Client instance

• name (str) – Name of feature.

• mostCommonValues (list[str]) – List of most common feature names in the prediction distribution not present in the training distribution.

• freqOutsideTrainingRange (float) – Frequency of prediction rows outside training distribution for the specified feature.

__repr__()

Return repr(self).

to_dict()

Get a dict representation of the parameters in this class

Returns:

The dict value representation of the class parameters

Return type:

dict

class abacusai.feature_drift_summary.NullViolation(client, name=None, violation=None, trainingNullFreq=None, predictionNullFreq=None)

Bases: abacusai.return_class.AbstractApiClass

Summary of anomalous null frequencies for a feature discovered by a model monitoring instance

Parameters:

• client (ApiClient) – An authenticated API Client instance

• name (str) – Name of feature.

• violation (str) – Description of null violation for a prediction feature.

• trainingNullFreq (float) – Proportion of null entries in training feature.

• predictionNullFreq (float) – Proportion of null entries in prediction feature.

__repr__()

Return repr(self).

to_dict()

Get a dict representation of the parameters in this class

Returns:

The dict value representation of the class parameters

Return type:

dict

class abacusai.feature_drift_summary.RangeViolation(client, name=None, trainingMin=None, trainingMax=None, predictionMin=None, predictionMax=None, freqAboveTrainingRange=None, freqBelowTrainingRange=None)

Bases: abacusai.return_class.AbstractApiClass

Summary of important range mismatches for a numerical feature discovered by a model monitoring instance

Parameters:

• client (ApiClient) – An authenticated API Client instance

• name (str) – Name of feature.

• trainingMin (float) – Minimum value of training distribution for the specified feature.

• trainingMax (float) – Maximum value of training distribution for the specified feature.

• predictionMin (float) – Minimum value of prediction distribution for the specified feature.

• predictionMax (float) – Maximum value of prediction distribution for the specified feature.

• freqAboveTrainingRange (float) – Frequency of prediction rows below training minimum for the specified feature.

• freqBelowTrainingRange (float) – Frequency of prediction rows above training maximum for the specified feature.

__repr__()

Return repr(self).

to_dict()

Get a dict representation of the parameters in this class

Returns:

The dict value representation of the class parameters

Return type:

dict

class abacusai.feature_drift_summary.AbstractApiClass(client, id)

__eq__(other)

Return self==value.

_get_attribute_as_dict(attribute)

class abacusai.feature_drift_summary.FeatureDriftSummary(client, featureIndex=None, name=None, distance=None, jsDistance=None, wsDistance=None, ksStatistic=None, predictionDrift=None, targetColumn=None, dataIntegrityTimeseries=None, nestedSummary=None, psi=None, csi=None, chiSquare=None, nullViolations={}, rangeViolations={}, catViolations={})

Bases: abacusai.return_class.AbstractApiClass

Summary of important model monitoring statistics for features available in a model monitoring instance

Parameters:

• client (ApiClient) – An authenticated API Client instance

• featureIndex (list[dict]) – A list of dicts of eligible feature names and corresponding overall feature drift measures.

• name (str) – Name of feature.

• distance (float) – Symmetric sum of KL divergences between the training distribution and the range of values in the specified window.

• jsDistance (float) – JS divergence between the training distribution and the range of values in the specified window.

• wsDistance (float) – Wasserstein distance between the training distribution and the range of values in the specified window.

• ksStatistic (float) – Kolmogorov-Smirnov statistic computed between the training distribution and the range of values in the specified window.

• predictionDrift (float) – Drift for the target column.

• targetColumn (str) – Target column name.

• dataIntegrityTimeseries (dict) – Frequency vs Data Integrity Violation Charts.

• nestedSummary (list[dict]) – Summary of model monitoring statistics for nested features.

• psi (float) – Population stability index computed between the training distribution and the range of values in the specified window.

• csi (float) – Characteristic Stability Index computed between the training distribution and the range of values in the specified window.

• chiSquare (float) – Chi-square statistic computed between the training distribution and the range of values in the specified window.

• nullViolations (NullViolation) – A list of dicts of feature names and a description of corresponding null violations.

• rangeViolations (RangeViolation) – A list of dicts of numerical feature names and corresponding prediction range discrepancies.

• catViolations (CategoricalRangeViolation) – A list of dicts of categorical feature names and corresponding prediction range discrepancies.

__repr__()

Return repr(self).

to_dict()

Get a dict representation of the parameters in this class

Returns:

The dict value representation of the class parameters

Return type:

dict