evidently.metrics.data_drift

Submodules

column_drift_metric module

class ColumnDriftMetric(column_name: str, stattest: Optional[Union[str, Callable[[Series, Series, str, float], Tuple[float, bool]], StatTest]] = None, stattest_threshold: Optional[float] = None)

Bases: Metric[ColumnDriftMetricResults]

Calculate drift metric for a column

Attributes:

column_name : str

stattest : Optional[Union[str, Callable[[Series, Series, str, float], Tuple[float, bool]], StatTest]]

stattest_threshold : Optional[float]

Methods:

calculate(data: InputData)

get_parameters()

class ColumnDriftMetricRenderer(color_options: Optional[ColorOptions] = None)

Bases: MetricRenderer

Attributes:

color_options : ColorOptions

Methods:

render_html(obj: ColumnDriftMetric)

render_json(obj: ColumnDriftMetric)

class ColumnDriftMetricResults(column_name: str, column_type: str, stattest_name: str, stattest_threshold: float, drift_score: Union[float, int], drift_detected: bool, current_distribution: Distribution, reference_distribution: Distribution, current_scatter: Optional[Dict[str, list]], x_name: Optional[str], plot_shape: Optional[Dict[str, float]])

Bases: object

Attributes:

column_name : str

column_type : str

current_distribution : Distribution

current_scatter : Optional[Dict[str, list]]

drift_detected : bool

drift_score : Union[float, int]

plot_shape : Optional[Dict[str, float]]

reference_distribution : Distribution

stattest_name : str

stattest_threshold : float

x_name : Optional[str]

column_value_plot module

class ColumnValuePlot(column_name: str)

Bases: Metric[ColumnValuePlotResults]

Attributes:

column_name : str

Methods:

calculate(data: InputData)

class ColumnValuePlotRenderer(color_options: Optional[ColorOptions] = None)

Bases: MetricRenderer

Attributes:

color_options : ColorOptions

Methods:

render_html(obj: ColumnValuePlot)

render_json(obj: ColumnValuePlot)

class ColumnValuePlotResults(column_name: str, datetime_column_name: Optional[str], current_scatter: pandas.core.frame.DataFrame, reference_scatter: pandas.core.frame.DataFrame)

Bases: object

Attributes:

column_name : str

current_scatter : DataFrame

datetime_column_name : Optional[str]

reference_scatter : DataFrame

data_drift_table module

class DataDriftTable(columns: Optional[List[str]] = None, stattest: Optional[Union[str, Callable[[Series, Series, str, float], Tuple[float, bool]], StatTest]] = None, cat_stattest: Optional[Union[str, Callable[[Series, Series, str, float], Tuple[float, bool]], StatTest]] = None, num_stattest: Optional[Union[str, Callable[[Series, Series, str, float], Tuple[float, bool]], StatTest]] = None, per_column_stattest: Optional[Dict[str, Union[str, Callable[[Series, Series, str, float], Tuple[float, bool]], StatTest]]] = None, stattest_threshold: Optional[float] = None, cat_stattest_threshold: Optional[float] = None, num_stattest_threshold: Optional[float] = None, per_column_stattest_threshold: Optional[Dict[str, float]] = None)

Bases: Metric[DataDriftTableResults]

Attributes:

columns : Optional[List[str]]

options : DataDriftOptions

Methods:

calculate(data: InputData)

get_parameters()

class DataDriftTableRenderer(color_options: Optional[ColorOptions] = None)

Bases: MetricRenderer

Attributes:

color_options : ColorOptions

Methods:

render_html(obj: DataDriftTable)

render_json(obj: DataDriftTable)

class DataDriftTableResults(number_of_columns: int, number_of_drifted_columns: int, share_of_drifted_columns: float, dataset_drift: bool, drift_by_columns: Dict[str, ColumnDataDriftMetrics], dataset_columns: DatasetColumns)

Bases: object

Attributes:

dataset_columns : DatasetColumns

dataset_drift : bool

drift_by_columns : Dict[str, ColumnDataDriftMetrics]

number_of_columns : int

number_of_drifted_columns : int

share_of_drifted_columns : float

dataset_drift_metric module

class DataDriftMetricsRenderer(color_options: Optional[ColorOptions] = None)

Bases: MetricRenderer

Attributes:

color_options : ColorOptions

Methods:

render_html(obj: DatasetDriftMetric)

render_json(obj: DatasetDriftMetric)

class DatasetDriftMetric(columns: Optional[List[str]] = None, drift_share: float = 0.5, stattest: Optional[Union[str, Callable[[Series, Series, str, float], Tuple[float, bool]], StatTest]] = None, cat_stattest: Optional[Union[str, Callable[[Series, Series, str, float], Tuple[float, bool]], StatTest]] = None, num_stattest: Optional[Union[str, Callable[[Series, Series, str, float], Tuple[float, bool]], StatTest]] = None, per_column_stattest: Optional[Dict[str, Union[str, Callable[[Series, Series, str, float], Tuple[float, bool]], StatTest]]] = None, stattest_threshold: Optional[float] = None, cat_stattest_threshold: Optional[float] = None, num_stattest_threshold: Optional[float] = None, per_column_stattest_threshold: Optional[Dict[str, float]] = None)

Bases: Metric[DatasetDriftMetricResults]

Attributes:

columns : Optional[List[str]]

drift_share : float

options : DataDriftOptions

Methods:

calculate(data: InputData)

get_parameters()

class DatasetDriftMetricResults(drift_share: float, number_of_columns: int, number_of_drifted_columns: int, share_of_drifted_columns: float, dataset_drift: bool)

Bases: object

Attributes:

dataset_drift : bool

drift_share : float

number_of_columns : int

number_of_drifted_columns : int

share_of_drifted_columns : float

target_by_features_table module

class TargetByFeaturesTable(columns: Optional[List[str]] = None)

Bases: Metric[TargetByFeaturesTableResults]

Attributes:

columns : Optional[List[str]]

Methods:

calculate(data: InputData)

class TargetByFeaturesTableRenderer(color_options: Optional[ColorOptions] = None)

Bases: MetricRenderer

Attributes:

color_options : ColorOptions

Methods:

render_html(obj: TargetByFeaturesTable)

render_json(obj: TargetByFeaturesTable)

class TargetByFeaturesTableResults(current_plot_data: pandas.core.frame.DataFrame, reference_plot_data: pandas.core.frame.DataFrame, target_name: Optional[str], curr_predictions: Optional[PredictionData], ref_predictions: Optional[PredictionData], columns: List[str], task: str)

Bases: object

Attributes:

columns : List[str]

curr_predictions : Optional[PredictionData]

current_plot_data : DataFrame

ref_predictions : Optional[PredictionData]

reference_plot_data : DataFrame

target_name : Optional[str]

task : str