analysis_plan#

scikitplot.feature_selection.analysis_plan(schema, target=None, *, rules=None, role='feature')[source]#

Route every feature to the plots, summaries and tests that fit its kind.

Parameters:

schemaFeatureSchema: Fitted schema.
targetstr or None, default=None: A target column of the schema, or a target kind ("binary", "numeric_continuous" …). None omits the bivariate columns’ content.
rulesmapping or None, default=None: Replacement for DEFAULT_ANALYSIS_RULES (same keys).
rolestr or sequence of str or None, default=”feature”: Roles to include.

Returns:

pandas.DataFrame: Indexed by feature with kind, plots, summaries, target_tests, target_plots and notes (tuples of names).

Parameters:

schema (FeatureSchema)
target (str | None)
rules (Mapping[str, Any] | None)
role (Any)

Return type:

DataFrame

Examples

>>> import pandas as pd
>>> from scikitplot.feature_selection import analysis_plan, profile_features
>>> X = pd.DataFrame({"x": [1.5, 2.5, 3.5, 50.5] * 5, "y": [0, 1] * 10})
>>> plan = analysis_plan(profile_features(X, {"roles": {"target": ["y"]}}), "y")
>>> plan.loc["x", "target_tests"], plan.loc["x", "notes"]
(('mannwhitneyu', 'ttest_ind'), ('has_outliers: robust_summaries', 'skewed: log_scale_axis'))