Ctrl+K

njab.sklearn.pca module

njab.sklearn.pca module#

njab.sklearn.pca.plot_explained_variance(pca: PCA, ax: Axes | None = None) → Axes[source]#

Plot explained variance of PCA from scikit-learn.

njab.sklearn.pca.run_pca(df_wide: DataFrame, n_components: int = 2) → tuple[DataFrame, PCA][source]#

Run PCA on DataFrame and return result.

Parameters:

  • df (pd.DataFrame) – DataFrame in wide format to fit features on.

  • n_components (int, optional) – Number of Principal Components to fit, by default 2

Returns:

principal compoments of DataFrame with same indices as in original DataFrame, and fitted PCA model of sklearn

Return type:

Tuple[pd.DataFrame, PCA]

Contents