Fit a PCA using scikit-learn

fit_pca.py

def fit_pca(pca_data, x_component=1, y_component=2, split_by=None):
    ...
    pca_df = df[vars]

    pca = PCA(n_components=n_components)
    pca.fit(pca_df)
    ...
    
    pca_data = pd.DataFrame(pca.fit_transform(pca_df))
    
    return pca_data
  

def plot_pca(pca_data, x_component=1, y_component=2, split_by=None):
    fig = figure(plot_width=1000, plot_height=1000)
    for pop in pca_data["split"].unique().tolist():
        ...
        
    return fig