Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| import matplotlib.pyplot as plt | |
| # from skops import hub_utils | |
| import time | |
| import pickle | |
| import numpy as np | |
| from sklearn.preprocessing import StandardScaler | |
| from sklearn.linear_model import LassoLarsIC | |
| from sklearn.pipeline import make_pipeline | |
| from sklearn.datasets import load_diabetes | |
| def load_dataset(): | |
| X, y = load_diabetes(return_X_y=True, as_frame=True) | |
| return X,y | |
| def aic_pipeline(X,y): | |
| lasso_lars_ic = make_pipeline(StandardScaler(), LassoLarsIC(criterion="aic")).fit(X, y) | |
| return lasso_lars_ic | |
| def zou_et_al_criterion_rescaling(criterion, n_samples, noise_variance): | |
| """Rescale the information criterion to follow the definition of Zou et al.""" | |
| return criterion - n_samples * np.log(2 * np.pi * noise_variance) - n_samples | |
| def zou_et_all_aic(lasso_lars_ic): | |
| aic_criterion = zou_et_al_criterion_rescaling( | |
| lasso_lars_ic[-1].criterion_, | |
| n_samples, | |
| lasso_lars_ic[-1].noise_variance_, | |
| ) | |
| index_alpha_path_aic = np.flatnonzero( | |
| lasso_lars_ic[-1].alphas_ == lasso_lars_ic[-1].alpha_ | |
| )[0] | |
| return index_alpha_path_aic, aic_criterion | |
| def zou_et_all_bic(lasso_lars_ic): | |
| lasso_lars_ic.set_params(lassolarsic__criterion="bic").fit(X, y) | |
| bic_criterion = zou_et_al_criterion_rescaling( | |
| lasso_lars_ic[-1].criterion_, | |
| n_samples, | |
| lasso_lars_ic[-1].noise_variance_, | |
| ) | |
| index_alpha_path_bic = np.flatnonzero( | |
| lasso_lars_ic[-1].alphas_ == lasso_lars_ic[-1].alpha_ | |
| )[0] | |
| return index_alpha_path_bic, bic_criterion | |
| def fn_assert_true(): | |
| assert index_alpha_path_bic == index_alpha_path_aic | |
| def visualize_input_data(): | |
| fig = plt.figure(1, facecolor="w", figsize=(5, 5)) | |
| plt.plot(aic_criterion, color="tab:blue", marker="o", label="AIC criterion") | |
| plt.plot(bic_criterion, color="tab:orange", marker="o", label="BIC criterion") | |
| plt.vlines( | |
| index_alpha_path_bic, | |
| aic_criterion.min(), | |
| aic_criterion.max(), | |
| color="black", | |
| linestyle="--", | |
| label="Selected alpha", | |
| ) | |
| plt.legend() | |
| plt.ylabel("Information criterion") | |
| plt.xlabel("Lasso model sequence") | |
| _ = plt.title("Lasso model selection via AIC and BIC") | |
| return fig | |
| title = " Lasso model selection via information criteria" | |
| with gr.Blocks(title=title) as demo: | |
| gr.Markdown(f"# {title}") | |
| gr.Markdown( | |
| """ | |
| A LassoLarsIC estimator is fit on a diabetes dataset and the AIC and the BIC criteria are used to select the best model. | |
| It is important to note that the optimization to find alpha with LassoLarsIC relies on the AIC or BIC criteria that are computed in-sample, | |
| thus on the training set directly. This approach differs from the cross-validation procedure | |
| """ | |
| ) | |
| gr.Markdown(" **https://scikit-learn.org/stable/auto_examples/linear_model/plot_lasso_lars_ic.html#sphx-glr-auto-examples-linear-model-plot-lasso-lars-ic-py**") | |
| ##process | |
| X,y = load_dataset() | |
| lasso_lars_ic = aic_pipeline(X,y) | |
| n_samples = X.shape[0] | |
| index_alpha_path_aic, aic_criterion = zou_et_all_aic(lasso_lars_ic) | |
| index_alpha_path_bic, bic_criterion = zou_et_all_bic(lasso_lars_ic) | |
| fn_assert_true() | |
| with gr.Tab("AIC BIC Criteria"): | |
| btn = gr.Button(value="Plot AIC BIC Criteria w Regularization") | |
| btn.click(visualize_input_data, outputs= gr.Plot(label='AIC BIC Criteria') ) | |
| demo.launch() |