app.py

import gradio as gr

from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.inspection import permutation_importance

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

def create_dataset():
    X, y = make_classification(
        n_samples=1000,
        n_features=10,
        n_informative=3,
        n_redundant=0,
        n_repeated=0,
        n_classes=2,
        random_state=0,
        shuffle=False,
    )

    X_train, X_test, y_train, y_test = train_test_split(X, y, stratify=y, random_state=42)
    return X_train, X_test, y_train, y_test 

def train_model():
    
    X_train, X_test, y_train, y_test = create_dataset()

    feature_names = [f"feature {i}" for i in range(X_train.shape[1])]
    forest = RandomForestClassifier(random_state=0)
    forest.fit(X_train, y_train)

    return forest, feature_names, X_test, y_test


def plot_mean_decrease(clf, feature_names):
    importances = clf.feature_importances_
    std = np.std([tree.feature_importances_ for tree in clf.estimators_], axis=0)

    forest_importances = pd.Series(importances, index=feature_names)

    fig, ax = plt.subplots()
    forest_importances.plot.bar(yerr=std, ax=ax)
    ax.set_title("Feature importances using MDI")
    ax.set_ylabel("Mean decrease in impurity")
    fig.tight_layout()

    return fig

def plot_feature_perm(clf, feature_names, X_test, y_test):
    result = permutation_importance(
        clf, X_test, y_test, n_repeats=10, random_state=42, n_jobs=2
    )
    forest_importances = pd.Series(result.importances_mean, index=feature_names)
    
    fig, ax = plt.subplots()
    forest_importances.plot.bar(yerr=result.importances_std, ax=ax)
    ax.set_title("Feature importances using permutation on full model")
    ax.set_ylabel("Mean accuracy decrease")
    fig.tight_layout()

    return fig

    

title = "Feature importances with a forest of trees 🌳"
description = """This example shows the use of a forest of trees to evaluate the importance of features on an artificial classification task. 
                The blue bars are the feature importances of the forest, along with their inter-trees variability represented by the error bars.
              """
            
with gr.Blocks() as demo:
    gr.Markdown(f"## {title}")
    gr.Markdown(description)

    # with gr.Column():
    clf, feature_names, X_test, y_test  = train_model()
    
    with gr.Row():
        plot = gr.Plot(plot_mean_decrease(clf, feature_names))
        plot2 = gr.Plot(plot_feature_perm(clf, feature_names, X_test, y_test))
            
            # input_data = gr.Dropdown(choices=feature_names, label="Feature", value="body-mass index")
            # coef = gr.Textbox(label="Coefficients")
            # mse = gr.Textbox(label="Mean squared error (MSE)")
            # r2 = gr.Textbox(label="R2 score")

    # input_data.change(fn=train_model, inputs=[input_data], outputs=[plot, coef, mse, r2], queue=False)

    
demo.launch(enable_queue=True)