app.py

import gradio as gr
import numpy as np
import matplotlib.pyplot as plt

from sklearn.ensemble import GradientBoostingClassifier
from sklearn.model_selection import KFold
from sklearn.model_selection import train_test_split
from sklearn.metrics import log_loss

from scipy.special import expit

theme = gr.themes.Monochrome(
    primary_hue="indigo",
    secondary_hue="blue",
    neutral_hue="slate",
)
model_card = f"""
## Description

The **Out-of-bag (OOB)** method is a useful technique for estimating the optimal number of boosting iterations.
This method is similar to cross-validation, but it does not require repeated model fitting and can be computed on-the-fly. 
**OOB** estimates are only applicable to Stochastic Gradient Boosting (i.e., subsample < 1.0). They are calculated from the improvement in loss based on examples not included in the bootstrap sample (i.e., out-of-bag examples). 
The **OOB** estimator provides a conservative estimate of the true test loss, but is still a reasonable approximation for a small number of trees. 
This demo shows the negative OOB improvements' cumulative sum as a function of the boosting iteration.

## Dataset

Simulation data
"""

def do_train(n_samples, n_splits, random_seed):
    # Generate data (adapted from G. Ridgeway's gbm example)
    random_state = np.random.RandomState(random_seed)
    x1 = random_state.uniform(size=n_samples)
    x2 = random_state.uniform(size=n_samples)
    x3 = random_state.randint(0, 4, size=n_samples)

    p = expit(np.sin(3 * x1) - 4 * x2 + x3)
    y = random_state.binomial(1, p, size=n_samples)

    X = np.c_[x1, x2, x3]

    X = X.astype(np.float32)
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5, random_state=random_seed)

    # Fit classifier with out-of-bag estimates
    params = {
        "n_estimators": 1200,
        "max_depth": 3,
        "subsample": 0.5,
        "learning_rate": 0.01,
        "min_samples_leaf": 1,
        "random_state": random_seed,
    }
    clf = GradientBoostingClassifier(**params)

    clf.fit(X_train, y_train)
    train_acc = clf.score(X_train, y_train)
    test_acc = clf.score(X_test, y_test)
    text = f"Train set accuracy: {train_acc*100:.2f}%. Test set accuracy: {test_acc*100:.2f}%"
    n_estimators = params["n_estimators"]
    x = np.arange(n_estimators) + 1

    def heldout_score(clf, X_test, y_test):
        """compute deviance scores on ``X_test`` and ``y_test``."""
        score = np.zeros((n_estimators,), dtype=np.float64)
        for i, y_proba in enumerate(clf.staged_predict_proba(X_test)):
            score[i] = 2 * log_loss(y_test, y_proba[:, 1])
        return score

    def cv_estimate(n_splits):
        cv = KFold(n_splits=n_splits)
        cv_clf = GradientBoostingClassifier(**params)
        val_scores = np.zeros((n_estimators,), dtype=np.float64)
        for train, test in cv.split(X_train, y_train):
            cv_clf.fit(X_train[train], y_train[train])
            val_scores += heldout_score(cv_clf, X_train[test], y_train[test])
        val_scores /= n_splits
        return val_scores

    # Estimate best n_splits using cross-validation
    cv_score = cv_estimate(n_splits)

    # Compute best n_splits for test data
    test_score = heldout_score(clf, X_test, y_test)

    # negative cumulative sum of oob improvements
    cumsum = -np.cumsum(clf.oob_improvement_)

    # min loss according to OOB
    oob_best_iter = x[np.argmin(cumsum)]

    # min loss according to test (normalize such that first loss is 0)
    test_score -= test_score[0]
    test_best_iter = x[np.argmin(test_score)]

    # min loss according to cv (normalize such that first loss is 0)
    cv_score -= cv_score[0]
    cv_best_iter = x[np.argmin(cv_score)]

    # color brew for the three curves
    oob_color = list(map(lambda x: x / 256.0, (190, 174, 212)))
    test_color = list(map(lambda x: x / 256.0, (127, 201, 127)))
    cv_color = list(map(lambda x: x / 256.0, (253, 192, 134)))

    # line type for the three curves
    oob_line = "dashed"
    test_line = "solid"
    cv_line = "dashdot"

    # plot curves and vertical lines for best iterations
    fig, ax = plt.subplots(figsize=(8, 6))
    ax.plot(x, cumsum, label="OOB loss", color=oob_color, linestyle=oob_line)
    ax.plot(x, test_score, label="Test loss", color=test_color, linestyle=test_line)
    ax.plot(x, cv_score, label="CV loss", color=cv_color, linestyle=cv_line)
    ax.axvline(x=oob_best_iter, color=oob_color, linestyle=oob_line)
    ax.axvline(x=test_best_iter, color=test_color, linestyle=test_line)
    ax.axvline(x=cv_best_iter, color=cv_color, linestyle=cv_line)

    # add three vertical lines to xticks
    xticks = plt.xticks()
    xticks_pos = np.array(
        xticks[0].tolist() + [oob_best_iter, cv_best_iter, test_best_iter]
    )
    xticks_label = np.array(list(map(lambda t: int(t), xticks[0])) + ["OOB", "CV", "Test"])
    ind = np.argsort(xticks_pos)
    xticks_pos = xticks_pos[ind]
    xticks_label = xticks_label[ind]
    ax.set_xticks(xticks_pos, xticks_label, rotation=90)

    ax.legend(loc="upper center")
    ax.set_ylabel("normalized loss")
    ax.set_xlabel("number of iterations")
    return fig, text


with gr.Blocks(theme=theme) as demo:
    gr.Markdown('''
            <div>
            <h1 style='text-align: center'>Gradient Boosting Out-of-Bag estimates</h1>
            </div>
        ''')
    gr.Markdown(model_card)
    gr.Markdown("Author: <a href=\"https://huggingface.co/vumichien\">Vu Minh Chien</a>. Based on the example from <a href=\"https://scikit-learn.org/stable/auto_examples/ensemble/plot_gradient_boosting_oob.html#sphx-glr-auto-examples-ensemble-plot-gradient-boosting-oob-py\">scikit-learn</a>")
    n_samples = gr.Slider(minimum=500, maximum=5000, step=500, value=500, label="Number of samples")
    n_splits = gr.Slider(minimum=2, maximum=10, step=1, value=3, label="Number of cross validation folds")
    random_seed = gr.Slider(minimum=0, maximum=2000, step=1, value=0, label="Random seed")

    with gr.Row():
        with gr.Column():
            plot = gr.Plot()
        with gr.Column():
            result = gr.Textbox(label="Resusts")
        
    n_samples.change(fn=do_train, inputs=[n_samples, n_splits, random_seed], outputs=[plot, result])
    n_splits.change(fn=do_train, inputs=[n_samples, n_splits, random_seed], outputs=[plot, result])
    random_seed.change(fn=do_train, inputs=[n_samples, n_splits, random_seed], outputs=[plot, result])

demo.launch()