|
import numpy as np |
|
import matplotlib.pyplot as plt |
|
from matplotlib.colors import ListedColormap |
|
plt.rcParams['figure.dpi'] = 100 |
|
|
|
from sklearn.ensemble import AdaBoostClassifier |
|
from sklearn.tree import DecisionTreeClassifier |
|
from sklearn.datasets import make_gaussian_quantiles |
|
from sklearn.inspection import DecisionBoundaryDisplay |
|
|
|
import gradio as gr |
|
|
|
|
|
C1, C2 = '#ff0000', '#0000ff' |
|
CMAP = ListedColormap([C1, C2]) |
|
GRANULARITY = 0.05 |
|
|
|
def get_decision_surface(X, y, model): |
|
x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1 |
|
y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1 |
|
xrange = np.arange(x_min, x_max, GRANULARITY) |
|
yrange = np.arange(y_min, y_max, GRANULARITY) |
|
xx, yy = np.meshgrid(xrange, yrange) |
|
|
|
Z = model.predict(np.c_[xx.ravel(), yy.ravel()]) |
|
Z = Z.reshape(xx.shape) |
|
|
|
return xx, yy, Z |
|
|
|
def create_plot(x1, y1, x2, y2, cov1, cov2, n1, n2, max_depth, n_estimators): |
|
|
|
X1, y1 = make_gaussian_quantiles( |
|
mean=(x1, y1), cov=cov1, n_samples=n1, n_features=2, n_classes=2 |
|
) |
|
X2, y2 = make_gaussian_quantiles( |
|
mean=(x2, y2), cov=cov2, n_samples=n2, n_features=2, n_classes=2 |
|
) |
|
X = np.concatenate((X1, X2)) |
|
y = np.concatenate((y1, -y2 + 1)) |
|
|
|
clf = AdaBoostClassifier(DecisionTreeClassifier(max_depth=max_depth), algorithm="SAMME", n_estimators=n_estimators) |
|
|
|
clf.fit(X, y) |
|
|
|
fig = plt.figure(figsize=(4.5, 6.9)) |
|
ax = fig.add_subplot(211) |
|
|
|
xx, yy, Z = get_decision_surface(X, y, clf) |
|
ax.contourf(xx, yy, Z, cmap=CMAP, alpha=0.4) |
|
|
|
X1, y1 = X[y==0], y[y==0] |
|
X2, y2 = X[y==1], y[y==1] |
|
|
|
ax.scatter(X1[:, 0], X1[:, 1], c=C1, edgecolor='k', s=20, label='Class A') |
|
ax.scatter(X2[:, 0], X2[:, 1], c=C2, edgecolor='k', s=20, label='Class B') |
|
|
|
ax.legend() |
|
ax.set_title(f'AdaBoostClassifier Decision Surface') |
|
|
|
scores = clf.decision_function(X) |
|
|
|
ax = fig.add_subplot(212) |
|
ax.hist(scores[y==0], bins=100, range=(scores.min(), scores.max()), facecolor=C1, label="Class A", alpha=0.5, edgecolor="k") |
|
ax.hist(scores[y==1], bins=100, range=(scores.min(), scores.max()), facecolor=C2, label="Class B", alpha=0.5, edgecolor="k") |
|
|
|
ax.set_xlabel('Score'); ax.set_ylabel('Frequency') |
|
ax.legend() |
|
ax.set_title('Decision Scores') |
|
fig.set_tight_layout(True) |
|
|
|
return fig |
|
|
|
info = ''' |
|
This example fits an [AdaBoost classifier](https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.AdaBoostClassifier.html#sklearn.ensemble.AdaBoostClassifier) on two non-linearly separable classes. The samples are generated using two [Gaussian quantiles](https://scikit-learn.org/stable/modules/generated/sklearn.datasets.make_gaussian_quantiles.html#sklearn.datasets.make_gaussian_quantiles) of configurable mean and covariance (see the sliders below). |
|
|
|
For the first generated Gaussian, the inner half quantile is assigned to Class A and the outer half quantile is assigned to class B. For the second generated quantile, the opposite assignment happens (inner = Class B, outer = Class A). |
|
|
|
A histogram of the decision scores of the AdaBoostClassifer is shown below. Values closer to -1 mean a high confidence that the sample belongs to Class A, and values closer to 1 mean a high confidence that the sample belongs to Class B. |
|
|
|
Use the controls below to change the Gaussian distribution parameters, number of generated samples in each Gaussian distribution, and the classifier's max_depth and n_estimators. |
|
|
|
Created by [@huabdul](https://huggingface.co/huabdul) based on [Scikit-learn docs](https://scikit-learn.org/stable/auto_examples/ensemble/plot_adaboost_twoclass.html). |
|
''' |
|
with gr.Blocks(analytics_enabled=False) as demo: |
|
with gr.Row(): |
|
with gr.Column(scale=2): |
|
gr.Markdown(info) |
|
with gr.Row(): |
|
with gr.Column(min_width=100): |
|
s_x1 = gr.Slider(-10, 10, value=0, step=0.1, label='Mean x1') |
|
with gr.Column(min_width=100): |
|
s_y1 = gr.Slider(-10, 10, value=0, step=0.1, label='Mean y1') |
|
with gr.Row(): |
|
with gr.Column(min_width=100): |
|
s_x2 = gr.Slider(-10, 10, value=2, step=0.1, label='Mean x2') |
|
with gr.Column(min_width=100): |
|
s_y2 = gr.Slider(-10, 10, value=2, step=0.1, label='Mean y2') |
|
|
|
with gr.Row(): |
|
with gr.Column(min_width=100): |
|
s_cov1 = gr.Slider(0.01, 5, value=1, step=0.01, label='Covariance 1') |
|
with gr.Column(min_width=100): |
|
s_cov2 = gr.Slider(0.01, 5, value=2, step=0.01, label='Covariance 2') |
|
|
|
with gr.Row(): |
|
with gr.Column(min_width=100): |
|
s_n_samples1 = gr.Slider(1, 1000, value=200, step=1, label='n_samples 1') |
|
with gr.Column(min_width=100): |
|
s_n_samples2 = gr.Slider(1, 1000, value=300, step=1, label='n_samples 2') |
|
|
|
with gr.Row(): |
|
with gr.Column(min_width=100): |
|
s_max_depth = gr.Slider(1, 50, value=1, step=1, label='AdaBoostClassifier max_depth') |
|
with gr.Column(min_width=100): |
|
s_n_estimators = gr.Slider(1, 500, value=300, step=1, label='AdaBoostClassifier n_estimators') |
|
|
|
btn = gr.Button('Submit') |
|
with gr.Column(scale=1.5): |
|
plot = gr.Plot(show_label=False) |
|
|
|
btn.click(create_plot, inputs=[s_x1, s_y1, s_x2, s_y2, s_cov1, s_cov2, s_n_samples1, s_n_samples2, s_max_depth, s_n_estimators], outputs=[plot]) |
|
demo.load(create_plot, inputs=[s_x1, s_y1, s_x2, s_y2, s_cov1, s_cov2, s_n_samples1, s_n_samples2, s_max_depth, s_n_estimators], outputs=[plot]) |
|
|
|
demo.launch() |
|
|
