|
import gradio as gr |
|
import numpy as np |
|
from sklearn.ensemble import RandomForestRegressor |
|
from sklearn.model_selection import train_test_split |
|
from sklearn.multioutput import MultiOutputRegressor |
|
import matplotlib |
|
matplotlib.use("Agg") |
|
import matplotlib.pyplot as plt |
|
|
|
def compare(max_depth,n_estimators): |
|
rng = np.random.RandomState(1) |
|
X = np.sort(200 * rng.rand(600, 1) - 100, axis=0) |
|
y = np.array([np.pi * np.sin(X).ravel(), np.pi * np.cos(X).ravel()]).T |
|
y += 0.5 - rng.rand(*y.shape) |
|
|
|
X_train, X_test, y_train, y_test = train_test_split( |
|
X, y, train_size=400, test_size=200, random_state=4 |
|
) |
|
|
|
regr_multirf = MultiOutputRegressor( |
|
RandomForestRegressor(n_estimators=n_estimators, max_depth=max_depth, random_state=0) |
|
) |
|
regr_multirf.fit(X_train, y_train) |
|
|
|
regr_rf = RandomForestRegressor(n_estimators=n_estimators, max_depth=max_depth, random_state=2) |
|
regr_rf.fit(X_train, y_train) |
|
|
|
|
|
y_multirf = regr_multirf.predict(X_test) |
|
y_rf = regr_rf.predict(X_test) |
|
|
|
|
|
fig, ax = plt.subplots() |
|
s = 50 |
|
a = 0.4 |
|
ax.scatter( |
|
y_test[:, 0], |
|
y_test[:, 1], |
|
edgecolor="k", |
|
c="navy", |
|
s=s, |
|
marker="s", |
|
alpha=a, |
|
label="Data", |
|
) |
|
ax.scatter( |
|
y_multirf[:, 0], |
|
y_multirf[:, 1], |
|
edgecolor="k", |
|
c="cornflowerblue", |
|
s=s, |
|
alpha=a, |
|
label="Multi RF score=%.2f" % regr_multirf.score(X_test, y_test), |
|
) |
|
ax.scatter( |
|
y_rf[:, 0], |
|
y_rf[:, 1], |
|
edgecolor="k", |
|
c="c", |
|
s=s, |
|
marker="^", |
|
alpha=a, |
|
label="RF score=%.2f" % regr_rf.score(X_test, y_test), |
|
) |
|
ax.set_xlim([-6, 6]) |
|
ax.set_ylim([-6, 6]) |
|
ax.set_xlabel("target 1") |
|
ax.set_ylabel("target 2") |
|
ax.set_title("Comparing random forests and the multi-output meta estimator") |
|
ax.legend() |
|
return fig |
|
|
|
title = "Comparing random forests and the multi-output meta estimator" |
|
with gr.Blocks(title=title) as demo: |
|
gr.Markdown(f"## {title}") |
|
gr.Markdown(""" |
|
This app demonstrates comparison of random forest with multi-output meta estimator for multi-output regression. |
|
A random forest regressor is trained on randomly generated data which is used as baseline and compared with multi-output meta estimator trained on the same dataset. |
|
The predicted outputs from each model are visualized in the plot together with the actual data. |
|
The maximum depth and number of estimator of the random forest can be adjusted and the effect can be seen in the resulting plot. |
|
This app is developed based on [scikit-learn example](https://scikit-learn.org/stable/auto_examples/ensemble/plot_random_forest_regression_multioutput.html#sphx-glr-auto-examples-ensemble-plot-random-forest-regression-multioutput-py) |
|
""") |
|
|
|
max_depth = gr.Slider(minimum=10, maximum=50, step=1, label = "Maximum Depth") |
|
n_estimators = gr.Slider(minimum=50, maximum=300, step=1, label = "Number of Estimators") |
|
|
|
plot = gr.Plot(label=title) |
|
n_estimators.change(fn=compare, inputs=[max_depth,n_estimators], outputs=[plot]) |
|
max_depth.change(fn=compare, inputs=[max_depth,n_estimators], outputs=[plot]) |
|
|
|
demo.launch() |
|
|
|
|
