|
import gradio as gr |
|
import numpy as np |
|
from matplotlib import pyplot as plt |
|
|
|
from sklearn import linear_model, datasets |
|
|
|
|
|
theme = gr.themes.Monochrome( |
|
primary_hue="indigo", |
|
secondary_hue="blue", |
|
neutral_hue="slate", |
|
) |
|
model_card = f""" |
|
## Description |
|
|
|
**Random sample consensus (RANSAC)** is a method to estimate a mathematical model from a set of observed data that may have some wrong information. |
|
The number of times it tries affects how likely it is to get a good answer. **RANSAC** is commonly used in photogrammetry to solve problems with linear or non-linear regression. |
|
It works by separating the input data into two groups: inliers (which may have some noise) and outliers (which are wrong data). It estimates the model only using the inliers. |
|
In this demo, a simulation regression dataset with noise is created, and then compare the results of fitting data in **Linear model** and **RANSAC**. |
|
You can play around with different ``number of samples`` and ``number of outliers`` to see the effect |
|
|
|
## Dataset |
|
|
|
Simulation dataset |
|
""" |
|
|
|
|
|
def do_train(n_samples, n_outliers): |
|
|
|
X, y, coef = datasets.make_regression( |
|
n_samples=n_samples, |
|
n_features=1, |
|
n_informative=1, |
|
noise=10, |
|
coef=True, |
|
random_state=0, |
|
) |
|
|
|
|
|
np.random.seed(0) |
|
X[:n_outliers] = 3 + 0.5 * np.random.normal(size=(n_outliers, 1)) |
|
y[:n_outliers] = -3 + 10 * np.random.normal(size=n_outliers) |
|
|
|
|
|
lr = linear_model.LinearRegression() |
|
lr.fit(X, y) |
|
|
|
|
|
ransac = linear_model.RANSACRegressor() |
|
ransac.fit(X, y) |
|
inlier_mask = ransac.inlier_mask_ |
|
outlier_mask = np.logical_not(inlier_mask) |
|
|
|
|
|
line_X = np.arange(X.min(), X.max())[:, np.newaxis] |
|
line_y = lr.predict(line_X) |
|
line_y_ransac = ransac.predict(line_X) |
|
|
|
text = f"True coefficients: {coef:.4f}.\nLinear regression coefficients: {lr.coef_[0]:.4f}.\nRANSAC coefficients: {ransac.estimator_.coef_[0]:.4f}." |
|
|
|
fig, axes = plt.subplots() |
|
|
|
axes.scatter( |
|
X[inlier_mask], y[inlier_mask], color="yellowgreen", marker=".", label="Inliers" |
|
) |
|
axes.scatter( |
|
X[outlier_mask], y[outlier_mask], color="gold", marker=".", label="Outliers" |
|
) |
|
axes.plot(line_X, line_y, color="navy", linewidth=2, label="Linear regressor") |
|
axes.plot( |
|
line_X, |
|
line_y_ransac, |
|
color="cornflowerblue", |
|
linewidth=2, |
|
label="RANSAC regressor", |
|
) |
|
axes.legend(loc="lower right") |
|
axes.set_xlabel("Input") |
|
axes.set_ylabel("Response") |
|
|
|
return fig, text |
|
|
|
|
|
|
|
with gr.Blocks(theme=theme) as demo: |
|
gr.Markdown(''' |
|
<div> |
|
<h1 style='text-align: center'>Robust linear model estimation using RANSAC</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/linear_model/plot_ransac.html#sphx-glr-auto-examples-linear-model-plot-ransac-py\">scikit-learn</a>") |
|
n_samples = gr.Slider(minimum=500, maximum=5000, step=500, value=500, label="Number of samples") |
|
n_outliers = gr.Slider(minimum=25, maximum=250, step=25, value=25, label="Number of outliers") |
|
with gr.Row(): |
|
with gr.Column(): |
|
plot = gr.Plot(label="Compare Linear regressor and RANSAC") |
|
with gr.Column(): |
|
results = gr.Textbox(label="Results") |
|
|
|
n_samples.change(fn=do_train, inputs=[n_samples, n_outliers], outputs=[plot, results]) |
|
n_outliers.change(fn=do_train, inputs=[n_samples, n_outliers], outputs=[plot, results]) |
|
|
|
demo.launch() |