|
import gradio as gr |
|
import time |
|
import numpy as np |
|
import matplotlib.pyplot as plt |
|
from sklearn.datasets import load_iris |
|
from sklearn.model_selection import train_test_split |
|
from sklearn.feature_selection import SelectKBest, f_classif |
|
from sklearn.pipeline import make_pipeline |
|
from sklearn.preprocessing import MinMaxScaler |
|
from sklearn.svm import LinearSVC |
|
|
|
theme = gr.themes.Monochrome( |
|
primary_hue="indigo", |
|
secondary_hue="blue", |
|
neutral_hue="slate", |
|
) |
|
model_card = f""" |
|
## Description |
|
|
|
**Univariate feature selection** can be used to improve classification accuracy on a noisy dataset. |
|
In **univariate feature selection**, each feature is evaluated independently, and a statistical test is used to determine its strength of association with the target variable. |
|
The most important features are then selected based on their statistical significance, typically using a threshold p-value or a pre-defined number of top features to select. |
|
|
|
In this demo, some noisy (non informative) features are added to the iris dataset then use **Support vector machine (SVM)** to classify the Iris dataset both before and after applying univariate feature selection. |
|
The results of the feature selection are presented through p-values and weights of SVMs, which are plotted for comparison. |
|
The objective of this demo is to evaluate the accuracy of the models and assess the impact of univariate feature selection on the model weights. |
|
You can play around with different ``number of top features`` and ``random seed``. |
|
|
|
## Dataset |
|
|
|
Iris dataset |
|
""" |
|
|
|
X, y = load_iris(return_X_y=True) |
|
|
|
|
|
E = np.random.RandomState(42).uniform(0, 0.1, size=(X.shape[0], 20)) |
|
|
|
|
|
X = np.hstack((X, E)) |
|
|
|
|
|
def do_train(k_features, random_state): |
|
|
|
X_train, X_test, y_train, y_test = train_test_split(X, y, stratify=y, random_state=random_state) |
|
selector = SelectKBest(f_classif, k=k_features) |
|
selector.fit(X_train, y_train) |
|
scores = -np.log10(selector.pvalues_) |
|
scores /= scores.max() |
|
|
|
|
|
fig1, axes1 = plt.subplots() |
|
X_indices = np.arange(X.shape[-1]) |
|
axes1.bar(X_indices - 0.05, scores, width=0.2) |
|
axes1.set_title("Feature univariate score") |
|
axes1.set_xlabel("Feature number") |
|
axes1.set_ylabel(r"Univariate score ($-Log(p_{value})$)") |
|
|
|
clf = make_pipeline(MinMaxScaler(), LinearSVC()) |
|
clf.fit(X_train, y_train) |
|
|
|
svm_weights = np.abs(clf[-1].coef_).sum(axis=0) |
|
svm_weights /= svm_weights.sum() |
|
|
|
clf_selected = make_pipeline(SelectKBest(f_classif, k=k_features), MinMaxScaler(), LinearSVC()) |
|
clf_selected.fit(X_train, y_train) |
|
|
|
svm_weights_selected = np.abs(clf_selected[-1].coef_).sum(axis=0) |
|
svm_weights_selected /= svm_weights_selected.sum() |
|
|
|
fig2, axes2 = plt.subplots() |
|
axes2.bar( |
|
X_indices - 0.45, scores, width=0.2, label=r"Univariate score ($-Log(p_{value})$)" |
|
) |
|
|
|
axes2.bar(X_indices - 0.25, svm_weights, width=0.2, label="SVM weight") |
|
|
|
axes2.bar( |
|
X_indices[selector.get_support()] - 0.05, |
|
svm_weights_selected, |
|
width=0.2, |
|
label="SVM weights after selection", |
|
) |
|
|
|
axes2.set_title("Comparing feature selection") |
|
axes2.set_xlabel("Feature number") |
|
axes2.set_yticks(()) |
|
axes2.axis("tight") |
|
axes2.legend(loc="upper right") |
|
|
|
text = f"Classification accuracy without selecting features: {clf.score(X_test, y_test)*100:.2f}%. Classification accuracy after univariate feature selection: {clf_selected.score(X_test, y_test)*100:.2f}%" |
|
|
|
return fig1, fig2, text |
|
|
|
|
|
|
|
with gr.Blocks(theme=theme) as demo: |
|
gr.Markdown(''' |
|
<div> |
|
<h1 style='text-align: center'>Univariate Feature Selection</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/feature_selection/plot_feature_selection.html#sphx-glr-auto-examples-feature-selection-plot-feature-selection-py\">scikit-learn</a>") |
|
k_features = gr.Slider(minimum=2, maximum=10, step=1, value=2, label="Number of top features to select") |
|
random_state = gr.Slider(minimum=0, maximum=2000, step=1, value=0, label="Random seed") |
|
with gr.Row(): |
|
with gr.Column(): |
|
plot_1 = gr.Plot(label="Univariate score") |
|
with gr.Column(): |
|
plot_2 = gr.Plot(label="Comparing feature selection") |
|
with gr.Row(): |
|
resutls = gr.Textbox(label="Results") |
|
|
|
k_features.change(fn=do_train, inputs=[k_features, random_state], outputs=[plot_1, plot_2, resutls]) |
|
random_state.change(fn=do_train, inputs=[k_features, random_state], outputs=[plot_1, plot_2, resutls]) |
|
|
|
demo.launch() |