app.py

import gradio as gr
from sklearn.datasets import make_blobs
from sklearn.cluster import KMeans
from sklearn.metrics import silhouette_samples, silhouette_score

import matplotlib.pyplot as plt
import matplotlib.cm as cm
import numpy as np

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


def main(
    n_clusters: int = 2,
    n_samples: int = 500,
    n_features: int = 2,
    n_centers: int = 4,
    cluster_std: int = 1,
):
    # Generating the sample data from make_blobs
    # This particular setting has one distinct cluster and 3 clusters placed close
    # together.
    X, y = make_blobs(
        n_samples=n_samples,
        n_features=n_features,
        centers=n_centers,
        cluster_std=cluster_std,
        center_box=(-10.0, 10.0),
        shuffle=True,
        random_state=1,
    )
    # For reproducibility
    n_clusters = int(n_clusters)
    fig1, ax1 = plt.subplots()
    fig1.set_size_inches(9, 4)
    fig2, ax2 = plt.subplots()
    fig2.set_size_inches(9, 4)
    # The 1st subplot is the silhouette plot
    # The silhouette coefficient can range from -1, 1 but in this example all
    # lie within [-0.1, 1]
    ax1.set_xlim([-0.1, 1])
    # The (n_clusters+1)*10 is for inserting blank space between silhouette
    # plots of individual clusters, to demarcate them clearly.
    ax1.set_ylim([0, len(X) + (n_clusters + 1) * 10])

    # Initialize the clusterer with n_clusters value and a random generator
    # seed of 10 for reproducibility.
    clusterer = KMeans(n_clusters=n_clusters, n_init="auto", random_state=10)
    cluster_labels = clusterer.fit_predict(X)

    # The silhouette_score gives the average value for all the samples.
    # This gives a perspective into the density and separation of the formed
    # clusters
    silhouette_avg = silhouette_score(X, cluster_labels)
    print(
        "For n_clusters =",
        n_clusters,
        "The average silhouette_score is :",
        silhouette_avg,
    )

    # Compute the silhouette scores for each sample
    sample_silhouette_values = silhouette_samples(X, cluster_labels)

    y_lower = 10
    for i in range(n_clusters):
        # Aggregate the silhouette scores for samples belonging to
        # cluster i, and sort them
        ith_cluster_silhouette_values = sample_silhouette_values[cluster_labels == i]

        ith_cluster_silhouette_values.sort()

        size_cluster_i = ith_cluster_silhouette_values.shape[0]
        y_upper = y_lower + size_cluster_i

        color = cm.nipy_spectral(float(i) / n_clusters)
        ax1.fill_betweenx(
            np.arange(y_lower, y_upper),
            0,
            ith_cluster_silhouette_values,
            facecolor=color,
            edgecolor=color,
            alpha=0.7,
        )

        # Label the silhouette plots with their cluster numbers at the middle
        ax1.text(-0.05, y_lower + 0.5 * size_cluster_i, str(i))

        # Compute the new y_lower for next plot
        y_lower = y_upper + 10  # 10 for the 0 samples

    ax1.set_title("The silhouette plot for the various clusters.")
    ax1.set_xlabel("The silhouette coefficient values")
    ax1.set_ylabel("Cluster label")

    # The vertical line for average silhouette score of all the values
    ax1.axvline(x=silhouette_avg, color="red", linestyle="--")

    ax1.set_yticks([])  # Clear the yaxis labels / ticks
    ax1.set_xticks([-0.1, 0, 0.2, 0.4, 0.6, 0.8, 1])

    # 2nd Plot showing the actual clusters formed
    colors = cm.nipy_spectral(cluster_labels.astype(float) / n_clusters)
    ax2.scatter(
        X[:, 0], X[:, 1], marker=".", s=30, lw=0, alpha=0.7, c=colors, edgecolor="k"
    )

    # Labeling the clusters
    centers = clusterer.cluster_centers_
    # Draw white circles at cluster centers
    ax2.scatter(
        centers[:, 0],
        centers[:, 1],
        marker="o",
        c="white",
        alpha=1,
        s=200,
        edgecolor="k",
    )

    for i, c in enumerate(centers):
        ax2.scatter(c[0], c[1], marker="$%d$" % i, alpha=1, s=50, edgecolor="k")

    ax2.set_title("The visualization of the clustered data.")
    ax2.set_xlabel("Feature space for the 1st feature")
    ax2.set_ylabel("Feature space for the 2nd feature")

    return fig1, fig2


title = """# Selecting the number of clusters with silhouette analysis on KMeans clustering 📊"""
description = """
            This app demonstrates a silhouette analysis for KMeans clustering on sample data.
            
            The purpose of a clustering algorithm is to find groups of similar data points. The purpose of a silhouette analysis is to determine the optimal number of clusters for a given clustering algorithm. The silhouette analysis can be used on any clustering algorithm, but it is most commonly used with KMeans clustering.
            """

with gr.Blocks(theme=theme) as demo:
    gr.Markdown(title)
    gr.Markdown(description)
    gr.Markdown("""### Dataset Generation Parameters""")
    with gr.Row():
        with gr.Column():
            n_samples = gr.inputs.Slider(
                minimum=100,
                maximum=1000,
                default=500,
                step=50,
                label="Number of Samples",
            )
            n_features = gr.inputs.Slider(
                minimum=2, maximum=5, default=2, step=1, label="Number of Features"
            )
            n_centers = gr.inputs.Slider(
                minimum=2, maximum=5, default=4, step=1, label="Number of Centers"
            )
            cluster_std = gr.inputs.Slider(
                minimum=0.0, maximum=1.0, default=1, step=0.1, label="Cluster deviation"
            )
            n_clusters = gr.inputs.Slider(
                minimum=2, maximum=6, default=2, step=1, label="Number of Clusters"
            )
            run_button = gr.Button("Analyse Silhouette")
    with gr.Row():
        plot_silhouette = gr.Plot()
        plot_clusters = gr.Plot()
    outputs = [plot_silhouette, plot_clusters]
    inputs = [n_clusters, n_samples, n_features, n_centers, cluster_std]
    run_button.click(fn=main, inputs=inputs, outputs=outputs)


demo.launch()