add initial version for the kmeans assumption dashboard

README.md

@@ -9,5 +9,6 @@ app_file: app.py
 pinned: false
 license: mit
 ---
+This dashboard is a live demonstration of the sklearn document at https://scikit-learn.org/stable/auto_examples/cluster/plot_kmeans_assumptions.html#sphx-glr-auto-examples-cluster-plot-kmeans-assumptions-py
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,165 @@
+"""This dashboard is a live demonstration of the sklearn document at
+https://scikit-learn.org/stable/auto_examples/cluster/plot_kmeans_assumptions.html#sphx-glr-auto-examples-cluster-plot-kmeans-assumptions-py
+"""
+import numpy as np
+import typing as tp
+import gradio as gr
+from sklearn.datasets import make_blobs
+from sklearn.cluster import KMeans
+import matplotlib.pyplot as plt
+
+title = "Demonstration of k-means assumptions"
+random_state = 170
+transformation = [[0.60834549, -0.63667341], [-0.40887718, 0.85253229]]
+
+# Defines 4 Apps for each demo senario
+class App:
+    name: tp.ClassVar[str]
+    description: tp.ClassVar[str]
+
+    def make_data(self, n_samples: int) -> tp.Tuple[np.ndarray, np.ndarray]:
+        raise NotImplementedError()
+
+    def kmeans_predict(self, n_cluster: int, X: np.ndarray) -> np.ndarray:
+        raise NotImplementedError()
+
+class MixGaussianBlobs(App):
+    name = "Mixture of Gaussian Blobs"
+    description = (
+        "In a real setting there is no uniquely defined true number of clusters. "
+        "An appropriate number of clusters has to be decided from data-based criteria"
+        " and knowledge of the intended goal."
+    )
+
+    def make_data(self, n_samples):
+        return make_blobs(n_samples=n_samples, random_state=random_state)
+
+    def kmeans_predict(self, n_clusters, X):
+        return KMeans(
+            n_clusters=n_clusters, n_init="auto", random_state=random_state
+        ).fit_predict(X)
+
+
+class AnisoDistBlobs(MixGaussianBlobs):
+    name = "Anisotropically Distributed Blobs"
+    description = (
+        "k-means consists of minimizing sample’s euclidean distances to the centroid of the"
+        " cluster they are assigned to. As a consequence, k-means is more appropriate for "
+        "clusters that are isotropic and normally distributed (i.e. spherical gaussians)"
+    )
+
+    def make_data(self, n_samples):
+        X, y = super().make_data(n_samples=n_samples)
+        X = np.dot(X, transformation)
+        return X, y
+
+
+class UnequalVariance(MixGaussianBlobs):
+    name = "Unequal Variance"
+    description = (
+        "k-means is equivalent to taking the maximum likelihood estimator for a 'mixture' "
+        "of k gaussian distributions with the same variances but with possibly different "
+        " means."
+    )
+
+    def make_data(self, n_samples):
+        return make_blobs(
+            n_samples=n_samples, cluster_std=[1.0, 2.5, 0.5], random_state=random_state
+        )
+
+
+class UnevenlySizedBlobs(MixGaussianBlobs):
+    name = "Unevenly Sized Blobs"
+    description = (
+        "There is no theoretical result about k-means that states that it requires similar"
+        " cluster sizes to perform well, yet minimizing euclidean distances does mean that"
+        " the more sparse and high-dimensional the problem is, the higher is the need to run "
+        "the algorithm with different centroid seeds to ensure a global minimal inertia."
+    )
+
+    def make_data(self, n_samples):
+        X, y = super().make_data(n_samples=n_samples)
+        X_filter = np.vstack(
+            (
+                X[y == 0][:500],
+                X[y == 1][:100],
+                X[y == 2][:10],
+            )
+        )
+        # print(len(X_filter[:, 0]))
+        # print(len(X_filter[:, 1]))
+        y_filter = [0] * 500 + [1] * 100 + [2] * 10
+        return X_filter, y_filter
+
+
+# Define instances of the apps
+_apps = [
+    MixGaussianBlobs(),
+    AnisoDistBlobs(),
+    UnequalVariance(),
+    UnevenlySizedBlobs(),
+]
+apps = {k.name: k for k in _apps}
+data_choices = [k.name for k in _apps]
+
+
+# Define the callback to the triggered when a button or a slider used by the user.
+def fn(data_choice, n_samples, n_clusters):
+    # Find the app and create sample data based on the user choice.
+    app = apps[data_choice]
+    X, y = app.make_data(n_samples)
+    fig_sample, ax_sample = plt.subplots()
+    ax_sample.set_title(app.name)
+    
+    # Execute the KMeans clustering.
+    y_pred = app.kmeans_predict(n_clusters, X)
+    ax_sample.scatter(X[:, 0], X[:, 1], c=y)
+    fig_pred, ax_pred = plt.subplots()
+    ax_pred.scatter(X[:, 0], X[:, 1], c=y_pred)
+    ax_pred.set_title(f"Unexpected KMeans Clusters (n_cluster={n_clusters})")
+
+    return f"## {app.description}", fig_sample, fig_pred
+
+
+# Define the dashboard layout and buttons
+with gr.Blocks(title=title) as demo:
+    gr.Markdown(f"# {title}")
+    gr.Markdown(
+        "This demo is based on "
+        "[sklearn document](https://scikit-learn.org/stable/auto_examples/cluster/plot_kmeans_assumptions.html#sphx-glr-auto-examples-cluster-plot-kmeans-assumptions-py)."
+        "It is meant to illustrate how K-Means can produce unexpected clusters in 4 different data sets"
+    )
+    with gr.Row():
+        data_choice = gr.Radio(
+            choices=data_choices,
+            value=data_choices[0],
+        )
+    with gr.Row():
+        n_samples = gr.Slider(
+            minimum=1500, maximum=3000, step=50, label="Number of Samples"
+        )
+        n_clusters = gr.Slider(minimum=2, maximum=8, step=1, label="Number of Clusters")
+    with gr.Accordion("Description"):
+        description = gr.Markdown(label="Description")
+    with gr.Row():
+        plot_sample = gr.Plot(label="Ground Truth Cluster")
+        plot_kmeans = gr.Plot(label="Unexpected KMeans Cluster")
+
+    data_choice.change(
+        fn=fn,
+        inputs=[data_choice, n_samples, n_clusters],
+        outputs=[description, plot_sample, plot_kmeans],
+    )
+    n_samples.change(
+        fn=fn,
+        inputs=[data_choice, n_samples, n_clusters],
+        outputs=[description, plot_sample, plot_kmeans],
+    )
+    n_clusters.change(
+        fn=fn,
+        inputs=[data_choice, n_samples, n_clusters],
+        outputs=[description, plot_sample, plot_kmeans],
+    )
+
+
+demo.launch()

requirements.txt

@@ -0,0 +1,2 @@
+scikit-learn==1.2.2
+matplotlib==3.7.1