File size: 1,776 Bytes
e839c0e bad0412 e839c0e bad0412 e839c0e bad0412 e839c0e bad0412 e839c0e bad0412 e839c0e bad0412 e839c0e bad0412 e839c0e bad0412 e839c0e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 |
import gradio as gr
import matplotlib.pyplot as plt
import numpy as np
from sklearn.cluster import MeanShift, estimate_bandwidth
from sklearn.datasets import make_blobs
def get_clusters_plot(n_blobs, quantile, cluster_std):
X, _, centers = make_blobs(
n_samples=10000, cluster_std=cluster_std, centers=n_blobs, return_centers=True
)
bandwidth = estimate_bandwidth(X, quantile=quantile, n_samples=500)
ms = MeanShift(bandwidth=bandwidth, bin_seeding=True)
ms.fit(X)
labels = ms.labels_
cluster_centers = ms.cluster_centers_
labels_unique = np.unique(labels)
n_clusters_ = len(labels_unique)
fig = plt.figure()
for k in range(n_clusters_):
my_members = labels == k
cluster_center = cluster_centers[k]
plt.scatter(X[my_members, 0], X[my_members, 1])
plt.plot(
cluster_center[0],
cluster_center[1],
"x",
markeredgecolor="k",
markersize=14,
)
message = f"## True Clusters: {len(centers)} | Detected Clusters: {n_clusters_}"
return fig, message
demo = gr.Interface(
get_clusters_plot,
[
gr.Slider(
minimum=2, maximum=10, label="Number of clusters in data", step=1, value=3
),
gr.Slider(
minimum=0,
maximum=1,
step=0.05,
value=0.2,
label="Quantile",
info="Used to determine clustering's bandwidth.",
),
gr.Slider(
minimum=0.1,
maximum=1,
label="Cluster standard deviation",
step=0.1,
value=0.6,
),
],
[gr.Plot(), gr.Markdown()],
allow_flagging="never",
)
if __name__ == "__main__":
demo.launch()
|