Duplicate from sklearn-docs/mean-shift-clustering

Co-authored-by: Carlos Miguel Patiño <cmpatino@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,125 @@
+
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# VS Code
+.vscode/
+
+# pycache
+__pycache__/

README.md

@@ -0,0 +1,13 @@
+---
+title: Mean Shift Clustering
+emoji: 💩
+colorFrom: blue
+colorTo: green
+sdk: gradio
+sdk_version: 3.24.1
+app_file: app.py
+pinned: false
+duplicated_from: sklearn-docs/mean-shift-clustering
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,121 @@
+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,
+        )
+        plt.xlabel("Feature 1")
+        plt.ylabel("Feature 2")
+
+    plt.title(f"Estimated number of clusters: {n_clusters_}")
+
+    if len(centers) != n_clusters_:
+        message = (
+            '<p style="text-align: center;">'
+            + f"The number of estimated clusters ({n_clusters_})"
+            + f" differs from the true number of clusters ({n_blobs})."
+            + " Try changing the `Quantile` parameter.</p>"
+        )
+    else:
+        message = (
+            '<p style="text-align: center;">'
+            + f"The number of estimated clusters ({n_clusters_})"
+            + f" matches the true number of clusters ({n_blobs})!</p>"
+        )
+    return fig, message
+
+
+with gr.Blocks() as demo:
+    gr.Markdown(
+        """
+            # Mean Shift Clustering
+
+            This space shows how to use the [Mean Shift Clustering](https://scikit-learn.org/stable/modules/generated/sklearn.cluster.MeanShift.html) algorithm to cluster 2D data points. You can change the parameters using the sliders and see how the model performs.
+            
+            This space is based on [sklearn's original demo](https://scikit-learn.org/stable/auto_examples/cluster/plot_mean_shift.html#sphx-glr-auto-examples-cluster-plot-mean-shift-py).
+            """
+    )
+    with gr.Row():
+        with gr.Column(scale=1):
+            n_blobs = gr.Slider(
+                minimum=2,
+                maximum=10,
+                label="Number of clusters in the data",
+                step=1,
+                value=3,
+            )
+            quantile = gr.Slider(
+                minimum=0,
+                maximum=1,
+                step=0.05,
+                value=0.2,
+                label="Quantile",
+                info="Used to determine clustering's bandwidth.",
+            )
+            cluster_std = gr.Slider(
+                minimum=0.1,
+                maximum=1,
+                label="Clusters' standard deviation",
+                step=0.1,
+                value=0.6,
+            )
+        with gr.Column(scale=4):
+            clusters_plots = gr.Plot(label="Clusters' Plot")
+            message = gr.HTML()
+
+    n_blobs.change(
+        get_clusters_plot,
+        [n_blobs, quantile, cluster_std],
+        [clusters_plots, message],
+        queue=False,
+    )
+    quantile.change(
+        get_clusters_plot,
+        [n_blobs, quantile, cluster_std],
+        [clusters_plots, message],
+        queue=False,
+    )
+    cluster_std.change(
+        get_clusters_plot,
+        [n_blobs, quantile, cluster_std],
+        [clusters_plots, message],
+        queue=False,
+    )
+    demo.load(
+        get_clusters_plot,
+        [n_blobs, quantile, cluster_std],
+        [clusters_plots, message],
+        queue=False,
+    )
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

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