Update app.py

app.py

@@ -1,8 +1,8 @@
 import numpy as np
 import gradio as gr
 
-from sklearn.datasets import make_biclusters
-from sklearn.cluster import SpectralCoclustering
+from sklearn.datasets import make_checkerboard
+from sklearn.cluster import SpectralBiclustering
 from sklearn.metrics import consensus_score
 
 import plotly.express as px
@@ -11,10 +11,10 @@ import plotly.express as px
 score = [0.0]
 
 
-def dataset(n_clusters=5, noise=5, n_rows=300, n_cols=300):
-    data, rows, columns = make_biclusters(
+def dataset(n_cluster_rows, n_cluster_cols, noise=5, n_rows=300, n_cols=300):
+    data, rows, columns = make_checkerboard(
         shape=(n_rows, n_cols),
-        n_clusters=n_clusters,
+        n_clusters=(n_cluster_rows, n_cluster_cols),
         noise=noise,
         shuffle=False,
         random_state=0,
@@ -24,10 +24,10 @@ def dataset(n_clusters=5, noise=5, n_rows=300, n_cols=300):
     return fig
 
 
-def shuffle_dataset(n_clusters=5, noise=5, n_rows=300, n_cols=300):
-    data, rows, columns = make_biclusters(
+def shuffle_dataset(n_cluster_rows, n_cluster_cols, noise=5, n_rows=300, n_cols=300):
+    data, rows, columns = make_checkerboard(
         shape=(n_rows, n_cols),
-        n_clusters=n_clusters,
+        n_clusters=(n_cluster_rows, n_cluster_cols),
         noise=noise,
         shuffle=False,
         random_state=0,
@@ -40,11 +40,19 @@ def shuffle_dataset(n_clusters=5, noise=5, n_rows=300, n_cols=300):
     return fig
 
 
-def model_fit(n_cluster, noise, n_rows, n_cols, n_clusters, svd_method):
-
-    data, rows, columns = make_biclusters(
+def model_fit(
+    n_cluster_rows,
+    n_cluster_cols,
+    noise,
+    n_rows,
+    n_cols,
+    n_cluster_rows_,
+    n_cluster_cols_,
+    svd_method,
+):
+    data, rows, columns = make_checkerboard(
         shape=(n_rows, n_cols),
-        n_clusters=n_cluster,
+        n_clusters=(n_cluster_rows, n_cluster_cols),
         noise=noise,
         shuffle=False,
         random_state=0,
@@ -55,8 +63,11 @@ def model_fit(n_cluster, noise, n_rows, n_cols, n_clusters, svd_method):
     col_idx = rng.permutation(data.shape[1])
     data = data[row_idx][:, col_idx]
     fig_shuffled = px.imshow(data, title="Shuffled Data")
-    model = SpectralCoclustering(
-        n_clusters=n_clusters, random_state=0, svd_method=svd_method
+    model = SpectralBiclustering(
+        n_clusters=(n_cluster_rows_, n_cluster_cols_),
+        method="log",
+        random_state=0,
+        svd_method=svd_method,
     )
     model.fit(data)
     score.append(
@@ -64,8 +75,14 @@ def model_fit(n_cluster, noise, n_rows, n_cols, n_clusters, svd_method):
     )
     fit_data = data[np.argsort(model.row_labels_)]
     fit_data = fit_data[:, np.argsort(model.column_labels_)].T
-    fig = px.imshow(fit_data, title="After Co-Clustering")
-    return fig_original, fig_shuffled, fig
+    fig = px.imshow(fit_data, title="After Bi-Clustering")
+
+    fig_1 = px.imshow(
+        np.outer(np.sort(model.row_labels_) + 1, np.sort(model.column_labels_) + 1),
+        title="Checkerboard structure of rearranged data",
+    )
+
+    return fig_original, fig_shuffled, fig, fig_1
 
 
 def get_score():
@@ -73,9 +90,9 @@ def get_score():
 
 
 with gr.Blocks() as demo:
-    gr.Markdown("## Spectral Co-Clustering")
+    gr.Markdown("## Spectral Bi-Clustering")
     gr.Markdown(
-        "Demo is based on the [Spectral Co-Clustering](https://scikit-learn.org/stable/auto_examples/bicluster/plot_spectral_coclustering.html) example from scikit-learn. The goal of co-clustering is to find subgroups of rows and columns that are highly correlated. The data is first shuffled, then the rows and columns are reordered to match the biclusters. The consensus score is a measure of how well the biclusters found by the model match the true biclusters. The score is between 0 and 1, with 1 being a perfect match."
+        "Demo is based on the [Spectral Bi-Clustering](https://scikit-learn.org/stable/auto_examples/bicluster/plot_spectral_coclustering.html) example from scikit-learn. The goal of co-clustering is to find subgroups of rows and columns that are highly correlated. The data is first shuffled, then the rows and columns are reordered to match the biclusters. The consensus score is a measure of how well the biclusters found by the model match the true biclusters. The score is between 0 and 1, with 1 being a perfect match."
     )
 
     with gr.Tab("Data"):
@@ -84,18 +101,25 @@ with gr.Blocks() as demo:
         with gr.Row():
             n_rows = gr.Slider(1, 500, label="Number of Rows", value=300, step=1)
             n_cols = gr.Slider(1, 500, label="Number of Columns", value=300, step=1)
-            n_cluster = gr.Slider(1, 50, label="Number of Clusters", value=5, step=1)
+            n_cluster_rows = gr.Slider(
+                1, 50, label="Number of Clusters Rows", value=5, step=1
+            )
+            n_cluster_cols = gr.Slider(
+                1, 50, label="Number of Clusters Columns", value=5, step=1
+            )
             noise = gr.Slider(0, 10, label="Noise", value=5, step=1)
         with gr.Row():
             gen_btn = gr.Button("Generate Data")
             shu_btn = gr.Button("Shuffle Data")
         with gr.Row():
             gen_btn.click(
-                fn=dataset, inputs=[n_cluster, noise, n_rows, n_cols], outputs=gr.Plot()
+                fn=dataset,
+                inputs=[n_cluster_rows, n_cluster_cols, noise, n_rows, n_cols],
+                outputs=gr.Plot(),
             )
             shu_btn.click(
                 fn=shuffle_dataset,
-                inputs=[n_cluster, noise, n_rows, n_cols],
+                inputs=[n_cluster_rows, n_cluster_cols, noise, n_rows, n_cols],
                 outputs=gr.Plot(),
             )
 
@@ -105,11 +129,21 @@ with gr.Blocks() as demo:
         with gr.Row():
             n_rows = gr.Slider(1, 500, label="Number of Rows", value=300, step=1)
             n_cols = gr.Slider(1, 500, label="Number of Columns", value=300, step=1)
-            n_cluster = gr.Slider(1, 50, label="Number of Clusters", value=5, step=1)
+            n_cluster_rows = gr.Slider(
+                1, 50, label="Number of Clusters Rows", value=5, step=1
+            )
+            n_cluster_cols = gr.Slider(
+                1, 50, label="Number of Clusters Columns", value=5, step=1
+            )
             noise = gr.Slider(0, 10, label="Noise", value=5, step=1)
         gr.Markdown("### Model Parameters")
         with gr.Row():
-            n_clusters = gr.Slider(1, 50, label="Number of Clusters", value=5, step=1)
+            n_cluster_rows_ = gr.Slider(
+                1, 50, label="Number of Clusters Rows", value=5, step=1
+            )
+            n_cluster_cols_ = gr.Slider(
+                1, 50, label="Number of Clusters Columns", value=5, step=1
+            )
             svd_method = gr.Dropdown(
                 ["randomized", "arpack"], label="SVD Method", value="randomized"
             )
@@ -117,8 +151,17 @@ with gr.Blocks() as demo:
         with gr.Row():
             model_btn.click(
                 fn=model_fit,
-                inputs=[n_cluster, noise, n_rows, n_cols, n_clusters, svd_method],
-                outputs=[gr.Plot(), gr.Plot(), gr.Plot()],
+                inputs=[
+                    n_cluster_rows,
+                    n_cluster_cols,
+                    noise,
+                    n_rows,
+                    n_cols,
+                    n_cluster_rows_,
+                    n_cluster_cols_,
+                    svd_method,
+                ],
+                outputs=[gr.Plot(), gr.Plot(), gr.Plot(), gr.Plot()],
             )
         gr.Markdown("### Consensus Score")
         score_btn = gr.Button("Get Score")