Update app.py

app.py

@@ -20,7 +20,7 @@ import gradio as gr
 
 C1, C2, C3 = '#ff0000', '#ffff00', '#0000ff'
 CMAP = ListedColormap([C1, C2, C3])
-GRANULARITY = 0.01
+GRANULARITY = 0.05
 SEED = 1
 N_ESTIMATORS = 30
 
@@ -68,14 +68,14 @@ def create_plot(feature_string, n_estimators, max_depth, model_idx):
 
     x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
     y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
-    xrange = np.arange(x_min, x_max, 0.1)
-    yrange = np.arange(y_min, y_max, 0.1)
+    xrange = np.arange(x_min, x_max, GRANULARITY)
+    yrange = np.arange(y_min, y_max, GRANULARITY)
     xx, yy = np.meshgrid(xrange, yrange)
 
     Z = model.predict(np.c_[xx.ravel(), yy.ravel()])
     Z = Z.reshape(xx.shape)
 
-    fig = plt.figure()
+    fig = plt.figure(figsize=(4, 3.5))
     ax = fig.add_subplot(111)
 
     ax.contourf(xx, yy, Z, cmap=CMAP, alpha=0.65)
@@ -88,6 +88,8 @@ def create_plot(feature_string, n_estimators, max_depth, model_idx):
     ax.set_xlabel(feature_list[0]); ax.set_ylabel(feature_list[1])
     ax.legend()
     ax.set_title(f'{model_name} | Score: {score}')
+    fig.set_tight_layout(True)
+    fig.set_constrained_layout(True)
 
     return fig
 
@@ -106,29 +108,34 @@ This plot compares the **decision surfaces** learned by a decision tree classifi
 There are in total **four features** in the Iris dataset. In this example you can select **two features at a time** for visualization purposes using the dropdown box below. All features are normalized to zero mean and unit standard deviation.
 
 Play around with the **number of estimators** in the ensembles and the **max depth** of the trees using the sliders.
+
+Created by [@hubadul](https://huggingface.co/huabdul) based on [scikit-learn docs](https://scikit-learn.org/stable/auto_examples/ensemble/plot_forest_iris.html).
 '''
 
 with gr.Blocks() as demo:
-    gr.Markdown(info)
-    selections = combinations(FEATURES, 2)
-    selections = [f'{s[0]}, {s[1]}' for s in selections] 
-    dd = gr.Dropdown(selections, value=selections[0], interactive=True, label="Input features")
-    slider_estimators = gr.Slider(1, 100, value=30, step=1, label='n_estimators')
-    slider_max_depth = gr.Slider(1, 50, value=10, step=1, label='max_depth')
-
-    counter = 0
-    for _ in iter_grid(2, 2):
-        if counter >= len(MODELS):
-            break
-        
-        plot = gr.Plot(label=f'{MODEL_NAMES[counter]}')
-        fn = partial(create_plot, model_idx=counter)
-
-        dd.change(fn, inputs=[dd, slider_estimators, slider_max_depth], outputs=[plot])
-        slider_estimators.change(fn, inputs=[dd, slider_estimators, slider_max_depth], outputs=[plot])
-        slider_max_depth.change(fn, inputs=[dd, slider_estimators, slider_max_depth], outputs=[plot])
-        demo.load(fn, inputs=[dd, slider_estimators, slider_max_depth], outputs=[plot])
-
-        counter += 1
+    with gr.Row():
+        with gr.Column(scale=1):
+            gr.Markdown(info)
+            selections = combinations(FEATURES, 2)
+            selections = [f'{s[0]}, {s[1]}' for s in selections] 
+            dd = gr.Dropdown(selections, value=selections[0], interactive=True, label="Input features")
+            slider_estimators = gr.Slider(1, 100, value=30, step=1, label='n_estimators')
+            slider_max_depth = gr.Slider(1, 50, value=10, step=1, label='max_depth')
+
+        with gr.Column(scale=2):
+            counter = 0
+            for _ in iter_grid(2, 2):
+                if counter >= len(MODELS):
+                    break
+                
+                plot = gr.Plot(show_label=False)
+                fn = partial(create_plot, model_idx=counter)
+
+                dd.change(fn, inputs=[dd, slider_estimators, slider_max_depth], outputs=[plot])
+                slider_estimators.change(fn, inputs=[dd, slider_estimators, slider_max_depth], outputs=[plot])
+                slider_max_depth.change(fn, inputs=[dd, slider_estimators, slider_max_depth], outputs=[plot])
+                demo.load(fn, inputs=[dd, slider_estimators, slider_max_depth], outputs=[plot])
+
+                counter += 1
 
 demo.launch()