Update app.py

app.py

@@ -20,15 +20,17 @@ model_card = f"""
 The **Out-of-bag (OOB)** method is a useful technique for estimating the optimal number of boosting iterations.
 This method is similar to cross-validation, but it does not require repeated model fitting and can be computed on-the-fly. 
 **OOB** estimates are only applicable to Stochastic Gradient Boosting (i.e., subsample < 1.0). They are calculated from the improvement in loss based on examples not included in the bootstrap sample (i.e., out-of-bag examples). 
-The **OOB** estimator provides a conservative estimate of the true test loss, but is still a reasonable approximation for a small number of trees. 
-This demo shows the negative OOB improvements' cumulative sum as a function of the boosting iteration.
+The **OOB** estimator provides a conservative estimate of the true test loss but is still a reasonable approximation for a small number of trees. 
+In this demonstration, a **GradientBoostingClassifier** model is trained on a simulation dataset, and the loss of the training set, test set, and OOB set are displayed in the figure.
+This information allows you to determine the level of generalization of your trained model on the simulation dataset.
+You can play around with ``number of samples``,``number of splits fold``, ``random seed``and ``number of estimator (step)``
 
 ## Dataset
 
 Simulation data
 """
 
-def do_train(n_samples, n_splits, random_seed):
+def do_train(n_samples, n_splits, random_seed, n_estimators):
     # Generate data (adapted from G. Ridgeway's gbm example)
     random_state = np.random.RandomState(random_seed)
     x1 = random_state.uniform(size=n_samples)
@@ -45,7 +47,7 @@ def do_train(n_samples, n_splits, random_seed):
 
     # Fit classifier with out-of-bag estimates
     params = {
-        "n_estimators": 1200,
+        "n_estimators": n_estimators,
         "max_depth": 3,
         "subsample": 0.5,
         "learning_rate": 0.01,
@@ -145,6 +147,7 @@ with gr.Blocks(theme=theme) as demo:
     n_samples = gr.Slider(minimum=500, maximum=5000, step=500, value=500, label="Number of samples")
     n_splits = gr.Slider(minimum=2, maximum=10, step=1, value=3, label="Number of cross validation folds")
     random_seed = gr.Slider(minimum=0, maximum=2000, step=1, value=0, label="Random seed")
+    n_estimators = gr.Slider(minimum=500, maximum=2000, step=100, value=500, label="Number of estimator step")
 
     with gr.Row():
         with gr.Column():
@@ -152,8 +155,9 @@ with gr.Blocks(theme=theme) as demo:
         with gr.Column():
             result = gr.Textbox(label="Resusts")
         
-    n_samples.change(fn=do_train, inputs=[n_samples, n_splits, random_seed], outputs=[plot, result])
-    n_splits.change(fn=do_train, inputs=[n_samples, n_splits, random_seed], outputs=[plot, result])
-    random_seed.change(fn=do_train, inputs=[n_samples, n_splits, random_seed], outputs=[plot, result])
+    n_samples.change(fn=do_train, inputs=[n_samples, n_splits, random_seed, n_estimators], outputs=[plot, result])
+    n_splits.change(fn=do_train, inputs=[n_samples, n_splits, random_seed, n_estimators], outputs=[plot, result])
+    random_seed.change(fn=do_train, inputs=[n_samples, n_splits, random_seed, n_estimators], outputs=[plot, result])
+    n_estimators.change(fn=do_train, inputs=[n_samples, n_splits, random_seed, n_estimators], outputs=[plot, result])
 
 demo.launch()