Update pages/1_Random_Data.py

pages/1_Random_Data.py

@@ -6,8 +6,6 @@ from sklearn.datasets import make_moons, make_circles, make_classification
 from sklearn.model_selection import train_test_split
 from sklearn.preprocessing import StandardScaler
 
-st.set_option('deprecation.showPyplotGlobalUse', False)
-
 st.title("🔢 Random Data Playground")
 st.markdown("Define hyperparameters, generate synthetic data, and train your neural network interactively.")
 
@@ -53,6 +51,9 @@ if submitted:
     st.pyplot(fig)
 
     if st.button("🚀 Train Model"):
+        progress_bar = st.progress(0)
+        status_text = st.empty()
+
         # Build model
         model = tf.keras.Sequential()
         model.add(tf.keras.layers.Input(shape=(2,)))
@@ -63,25 +64,24 @@ if submitted:
         optimizer = tf.keras.optimizers.Adam(learning_rate=learning_rate)
         model.compile(optimizer=optimizer, loss='binary_crossentropy', metrics=['accuracy'])
 
-        # Progress bar
-        progress_bar = st.progress(0)
-        status_text = st.empty()
-        train_loss = []
-        val_loss = []
+        # Custom training loop to show progress
+        class StreamlitCallback(tf.keras.callbacks.Callback):
+            def on_epoch_end(self, epoch, logs=None):
+                percent = (epoch + 1) / epochs
+                progress_bar.progress(min(percent, 1.0))
+                status_text.text(f"Epoch {epoch+1}/{epochs} - Loss: {logs['loss']:.4f}, Val Loss: {logs['val_loss']:.4f}")
 
-        for epoch in range(epochs):
-            history = model.fit(X_train, y_train, batch_size=batch_size, epochs=1, validation_split=0.2, verbose=0)
-            train_loss.append(history.history['loss'][0])
-            val_loss.append(history.history['val_loss'][0])
-            progress_bar.progress((epoch + 1) / epochs)
-            status_text.text(f"Epoch {epoch+1}/{epochs} — Loss: {train_loss[-1]:.4f} — Val Loss: {val_loss[-1]:.4f}")
+        history = model.fit(
+            X_train, y_train,
+            batch_size=batch_size,
+            epochs=epochs,
+            validation_split=0.2,
+            verbose=0,
+            callbacks=[StreamlitCallback()]
+        )
 
         st.success("✅ Model Trained!")
 
-        # Final loss values
-        st.write(f"📉 Final Train Loss: **{train_loss[-1]:.4f}**")
-        st.write(f"🧪 Final Validation Loss: **{val_loss[-1]:.4f}**")
-
         # Decision Region After Training
         st.subheader("🌈 Decision Region After Training")
         preds = model.predict(np.c_[xx.ravel(), yy.ravel()]).reshape(xx.shape)
@@ -90,12 +90,18 @@ if submitted:
         ax.scatter(X_scaled[:, 0], X_scaled[:, 1], c=y, cmap=plt.cm.bwr, edgecolor='k')
         st.pyplot(fig)
 
-        # Loss Plots
-        st.subheader("📈 Training vs Validation Loss")
+        # Loss Plot
+        st.subheader("📉 Training vs Validation Loss")
         fig, ax = plt.subplots()
-        ax.plot(train_loss, label='Train Loss')
-        ax.plot(val_loss, label='Validation Loss')
+        ax.plot(history.history['loss'], label='Train Loss')
+        ax.plot(history.history['val_loss'], label='Validation Loss')
         ax.set_xlabel("Epochs")
         ax.set_ylabel("Loss")
         ax.legend()
         st.pyplot(fig)
+
+        # Loss values
+        final_train_loss = history.history['loss'][-1]
+        final_val_loss = history.history['val_loss'][-1]
+        st.write(f"🧮 **Final Train Loss**: `{final_train_loss:.4f}`")
+        st.write(f"🧪 **Final Validation Loss**: `{final_val_loss:.4f}`")