Update app.py

app.py

@@ -4,7 +4,12 @@ import matplotlib.pyplot as plt
 import seaborn as sns
 import graphviz
 import time
+import tensorflow as tf
+from tensorflow import keras
+from tensorflow.keras import layers
+from sklearn.model_selection import train_test_split
 from sklearn.datasets import make_moons, make_circles, make_classification, make_blobs
+from mlxtend.plotting import plot_decision_regions
 
 # Set Streamlit page title
 st.set_page_config(page_title="Neural Network Trainer", layout="wide")
@@ -21,7 +26,7 @@ if "test_loss_history" not in st.session_state:
 
 # ================= TRAINING CONTROL PANEL (Top) =================
 st.markdown("### Training Controls")
-col1, col2, col3, col4, col5, col6, col7 = st.columns(7)
+col1, col2, col3, col4, col5, col6, col7, col8, col9 = st.columns(9)
 
 with col1:
     if st.button("↩️ Reset"):
@@ -43,12 +48,11 @@ with col6:
     learning_rate = st.selectbox("Learning Rate", [0.0001, 0.001, 0.01, 0.03, 0.1])
 with col7:
     num_epochs = st.slider("Epochs", 1, 100, 10)
-
-if st.session_state.running:
-    time.sleep(1)
-    st.session_state.epoch += 1
-    st.session_state.train_loss_history.append(np.exp(-0.1 * st.session_state.epoch) + np.random.uniform(0, 0.05))
-    st.session_state.test_loss_history.append(np.exp(-0.1 * st.session_state.epoch) + np.random.uniform(0, 0.05) + 0.02)
+with col8:
+    batch_size = st.slider("Batch Size", 1, 100, 10)
+with col9:
+    dataset_option = st.selectbox("Select Dataset", ["Moons", "Circles", "Blobs", "Classification"])
+    noise = st.slider("Noise Level", 0.0, 0.5, 0.2)
 
 # ================= MAIN LAYOUT =================
 col_features, col_hidden, col_plot = st.columns([2, 2, 3])
@@ -66,39 +70,6 @@ with col_hidden:
     hidden_layers = st.slider("Number of Hidden Layers", 1, 7, 2)
     neurons = [st.slider(f"Neurons in Layer {i+1}", 1, 20, 4) for i in range(hidden_layers)]
 
-# ========== DECISION REGION PLOT (Right) ========== #
-with col_plot:
-    st.header("Decision Region & Loss Plot")
-    fig, ax = plt.subplots()
-    x_min, x_max = -2, 2
-    y_min, y_max = -2, 2
-    xx, yy = np.meshgrid(np.linspace(x_min, x_max, 100), np.linspace(y_min, y_max, 100))
-    zz = np.sin(xx) * np.cos(yy)  # Placeholder function
-    sns.heatmap(zz, cmap="coolwarm", alpha=0.5, ax=ax)
-    ax.set_title("Decision Region")
-    st.pyplot(fig)
-
-    # Loss Plot
-    fig, ax = plt.subplots()
-    ax.plot(range(len(st.session_state.train_loss_history)), st.session_state.train_loss_history, marker="o", label="Train Loss")
-    ax.plot(range(len(st.session_state.test_loss_history)), st.session_state.test_loss_history, marker="s", label="Test Loss")
-    ax.set_title("Epoch vs. Loss")
-    ax.set_xlabel("Epoch")
-    ax.set_ylabel("Loss")
-    ax.legend()
-    st.pyplot(fig)
-
-# ================= DATASET SELECTION (Sidebar) =================
-st.sidebar.header("DATA")
-dataset_option = st.sidebar.radio(
-    "Which dataset do you want to use?",
-    ("Moons", "Circles", "Spiral", "Blobs"),
-    index=2
-)
-train_ratio = st.sidebar.slider("Ratio of training to test data:", 10, 90, 50, format="%d%%")
-noise = st.sidebar.slider("Noise:", 0.0, 1.0, 0.1, step=0.1)
-batch_size = st.sidebar.slider("Batch size:", 1, 100, 10)
-
 # ================= DATASET GENERATION =================
 def generate_data():
     if dataset_option == "Moons":
@@ -108,21 +79,48 @@ def generate_data():
     elif dataset_option == "Blobs":
         X, y = make_blobs(n_samples=1000, centers=2, cluster_std=noise)
     else:
-        theta = np.sqrt(np.random.rand(1000)) * 2 * np.pi
-        r = theta
-        X = np.array([r * np.cos(theta), r * np.sin(theta)]).T
-        y = (theta % (2 * np.pi)) > np.pi
+        X, y = make_classification(n_samples=1000, n_features=2, n_classes=2, n_clusters_per_class=1, n_redundant=0, flip_y=noise)
     return X, y
 
 X, y = generate_data()
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+# ========== TRAINING ANN ========== #
+def build_ann():
+    model = keras.Sequential()
+    model.add(layers.Input(shape=(X.shape[1],)))
+    for units in neurons:
+        model.add(layers.Dense(units, activation=activation.lower()))
+    model.add(layers.Dense(1, activation="sigmoid" if problem_type == "Classification" else "linear"))
+    model.compile(optimizer=keras.optimizers.Adam(learning_rate), loss="binary_crossentropy" if problem_type == "Classification" else "mse")
+    return model
 
-# =================== DISPLAY DATA PLOT ===================
-st.sidebar.subheader("Dataset Visualization")
-fig, ax = plt.subplots()
-sns.scatterplot(x=X[:, 0], y=X[:, 1], hue=y, palette="plasma", ax=ax)
-st.sidebar.pyplot(fig)
+if st.session_state.running:
+    model = build_ann()
+    history = model.fit(X_train, y_train, epochs=num_epochs, batch_size=batch_size, validation_data=(X_test, y_test), verbose=0)
+    st.session_state.train_loss_history = history.history["loss"]
+    st.session_state.test_loss_history = history.history["val_loss"]
 
-# =================== DRAW NEURAL NETWORK ===================
+# ========== LOSS PLOT ========== #
+with col_plot:
+    st.header("Loss Plot")
+    fig, ax = plt.subplots()
+    ax.plot(range(1, len(st.session_state.train_loss_history) + 1), st.session_state.train_loss_history, marker="o", label="Train Loss")
+    ax.plot(range(1, len(st.session_state.test_loss_history) + 1), st.session_state.test_loss_history, marker="s", label="Test Loss")
+    ax.set_title("Epoch vs. Loss")
+    ax.set_xlabel("Epoch")
+    ax.set_ylabel("Loss")
+    ax.legend()
+    st.pyplot(fig)
+
+# =================== DECISION REGION =================== #
+if problem_type == "Classification":
+    fig, ax = plt.subplots()
+    plot_decision_regions(X_train, y_train, clf=model, ax=ax)
+    ax.set_title("Decision Region")
+    st.pyplot(fig)
+
+# =================== DRAW NEURAL NETWORK =================== #
 def draw_neural_network():
     graph = graphviz.Digraph()
     graph.node("X1", "X₁", shape="circle", style="filled", fillcolor="lightblue")
@@ -142,9 +140,3 @@ def draw_neural_network():
     return graph
 
 st.graphviz_chart(draw_neural_network())
-
-# =================== TRAINING STATUS ===================
-if st.session_state.running:
-    st.write("🚀 Training started...")
-elif not st.session_state.running and st.session_state.epoch > 0:
-    st.write("⏸️ Training paused.")