Update app.py

app.py

@@ -9,22 +9,23 @@ from sklearn.datasets import make_moons, make_circles, make_classification, make
 # Set Streamlit page title
 st.set_page_config(page_title="Neural Network Trainer", layout="wide")
 
-# Session State for Training Controls
+# ================= Session State for Training Controls =================
 if "epoch" not in st.session_state:
     st.session_state.epoch = 0
-    st.session_state.losses = []
 if "running" not in st.session_state:
     st.session_state.running = False
+if "loss_history" not in st.session_state:
+    st.session_state.loss_history = []
 
-# Training Control Panel
+# ================= TRAINING CONTROL PANEL (Top) =================
 st.markdown("### Training Controls")
-col1, col2, col3, col4, col5 = st.columns(5)
+col1, col2, col3, col4, col5, col6 = st.columns(6)
 
 with col1:
     if st.button("↩️ Reset"):
         st.session_state.epoch = 0
-        st.session_state.losses = []
         st.session_state.running = False
+        st.session_state.loss_history = []
 with col2:
     if st.button("▶️ Train"):
         st.session_state.running = True
@@ -34,27 +35,70 @@ with col3:
 with col4:
     activation = st.selectbox("Activation", ["ReLU", "Sigmoid", "Tanh"])
 with col5:
+    problem_type = st.selectbox("Problem Type", ["Classification", "Regression"])
+with col6:
     learning_rate = st.selectbox("Learning Rate", [0.0001, 0.001, 0.01, 0.03, 0.1])
 
 if st.session_state.running:
-    time.sleep(1)  # Simulating training
+    time.sleep(1)
     st.session_state.epoch += 1
-    st.session_state.losses.append(np.exp(-0.1 * st.session_state.epoch) + np.random.uniform(0, 0.05))  # Mock loss
+    st.session_state.loss_history.append(np.exp(-0.1 * st.session_state.epoch) + np.random.uniform(0, 0.05))
 
-# Sidebar - Dataset Selection
-st.sidebar.header("DATA")
-dataset_option = st.sidebar.radio("Select Dataset", ("Moons", "Circles", "Spiral", "Blobs"))
-train_ratio = st.sidebar.slider("Train-Test Split %", 10, 90, 50, format="%d%%")
-noise = st.sidebar.slider("Noise", 0.0, 1.0, 0.1, step=0.1)
+# ================= MAIN LAYOUT =================
+col_features, col_hidden, col_plot = st.columns([2, 2, 3])
+
+# ========== FEATURES PANEL (Left) ========== #
+with col_features:
+    st.header("FEATURES")
+    st.write("Select input features:")
+    x1 = st.checkbox("X₁", value=True)
+    x2 = st.checkbox("X₂", value=True)
+
+# ========== HIDDEN LAYERS PANEL (Middle) ========== #
+with col_hidden:
+    st.header("HIDDEN LAYERS")
+    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)
 
-# Dataset Generation
+    # Loss Plot
+    fig, ax = plt.subplots()
+    ax.plot(range(len(st.session_state.loss_history)), st.session_state.loss_history, marker="o")
+    ax.set_title("Epoch vs. Loss")
+    ax.set_xlabel("Epoch")
+    ax.set_ylabel("Loss")
+    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":
         X, y = make_moons(n_samples=1000, noise=noise)
     elif dataset_option == "Circles":
         X, y = make_circles(n_samples=1000, noise=noise)
     elif dataset_option == "Blobs":
-        X, y = make_blobs(n_samples=1000, centers=2, cluster_std=noise * 5)
+        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
@@ -64,66 +108,35 @@ def generate_data():
 
 X, y = generate_data()
 
-# Feature Selection
-st.header("FEATURES")
-col_features, col_nn, col_plot = st.columns([2, 2, 3])
-
-with col_features:
-    x1 = st.checkbox("X₁", value=True)
-    x2 = st.checkbox("X₂", value=True)
-    selected_features = [i for i, selected in enumerate([x1, x2]) if selected]
-    X = X[:, selected_features] if selected_features else np.zeros((X.shape[0], 1))
+# =================== 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)
 
-# Neural Network Display
+# =================== DRAW NEURAL NETWORK ===================
 def draw_neural_network():
     graph = graphviz.Digraph()
-    prev_layer = [f"X{i+1}" for i in range(len(selected_features))]
-    for node in prev_layer:
-        graph.node(node, node, shape="circle", style="filled", fillcolor="lightblue")
-    graph.node("H1", "Hidden Neuron", shape="circle", style="filled", fillcolor="lightyellow")
-    for node in prev_layer:
-        graph.edge(node, "H1")
+    graph.node("X1", "X₁", shape="circle", style="filled", fillcolor="lightblue")
+    graph.node("X2", "X₂", shape="circle", style="filled", fillcolor="lightblue")
+    prev_layer = ["X1", "X2"]
+    for i, num_neurons in enumerate(neurons):
+        current_layer = [f"H{i+1}{j+1}" for j in range(num_neurons)]
+        for neuron in current_layer:
+            graph.node(neuron, neuron, shape="circle", style="filled", fillcolor="lightyellow")
+        for prev in prev_layer:
+            for curr in current_layer:
+                graph.edge(prev, curr)
+        prev_layer = current_layer
     graph.node("Output", "Output", shape="circle", style="filled", fillcolor="lightgreen")
-    graph.edge("H1", "Output")
+    for neuron in prev_layer:
+        graph.edge(neuron, "Output")
     return graph
 
-with col_nn:
-    st.graphviz_chart(draw_neural_network())
-
-# Decision Region Plot
-def plot_decision_regions():
-    xx, yy = np.meshgrid(np.linspace(X[:, 0].min() - 1, X[:, 0].max() + 1, 100),
-                         np.linspace(X[:, 1].min() - 1, X[:, 1].max() + 1, 100))
-    Z = np.random.choice([0, 1], size=xx.shape)  # Placeholder for model predictions
-    fig, ax = plt.subplots()
-    ax.contourf(xx, yy, Z, alpha=0.3, cmap="plasma")
-    sns.scatterplot(x=X[:, 0], y=X[:, 1], hue=y, palette="plasma", edgecolor="k", ax=ax)
-    st.pyplot(fig)
-
-with col_plot:
-    st.header("Decision Region")
-    plot_decision_regions()
-
-# Loss Plot
-def plot_loss():
-    fig, ax = plt.subplots()
-    ax.plot(range(len(st.session_state.losses)), st.session_state.losses, marker='o', linestyle='-')
-    ax.set_xlabel("Epoch")
-    ax.set_ylabel("Loss")
-    ax.set_title("Epoch vs Loss")
-    st.pyplot(fig)
-
-st.header("Training Progress")
-plot_loss()
-
-# Dataset Visualization
-st.sidebar.subheader("Dataset Visualization")
-fig, ax = plt.subplots()
-sns.scatterplot(x=X[:, 0], y=X[:, 1], hue=y, palette="plasma", edgecolor="k", ax=ax)
-st.sidebar.pyplot(fig)
+st.graphviz_chart(draw_neural_network())
 
-# Training Status
+# =================== TRAINING STATUS ===================
 if st.session_state.running:
-    st.write("🚀 Training in Progress...")
+    st.write("🚀 Training started...")
 elif not st.session_state.running and st.session_state.epoch > 0:
-    st.write("⏸️ Training Paused.")
+    st.write("⏸️ Training paused.")