Update app.py

app.py

@@ -4,24 +4,26 @@ import matplotlib.pyplot as plt
 import seaborn as sns
 import graphviz
 import time
-from sklearn.datasets import make_moons, make_circles, make_classification
+from sklearn.datasets import make_moons, make_circles, make_classification, make_blobs
 
 # 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
 
-# ================= TRAINING CONTROL PANEL (Top) =================
+# Training Control Panel
 st.markdown("### Training Controls")
-col1, col2, col3, col4, col5, col6, col7, col8, col9 = st.columns(9)
+col1, col2, col3, col4, col5 = st.columns(5)
 
 with col1:
     if st.button("↩️ Reset"):
         st.session_state.epoch = 0
+        st.session_state.losses = []
         st.session_state.running = False
 with col2:
     if st.button("▶️ Train"):
@@ -30,86 +32,31 @@ with col3:
     if st.button("⏸️ Pause"):
         st.session_state.running = False
 with col4:
-    activation = st.selectbox("Activation", ["ReLU", "Sigmoid", "Tanh", "LeakyReLU"])
+    activation = st.selectbox("Activation", ["ReLU", "Sigmoid", "Tanh"])
 with col5:
-    regularization = st.selectbox("Regularization", ["None", "L1", "L2"])
-with col6:
-    reg_rate = st.selectbox("Regularization Rate", [0.0001, 0.001, 0.01, 0.1]) if regularization in ["L1", "L2"] else 0
-with col7:
-    problem_type = st.selectbox("Problem Type", ["Classification", "Regression"])
-with col8:
     learning_rate = st.selectbox("Learning Rate", [0.0001, 0.001, 0.01, 0.03, 0.1])
-with col9:
-    st.write(f"Epoch: **{st.session_state.epoch}**")
 
-# 🚀 **Fix:** Run training loop without breaking Streamlit
 if st.session_state.running:
     time.sleep(1)  # Simulating training
     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
 
-# ================= MAIN LAYOUT =================
-col_features, col_hidden, col_output = st.columns([2, 2, 2])
-
-# ========== FEATURES PANEL (Left) ========== #
-with col_features:
-    st.header("FEATURES")
-    st.write("Which properties do you want to feed in?")
-    
-    x1 = st.checkbox("X₁", value=True)
-    x2 = st.checkbox("X₂", value=True)
-    x1_squared = st.checkbox("X₁²")
-    x2_squared = st.checkbox("X₂²")
-    x1_x2 = st.checkbox("X₁X₂")
-    sin_x1 = st.checkbox("sin(X₁)")
-    sin_x2 = st.checkbox("sin(X₂)")
-
-# ========== HIDDEN LAYERS PANEL (Middle) ========== #
-with col_hidden:
-    st.header("HIDDEN LAYERS")
-    hidden_layers = st.slider("Number of Hidden Layers", 1, 7, 2)
-
-    neurons = []
-    for i in range(hidden_layers):
-        neurons.append(st.slider(f"Neurons in Layer {i+1}", 1, 20, 4))
-
-# ========== OUTPUT PANEL (Right) ========== #
-with col_output:
-    st.header("OUTPUT")
-    st.write("Test Loss: *0.501*")
-    st.write("Training Loss: *0.507*")
-
-    # Spiral Plot with Updated Color Palette
-    x = np.linspace(-6, 6, 300)
-    y = np.sin(x) + np.random.normal(0, 0.1, x.shape)
-
-    fig, ax = plt.subplots()
-    sns.scatterplot(x=x, y=y, hue=x, palette="plasma", ax=ax)
-    st.pyplot(fig)
-
-    show_test_data = st.checkbox("Show test data")
-    discretize_output = st.checkbox("Discretize output")
-
-# ================= DATASET SELECTION (Sidebar) =================
+# 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)
 
-dataset_option = st.sidebar.radio(
-    "Which dataset do you want to use?",
-    ("Moons", "Circles", "Spiral"),
-    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 =================
+# Dataset Generation
 def generate_data():
     if dataset_option == "Moons":
-        X, y = make_moons(n_samples=500, noise=noise)
+        X, y = make_moons(n_samples=1000, noise=noise)
     elif dataset_option == "Circles":
-        X, y = make_circles(n_samples=500, noise=noise)
+        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)
     else:
-        theta = np.sqrt(np.random.rand(500)) * 2 * np.pi
+        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
@@ -117,44 +64,66 @@ def generate_data():
 
 X, y = generate_data()
 
-# =================== DRAW NEURAL NETWORK ===================
+# 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))
+
+# Neural Network Display
 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("Output", "Output", shape="circle", style="filled", fillcolor="lightgreen")
+    graph.edge("H1", "Output")
+    return graph
 
-    # Input Layer
-    graph.node("X1", "X₁", shape="circle", style="filled", fillcolor="lightblue")
-    graph.node("X2", "X₂", shape="circle", style="filled", fillcolor="lightblue")
+with col_nn:
+    st.graphviz_chart(draw_neural_network())
 
-    prev_layer = ["X1", "X2"]
+# 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)
 
-    # Hidden Layers
-    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
+with col_plot:
+    st.header("Decision Region")
+    plot_decision_regions()
 
-    # Output Layer
-    graph.node("Output", "Output", shape="circle", style="filled", fillcolor="lightgreen")
-    for neuron in prev_layer:
-        graph.edge(neuron, "Output")
+# 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)
 
-    return graph
+st.header("Training Progress")
+plot_loss()
 
-# =================== DISPLAY DATA PLOT ===================
+# Dataset Visualization
 st.sidebar.subheader("Dataset Visualization")
 fig, ax = plt.subplots()
-ax.scatter(X[:, 0], X[:, 1], c=y, cmap="plasma", edgecolors="k")
+sns.scatterplot(x=X[:, 0], y=X[:, 1], hue=y, palette="plasma", edgecolor="k", ax=ax)
 st.sidebar.pyplot(fig)
 
-# =================== DISPLAY NEURAL NETWORK ===================
-st.graphviz_chart(draw_neural_network())
-
-# =================== TRAINING STATUS ===================
+# Training Status
 if st.session_state.running:
-    st.write("🚀 Training started...")
+    st.write("🚀 Training in Progress...")
 elif not st.session_state.running and st.session_state.epoch > 0:
-    st.write("⏸️ Training paused.")
+    st.write("⏸️ Training Paused.")