Update app.py

app.py

@@ -1,104 +1,210 @@
+Rohith Ramdass
+rohith.r18
+Idle
+
+Rohith Ramdass — 1/23/25, 3:30 PM
+hi
+Attachment file type: unknown
+chandrika_classification (1).ipynb
+1.13 MB
+N_Days,Status,Drug,Age,Sex,Ascites,Hepatomegaly,Spiders,Edema,Bilirubin,Cholesterol,Albumin,Copper,Alk_Phos,SGOT,Tryglicerides,Platelets,Prothrombin,Stage
+2221,C,Placebo,18499,F,N,Y,N,N,0.5,149.0,4.04,227.0,598.0,52.7,57.0,256.0,9.9,1
+1230,C,Placebo,19724,M,Y,N,Y,N,0.5,219.0,3.93,22.0,663.0,45.0,75.0,220.0,10.8,2
+4184,C,Placebo,11839,F,N,N,N,N,0.5,320.0,3.54,51.0,1243.0,122.45,80.0,225.0,10.0,2
+2090,D,Placebo,16467,F,N,N,N,N,0.7,255.0,3.74,23.0,1024.0,77.5,58.0,151.0,10.2,2
+2105,D,Placebo,21699,F,N,Y,N,N,1.9,486.0,3.54,74.0,1052.0,108.5,109.0,151.0,11.5,1... (3 MB left)
+Expand
+liver_cirrhosis.csv
+3 MB
+Rohith Ramdass — 1/23/25, 5:02 PM
+Attachment file type: unknown
+Consumer_Electronics_Sales_Prediction_Main (1) (1).ipynb
+1.90 MB
+yamunagovindha — 1/31/25, 7:16 PM
+hi  classification dhi  file petava nedhi
+Rohith Ramdass — 1/31/25, 7:25 PM
+Attachment file type: unknown
+Consumer_Electronics_Sales_Prediction_Final (1) (1).ipynb
+5.51 MB
+ide kada or face detection?
+yamunagovindha — 1/31/25, 7:27 PM
+ha ide
+yamunagovindha — 2/6/25, 6:07 PM
+Attachment file type: document
+IMDB_PPT (1).pptx
+1.76 MB
+yamunagovindha — Today at 11:43 AM
 import streamlit as st
 import numpy as np
 import matplotlib.pyplot as plt
-import networkx as nx
-from sklearn.datasets import make_classification, make_moons, make_circles, make_regression
-from sklearn.model_selection import train_test_split
-from sklearn.preprocessing import StandardScaler
-from tensorflow import keras
-from tensorflow.keras import layers
+import seaborn as sns
+import graphviz
+import time
+Expand
+message.txt
+6 KB
+
+yamunagovindha
+123yamu_
+import streamlit as st
+import numpy as np
+import matplotlib.pyplot as plt
+import seaborn as sns
+import graphviz
+import time
+from sklearn.datasets import make_moons, make_circles, make_classification
+
+# Set Streamlit page title
+st.set_page_config(page_title="Neural Network Trainer", layout="wide")
 
-# Title Bar
-st.title("Neural Network Playground")
+# ================= Session State for Training Controls =================
+if "epoch" not in st.session_state:
+    st.session_state.epoch = 0
+if "running" not in st.session_state:
+    st.session_state.running = False
 
-# Navigation Bar
-col1, col2, col3, col4, col5, col6, col7 = st.columns(7)
+# ================= TRAINING CONTROL PANEL (Top) =================
+st.markdown("### Training Controls")
+col1, col2, col3, col4, col5, col6, col7, col8, col9 = st.columns(9)
 
 with col1:
-    epochs = st.selectbox("Epochs", [100, 200, 500, 800, 1000, 1500, 2000])
+    if st.button("↩️ Reset"):
+        st.session_state.epoch = 0
+        st.session_state.running = False
 with col2:
-    learning_rate = st.selectbox("Learning Rate", [0.0001, 0.001, 0.01, 0.1, 0.3, 1, 3, 10])
+    if st.button("▶️ Train"):
+        st.session_state.running = True
 with col3:
-    activation = st.selectbox("Activation Function", ["ReLU", "Tanh", "Sigmoid", "Linear"])
+    if st.button("⏸️ Pause"):
+        st.session_state.running = False
 with col4:
-    reg_type = st.selectbox("Regularization Type", ["L1", "L2", "None"])
-    reg_rate = st.slider("Regularization Rate", 0.0, 0.1, 0.01, step=0.01)
+    activation = st.selectbox("Activation", ["ReLU", "Sigmoid", "Tanh", "LeakyReLU"])
 with col5:
-    problem_type = st.selectbox("Problem Type", ["Classification", "Regression"])
+    regularization = st.selectbox("Regularization", ["None", "L1", "L2"])
 with col6:
-    play = st.button("Train Model")
+    reg_rate = st.selectbox("Regularization Rate", [0.0001, 0.001, 0.01, 0.1]) if regularization in ["L1", "L2"] else 0
 with col7:
-    epoch_counter = st.empty()
-
-# Dataset Selection & Preprocessing
-st.subheader("Dataset Selection & Preprocessing")
-dataset_type = st.selectbox("Select Dataset", ["Binary Classification", "XOR", "Binary Spiral", "Binary Circles", "Regression 1", "Regression 2"])
-test_ratio = st.slider("Train-Test Split Ratio", 0.1, 0.5, 0.2, step=0.05)
-batch_size = st.slider("Batch Size", 4, 64, 16, step=2)
-
-data_generated = False
-X_train, X_test, y_train, y_test = None, None, None, None
-
-if st.button("Generate Dataset"):
-    if dataset_type == "Binary Classification":
-        X, y = make_classification(n_samples=1000, n_features=2, n_classes=2, random_state=42)
-    elif dataset_type == "XOR":
-        X, y = make_moons(n_samples=1000, noise=0.2, random_state=42)
-    elif dataset_type == "Binary Spiral":
-        X, y = make_circles(n_samples=1000, noise=0.2, factor=0.5, random_state=42)
-    elif dataset_type == "Regression 1":
-        X, y = make_regression(n_samples=1000, n_features=1, noise=5, random_state=42)
-    elif dataset_type == "Regression 2":
-        X = np.linspace(-1, 1, 1000).reshape(-1, 1)
-        y = X ** 3 + 0.1 * np.random.randn(1000, 1).flatten()
-    
-    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=test_ratio, random_state=42)
-    scaler = StandardScaler()
-    X_train = scaler.fit_transform(X_train)
-    X_test = scaler.transform(X_test)
-    data_generated = True
-    st.success("Dataset Generated Successfully")
-    st.subheader("Dataset Preview")
-    st.write("Features:")
-    st.write(X[:5])
-    st.write("Labels:")
-    st.write(y[:5])
-
-# Model Training
-if play and data_generated:
-    model = keras.Sequential()
-    model.add(layers.InputLayer(input_shape=(X_train.shape[1],)))
-    
-    for i in range(3):  # Defaulting to 3 layers
-        model.add(layers.Dense(10, activation=activation.lower(),
-                               kernel_regularizer=keras.regularizers.l1(reg_rate) if reg_type == "L1" else
-                               (keras.regularizers.l2(reg_rate) if reg_type == "L2" else None)))
-        model.add(layers.Dropout(0.2))
-    
-    model.add(layers.Dense(1, activation="sigmoid" if problem_type == "Classification" else "linear"))
-    model.compile(optimizer=keras.optimizers.Adam(learning_rate=learning_rate),
-                  loss="binary_crossentropy" if problem_type == "Classification" else "mse",
-                  metrics=["accuracy"] if problem_type == "Classification" else [])
-    
-    history = model.fit(X_train, y_train, epochs=epochs, batch_size=batch_size, verbose=0, validation_data=(X_test, y_test))
-    st.success("Model Training Complete")
-    
-    # Plot Training History
-    st.subheader("Training Progress")
-    fig, ax = plt.subplots(1, 2, figsize=(15, 6))
-    ax[0].plot(history.history['loss'], label='Training Loss')
-    ax[0].plot(history.history['val_loss'], label='Validation Loss')
-    ax[0].set_title("Loss Curve")
-    ax[0].set_xlabel("Epochs")
-    ax[0].set_ylabel("Loss")
-    ax[0].legend()
-    
-    if problem_type == "Classification":
-        ax[1].plot(history.history['accuracy'], label='Training Accuracy')
-        ax[1].plot(history.history['val_accuracy'], label='Validation Accuracy')
-        ax[1].set_title("Accuracy Curve")
-        ax[1].set_xlabel("Epochs")
-        ax[1].set_ylabel("Accuracy")
-        ax[1].legend()
+    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
+
+# ================= 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) =================
+st.sidebar.header("DATA")
+
+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 =================
+def generate_data():
+    if dataset_option == "Moons":
+        X, y = make_moons(n_samples=500, noise=noise)
+    elif dataset_option == "Circles":
+        X, y = make_circles(n_samples=500, noise=noise)
+    else:
+        theta = np.sqrt(np.random.rand(500)) * 2 * np.pi
+        r = theta
+        X = np.array([r * np.cos(theta), r * np.sin(theta)]).T
+        y = (theta % (2 * np.pi)) > np.pi
+    return X, y
+
+X, y = generate_data()
+
+# =================== DRAW NEURAL NETWORK ===================
+def draw_neural_network():
+    graph = graphviz.Digraph()
+
+    # Input Layer
+    graph.node("X1", "X₁", shape="circle", style="filled", fillcolor="lightblue")
+    graph.node("X2", "X₂", shape="circle", style="filled", fillcolor="lightblue")
+
+    prev_layer = ["X1", "X2"]
+
+    # 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
+
+    # Output Layer
+    graph.node("Output", "Output", shape="circle", style="filled", fillcolor="lightgreen")
+    for neuron in prev_layer:
+        graph.edge(neuron, "Output")
+
+    return graph
+
+# =================== DISPLAY DATA PLOT ===================
+st.sidebar.subheader("Dataset Visualization")
+fig, ax = plt.subplots()
+ax.scatter(X[:, 0], X[:, 1], c=y, cmap="plasma", edgecolors="k")
+st.sidebar.pyplot(fig)
+
+# =================== DISPLAY NEURAL NETWORK ===================
+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.")
+message.txt
+6 KB