Update app.py

app.py

@@ -1,23 +1,15 @@
 import streamlit as st
-
-# UI Inputs
-dataset = st.selectbox("Choose a Dataset", ["moons", "circles", "blobs"])
-learning_rate = st.number_input("Learning Rate", value=0.01, format="%.4f")
-activation = st.selectbox("Activation Function", ["relu", "sigmoid", "tanh"])
-split_ratio = st.slider("Train-Test Split Ratio", 0.5, 0.9, 0.7)
-batch_size = st.number_input("Batch Size", value=32, step=16)
-
-if st.button("Train Model"):
-    # Call your training and plotting function
-    train_and_visualize(dataset, learning_rate, activation, split_ratio, batch_size)
-
+import numpy as np
+import matplotlib.pyplot as plt
 from sklearn.datasets import make_moons, make_circles, make_blobs
 from sklearn.model_selection import train_test_split
 from sklearn.preprocessing import StandardScaler
 import tensorflow as tf
-from tensorflow.keras import models, layers
-import matplotlib.pyplot as plt
-import numpy as np
+from tensorflow.keras import layers, models
+
+# -------------------------------
+# Helper Functions
+# -------------------------------
 
 def generate_data(dataset, test_size):
     if dataset == "moons":
@@ -34,7 +26,7 @@ def build_model(activation, learning_rate):
     model = models.Sequential([
         layers.Dense(10, input_shape=(2,), activation=activation),
         layers.Dense(10, activation=activation),
-        layers.Dense(1, activation="sigmoid")
+        layers.Dense(1, activation='sigmoid')
     ])
     optimizer = tf.keras.optimizers.Adam(learning_rate=learning_rate)
     model.compile(optimizer=optimizer, loss='binary_crossentropy', metrics=['accuracy'])
@@ -45,11 +37,12 @@ def plot_decision_boundary(model, X, y):
     y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
     xx, yy = np.meshgrid(np.linspace(x_min, x_max, 200),
                          np.linspace(y_min, y_max, 200))
-    preds = model.predict(np.c_[xx.ravel(), yy.ravel()])
+    grid = np.c_[xx.ravel(), yy.ravel()]
+    preds = model.predict(grid)
     preds = preds.reshape(xx.shape)
 
-    plt.contourf(xx, yy, preds, alpha=0.5)
-    plt.scatter(X[:, 0], X[:, 1], c=y, cmap=plt.cm.RdBu)
+    plt.contourf(xx, yy, preds, cmap="RdBu", alpha=0.6)
+    plt.scatter(X[:, 0], X[:, 1], c=y, cmap="RdBu", edgecolors='white')
     plt.title("Decision Boundary")
     st.pyplot(plt.gcf())
     plt.clf()
@@ -57,6 +50,8 @@ def plot_decision_boundary(model, X, y):
 def plot_loss(history):
     plt.plot(history.history['loss'], label='Train Loss')
     plt.plot(history.history['val_loss'], label='Test Loss')
+    plt.xlabel('Epoch')
+    plt.ylabel('Loss')
     plt.legend()
     plt.title("Training vs Testing Error")
     st.pyplot(plt.gcf())
@@ -67,5 +62,23 @@ def train_and_visualize(dataset, lr, act, split, batch):
     model = build_model(act, lr)
     history = model.fit(X_train, y_train, epochs=50, batch_size=batch,
                         validation_data=(X_test, y_test), verbose=0)
-    plot_decision_boundary(model, np.vstack((X_train, X_test)), np.hstack((y_train, y_test)))
+    X_combined = np.vstack((X_train, X_test))
+    y_combined = np.concatenate((y_train, y_test))
+    plot_decision_boundary(model, X_combined, y_combined)
     plot_loss(history)
+
+# -------------------------------
+# Streamlit UI
+# -------------------------------
+
+st.title("🧠 Neural Network Playground")
+
+dataset = st.selectbox("Choose Dataset", ["moons", "circles", "blobs"])
+learning_rate = st.number_input("Learning Rate", value=0.01, format="%.4f")
+activation = st.selectbox("Activation Function", ["relu", "sigmoid", "tanh"])
+split_ratio = st.slider("Train-Test Split Ratio", 0.5, 0.9, 0.7)
+batch_size = st.number_input("Batch Size", value=32, step=16)
+
+if st.button("Train Model"):
+    with st.spinner("Training in progress..."):
+        train_and_visualize(dataset, learning_rate, activation, split_ratio, batch_size)