app.py

import streamlit as st
import numpy as np
from sklearn.datasets import make_circles
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
from tensorflow.keras.optimizers import Adam
import matplotlib.pyplot as plt

# Set Streamlit page config
st.set_page_config(page_title="ML Playground", layout="centered")

st.title("🧠 TensorFlow Playground Clone")
st.markdown("Train a simple neural network on a synthetic dataset like circles")

# Sidebar controls
st.sidebar.header("Model Settings")

# Dataset
dataset = st.sidebar.selectbox("Dataset", ["Circle"])
n_samples = st.sidebar.slider("Number of Samples", 100, 1000, 300)

# Model settings
layers = st.sidebar.text_input("Network Shape (comma-separated)", "4,2")
activation = st.sidebar.selectbox("Activation", ["relu", "tanh", "sigmoid"])
learning_rate = st.sidebar.slider("Learning Rate", 0.001, 0.1, 0.03, step=0.001)
epochs = st.sidebar.slider("Epochs", 10, 200, 50)

# Generate dataset
X, y = make_circles(n_samples=n_samples, factor=0.5, noise=0.05, random_state=0)
X = StandardScaler().fit_transform(X)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5, random_state=42)

# Build model
model = Sequential()
layer_sizes = [int(n.strip()) for n in layers.split(",") if n.strip().isdigit()]
input_dim = X.shape[1]

# Input + hidden layers
model.add(Dense(layer_sizes[0], input_dim=input_dim, activation=activation))
for size in layer_sizes[1:]:
    model.add(Dense(size, activation=activation))

# Output layer
model.add(Dense(1, activation='sigmoid'))

optimizer = Adam(learning_rate=learning_rate)
model.compile(loss='binary_crossentropy', optimizer=optimizer, metrics=['accuracy'])

# Training
with st.spinner("Training model..."):
    history = model.fit(X_train, y_train, epochs=epochs, verbose=0, validation_data=(X_test, y_test))

# Plotting
fig, ax = plt.subplots()
ax.plot(history.history['accuracy'], label='Train Accuracy')
ax.plot(history.history['val_accuracy'], label='Val Accuracy')
ax.set_title("Training Progress")
ax.set_xlabel("Epoch")
ax.set_ylabel("Accuracy")
ax.legend()
st.pyplot(fig)

# Final Accuracy
train_acc = model.evaluate(X_train, y_train, verbose=0)[1]
test_acc = model.evaluate(X_test, y_test, verbose=0)[1]
st.success(f"✅ Final Training Accuracy: {train_acc:.2f}")
st.success(f"✅ Final Testing Accuracy: {test_acc:.2f}")