{
    "cells": [
        {
            "cell_type": "markdown",
            "metadata": {},
            "source": [
                "# ML Practice Series: Module 25 - Model Deployment with Streamlit\n",
                "\n",
                "A model in a notebook is just an experiment. A **deployed model** is a product! In this module, you'll learn to turn your ML models into interactive web applications using **Streamlit**.\n",
                "\n",
                "### Objectives:\n",
                "1. **Streamlit Basics**: Creating interactive UIs with pure Python.\n",
                "2. **Model Persistence**: Saving and loading models with `joblib`.\n",
                "3. **User Input**: Sliders, text boxes, and file uploads.\n",
                "4. **Real-Time Prediction**: Deploying your Iris classifier as a web app.\n",
                "\n",
                "---"
            ]
        },
        {
            "cell_type": "markdown",
            "metadata": {},
            "source": [
                "## 1. Training and Saving a Model\n",
                "\n",
                "First, let's train a simple classifier and save it to disk."
            ]
        },
        {
            "cell_type": "code",
            "execution_count": null,
            "metadata": {},
            "outputs": [],
            "source": [
                "from sklearn.datasets import load_iris\n",
                "from sklearn.ensemble import RandomForestClassifier\n",
                "import joblib\n",
                "\n",
                "# Load and train\n",
                "iris = load_iris()\n",
                "X, y = iris.data, iris.target\n",
                "\n",
                "model = RandomForestClassifier(n_estimators=100, random_state=42)\n",
                "model.fit(X, y)\n",
                "\n",
                "# Save the model\n",
                "joblib.dump(model, 'iris_model.pkl')\n",
                "print(\"Model saved as iris_model.pkl\")"
            ]
        },
        {
            "cell_type": "markdown",
            "metadata": {},
            "source": [
                "## 2. Creating a Streamlit App\n",
                "\n",
                "### Task 1: Build the App\n",
                "Create a file called `app.py` with the following Streamlit code. This app will:\n",
                "1. Load the saved model\n",
                "2. Accept user inputs (sepal/petal measurements)\n",
                "3. Make predictions in real-time"
            ]
        },
        {
            "cell_type": "code",
            "execution_count": null,
            "metadata": {},
            "outputs": [],
            "source": [
                "%%writefile app.py\n",
                "import streamlit as st\n",
                "import joblib\n",
                "import numpy as np\n",
                "\n",
                "# Load the model\n",
                "model = joblib.load('iris_model.pkl')\n",
                "\n",
                "st.title('🌸 Iris Species Predictor')\n",
                "st.write('Enter the flower measurements to predict the species!')\n",
                "\n",
                "# User inputs\n",
                "sepal_length = st.slider('Sepal Length (cm)', 4.0, 8.0, 5.8)\n",
                "sepal_width = st.slider('Sepal Width (cm)', 2.0, 4.5, 3.0)\n",
                "petal_length = st.slider('Petal Length (cm)', 1.0, 7.0, 4.0)\n",
                "petal_width = st.slider('Petal Width (cm)', 0.1, 2.5, 1.2)\n",
                "\n",
                "# Make prediction\n",
                "if st.button('Predict Species'):\n",
                "    features = np.array([[sepal_length, sepal_width, petal_length, petal_width]])\n",
                "    prediction = model.predict(features)\n",
                "    species = ['Setosa', 'Versicolor', 'Virginica']\n",
                "    \n",
                "    st.success(f'Predicted Species: **{species[prediction[0]]}**')\n",
                "    st.balloons()"
            ]
        },
        {
            "cell_type": "markdown",
            "metadata": {},
            "source": [
                "## 3. Running the App\n",
                "\n",
                "### Task 2: Launch Streamlit\n",
                "Open your terminal and run:\n",
                "```bash\n",
                "streamlit run app.py\n",
                "```\n",
                "\n",
                "Your browser will open with an interactive web app!"
            ]
        },
        {
            "cell_type": "markdown",
            "metadata": {},
            "source": [
                "## 4. Advanced Features\n",
                "\n",
                "### Task 3: File Upload\n",
                "Modify `app.py` to allow users to upload a CSV file and make batch predictions."
            ]
        },
        {
            "cell_type": "markdown",
            "metadata": {},
            "source": [
                "<details>\n",
                "<summary><b>Click to see Solution</b></summary>\n",
                "\n",
                "```python\n",
                "# Add this to your app.py\n",
                "import pandas as pd\n",
                "\n",
                "uploaded_file = st.file_uploader(\"Upload CSV for batch predictions\", type=\"csv\")\n",
                "\n",
                "if uploaded_file is not None:\n",
                "    df = pd.read_csv(uploaded_file)\n",
                "    predictions = model.predict(df)\n",
                "    df['Predicted Species'] = [species[p] for p in predictions]\n",
                "    st.write(df)\n",
                "```\n",
                "</details>"
            ]
        },
        {
            "cell_type": "markdown",
            "metadata": {},
            "source": [
                "--- \n",
                "### Deployment Mastered! \n",
                "You now know how to turn any ML model into a shareable web app.\n",
                "Next: **End-to-End ML Project Workflow**."
            ]
        }
    ],
    "metadata": {
        "kernelspec": {
            "display_name": "Python 3",
            "language": "python",
            "name": "python3"
        },
        "language_info": {
            "codemirror_mode": {
                "name": "ipython",
                "version": 3
            },
            "file_extension": ".py",
            "mimetype": "text/x-python",
            "name": "python",
            "nbconvert_exporter": "python",
            "pygments_lexer": "ipython3",
            "version": "3.12.7"
        }
    },
    "nbformat": 4,
    "nbformat_minor": 4
}