import streamlit as st

st.set_page_config(page_title="Random Forest", page_icon="🌲", layout="wide")

# Title
st.markdown("<h1 style='text-align:center;'>🌲 Random Forest Algorithm</h1>", unsafe_allow_html=True)

# Introduction
st.header("📚 What is Random Forest?")
st.markdown("""
Random Forest is a **supervised learning algorithm** used for both **classification** and **regression** tasks.

It works by building a large number of **decision trees** and combining their results to make a final prediction.  
Think of it like a group of people (trees) voting on an answer – this **reduces overfitting** and improves accuracy.
""")

# Real-world Uses
st.header("🎯 Where is Random Forest Used?")
st.markdown("""
- 🌾 Crop disease detection  
- 📊 Stock market predictions  
- 🏥 Medical diagnosis  
- 💳 Fraud detection  
- 👥 Customer churn prediction  
""")

# How it works
st.header("⚙️ How Random Forest Works")

with st.expander("Step 1: Bootstrapping (Sampling with Replacement)"):
    st.markdown("""
    - Randomly select multiple **subsets** of the dataset (with replacement).
    - Each subset is used to train a **separate decision tree**.
    """)

with st.expander("Step 2: Tree Building"):
    st.markdown("""
    - For each decision tree, choose a **random subset of features** at every split.
    - This randomness helps in creating **diverse trees**, reducing correlation.
    """)

with st.expander("Step 3: Aggregating Results"):
    st.markdown("""
    - **Classification**: Majority Voting (most common class wins)  
    - **Regression**: Average of all tree predictions  
    """)

# Visual Illustration
st.header("🌳 Visual Intuition")
st.image("https://upload.wikimedia.org/wikipedia/commons/7/76/Random_forest_diagram_complete.png", caption="Random Forest Structure", use_container_width=True)

# Advantages
st.header("✅ Why Use Random Forest?")
st.markdown("""
- Handles both classification and regression  
- Reduces overfitting compared to a single decision tree  
- Works well with large datasets and high-dimensional data  
- Robust to outliers and missing data  
""")

# Hyperparameters
st.header("🛠️ Key Hyperparameters")

with st.expander("🌲 n_estimators"):
    st.markdown("Number of trees in the forest. More trees = better performance, but more computation.")

with st.expander("🧮 max_depth"):
    st.markdown("Maximum depth of each tree. Controls overfitting.")

with st.expander("🔀 max_features"):
    st.markdown("Number of features to consider at each split (auto, sqrt, log2).")

with st.expander("🪓 min_samples_split"):
    st.markdown("Minimum samples required to split a node.")

with st.expander("🎯 criterion"):
    st.markdown("Function to measure the quality of a split (`gini` or `entropy` for classification).")

# Evaluation Metrics
st.header("📏 Evaluation Metrics")

with st.expander("✔️ Accuracy"):
    st.latex(r"Accuracy = \frac{TP + TN}{TP + TN + FP + FN}")
    st.markdown("Overall how often the model was correct.")

with st.expander("🎯 Precision"):
    st.latex(r"Precision = \frac{TP}{TP + FP}")
    st.markdown("Out of all predicted positives, how many were actually positive?")

with st.expander("🔍 Recall"):
    st.latex(r"Recall = \frac{TP}{TP + FN}")
    st.markdown("Out of all actual positives, how many did we correctly identify?")

with st.expander("⚖️ F1 Score"):
    st.latex(r"F1 = 2 \cdot \frac{Precision \cdot Recall}{Precision + Recall}")
    st.markdown("Harmonic mean of precision and recall.")

with st.expander("📉 ROC-AUC"):
    st.markdown("Measures the tradeoff between true positive rate and false positive rate.")

# Summary
st.header("📌 Summary")
st.markdown("""
- Random Forest is an **ensemble** of decision trees  
- Uses **bagging** and **feature randomness** to create a robust model  
- Great for **accuracy**, **stability**, and **generalization**  
- Handles missing data and avoids overfitting well  
- Best when you need strong baseline performance with minimal tuning  
""")

st.success("🎉 Now you’ve got a solid grip on Random Forest!")