import streamlit as st

# ⚙️ Model Building & Evaluation
st.markdown("""
## ⚙️ Model Building & Evaluation

### 🏗️ Model Building:

The classification model was built using the **KNN Classifier**, a robust ensemble learning method suitable for handling both numerical and categorical data.

**Model Pipeline:**

- **Preprocessing**:  
  - Applied **ColumnTransformer** to handle both categorical and numerical features.
  - Used **StandardScaler** for scaling continuous variables.
  - Encoded categorical columns using **OrdinalEncoder** (where appropriate).

- **Model**:  
  - Trained using **KNearestNeighbors Classifier** from `scikit-learn` with tuned hyperparameters.

---

### ✅ Model Training:

- The dataset was split into **training and testing sets** using an 80-20 split.
- The model was trained on the training set using the engineered features.
- Proper cross-validation techniques were used to avoid overfitting.

---

### 📊 Model Evaluation:

**Evaluation Metrics Used:**

- **Accuracy** – Measures the overall correctness of the model.  
- **Precision** – Measures how many predicted "High Risk" projects were actually high risk.  
- **Recall** – Indicates how many actual high-risk projects were correctly identified.  
- **F1 Score** – Harmonic mean of precision and recall for balanced performance.  
- **Confusion Matrix** – Visual breakdown of correct and incorrect classifications.

---

The model demonstrated **strong classification performance** on the test dataset, achieving good scores across all metrics.  
It was then saved as a **.pkl** file for deployment and integrated into the Streamlit app for real-time predictions.
""")


if st.button('Go to Deployment'):
    st.switch_page("pages/6 Deployment.py")

if st.button('Back'):
    st.switch_page("pages/4 Feature Engineering.py")