import streamlit as st

st.title("🛠️ Feature Engineering & Feature Selection")

st.markdown("""
## ✨ Feature Engineering:
Several transformations were applied to prepare the dataset for modeling:
- **Encoding:** Applied Ordinal Encoding for categorical variables.
- **Scaling:** Used RobustScaler to handle skewness and outliers.

---

## ✅ Selected Features:
The following features were selected for model training:
- Airline
- Source City
- Departure Time
- Stops
- Arrival Time
- Destination City
- Class
- Duration
- Days Left

---

## 🚫 Dropped Features:
- Unnecessary or redundant columns that did not add predictive power.

The processed dataset was then used to train and evaluate multiple regression algorithms, including KNN, Linear Regression, Decision Tree, Random Forest, and XGBoost.
""")

if st.button('Next'):
    st.switch_page('pages/5_Model_Building.py')

if st.button('Go to EDA'):
    st.switch_page('pages/3_EDA.py')