import streamlit as st

# Page Title
st.title("📈 Exploratory Data Analysis (EDA)")

# Data Exploration Section
st.markdown("""
### 🔍 Data Exploration:
The dataset was analyzed to uncover patterns and relationships between features and depression status.

Key areas of focus included:
- Distribution of depression across genders  
- Impact of academic pressure on depression risk  
- Correlation between sleep duration and mental well-being  
- Relationship between financial stress and depression  
- Influence of CGPA and dietary habits on student mental health
""")

# Key Observations Section
st.markdown("""
### 📊 Key Observations:
- Students reporting **higher academic pressure** were more likely to show signs of depression  
- **Inadequate sleep** and **unbalanced diet** were common among students predicted as depressed  
- **Financial stress** and **low CGPA** had strong associations with depression  
- Female students showed slightly higher reported cases of depression in the dataset
""")

# Visualization Techniques Section
st.markdown("""
### 📉 Visualization Techniques:
- **Countplots** to examine category distributions like gender, class, and stress levels  
- **Boxplots** to explore spread and variation in numerical features (e.g., CGPA, Age)  
- **Heatmaps** to visualize feature correlations and identify multicollinearity

These insights helped refine feature selection and informed model-building decisions.
""")


if st.button("Next >>"):
    st.switch_page(r"pages/4 Feature Engineering.py")

if st.button("<< Back"):
    st.switch_page(r"pages/2 Data Understanding.py")