import streamlit as st
import pandas as pd
import plotly.express as px
import pydeck as pdk

# Set page layout and title
st.set_page_config(page_title="AI-Powered Air Quality Dashboard", layout="wide")

# CSS for custom styling
st.markdown("""
    <style>
        .card {
            background-color: #ffffff;
            padding: 20px;
            border-radius: 15px;
            box-shadow: 0 4px 12px rgba(0, 0, 0, 0.1);
            margin-bottom: 20px;
        }
        .header {
            font-size: 26px;
            font-weight: bold;
            color: #333333;
            text-align: center;
            margin-top: 10px;
            margin-bottom: 20px;
        }
        .subheader {
            font-size: 20px;
            color: #555555;
            font-weight: 600;
            margin-top: 10px;
            margin-bottom: 15px;
        }
        .recommendation {
            background-color: #f0f9ff;
            padding: 15px;
            border-radius: 10px;
            border-left: 5px solid #007bff;
            color: #007bff;
            font-weight: bold;
        }
    </style>
""", unsafe_allow_html=True)

# Sidebar for user interaction
st.sidebar.header("Air Quality Monitoring")
station_list = ["Louisville", "Lexington", "Richmond", "Elizabethtown"]
selected_station = st.sidebar.selectbox("Select AQI Station", station_list)

# Mock air quality data (can be replaced with real data)
aqi_data = {
    "Louisville": {"AQI": 50, "Pollutant": "Carbon Monoxide", "CO_ppb": 572.21},
    "Lexington": {"AQI": 150, "Pollutant": "Ozone", "O3_ppb": 70.00},
    "Richmond": {"AQI": 400, "Pollutant": "PM2.5", "PM25_ug/m3": 180.00},
    "Elizabethtown": {"AQI": 85, "Pollutant": "Sulfur Dioxide", "SO2_ppb": 15.00},
}

# Header
st.markdown("<div class='header'>AI-Powered Air Quality Dashboard</div>", unsafe_allow_html=True)

# Get selected station's data
station_data = aqi_data[selected_station]

# --- Cards Section ---
col1, col2, col3 = st.columns(3)

# Card 1: AQI Summary
with col1:
    st.markdown("<div class='card'>", unsafe_allow_html=True)
    st.metric(label="Air Quality Index (AQI)", value=station_data["AQI"])
    st.write(f"**Top Pollutant:** {station_data['Pollutant']}")
    st.write(f"**Concentration:** {station_data.get('CO_ppb', station_data.get('PM25_ug/m3', 'N/A'))} ppb/µg/m³")
    st.markdown("</div>", unsafe_allow_html=True)

# Card 2: AI Recommendation
with col2:
    st.markdown("<div class='card'>", unsafe_allow_html=True)
    st.write("<div class='subheader'>AI Recommendation</div>", unsafe_allow_html=True)
    
    # Generate recommendation based on AQI severity
    if station_data["AQI"] <= 50:
        recommendation = "The air quality is good. It's a great day to enjoy outdoor activities."
    elif station_data["AQI"] <= 100:
        recommendation = "The air quality is moderate. Sensitive groups may need to limit prolonged outdoor activities."
    elif station_data["AQI"] <= 150:
        recommendation = "Unhealthy for sensitive groups. Reduce outdoor exertion if you have heart or lung conditions."
    else:
        recommendation = "The air is hazardous. It's strongly recommended to stay indoors and use air purifiers."

    st.markdown(f"<div class='recommendation'>{recommendation}</div>", unsafe_allow_html=True)
    st.markdown("</div>", unsafe_allow_html=True)

# Card 3: Health Impact Insights
with col3:
    st.markdown("<div class='card'>", unsafe_allow_html=True)
    st.write("<div class='subheader'>Health Impact</div>", unsafe_allow_html=True)
    st.write("""
    - **General Population:** No immediate danger at low AQI levels.
    - **Sensitive Groups:** Individuals with heart or lung conditions may experience symptoms at higher AQI.
    """)
    st.markdown("</div>", unsafe_allow_html=True)

# --- Trends Visualization ---
st.subheader("AQI Trends Over Time")
trend_data = pd.DataFrame({
    "Date": ["2023-01-01", "2023-01-02", "2023-01-03", "2023-01-04"],
    "AQI": [station_data["AQI"] - 20, station_data["AQI"], station_data["AQI"] + 30, station_data["AQI"] - 10]
})

trend_chart = px.line(trend_data, x="Date", y="AQI", title=f"AQI Trend for {selected_station}")
trend_chart.update_traces(line=dict(color="#007bff"))
trend_chart.update_layout(plot_bgcolor="rgba(0,0,0,0)", paper_bgcolor="rgba(0,0,0,0)")
st.plotly_chart(trend_chart, use_container_width=True)

# --- Map Section ---
st.subheader("Air Quality Stations Map")
map_data = pd.DataFrame(
    [
        {"lat": 38.2527, "lon": -85.7585, "AQI": 50},  # Louisville
        {"lat": 38.0406, "lon": -84.5037, "AQI": 150},  # Lexington
        {"lat": 37.7479, "lon": -84.2947, "AQI": 400},  # Richmond
        {"lat": 37.6939, "lon": -85.8591, "AQI": 85},   # Elizabethtown
    ]
)

# Render the map with AQI points
aqi_map = pdk.Deck(
    map_style="mapbox://styles/mapbox/light-v9",
    initial_view_state=pdk.ViewState(
        latitude=38.0,
        longitude=-85.5,
        zoom=7,
        pitch=50,
    ),
    layers=[
        pdk.Layer(
            "ScatterplotLayer",
            data=map_data,
            get_position="[lon, lat]",
            get_radius=5000,
            get_fill_color="[255-AQI, 100, AQI/2, 150]",
            pickable=True,
        )
    ],
)

st.pydeck_chart(aqi_map)

# --- Footer ---
st.write("---")
st.write("Learn more about air quality and its impact [here](https://www.epa.gov/air-quality-index).")