Create app.py

app.py

@@ -0,0 +1,317 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+import plotly.express as px
+import folium
+from streamlit_folium import st_folium
+import requests  
+# ----------------------------------------------------
+# 1. Load data
+# ----------------------------------------------------
+@st.cache_data
+def load_data():
+    daily_df = pd.read_csv("daily_data_2013_2024.csv", parse_dates=["date"])
+    monthly_df = pd.read_csv("monthly_data_2013_2024.csv")
+    return daily_df, monthly_df
+
+daily_data, monthly_data = load_data()
+
+# Pre-define your location dictionary so we can map lat/lon
+LOCATIONS = {
+    "Karagwe": {"lat": -1.7718, "lon": 30.9876},
+    "Masasi":  {"lat": -10.7167, "lon": 38.8000},
+    "Igunga":  {"lat": -4.2833, "lon": 33.8833}
+}
+
+# ----------------------------------------------------
+# 2. Streamlit UI Layout
+# ----------------------------------------------------
+st.title("Malaria & Dengue Outbreak Analysis (2013–2024)")
+
+st.sidebar.header("Filters & Options")
+
+# Choose disease type
+disease_choice = st.sidebar.radio("Select Disease", ["Malaria", "Dengue"])
+
+# Choose data granularity
+data_choice = st.sidebar.radio("Data Granularity", ["Monthly", "Daily"])
+
+# Let user filter location(s)
+location_list = list(LOCATIONS.keys())
+selected_locations = st.sidebar.multiselect("Select Location(s)", location_list, default=location_list)
+
+# For monthly data
+if data_choice == "Monthly":
+    year_min = int(monthly_data["year"].min())
+    year_max = int(monthly_data["year"].max())
+    year_range = st.sidebar.slider(
+        "Select Year Range", 
+        min_value=year_min, 
+        max_value=year_max,
+        value=(year_min, year_max)
+    )
+# For daily data
+else:
+    date_min = daily_data["date"].min()
+    date_max = daily_data["date"].max()
+    date_range = st.sidebar.date_input(
+        "Select Date Range", 
+        [date_min, date_max],
+        min_value=date_min,
+        max_value=date_max
+    )
+
+# ----------------------------------------------------
+# 3. Filter data based on user input
+# ----------------------------------------------------
+if data_choice == "Monthly":
+    df = monthly_data[monthly_data["location"].isin(selected_locations)].copy()
+    # Filter year range
+    df = df[(df["year"] >= year_range[0]) & (df["year"] <= year_range[1])]
+    # Create a "date" column for monthly data
+    df["date"] = pd.to_datetime(df["year"].astype(str) + "-" + df["month"].astype(str) + "-01")
+
+else:
+    df = daily_data[daily_data["location"].isin(selected_locations)].copy()
+    # Filter date range
+    df = df[
+        (df["date"] >= pd.to_datetime(date_range[0])) 
+        & (df["date"] <= pd.to_datetime(date_range[1]))
+    ]
+
+# ----------------------------------------------------
+# 4. Interactive Plotly Time-Series
+# ----------------------------------------------------
+st.subheader(f"{data_choice} {disease_choice} Risk & Climate Parameters")
+
+risk_col = "malaria_risk" if disease_choice == "Malaria" else "dengue_risk"
+
+if data_choice == "Monthly":
+    fig = px.line(
+        df, x="date", y=risk_col, color="location", 
+        title=f"{disease_choice} Risk Over Time ({data_choice})"
+    )
+    fig.update_layout(yaxis_title="Risk (0–1)")
+    st.plotly_chart(fig, use_container_width=True)
+    
+    col1, col2 = st.columns(2)
+    with col1:
+        fig_temp = px.line(
+            df, x="date", y="temp_avg", color="location",
+            title="Average Temperature (°C)"
+        )
+        st.plotly_chart(fig_temp, use_container_width=True)
+    with col2:
+        fig_rain = px.line(
+            df, x="date", y="monthly_rainfall_mm", color="location",
+            title="Monthly Rainfall (mm)"
+        )
+        st.plotly_chart(fig_rain, use_container_width=True)
+
+    # Show outbreak months
+    if disease_choice == "Malaria":
+        flag_col = "malaria_outbreak"
+    else:
+        flag_col = "dengue_outbreak"
+
+    outbreak_months = df[df[flag_col] == True]
+    if not outbreak_months.empty:
+        st.write(f"**Months with likely {disease_choice} outbreak:**")
+        st.dataframe(outbreak_months[[
+            "location","year","month","temp_avg","humidity","monthly_rainfall_mm",flag_col
+        ]])
+    else:
+        st.write(f"No months meet the {disease_choice} outbreak criteria in this selection.")
+
+else:
+    # Daily data
+    fig = px.line(
+        df, x="date", y=risk_col, color="location",
+        title=f"{disease_choice} Daily Risk Over Time (2013–2024)"
+    )
+    fig.update_layout(yaxis_title="Risk (0–1)")
+    st.plotly_chart(fig, use_container_width=True)
+    
+    col1, col2 = st.columns(2)
+    with col1:
+        fig_temp = px.line(
+            df, x="date", y="temp_avg", color="location",
+            title="Daily Avg Temperature (°C)"
+        )
+        st.plotly_chart(fig_temp, use_container_width=True)
+    with col2:
+        fig_rain = px.line(
+            df, x="date", y="daily_rainfall_mm", color="location",
+            title="Daily Rainfall (mm)"
+        )
+        st.plotly_chart(fig_rain, use_container_width=True)
+
+# ----------------------------------------------------
+# 5. Correlation Heatmap
+# ----------------------------------------------------
+st.subheader(f"Correlation Heatmap - {data_choice} Data")
+
+if data_choice == "Monthly":
+    subset_cols = ["temp_avg", "humidity", "monthly_rainfall_mm", "malaria_risk", "dengue_risk"]
+else:
+    subset_cols = ["temp_avg", "humidity", "daily_rainfall_mm", "malaria_risk", "dengue_risk"]
+
+corr_df = df[subset_cols].corr()
+fig_corr = px.imshow(
+    corr_df, text_auto=True, aspect="auto", 
+    title="Correlation Matrix of Weather & Risk"
+)
+st.plotly_chart(fig_corr, use_container_width=True)
+
+# ----------------------------------------------------
+# 6. Add Real-Time Weather in Folium Map + Outbreak Info
+# ----------------------------------------------------
+st.subheader("Interactive Map")
+st.markdown(
+    """
+    **Note**: We only have 3 locations for the CSV data.  
+    Markers now also show **real-time weather** from OpenWeather & an **outbreak** indicator.
+    """
+)
+
+# --- 6A. Helper function to get current weather from OpenWeather ---
+API_KEY = "c5b5c5ee6c497c6b1869ed926582a1ea"  # <-- Your OpenWeather API key
+
+def get_current_weather(lat, lon, api_key=API_KEY):
+    """
+    Fetch current weather data from OpenWeather for given lat/lon.
+    Returns a dict with {temp, humidity, description} if successful; else None.
+    """
+    url = f"https://api.openweathermap.org/data/2.5/weather?lat={lat}&lon={lon}&appid={api_key}&units=metric"
+    try:
+        resp = requests.get(url)
+        if resp.status_code == 200:
+            data = resp.json()
+            # Extract a few relevant fields:
+            current_temp = data["main"]["temp"]
+            humidity = data["main"]["humidity"]
+            weather_desc = data["weather"][0]["description"]
+            return {
+                "temp": current_temp,
+                "humidity": humidity,
+                "description": weather_desc
+            }
+        else:
+            return None
+    except Exception as e:
+        # In production, you'd handle logging or fallback here
+        return None
+
+# --- 6B. Create Folium Map ---
+m = folium.Map(location=[-6.0, 35.0], zoom_start=6)
+
+if disease_choice == "Malaria":
+    outbreak_flag_col = "malaria_outbreak"
+else:
+    outbreak_flag_col = "dengue_outbreak"
+
+# For each location, we show both the CSV-based stats AND real-time weather
+if data_choice == "Monthly":
+    for loc in selected_locations:
+        loc_info = LOCATIONS[loc]
+        loc_df = df[df["location"] == loc]
+        
+        if loc_df.empty:
+            continue
+        
+        # Averages from the CSV data
+        avg_risk = loc_df[risk_col].mean()
+        avg_temp = loc_df["temp_avg"].mean()
+        avg_rain = loc_df["monthly_rainfall_mm"].mean()
+        
+        # Check if there's an outbreak in the filtered monthly data
+        outbreak_count = loc_df[loc_df[outbreak_flag_col] == True].shape[0]
+        outbreak_status = "Yes" if outbreak_count > 0 else "No"
+        
+        # Fetch real-time weather
+        weather_now = get_current_weather(loc_info["lat"], loc_info["lon"], API_KEY)
+        
+        if weather_now:
+            rt_temp = weather_now["temp"]
+            rt_hum = weather_now["humidity"]
+            rt_desc = weather_now["description"]
+        else:
+            rt_temp = None
+            rt_hum = None
+            rt_desc = "N/A"
+        
+        # Build the popup HTML
+        popup_html = f"""
+        <b>{loc}</b><br/>
+        Disease: {disease_choice}<br/>
+        Outbreak Now (in selection)? {outbreak_status}<br/>
+        <br/>
+        <u>Historical/Forecasted Averages (CSV)</u><br/>
+        Avg Risk (selected range): {avg_risk:.2f}<br/>
+        Avg Temp (°C): {avg_temp:.2f}<br/>
+        Avg Rainfall (mm): {avg_rain:.2f}<br/>
+        <br/>
+        <u>Real-Time Weather (OpenWeather)</u><br/>
+        Current Temp (°C): {rt_temp if rt_temp else 'N/A'}<br/>
+        Current Humidity (%): {rt_hum if rt_hum else 'N/A'}<br/>
+        Conditions: {rt_desc}
+        """
+        
+        folium.Marker(
+            location=[loc_info["lat"], loc_info["lon"]],
+            popup=popup_html,
+            tooltip=f"{loc} ({disease_choice})"
+        ).add_to(m)
+
+else:
+    # Daily data
+    for loc in selected_locations:
+        loc_info = LOCATIONS[loc]
+        loc_df = df[df["location"] == loc]
+        
+        if loc_df.empty:
+            continue
+        
+        avg_risk = loc_df[risk_col].mean()
+        avg_temp = loc_df["temp_avg"].mean()
+        avg_rain = loc_df["daily_rainfall_mm"].mean()
+        
+        # Check outbreak
+        outbreak_count = loc_df[loc_df[outbreak_flag_col] == True].shape[0]
+        outbreak_status = "Yes" if outbreak_count > 0 else "No"
+        
+        # Real-time weather
+        weather_now = get_current_weather(loc_info["lat"], loc_info["lon"], API_KEY)
+        if weather_now:
+            rt_temp = weather_now["temp"]
+            rt_hum = weather_now["humidity"]
+            rt_desc = weather_now["description"]
+        else:
+            rt_temp = None
+            rt_hum = None
+            rt_desc = "N/A"
+        
+        popup_html = f"""
+        <b>{loc}</b><br/>
+        Disease: {disease_choice}<br/>
+        Outbreak Now (in selection)? {outbreak_status}<br/>
+        <br/>
+        <u>Historical/Forecasted Averages (CSV)</u><br/>
+        Avg Risk (selected range): {avg_risk:.2f}<br/>
+        Avg Temp (°C): {avg_temp:.2f}<br/>
+        Avg Rain (mm/day): {avg_rain:.2f}<br/>
+        <br/>
+        <u>Real-Time Weather (OpenWeather)</u><br/>
+        Current Temp (°C): {rt_temp if rt_temp else 'N/A'}<br/>
+        Current Humidity (%): {rt_hum if rt_hum else 'N/A'}<br/>
+        Conditions: {rt_desc}
+        """
+        
+        folium.Marker(
+            location=[loc_info["lat"], loc_info["lon"]],
+            popup=popup_html,
+            tooltip=f"{loc} ({disease_choice})"
+        ).add_to(m)
+
+# Render Folium map in Streamlit
+st_data = st_folium(m, width=700, height=500)