Create app.py

app.py

@@ -0,0 +1,448 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+import plotly.express as px
+import plotly.graph_objs as go
+import folium
+from streamlit_folium import st_folium
+from datetime import timedelta
+
+# ----------------------------------------------------
+# 1. Load data
+# ----------------------------------------------------
+@st.cache_data
+def load_data():
+    # Load daily and monthly CSV from local files (or a URL if needed)
+    daily_df = pd.read_csv("daily_data_2013_2024.csv", parse_dates=["date"])
+    monthly_df = pd.read_csv("monthly_data_2013_2024.csv")
+    # If monthly_df also needs a 'date' column for plotting, you can create:
+    # monthly_df["date"] = pd.to_datetime(monthly_df["year"].astype(str) + "-" + monthly_df["month"].astype(str) + "-01")
+    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 to focus on
+disease_choice = st.sidebar.radio("Select Disease", ["Malaria", "Dengue"], index=0)
+
+# Choose data granularity
+data_choice = st.sidebar.radio("Data Granularity", ["Monthly", "Daily"], index=0)
+
+# 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, let user select a year range
+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),
+        step=1
+    )
+# For daily data, let user select a date range
+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":
+    # Subset monthly data for selected locations
+    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 plotting
+    df["date"] = pd.to_datetime(df["year"].astype(str) + "-" + df["month"].astype(str) + "-01")
+
+else:
+    # Subset daily data
+    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 (Original)
+# ----------------------------------------------------
+st.subheader(f"{data_choice} {disease_choice} Risk & Climate Parameters")
+
+# Decide which columns are relevant for risk
+risk_col = "malaria_risk" if disease_choice == "Malaria" else "dengue_risk"
+
+if data_choice == "Monthly":
+    # Plot a line chart of risk vs. date
+    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)
+    
+    # Temperature & Rainfall side-by-side
+    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:
+        # 'monthly_rainfall_mm' is total monthly rainfall
+        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 flags if focusing on monthly
+    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:
+    # For daily data, plot daily risk
+    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)
+    
+    # Temperature & Rainfall side-by-side
+    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 (Original)
+# ----------------------------------------------------
+st.subheader(f"Correlation Heatmap - {data_choice} Data")
+
+# Option to choose correlation method
+corr_method = st.selectbox("Correlation Method", ["pearson", "spearman"], index=0)
+
+# We'll pick relevant numeric columns
+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(method=corr_method)
+fig_corr = px.imshow(
+    corr_df, 
+    text_auto=True, 
+    aspect="auto",
+    title=f"Correlation Matrix of Weather & Risk ({corr_method.capitalize()})"
+)
+st.plotly_chart(fig_corr, use_container_width=True)
+
+# ----------------------------------------------------
+# 6. Interactive Map (Original)
+# ----------------------------------------------------
+st.subheader("Interactive Map")
+st.markdown(
+    """
+    **Note**: We only have 3 locations. Each marker popup shows some aggregated
+    stats for the displayed data range.
+    """
+)
+
+# Create a base map centered roughly in Tanzania
+m = folium.Map(location=[-6.0, 35.0], zoom_start=6)
+
+# Show monthly or daily aggregates in the popups
+if data_choice == "Monthly":
+    for loc in selected_locations:
+        loc_info = LOCATIONS[loc]
+        loc_df = df[df["location"] == loc]
+        if loc_df.empty:
+            continue
+        # Basic stats
+        avg_risk = loc_df[risk_col].mean()
+        avg_temp = loc_df["temp_avg"].mean()
+        avg_rain = loc_df["monthly_rainfall_mm"].mean()
+        
+        # Build popup HTML
+        popup_html = f"""
+        <b>{loc}</b><br/>
+        Disease: {disease_choice}<br/>
+        Avg Risk (in selection): {avg_risk:.2f}<br/>
+        Avg Temp (°C): {avg_temp:.2f}<br/>
+        Avg Rainfall (mm): {avg_rain:.2f}<br/>
+        """
+        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()
+        
+        popup_html = f"""
+        <b>{loc}</b><br/>
+        Disease: {disease_choice}<br/>
+        Avg Risk (in selection): {avg_risk:.2f}<br/>
+        Avg Temp (°C): {avg_temp:.2f}<br/>
+        Avg Rain (mm/day): {avg_rain:.2f}<br/>
+        """
+        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)
+
+# ----------------------------------------------------
+# 7. Additional Explorations (New Features)
+# ----------------------------------------------------
+st.header("Additional Explorations")
+
+###############################################################################
+# 7.1 Compare Malaria & Dengue Risk Side-by-Side (same chart) for the same data
+###############################################################################
+st.subheader("Compare Malaria & Dengue Risk Over Time")
+compare_both = st.checkbox("Compare Both Diseases on One Plot")
+
+if compare_both:
+    # We'll create two columns for Malaria & Dengue in the same DF subset
+    # Already have "malaria_risk" and "dengue_risk" in the data
+    # Filter the same df but plot them together:
+    
+    # Convert to "long" format for easy plotting with Plotly
+    # e.g. columns: date, location, disease, risk
+    if data_choice == "Monthly":
+        # We have date, location, malaria_risk, dengue_risk
+        df_long = df.melt(
+            id_vars=["date","location","temp_avg","humidity"],
+            value_vars=["malaria_risk","dengue_risk"],
+            var_name="disease",
+            value_name="risk"
+        )
+    else:
+        df_long = df.melt(
+            id_vars=["date","location","temp_avg","humidity"],
+            value_vars=["malaria_risk","dengue_risk"],
+            var_name="disease",
+            value_name="risk"
+        )
+    
+    # We only want to show locations user selected, but the df is already filtered
+    # so just plot:
+    title_str = "Malaria vs. Dengue Risk"
+    fig_compare = px.line(
+        df_long, 
+        x="date", 
+        y="risk", 
+        color="location", 
+        line_dash="disease",
+        title=title_str
+    )
+    fig_compare.update_layout(yaxis_title="Risk (0–1)")
+    st.plotly_chart(fig_compare, use_container_width=True)
+
+##################################################
+# 7.2 Scatter Matrix (Pairwise relationships)
+##################################################
+st.subheader("Scatter Matrix of Risk & Weather Parameters")
+
+# Let user choose which columns to include (besides the default subset)
+scatter_cols = st.multiselect(
+    "Choose additional columns to include in Scatter Matrix (besides risk & weather).",
+    ["temp_avg","humidity","monthly_rainfall_mm","daily_rainfall_mm","malaria_risk","dengue_risk"],
+    default=["temp_avg","humidity","malaria_risk","dengue_risk"]
+)
+
+if len(scatter_cols) < 2:
+    st.warning("Please select at least two columns to generate a scatter matrix.")
+else:
+    # Prepare data for scatter matrix
+    sm_df = df[scatter_cols].copy()
+    # For monthly vs daily, the rainfall column might differ
+    # If user selected 'monthly_rainfall_mm' but the data is daily, that column might not exist.
+    # So we can drop missing columns gracefully:
+    sm_df = sm_df.dropna(axis=1, how='all')
+    
+    # Using Plotly's scatter_matrix:
+    fig_sm = px.scatter_matrix(
+        sm_df,
+        dimensions=sm_df.columns,
+        title="Scatter Matrix",
+        color_discrete_sequence=["#636EFA"]  # Adjust color if you like
+    )
+    fig_sm.update_layout(width=800, height=800)
+    st.plotly_chart(fig_sm, use_container_width=True)
+
+##################################################
+# 7.3 Simple Time-Lag Correlation (Example)
+##################################################
+st.subheader("Time-Lag Correlation (Experimental)")
+
+st.markdown("""
+Here, you can experiment with a simple lag analysis. For example, check how 
+temperature or rainfall in previous weeks/months correlates with **current** 
+Malaria/Dengue risk.
+""")
+
+time_lag = st.slider("Select Lag (days) to shift weather parameters", min_value=0, max_value=60, value=0, step=5)
+
+# Example: Shift rainfall & temperature columns by the selected lag and see correlation with disease risk
+df_lag = df.copy()
+
+if data_choice == "Daily" and time_lag > 0:
+    # Shift daily rainfall/temperature backward by 'time_lag' days
+    df_lag = df_lag.sort_values("date")  # ensure sorted by date
+    df_lag["temp_avg_lag"] = df_lag.groupby("location")["temp_avg"].shift(time_lag)
+    df_lag["rain_lag"] = df_lag.groupby("location")["daily_rainfall_mm"].shift(time_lag)
+    # If we want to see correlation with today's risk
+    # we can drop rows with NaN in the lag columns
+    df_lag.dropna(subset=["temp_avg_lag","rain_lag"], inplace=True)
+
+elif data_choice == "Monthly" and time_lag > 0:
+    # Shift monthly rainfall & temp by 'time_lag' (in days) => must approximate?
+    # We'll interpret the slider as months if data is monthly. 
+    # But that might not be precise if "time_lag" is in days. For simplicity, we convert days -> months ~ 30 days
+    month_lag = time_lag // 30  # approximate conversion
+    if month_lag > 0:
+        df_lag = df_lag.sort_values("date")
+        df_lag["temp_avg_lag"] = df_lag.groupby("location")["temp_avg"].shift(month_lag)
+        df_lag["rain_lag"] = df_lag.groupby("location")["monthly_rainfall_mm"].shift(month_lag)
+        df_lag.dropna(subset=["temp_avg_lag","rain_lag"], inplace=True)
+
+# Now we compute correlation between risk_col and these lagged columns, if they exist
+if "temp_avg_lag" in df_lag.columns and "rain_lag" in df_lag.columns:
+    lag_corr_temp = df_lag[risk_col].corr(df_lag["temp_avg_lag"], method=corr_method)
+    lag_corr_rain = df_lag[risk_col].corr(df_lag["rain_lag"], method=corr_method)
+
+    st.write(f"**Correlation between {disease_choice} Risk and lagged Temperature**: {lag_corr_temp:.3f}")
+    st.write(f"**Correlation between {disease_choice} Risk and lagged Rainfall**: {lag_corr_rain:.3f}")
+else:
+    st.write("No lag columns or lag is set to 0. Increase the lag to see results.")
+
+##################################################
+# 7.4 Outbreak Statistics
+##################################################
+st.subheader("Outbreak Statistics")
+
+st.markdown("""
+This section gives you the **count** of outbreak periods based on user selection
+and some summary statistics.
+""")
+
+if disease_choice == "Malaria":
+    outbreak_flag_col = "malaria_outbreak"
+else:
+    outbreak_flag_col = "dengue_outbreak"
+
+# Summarize outbreak by location
+if outbreak_flag_col in df.columns:
+    outbreak_count_by_loc = df[df[outbreak_flag_col] == True].groupby("location").size().reset_index(name="outbreak_count")
+    st.write("**Number of outbreak instances (in current selection) by location:**")
+    st.dataframe(outbreak_count_by_loc)
+else:
+    st.write(f"No outbreak flag column found for {disease_choice}.")
+
+# Show average temperature, rainfall, humidity during outbreak vs non-outbreak
+if outbreak_flag_col in df.columns:
+    with st.expander("Compare Weather Averages During Outbreak vs. Non-Outbreak"):
+        outbreak_df = df[df[outbreak_flag_col] == True]
+        non_outbreak_df = df[df[outbreak_flag_col] == False]
+        
+        if not outbreak_df.empty:
+            avg_temp_outbreak = outbreak_df["temp_avg"].mean()
+            avg_hum_outbreak = outbreak_df["humidity"].mean()
+            if data_choice == "Daily":
+                avg_rain_outbreak = outbreak_df["daily_rainfall_mm"].mean()
+            else:
+                avg_rain_outbreak = outbreak_df["monthly_rainfall_mm"].mean()
+            
+            avg_temp_non = non_outbreak_df["temp_avg"].mean()
+            avg_hum_non = non_outbreak_df["humidity"].mean()
+            if data_choice == "Daily":
+                avg_rain_non = non_outbreak_df["daily_rainfall_mm"].mean()
+            else:
+                avg_rain_non = non_outbreak_df["monthly_rainfall_mm"].mean()
+
+            st.write(f"**Outbreak Periods** ({disease_choice}):")
+            st.write(f"- Avg Temperature: {avg_temp_outbreak:.2f} °C")
+            st.write(f"- Avg Humidity: {avg_hum_outbreak:.2f}%")
+            st.write(f"- Avg Rainfall: {avg_rain_outbreak:.2f} mm")
+
+            st.write(f"**Non-Outbreak Periods** ({disease_choice}):")
+            st.write(f"- Avg Temperature: {avg_temp_non:.2f} °C")
+            st.write(f"- Avg Humidity: {avg_hum_non:.2f}%")
+            st.write(f"- Avg Rainfall: {avg_rain_non:.2f} mm")
+        else:
+            st.write(f"No {disease_choice} outbreaks found in the current selection.")