Spaces:
Running
Running
| 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 | |
| # ---------------------------------------------------- | |
| # 1. Load 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 (like first day of month), 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"]) | |
| # 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, 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)) | |
| # 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 (1st of each month) | |
| # This can help create a time-series for Plotly | |
| 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 | |
| # ---------------------------------------------------- | |
| st.subheader(f"{data_choice} {disease_choice} Risk & Climate Parameters") | |
| # Decide which columns are relevant | |
| risk_col = "malaria_risk" if disease_choice == "Malaria" else "dengue_risk" | |
| if data_choice == "Monthly": | |
| # We'll plot a line chart of risk, temperature, and rainfall 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) | |
| # Optionally plot temperature / rainfall on another figure | |
| 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) | |
| # Similarly, temperature & daily rainfall | |
| 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") | |
| # 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() | |
| 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. Interactive Map (Folium) | |
| # ---------------------------------------------------- | |
| 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) | |
| # We'll show monthly or daily aggregates in the popups | |
| if data_choice == "Monthly": | |
| # For each location, let's gather monthly avg for the current df | |
| # Then we can show a simple summary in the popup | |
| for loc in selected_locations: | |
| loc_info = LOCATIONS[loc] | |
| loc_df = df[df["location"] == loc] | |
| if loc_df.empty: | |
| continue | |
| # Basic stats: average risk, average rainfall, etc | |
| 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) | |