Update app.py

app.py

@@ -43,7 +43,7 @@ def load_data():
         # Sanitize Headers (removes hidden spaces)
         df.columns = df.columns.str.strip()
         
-        # Validation: Check if columns exist
+        # Validation
         required_cols = ['Power (MW)', 'Carbon Intensity', 'Annual Million tCO2']
         missing = [c for c in required_cols if c not in df.columns]
         if missing:
@@ -64,13 +64,28 @@ def load_data():
     df['Carbon Intensity'] = df['Carbon Intensity'].apply(clean_numeric)
     df['Annual Million tCO2'] = df['Annual Million tCO2'].apply(clean_numeric)
 
-    # --- MATH CHECK (Verification) ---
+    # --- CLEAN OWNER NAMES ---
+    # Remove "#confident", "#likely", etc.
+    if 'Owner' in df.columns:
+        df['Owner'] = df['Owner'].astype(str).str.split('#').str[0].str.strip()
+
+    # --- SIMPLIFY GRID STATUS ---
+    # Create a clean category for the filter (Grid vs Off-Grid vs Hybrid)
+    def simplify_status(status):
+        s = str(status).lower()
+        if 'off-grid' in s or 'gas' in s: return "Off-Grid / Fossil"
+        elif 'hybrid' in s or 'nuclear' in s: return "Hybrid / Nuclear"
+        elif 'grid' in s: return "Grid Connected"
+        else: return "Unknown"
+    
+    df['Simple_Connection'] = df['Grid Status'].apply(simplify_status)
+
+    # --- MATH CHECK ---
     # Formula: MW * 8760 hours * (Intensity kg/MWh / 1000 to get tonnes) / 1,000,000 to get Million Tonnes
     # We calculate this to double-check the CSV's reported numbers
     df['Calculated_Mt'] = (df['Power (MW)'] * 8760 * df['Carbon Intensity']) / 1e9
     
     # Use the Reported number, but normalize it (Handle the 13,093 vs 13.1 issue)
-    # If the number is > 100, it's likely in Kilotonnes, so divide by 1000
     df['Emissions_Mt'] = df['Annual Million tCO2'].apply(lambda x: x / 1000 if x > 100 else x)
     
     # --- Geocoding (Manual Overrides for missing Lat/Long) ---
@@ -86,7 +101,7 @@ def load_data():
         mask = df['Project'].astype(str).str.contains(key, case=False, na=False)
         df.loc[mask, ['Latitude', 'Longitude']] = coords
 
-    # Parse DMS coordinates (e.g., 42°40'28"N) if they exist
+    # Parse DMS coordinates
     def dms_to_dd(val):
         if isinstance(val, str) and '°' in val:
             try:
@@ -101,7 +116,6 @@ def load_data():
         df[col] = df[col].apply(dms_to_dd)
         df[col] = pd.to_numeric(df[col], errors='coerce')
 
-    # Drop rows that still have no location
     df = df.dropna(subset=['Latitude', 'Longitude'])
 
     # --- Enrichment for Tooltip ---
@@ -128,22 +142,26 @@ df = load_data()
 st.sidebar.header("🌍 Frontier AI Emissions")
 st.sidebar.markdown("Filter the map to analyze the carbon footprint of planned AI infrastructure.")
 
-# Filters
+# Filters: Connection Type (Simplified)
+# We sort them to ensure consistent order
+connection_options = sorted(df['Simple_Connection'].unique())
 grid_filter = st.sidebar.multiselect(
     "Connection Type",
-    options=df['Grid Status'].unique(),
-    default=df['Grid Status'].unique()
+    options=connection_options,
+    default=connection_options
 )
 
+# Filters: Owner (Cleaned)
+owner_options = sorted(df['Owner'].unique())
 owner_filter = st.sidebar.multiselect(
     "Owner",
-    options=df['Owner'].unique(),
-    default=df['Owner'].unique()
+    options=owner_options,
+    default=owner_options
 )
 
 # Apply filters
 filtered_df = df[
-    (df['Grid Status'].isin(grid_filter)) & 
+    (df['Simple_Connection'].isin(grid_filter)) & 
     (df['Owner'].isin(owner_filter))
 ]
 
@@ -158,7 +176,7 @@ st.sidebar.markdown("### 📊 Aggregate Impact")
 
 col1, col2 = st.sidebar.columns(2)
 col1.metric("Total Power", f"{total_power:.1f} GW", help="Total capacity of visible projects")
-col2.metric("Annual Emissions", f"{total_emissions:.1f} Mt", help="Million Tonnes CO2/year")
+col2.metric("Annual Emissions", f"{total_emissions:.1f} Mt", help="Million Tonnes CO2e/year")
 
 st.sidebar.markdown(f"""
 <div class="metric-card">
@@ -173,8 +191,8 @@ st.sidebar.markdown(f"**Avg Carbon Intensity:** {avg_intensity:.0f} kg/MWh")
 st.title("The Carbon Footprint of Frontier AI")
 st.markdown(
     "This map visualizes the annual emissions of major planned AI data centers. "
-    "**Bubble size** represents CO₂ emissions. **Color** indicates grid status "
-    "(<span style='color:#FF4136'><b>Red = Off-Grid/Gas</b></span>, <span style='color:#0074D9'><b>Blue = Grid</b></span>).",
+    "**Bubble size** represents CO₂e emissions. **Color** indicates grid status "
+    "(<span style='color:#FF4136'><b>Red = Off-Grid/Fossil</b></span>, <span style='color:#0074D9'><b>Blue = Grid Connected</b></span>).",
     unsafe_allow_html=True
 )
 
@@ -195,20 +213,19 @@ layer = pdk.Layer(
     get_line_color=[0, 0, 0],
 )
 
-# Tooltip
+# Tooltip (Updated for Data Center Name & Subscript)
 tooltip = {
     "html": """
-        <div style="font-family: sans-serif; padding: 10px; color: white;">
-            <h3 style="margin:0;">{Project}</h3>
-            <hr style="border-top: 1px solid #555;">
+        <div style="font-family: sans-serif; padding: 8px; color: white; max-width: 250px;">
+            <h4 style="margin:0; padding-bottom:5px;">{Data Center Name}</h4>
+            <hr style="border-top: 1px solid #555; margin: 5px 0;">
             <b>Owner:</b> {Owner}<br/>
-            <b>Location:</b> {Location}<br/>
             <b>Power:</b> {Power (MW)} MW<br/>
-            <b>Status:</b> {Grid Status}<br/>
+            <b>Status:</b> {Simple_Connection}<br/>
             <br/>
-            <b style="font-size: 1.1em; color: #ffcccb;">Annual Emissions: {Emissions_Mt} MtCO₂</b><br/>
-            <i style="font-size: 0.9em;">(Intensity: {Carbon Intensity} kg/MWh)</i>
-            <hr style="border-top: 1px dashed #555;">
+            <b style="font-size: 1.1em; color: #ffcccb;">Emissions: {Emissions_Mt} MtCO<sub>2</sub>e</b><br/>
+            <i style="font-size: 0.8em; color: #ccc;">(Intensity: {Carbon Intensity} kg/MWh)</i>
+            <hr style="border-top: 1px dashed #555; margin: 5px 0;">
             <b>🚗 Equal to:</b> {Cars_Equivalent_Millions} Million Cars<br/>
             <b>🏭 Equal to:</b> {Coal_Plants_Equivalent} Coal Power Plants
         </div>
@@ -217,13 +234,16 @@ tooltip = {
         "backgroundColor": "#1E1E1E",
         "border": "1px solid #333",
         "borderRadius": "8px",
-        "color": "white"
+        "color": "white",
+        "zIndex": "1000"
     }
 }
 
 # Render Map
+# FIX: Removed 'mapbox://' style to prevent black screen. 
+# Using map_style=None uses the default adaptable map.
 st.pydeck_chart(pdk.Deck(
-    map_style="mapbox://styles/mapbox/dark-v11", # Or use default 'dark' if no token
+    map_style=None, 
     initial_view_state=pdk.ViewState(
         latitude=39.8,
         longitude=-98.6,
@@ -238,6 +258,6 @@ st.pydeck_chart(pdk.Deck(
 st.markdown("---")
 st.caption(
     "**Methodology:** Emissions calculated based on publicly stated power capacity (MW) and regional/source-specific carbon intensity. "
-    "Car equivalents assume 4.6 metric tonnes CO₂ per passenger vehicle per year (EPA). "
-    "Coal plant equivalent assumes ~4.0 MtCO₂/year for a typical plant."
+    "Car equivalents assume 4.6 metric tonnes CO₂e per passenger vehicle per year (EPA). "
+    "Coal plant equivalent assumes ~4.0 MtCO₂e/year for a typical plant."
 )