Update app.py

app.py

@@ -2,32 +2,70 @@ import pandas as pd
 import gradio as gr
 import plotly.graph_objects as go
 
-# ===============================
-# DATA
-# ===============================
+def make_demo_df():
+    return pd.DataFrame([
+        ["Paris", "E-Scooter", 4.6, 4.1, 0.12, 0.06],
+        ["Paris", "E-Bike", 4.3, 4.2, 0.14, 0.05],
+        ["Berlin", "E-Scooter", 4.9, 3.8, 0.05, 0.08],
+        ["Berlin", "E-Bike", 4.5, 4.0, 0.09, 0.06],
+        ["Madrid", "E-Scooter", 4.2, 4.3, 0.17, 0.05],
+        ["Warsaw", "Shared-EV", 5.0, 4.0, 0.07, 0.05],
+    ], columns=[
+        "city", "vehicle_type", "avg_final_price_eur",
+        "avg_rating", "avg_sentiment", "cancellation_rate"
+    ])
 
 def load_data():
     try:
         df = pd.read_csv("merged_summary.csv")
-    except:
-        df = pd.DataFrame([
-            ["Paris", "E-Scooter", 4.6, 4.1, 0.12, 0.06],
-            ["Berlin", "E-Bike", 4.5, 4.0, 0.09, 0.06],
-            ["Madrid", "E-Scooter", 4.2, 4.3, 0.17, 0.05],
-            ["Warsaw", "Shared-EV", 5.0, 4.0, 0.07, 0.05],
-        ], columns=[
-            "city", "vehicle_type", "avg_final_price_eur",
-            "avg_rating", "avg_sentiment", "cancellation_rate"
-        ])
-    return df
-
+    except Exception:
+        return make_demo_df()
+
+    df.columns = [str(c).strip() for c in df.columns]
+
+    rename_map = {}
+
+    for c in df.columns:
+        cl = c.lower().strip()
+
+        if cl == "city":
+            rename_map[c] = "city"
+        elif cl in ["vehicle_type", "ride_type", "vehicle", "vehicletype"]:
+            rename_map[c] = "vehicle_type"
+        elif cl in ["avg_final_price_eur", "final_price_eur", "avg_price", "avg_final_price", "price"]:
+            rename_map[c] = "avg_final_price_eur"
+        elif cl in ["avg_rating", "rating", "avg_star_rating", "star_rating"]:
+            rename_map[c] = "avg_rating"
+        elif cl in ["avg_sentiment", "sentiment", "compound", "vader_compound", "avg_compound_score"]:
+            rename_map[c] = "avg_sentiment"
+        elif cl in ["cancellation_rate", "cancel_rate", "avg_cancellation_rate"]:
+            rename_map[c] = "cancellation_rate"
+
+    df = df.rename(columns=rename_map)
+
+    required = [
+        "city",
+        "vehicle_type",
+        "avg_final_price_eur",
+        "avg_rating",
+        "avg_sentiment",
+        "cancellation_rate",
+    ]
+
+    for col in required:
+        if col not in df.columns:
+            if col in ["city", "vehicle_type"]:
+                df[col] = "Unknown"
+            else:
+                df[col] = 0.0
+
+    for col in ["avg_final_price_eur", "avg_rating", "avg_sentiment", "cancellation_rate"]:
+        df[col] = pd.to_numeric(df[col], errors="coerce").fillna(0)
 
-# ===============================
-# DASHBOARD
-# ===============================
+    return df
 
 def render_dashboard(city, vehicle):
-    df = load_data()
+    df = load_data().copy()
 
     if city != "All":
         df = df[df["city"] == city]
@@ -35,38 +73,54 @@ def render_dashboard(city, vehicle):
         df = df[df["vehicle_type"] == vehicle]
 
     if df.empty:
-        return "No data", go.Figure(), go.Figure(), go.Figure()
+        empty = go.Figure()
+        empty.update_layout(title="No data for selected filters")
+        return "### No data available", empty, empty, empty
 
     avg_price = df["avg_final_price_eur"].mean()
     avg_rating = df["avg_rating"].mean()
     avg_cancel = df["cancellation_rate"].mean()
 
     kpi = f"""
-    ### KPIs
-    - Avg Price: €{avg_price:.2f}
-    - Avg Rating: {avg_rating:.2f}
-    - Cancellation Rate: {avg_cancel:.2%}
-    """
+### KPIs
+- Avg Price: EUR {avg_price:.2f}
+- Avg Rating: {avg_rating:.2f}
+- Cancellation Rate: {avg_cancel:.2%}
+"""
+
+    seg = df.groupby(["city", "vehicle_type"], as_index=False).agg(
+        avg_final_price_eur=("avg_final_price_eur", "mean"),
+        avg_rating=("avg_rating", "mean"),
+        cancellation_rate=("cancellation_rate", "mean"),
+    )
 
     fig1 = go.Figure()
-    fig1.add_bar(x=df["city"], y=df["avg_final_price_eur"])
-    fig1.update_layout(title="Average Price")
+    fig1.add_bar(
+        x=[f"{r['city']} - {r['vehicle_type']}" for _, r in seg.iterrows()],
+        y=seg["avg_final_price_eur"]
+    )
+    fig1.update_layout(title="Average Price by City / Vehicle")
 
     fig2 = go.Figure()
-    fig2.add_bar(x=df["city"], y=df["avg_rating"])
-    fig2.update_layout(title="Average Rating")
+    fig2.add_bar(
+        x=[f"{r['city']} - {r['vehicle_type']}" for _, r in seg.iterrows()],
+        y=seg["avg_rating"]
+    )
+    fig2.update_layout(title="Average Rating by City / Vehicle")
+
+    city_agg = df.groupby("city", as_index=False).agg(
+        cancellation_rate=("cancellation_rate", "mean")
+    )
 
     fig3 = go.Figure()
-    fig3.add_bar(x=df["city"], y=df["cancellation_rate"])
-    fig3.update_layout(title="Cancellation Rate")
+    fig3.add_bar(
+        x=city_agg["city"],
+        y=city_agg["cancellation_rate"]
+    )
+    fig3.update_layout(title="Cancellation Rate by City")
 
     return kpi, fig1, fig2, fig3
 
-
-# ===============================
-# PREDICTION
-# ===============================
-
 def predict(price, discount):
     score = 0.5
     if price < 5:
@@ -80,23 +134,18 @@ def predict(price, discount):
         "label": "High" if score > 0.5 else "Low"
     }
 
-
-# ===============================
-# UI
-# ===============================
-
 with gr.Blocks() as demo:
     gr.Markdown("# Urban Mobility App")
 
     with gr.Tab("Dashboard"):
         city = gr.Dropdown(
-            ["All", "Paris", "Berlin", "Madrid", "Warsaw"],
+            ["All", "Paris", "Berlin", "Madrid", "Warsaw", "Turin"],
             value="All",
             label="City"
         )
 
         vehicle = gr.Dropdown(
-            ["All", "E-Scooter", "E-Bike", "Shared-EV"],
+            ["All", "E-Scooter", "E-Bike", "Shared-EV", "Bus-Connect"],
             value="All",
             label="Vehicle"
         )
@@ -123,6 +172,5 @@ with gr.Blocks() as demo:
 
         btn2.click(predict, inputs=[price, discount], outputs=out)
 
-
 if __name__ == "__main__":
     demo.launch()