final fix

app.py

@@ -25,6 +25,10 @@ MODEL_FEATURES = NUMERIC_FEATURES + CATEGORICAL_FEATURES
 
 def load_dataset() -> pd.DataFrame:
     df = pd.read_csv(DATA_PATH)
+    df["Make"] = df["Make"].apply(lambda v: v.upper())
+    df["Vehicle Class"] = df["Vehicle Class"].apply(
+        lambda v: v.upper().replace(": ", " - ")
+    )
     return df[MODEL_FEATURES + [TARGET]].copy()
 
 
@@ -87,7 +91,8 @@ def build_relationship_plot():
     ax.set_title("Fuel Consumption vs CO2 Emissions")
     ax.set_xlabel("Fuel Consumption Comb (L/100 km)")
     ax.set_ylabel("CO2 Emissions (g/km)")
-    ax.grid(alpha=0.2)
+    ax.set_facecolor("#fafafa")
+    ax.grid(alpha=0.2, linestyle="--", linewidth=0.6)
     ax.legend(title="Fuel Type", fontsize=8)
     fig.tight_layout()
     return fig
@@ -101,13 +106,46 @@ def build_vehicle_class_plot():
         .head(10)
     )
 
-    fig, ax = plt.subplots(figsize=(9, 5))
+    fig, ax = plt.subplots(figsize=(8, 5))
     ax.barh(class_df["Vehicle Class"], class_df[TARGET], color="#2a9d8f")
     ax.invert_yaxis()
     ax.set_title("Top 10 Vehicle Classes by Average CO2 Emissions")
     ax.set_xlabel("Average CO2 Emissions (g/km)")
     ax.set_ylabel("Vehicle Class")
-    ax.grid(axis="x", alpha=0.2)
+    ax.set_facecolor("#fafafa")
+    ax.grid(axis="x", alpha=0.2, linestyle="--", linewidth=0.6)
+    fig.tight_layout()
+    return fig
+
+
+def build_emissions_distribution_plot():
+    fig, ax = plt.subplots(figsize=(8, 5))
+    ax.hist(DATAFRAME[TARGET].dropna(), bins=30, color="#f4a261", edgecolor="white")
+    ax.set_title("Distribution of CO2 Emissions")
+    ax.set_xlabel("CO2 Emissions (g/km)")
+    ax.set_ylabel("Frequency")
+    ax.set_facecolor("#fafafa")
+    ax.grid(axis="y", alpha=0.2, linestyle="--", linewidth=0.6)
+    fig.tight_layout()
+    return fig
+
+
+def build_engine_size_plot():
+    plot_df = DATAFRAME[["Engine Size(L)", TARGET]].dropna()
+
+    fig, ax = plt.subplots(figsize=(8, 5))
+    ax.scatter(
+        plot_df["Engine Size(L)"],
+        plot_df[TARGET],
+        alpha=0.6,
+        color="#457b9d",
+        s=30,
+    )
+    ax.set_title("Engine Size vs CO2 Emissions")
+    ax.set_xlabel("Engine Size(L)")
+    ax.set_ylabel("CO2 Emissions(g/km)")
+    ax.set_facecolor("#fafafa")
+    ax.grid(alpha=0.2, linestyle="--", linewidth=0.6)
     fig.tight_layout()
     return fig
 
@@ -144,21 +182,20 @@ def predict_co2_emission(
 
 DESCRIPTION = f"""
 # CO2 Emissions Predictor
-This Hugging Face Space deploys **Model 4 - Parsimonious Mixed** from the notebook.
+This app predicts **CO2 emissions** for a vehicle.
 
-The app loads a compressed model artifact exported from the notebook and predicts
-**CO2 Emissions (g/km)** from:
+It uses the following inputs:
 - Engine Size(L)
 - Cylinders
 - Fuel Consumption Comb (L/100 km)
 - Vehicle Class
 - Fuel Type
 
-Current holdout metrics from the notebook-style split:
+Model performance on test data:
 - Test RMSE: {METRICS["Test RMSE"]}
 - Test R2: {METRICS["Test R2"]}
 
-The app also includes charts to visualize key relationships and trends in the dataset.
+The charts below help show simple patterns in the dataset.
 """
 
 
@@ -198,9 +235,9 @@ with gr.Blocks(title="CO2 Emissions Predictor") as demo:
             label="Fuel Type",
         )
 
-    predict_button = gr.Button("Predict CO2 Emission")
-    prediction = gr.Number(label="Predicted CO2 Emissions (g/km)")
-    summary = gr.Textbox(label="Prediction Summary", lines=7)
+    predict_button = gr.Button("Predict")
+    prediction = gr.Number(label="Predicted CO2 (g/km)")
+    summary = gr.Textbox(label="Result Summary", lines=7)
 
     predict_button.click(
         fn=predict_co2_emission,
@@ -214,15 +251,33 @@ with gr.Blocks(title="CO2 Emissions Predictor") as demo:
         outputs=[prediction, summary],
     )
 
-    gr.Markdown("## Data Insights")
+    gr.Markdown("## Charts")
     gr.Markdown(
-        "These charts highlight how fuel consumption relates to CO2 emissions "
-        "and which vehicle classes tend to produce the highest average emissions."
+        "- Distribution of CO2 emissions across the dataset.\n"
+        "- Relationship between fuel consumption and CO2 emissions.\n"
+        "- Relationship between engine size and CO2 emissions.\n"
+        "- Vehicle classes with the highest average CO2 emissions."
     )
 
     with gr.Row():
-        gr.Plot(value=build_relationship_plot, label="Relationship Plot")
-        gr.Plot(value=build_vehicle_class_plot, label="Trend Plot")
+        gr.Plot(
+            value=build_emissions_distribution_plot,
+            label="Distribution of CO2 Emissions",
+        )
+        gr.Plot(
+            value=build_relationship_plot,
+            label="Fuel Consumption vs CO2 Emissions",
+        )
+
+    with gr.Row():
+        gr.Plot(
+            value=build_engine_size_plot,
+            label="Engine Size vs CO2 Emissions",
+        )
+        gr.Plot(
+            value=build_vehicle_class_plot,
+            label="Top Vehicle Classes by CO2 Emissions",
+        )
 
     gr.Examples(
         examples=[

best_model.joblib

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f321bac88a9d81fccd916e6037b05275fe2dcdbbdda663f3556d569efed93cfb
-size 72379
+oid sha256:5f9c488e0a4cefc6abcd77439f154de629be98a1db2bf67b1b9778de7d895f8b
+size 69989

model4_parsimonious.joblib

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:12211b8d1aaf92f4520704370b799c5b6b10ef6c841a8d56b061795829d08731
-size 15105