Update app.py

app.py

@@ -1,28 +1,32 @@
 import gradio as gr
 import matplotlib.pyplot as plt
-import numpy as np
-from PIL import Image
+import pandas as pd
+import os
 import random
 
-# -------------------------------
-# Global Counters
-# -------------------------------
+# ===============================
+# GLOBAL VARIABLES
+# ===============================
 total_vehicles = 0
 ev_count = 0
-total_co2_saved = 0  # in kg
+total_co2_saved = 0
 
-# -------------------------------
-# CO2 Assumptions
-# -------------------------------
 DISTANCE_KM = 10
 CO2_PER_KM_PETROL = 0.150  # 150g = 0.15kg per km
 CO2_SAVED_PER_EV = DISTANCE_KM * CO2_PER_KM_PETROL  # 1.5 kg
 
+FEEDBACK_FILE = "feedback.csv"
 
-# -------------------------------
-# Dummy Vehicle Classifier
-# Replace this with your YOLO model
-# -------------------------------
+# Create CSV if not exists
+if not os.path.exists(FEEDBACK_FILE):
+    df_init = pd.DataFrame(columns=["Predicted_Label", "Feedback"])
+    df_init.to_csv(FEEDBACK_FILE, index=False)
+
+
+# ===============================
+# DUMMY VEHICLE CLASSIFIER
+# Replace with YOLO model
+# ===============================
 def classify_vehicle():
     vehicle_types = [
         "Car",
@@ -34,11 +38,11 @@ def classify_vehicle():
     return random.choice(vehicle_types)
 
 
-# -------------------------------
-# Dashboard Plot
-# -------------------------------
+# ===============================
+# DASHBOARD PLOT
+# ===============================
 def generate_dashboard():
-    global total_vehicles, ev_count, total_co2_saved
+    global total_vehicles, ev_count
 
     non_ev = total_vehicles - ev_count
 
@@ -53,36 +57,33 @@ def generate_dashboard():
     return fig
 
 
-# -------------------------------
-# Main Detection Function
-# -------------------------------
+# ===============================
+# DETECTION FUNCTION
+# ===============================
 def detect_image(image, threshold):
 
     global total_vehicles, ev_count, total_co2_saved
 
     if image is None:
-        return None, "Please upload an image.", \
+        return None, "Upload an image first.", \
                "### 🚘 Total Vehicles: 0", \
                "### ⚡ EV Vehicles: 0", \
                "### 📊 EV Adoption Rate: 0%", \
                "### 🌱 CO₂ Saved: 0 kg", \
-               generate_dashboard()
+               generate_dashboard(), ""
 
-    # Simulated detection
     vehicle_type = classify_vehicle()
 
     total_vehicles += 1
-
     co2_saved_this = 0
 
-    if vehicle_type.lower() == "electric vehicle":
+    if vehicle_type == "Electric Vehicle":
         ev_count += 1
         co2_saved_this = CO2_SAVED_PER_EV
         total_co2_saved += co2_saved_this
 
     ev_percent = (ev_count / total_vehicles) * 100
 
-    # Create dummy detection visualization
     fig, ax = plt.subplots()
     ax.imshow(image)
     ax.set_title(f"Detected: {vehicle_type}")
@@ -90,8 +91,8 @@ def detect_image(image, threshold):
 
     result_text = f"""
 Vehicle Type: {vehicle_type}
-Confidence Threshold Used: {threshold}
-CO₂ Saved (This Vehicle): {co2_saved_this:.2f} kg
+Confidence Threshold: {threshold}
+CO₂ Saved (This Detection): {co2_saved_this:.2f} kg
 """
 
     total_card = f"### 🚘 Total Vehicles: {total_vehicles}"
@@ -108,48 +109,174 @@ CO₂ Saved (This Vehicle): {co2_saved_this:.2f} kg
         ev_card,
         percent_card,
         co2_card,
-        dashboard_fig
+        dashboard_fig,
+        vehicle_type
     )
 
 
-# -------------------------------
-# Gradio UI
-# -------------------------------
+# ===============================
+# FEEDBACK FUNCTIONS
+# ===============================
+def save_feedback(predicted_label, feedback):
+
+    df = pd.read_csv(FEEDBACK_FILE)
+
+    new_row = {
+        "Predicted_Label": predicted_label,
+        "Feedback": feedback
+    }
+
+    df = pd.concat([df, pd.DataFrame([new_row])], ignore_index=True)
+    df.to_csv(FEEDBACK_FILE, index=False)
+
+    return "✅ Feedback Saved!"
+
+
+def calculate_metrics():
+
+    df = pd.read_csv(FEEDBACK_FILE)
+
+    if len(df) == 0:
+        return "No feedback data available.", None
+
+    tp = len(df[df["Feedback"] == "Correct"])
+    fp = len(df[df["Feedback"] == "Incorrect"])
+
+    total = len(df)
+
+    precision = tp / (tp + fp) if (tp + fp) != 0 else 0
+    recall = tp / total if total != 0 else 0
+
+    metrics_text = f"""
+Total Samples: {total}
+
+True Positives (Correct): {tp}
+False Positives (Incorrect): {fp}
+
+Precision: {precision:.2f}
+Recall: {recall:.2f}
+"""
+
+    fig, ax = plt.subplots()
+    matrix = [[tp, fp],
+              [0, 0]]
+
+    ax.imshow(matrix)
+    ax.set_xticks([0,1])
+    ax.set_yticks([0,1])
+    ax.set_xticklabels(["Correct", "Incorrect"])
+    ax.set_yticklabels(["Predicted"])
+
+    for i in range(2):
+        for j in range(2):
+            ax.text(j, i, matrix[i][j], ha="center", va="center")
+
+    ax.set_title("Confusion Matrix")
+
+    return metrics_text, fig
+
+
+def reset_database():
+    df = pd.DataFrame(columns=["Predicted_Label", "Feedback"])
+    df.to_csv(FEEDBACK_FILE, index=False)
+    return "🗑 Database Reset Successfully!"
+
+
+def download_feedback():
+    return FEEDBACK_FILE
+
+
+# ===============================
+# GRADIO UI
+# ===============================
 with gr.Blocks(theme=gr.themes.Soft()) as demo:
 
-    gr.Markdown("## 🚦 Smart Vehicle Classification & EV CO₂ Analytics Dashboard")
+    # ----------------------------
+    # DETECTION TAB
+    # ----------------------------
+    with gr.Tab("🚦 Detection System"):
 
-    slider = gr.Slider(0.3, 1.0, 0.5, step=0.05, label="Confidence Threshold")
+        gr.Markdown("## Smart Vehicle Classification & EV CO₂ Dashboard")
 
-    with gr.Row():
-        img_input = gr.Image(type="pil", label="Upload Vehicle Image")
-        img_output = gr.Plot(label="Detection Output")
+        slider = gr.Slider(0.3, 1.0, 0.5, step=0.05, label="Confidence Threshold")
 
-    result_box = gr.Textbox(label="Detection Result", lines=5)
+        with gr.Row():
+            img_input = gr.Image(type="pil", label="Upload Vehicle Image")
+            img_output = gr.Plot(label="Detection Output")
 
-    # Metric Cards
-    with gr.Row():
-        total_card = gr.Markdown("### 🚘 Total Vehicles: 0")
-        ev_card = gr.Markdown("### ⚡ EV Vehicles: 0")
-        percent_card = gr.Markdown("### 📊 EV Adoption Rate: 0%")
-        co2_card = gr.Markdown("### 🌱 CO₂ Saved: 0 kg")
+        result_box = gr.Textbox(label="Detection Result", lines=5)
 
-    dashboard_plot = gr.Plot(label="Analytics Dashboard")
+        with gr.Row():
+            total_card = gr.Markdown("### 🚘 Total Vehicles: 0")
+            ev_card = gr.Markdown("### ⚡ EV Vehicles: 0")
+            percent_card = gr.Markdown("### 📊 EV Adoption Rate: 0%")
+            co2_card = gr.Markdown("### 🌱 CO₂ Saved: 0 kg")
 
-    detect_btn = gr.Button("🔍 Detect Vehicle")
+        dashboard_plot = gr.Plot(label="Analytics Dashboard")
+
+        predicted_label_state = gr.State()
+
+        detect_btn = gr.Button("🔍 Detect Vehicle")
+
+        detect_btn.click(
+            fn=detect_image,
+            inputs=[img_input, slider],
+            outputs=[
+                img_output,
+                result_box,
+                total_card,
+                ev_card,
+                percent_card,
+                co2_card,
+                dashboard_plot,
+                predicted_label_state
+            ]
+        )
+
+        gr.Markdown("### Provide Feedback")
+
+        correct_btn = gr.Button("✔ Correct")
+        incorrect_btn = gr.Button("✘ Incorrect")
+        feedback_status = gr.Textbox(label="Feedback Status")
+
+        correct_btn.click(
+            fn=save_feedback,
+            inputs=[predicted_label_state, gr.State("Correct")],
+            outputs=feedback_status
+        )
+
+        incorrect_btn.click(
+            fn=save_feedback,
+            inputs=[predicted_label_state, gr.State("Incorrect")],
+            outputs=feedback_status
+        )
+
+    # ----------------------------
+    # ADMIN DASHBOARD TAB
+    # ----------------------------
+    with gr.Tab("📊 Admin Dashboard"):
+
+        gr.Markdown("## Model Evaluation Dashboard")
+
+        metrics_box = gr.Textbox(label="Evaluation Metrics", lines=10)
+        confusion_plot = gr.Plot()
+
+        evaluate_btn = gr.Button("Calculate Metrics")
+
+        evaluate_btn.click(
+            fn=calculate_metrics,
+            outputs=[metrics_box, confusion_plot]
+        )
+
+        gr.Markdown("### Download Feedback CSV")
+        download_btn = gr.File()
+        download_btn.click(fn=download_feedback, outputs=download_btn)
+
+        gr.Markdown("### Reset Database")
+        reset_btn = gr.Button("Reset Database")
+        reset_output = gr.Textbox()
+
+        reset_btn.click(fn=reset_database, outputs=reset_output)
 
-    detect_btn.click(
-        fn=detect_image,
-        inputs=[img_input, slider],
-        outputs=[
-            img_output,
-            result_box,
-            total_card,
-            ev_card,
-            percent_card,
-            co2_card,
-            dashboard_plot
-        ]
-    )
 
 demo.launch()