Update app.py

app.py

@@ -9,6 +9,18 @@ from sklearn.preprocessing import LabelEncoder
 import requests 
 from io import BytesIO
 import gdown
+from PIL import Image
+from transformers import AutoFeatureExtractor, AutoModelForImageClassification
+import torch
+from datetime import datetime
+
+# --- Set page configuration ---
+st.set_page_config(
+    page_title="Car Analysis Tool",
+    page_icon="🚗",
+    layout="wide",
+    initial_sidebar_state="expanded"
+)
 
 # --- Set page configuration ---
 st.set_page_config(
@@ -411,6 +423,39 @@ def style_metric_container(label, value):
         </div>
     """, unsafe_allow_html=True)
 
+def classify_image(image):
+    try:
+        model_name = "dima806/car_models_image_detection"
+        feature_extractor = AutoFeatureExtractor.from_pretrained(model_name)
+        model = AutoModelForImageClassification.from_pretrained(model_name)
+
+        inputs = feature_extractor(images=image, return_tensors="pt")
+        
+        with torch.no_grad():
+            outputs = model(**inputs)
+
+        logits = outputs.logits
+        predicted_class_idx = logits.argmax(-1).item()
+        predicted_class_label = model.config.id2label[predicted_class_idx]
+        score = torch.nn.functional.softmax(logits, dim=-1)[0, predicted_class_idx].item()
+
+        return [{'label': predicted_class_label, 'score': score}]
+    except Exception as e:
+        st.error(f"Classification error: {e}")
+        return None
+
+def get_car_overview(brand, model, year):
+    try:
+        prompt = f"Provide an overview of the following car:\nYear: {year}\nMake: {brand}\nModel: {model}\n"
+        response = openai.ChatCompletion.create(
+            model="gpt-3.5-turbo",
+            messages=[{"role": "user", "content": prompt}]
+        )
+        return response.choices[0].message['content']
+    except Exception as e:
+        st.error(f"Error getting car overview: {str(e)}")
+        return None
+
 def search_dataset(dataset, make, model=None):
     """
     Search the dataset for the specified make and model. If no model is provided,
@@ -662,17 +707,21 @@ def predict_with_ranges(inputs, model, label_encoders):
         'max_price': max_price
     }
 # --- Main Application ---
-def main(model, label_encoders, dataset):
-    col1, col2 = st.columns([2, 1])
+def main():
+    # Load necessary data and models
+    try:
+        original_data = load_datasets()
+        model, label_encoders = load_model_and_encodings()
+    except Exception as e:
+        st.error(f"Error loading data or models: {str(e)}")
+        st.stop()
 
-    with col1:
-        st.markdown("""
-            <h1 style='text-align: center;'>The Guide 🚗</h1>
-            <p style='text-align: center; color: #666; font-size: 1.1rem; margin-bottom: 2rem;'>
-                A cutting-edge data science project leveraging machine learning to detect which car would be best for you.
-            </p>
-        """, unsafe_allow_html=True)
-        
+    # Create tabs
+    tab1, tab2 = st.tabs(["Price Prediction", "Image Analysis"])
+
+    with tab1:
+        st.title("Car Price Prediction")
+        # [Previous prediction interface code]
         inputs, predict_button = create_prediction_interface()
         
         if predict_button:
@@ -685,24 +734,75 @@ def main(model, label_encoders, dataset):
                 - **Model Prediction**: ${prediction_results['predicted_price']:,.2f}
             """)
 
-        # Generate and display the graph
-        fig = create_market_trends_plot_with_model(model, inputs["make"], inputs, label_encoders)
-        if fig:
-            st.pyplot(fig)
+            # Generate and display the graph
+            fig = create_market_trends_plot_with_model(model, inputs["make"], inputs, label_encoders)
+            if fig:
+                st.pyplot(fig)
+
+    with tab2:
+        st.title("Car Image Analysis")
+        
+        # File uploader and camera input
+        uploaded_file = st.file_uploader("Choose a car image", type=["jpg", "jpeg", "png"])
+        camera_image = st.camera_input("Or take a picture of the car")
+
+        # Process the image
+        if uploaded_file is not None:
+            image = Image.open(uploaded_file)
+        elif camera_image is not None:
+            image = Image.open(camera_image)
         else:
-            st.warning("No graph generated. Please check your data or selection.")
+            image = None
 
-    with col2:
-        create_assistant_section(dataset)
+        if image is not None:
+            st.image(image, caption='Uploaded Image', use_container_width=True)
+            
+            # Classify the image
+            with st.spinner('Analyzing image...'):
+                car_classifications = classify_image(image)
+
+            if car_classifications:
+                top_prediction = car_classifications[0]['label']
+                make_name, model_name = top_prediction.split(' ', 1)
+                current_year = datetime.now().year
+
+                # Display results
+                col1, col2 = st.columns(2)
+                col1.metric("Identified Make", make_name)
+                col2.metric("Identified Model", model_name)
+
+                # Get car overview
+                overview = get_car_overview(make_name, model_name, current_year)
+                if overview:
+                    st.subheader("Car Overview")
+                    st.write(overview)
+
+                # Use the prediction model with the identified car
+                st.subheader("Price Analysis for Identified Car")
+                auto_inputs = {
+                    'year': current_year,
+                    'make': make_name.lower(),
+                    'model': model_name.lower(),
+                    'condition': 'good',  # Default values
+                    'fuel': 'gas',
+                    'odometer': 0,
+                    'title_status': 'clean',
+                    'transmission': 'automatic',
+                    'drive': 'fwd',
+                    'size': 'mid-size',
+                    'type': 'sedan',
+                    'paint_color': 'white'
+                }
+
+                # Get prediction for the identified car
+                prediction_results = predict_with_ranges(auto_inputs, model, label_encoders)
+                
+                st.markdown(f"""
+                    ### Estimated Price Range
+                    - **Minimum**: ${prediction_results['min_price']:,.2f}
+                    - **Maximum**: ${prediction_results['max_price']:,.2f}
+                    - **Predicted**: ${prediction_results['predicted_price']:,.2f}
+                """)
 
 if __name__ == "__main__":
-    try:
-        # Load data and model
-        original_data = load_datasets()
-        model, label_encoders = load_model_and_encodings()
-        
-        # Call the main function
-        main(model, label_encoders, original_data)
-    except Exception as e:
-        st.error(f"Error loading data or models: {str(e)}")
-        st.stop()
+    main()