Update app.py

app.py

@@ -1,59 +1,14 @@
 import streamlit as st
-import pandas as pd
-import openai
-import joblib
 from PIL import Image
-import matplotlib.pyplot as plt
-import numpy as np
-from huggingface_hub import hf_hub_download
 from transformers import AutoFeatureExtractor, AutoModelForImageClassification
 import torch
 from datetime import datetime
-from sklearn.preprocessing import LabelEncoder
-
-# Initialize label encoders for categorical variables
-make_encoder = LabelEncoder()
-model_encoder = LabelEncoder()
-condition_encoder = LabelEncoder()
-fuel_encoder = LabelEncoder()
-title_status_encoder = LabelEncoder()
-transmission_encoder = LabelEncoder()
-drive_encoder = LabelEncoder()
-size_encoder = LabelEncoder()
-type_encoder = LabelEncoder()
-paint_color_encoder = LabelEncoder()
-
-# Fit the encoders with some sample data (you may want to use your actual dataset for this)
-sample_data = {
-    'Make': ['Toyota', 'Honda', 'Ford', 'Chevrolet', 'Nissan'],
-    'model': ['Camry', 'Civic', 'F-150', 'Silverado', 'Altima'],
-    'condition': ['Used', 'New', 'Excellent', 'Good', 'Fair'],
-    'fuel': ['Gasoline', 'Diesel', 'Electric', 'Hybrid', 'CNG'],
-    'title_status': ['Clean', 'Salvage', 'Rebuilt', 'Lien', 'Missing'],
-    'transmission': ['Automatic', 'Manual', 'CVT', 'DCT', 'AMT'],
-    'drive': ['Fwd', 'Rwd', 'Awd', '4wd', 'Other'],
-    'size': ['Mid-Size', 'Full-Size', 'Compact', 'Sub-Compact', 'Crossover'],
-    'type': ['Sedan', 'SUV', 'Truck', 'Coupe', 'Van'],
-    'paint_color': ['White', 'Black', 'Silver', 'Red', 'Blue']
-}
-
-for feature, encoder in [('Make', make_encoder), ('model', model_encoder), ('condition', condition_encoder),
-                         ('fuel', fuel_encoder), ('title_status', title_status_encoder),
-                         ('transmission', transmission_encoder), ('drive', drive_encoder),
-                         ('size', size_encoder), ('type', type_encoder), ('paint_color', paint_color_encoder)]:
-    encoder.fit(sample_data[feature])
-
-# Dataset loading function with caching
-@st.cache_data
-def load_datasets():
-    try:
-        with st.spinner('Loading dataset...'):
-            original_data = pd.read_csv('CTP_Model1.csv', low_memory=False)
-            return original_data
-    except Exception as e:
-        st.error(f"Error loading dataset: {str(e)}")
-        raise e
+import openai
 
+# Initialize OpenAI API key
+openai.api_key = st.secrets["GPT_TOKEN"]
+
+# Function to classify the car image using pre-trained model
 def classify_image(image):
     try:
         # Load the model and feature extractor
@@ -83,6 +38,7 @@ def classify_image(image):
         st.error(f"Classification error: {e}")
         return None
 
+# Function to get an overview of the car using OpenAI
 def get_car_overview(brand, model, year):
     prompt = f"Provide an overview of the following car:\nYear: {year}\nMake: {brand}\nModel: {model}\n"
     response = openai.ChatCompletion.create(
@@ -91,61 +47,9 @@ def get_car_overview(brand, model, year):
     )
     return response.choices[0].message['content']
 
-def load_model_and_encodings():
-    try:
-        with st.spinner('Loading model...'):
-            model_content = hf_hub_download(repo_id="EdBoy2202/car_prediction_model", filename="car_price_modelv3.pkl")
-            model = joblib.load(model_content)
-
-            # Debug: Print the expected feature names
-            st.write("Model loaded successfully.")
-            st.write("Expected feature names:")
-            st.write(model.feature_names_in_)  # Display the feature names
-        return model
-    except Exception as e:
-        st.error(f"Error loading model: {str(e)}")
-        raise e
-
-def predict_price(model, brand, model_name, year):
-    # Create a dictionary with default values for the specified categories
-    input_data = {
-        'year': year,
-        'odometer': year * 12000,  # Estimate based on year and average annual mileage
-        'age': datetime.now().year - year,
-        'age_squared': (datetime.now().year - year) ** 2,
-        'mileage_per_year': 12000,
-        'Make': make_encoder.transform([brand])[0],
-        'model': model_encoder.transform([model_name])[0],
-        'condition': condition_encoder.transform(['Used'])[0],
-        'fuel': fuel_encoder.transform(['Gasoline'])[0],
-        'title_status': title_status_encoder.transform(['Clean'])[0],
-        'transmission': transmission_encoder.transform(['Automatic'])[0],
-        'drive': drive_encoder.transform(['Fwd'])[0],
-        'size': size_encoder.transform(['Mid-Size'])[0],
-        'type': type_encoder.transform(['Sedan'])[0],
-        'paint_color': paint_color_encoder.transform(['White'])[0]
-    }
-    
-    # Prepare the input for the model
-    input_df = pd.DataFrame([input_data])
-    
-    # Ensure all expected columns are present and in the correct order
-    expected_columns = ['year', 'odometer', 'age', 'age_squared', 'mileage_per_year', 'Make', 'model', 'condition', 'fuel', 'title_status', 'transmission', 'drive', 'size', 'type', 'paint_color']
-    input_df = input_df[expected_columns]
-    
-    # Predict the price
-    predicted_price = model.predict(input_df)
-    return predicted_price[0]
-
 # Streamlit App
 st.title("Auto Appraise")
-st.write("Upload a car image or take a picture to get its brand, model, overview, and expected price!")
-
-# Load model and encodings
-model = load_model_and_encodings()
-
-# Initialize OpenAI API key
-openai.api_key = st.secrets["GPT_TOKEN"]
+st.write("Upload a car image or take a picture to get its brand, model, and overview!")
 
 # Get the session state
 if 'image' not in st.session_state:
@@ -201,28 +105,7 @@ if st.session_state.image is not None:
         st.write("Car Overview:")
         st.write(overview)
 
-        # Interactive Price Prediction
-        st.subheader("Price Prediction Over Time")
-        selected_years = st.slider("Select range of years for price prediction", 
-                                     min_value=2000, max_value=2023, value=(2010, 2023))
-
-        years = np.arange(selected_years[0], selected_years[1] + 1)
-        predicted_prices = []
-
-        for year in years:
-            price = predict_price(model, make_name, model_name, year)
-            predicted_prices.append(price)
-
-        # Plotting the results
-        plt.figure(figsize=(10, 5))
-        plt.plot(years, predicted_prices, marker='o')
-        plt.title(f"Predicted Price of {make_name} {model_name} Over Time")
-        plt.xlabel("Year")
-        plt.ylabel("Predicted Price ($)")
-        plt.grid()
-        st.pyplot(plt)
-
     else:
         st.error("Could not classify the image. Please try again with a different image.")
 else:
-    st.write("Please upload an image or take a picture to proceed.")
+    st.write("Please upload an image or take a picture to proceed.")