🚗 Car Price Prediction with PyTorch

📖 Overview

This project predicts used car prices using a feedforward neural network regression model built in PyTorch.

• 📊 Neural Network Regression Model with Batch Normalization and Dropout for better training stability and generalization
• 🧩 Structured data preprocessing with numeric clipping, categorical encoding, and feature normalization
• ⚖️ Mean Squared Error (MSE) as the loss function
• 🧠 Adam optimizer for training
• 🔀 Train/Validation/Test split for robust evaluation
• 📈 Feature & target normalization using training statistics
• 💾 Saving/loading trained model and preprocessing artifacts for inference
• 🎨 Interactive Gradio Interface for real-time prediction

---

🖼️ Application Screenshot

Below is a preview of the Gradio Interface used for real-time prediction:

---

🧩 Libraries

• PyTorch – model, training, and inference
• pandas – data handling & preprocessing
• scikit-learn – ColumnTransformer, standardization, one-hot encoding
• matplotlib – plotting loss curves
• pickle – saving/loading feature transformer, statistics and trained model
• Gradio — interactive web interface for real-time model demos

---

⚙️ Requirements

• Python 3.13+
• Recommended editor: VS Code

---

📦 Installation

• Clone the repository

git clone https://github.com/hurkanugur/Car-Price-Predictor.git

• Navigate to the Car-Price-Predictor directory

cd Car_Price_Predictor

• Install dependencies

pip install -r requirements.txt

---

🔧 Setup Python Environment in VS Code

1. View → Command Palette → Python: Create Environment
2. Choose Venv and your Python version
3. Select requirements.txt to install dependencies
4. Click OK

---

📂 Project Structure

assets/
└── app_screenshot.png           # Screenshot of the application

data/
└── car_price_dataset.csv        # Raw used car data

model/
├── car_price_model.pth          # Trained PyTorch model
├── feature_transformer.pkl      # Fitted preprocessing transformer
└── statistics.pkl               # Preprocessing stats

src/
├── config.py                    # Paths, hyperparameters, split ratios
├── dataset.py                   # Data loading & preprocessing
├── device_manager.py            # Selects and manages compute device
├── train.py                     # Training pipeline
├── inference.py                 # Inference pipeline
├── model.py                     # Neural network definition
└── visualize.py                 # Training/validation plots

main/
├── main_train.py                # Entry point for training
└── main_inference.py            # Entry point for inference

requirements.txt                 # Python dependencies

---

📂 Model Architecture

Input → Linear(256) → BatchNorm → ReLU → Dropout(0.2)
      → Linear(128) → BatchNorm → ReLU → Dropout(0.2)
      → Linear(64)  → BatchNorm → ReLU → Dropout(0.1)
      → Linear(1)   → Output

---

📂 Train the Model

Navigate to the project directory:

cd Car_Price_Predictor

Run the training script:

python -m main.main_train

or

python3 -m main.main_train

---

📂 Run Inference / Make Predictions

Navigate to the project directory:

cd Car_Price_Predictor

Run the app:

python -m main.main_inference

or

python3 -m main.main_inference