ISSUES_FIXED.md project_info.json README.md .gitignore COMPLETE_DOCUMENTATION.md convert_videos.py predict_price.py

README.md

# Housing Price Prediction Dataset

**RSK World - Free Programming Resources & Source Code**
**Website:** https://rskworld.in
**Contact:** help@rskworld.in, support@rskworld.in
**Phone:** +91 93305 39277
**Founder:** Molla Samser
**Designer & Tester:** Rima Khatun
**Created:** 2026

## Overview

This dataset includes property features like size, bedrooms, bathrooms, location coordinates, neighborhood data, and sale prices. Perfect for regression models, feature engineering, and real estate analytics.

## Dataset Description

### Features

- **Property Features:**
- `id`: Unique identifier for each property
- `bedrooms`: Number of bedrooms
- `bathrooms`: Number of bathrooms
- `sqft_living`: Square footage of living area
- `sqft_lot`: Square footage of lot
- `floors`: Number of floors
- `sqft_above`: Square footage above ground
- `sqft_basement`: Square footage of basement

- **Location Data:**
- `lat`: Latitude coordinate
- `long`: Longitude coordinate
- `zipcode`: ZIP code
- `neighborhood`: Neighborhood name

- **Quality Features:**
- `waterfront`: Whether property has waterfront view (0/1)
- `view`: Quality of view (0-4)
- `condition`: Overall condition (1-5)
- `grade`: Overall grade (1-13)
- `yr_built`: Year built
- `yr_renovated`: Year renovated (0 if never renovated)

- **Comparative Features:**
- `sqft_living15`: Average square footage of living area for 15 nearest neighbors
- `sqft_lot15`: Average square footage of lot for 15 nearest neighbors

- **Target Variable:**
- `price`: Sale price of the property

## File Structure

```
housing-prices/
├── housing_prices.csv # Main dataset in CSV format
├── housing_prices.json # Dataset in JSON format
├── data_analysis.py # Python script for data analysis
├── data_visualization.py # Python script for data visualization
├── housing_price_prediction.ipynb # Jupyter notebook for interactive analysis
├── requirements.txt # Python dependencies
├── README.md # This file
└── plots/ # Generated visualization plots (created when running scripts)
```

## Installation

1. Clone or download this repository
2. Install required dependencies:

```bash
pip install -r requirements.txt
```

## Usage

### Python Scripts

**Basic Analysis:**
```bash
python data_analysis.py # Basic data analysis and linear regression
python data_visualization.py # Create data visualizations
python validate_data.py # Validate dataset integrity
```

**Advanced Features (NEW in 2026):**
```bash
python advanced_models.py # Advanced ML models (XGBoost, LightGBM, etc.)
python feature_engineering.py # Advanced feature engineering
python hyperparameter_tuning.py # Hyperparameter tuning with Grid/Randomized Search
python model_comparison.py # Compare multiple models with visualization
```

### Jupyter Notebook

Open and run `housing_price_prediction.ipynb` for interactive analysis:
```bash
jupyter notebook housing_price_prediction.ipynb
```

## Technologies Used

- **CSV/JSON**: Data storage formats
- **Pandas**: Data manipulation and analysis
- **NumPy**: Numerical computing
- **Scikit-learn**: Machine learning framework (Linear Regression, Random Forest, Gradient Boosting, etc.)
- **XGBoost**: Advanced gradient boosting library
- **LightGBM**: Fast gradient boosting framework
- **Matplotlib**: Data visualization
- **Seaborn**: Statistical data visualization
- **Jupyter Notebook**: Interactive analysis
- **Joblib**: Model persistence
- **SciPy**: Scientific computing utilities

## Model Performance

The dataset is suitable for:
- **Basic Models**: Linear Regression, Ridge, Lasso, Elastic Net
- **Tree-based Models**: Decision Tree, Random Forest, Gradient Boosting
- **Advanced Models**: XGBoost, LightGBM (optional)
- **Feature Engineering**: Create derived features, handle outliers, scaling, PCA
- **Hyperparameter Tuning**: Grid Search, Randomized Search
- **Model Comparison**: Cross-validation, performance metrics comparison
- **Real Estate Analytics**: Price prediction, feature importance analysis

## Dataset Statistics

- **Total Records:** 50 properties
- **Features:** 20 columns
- **Price Range:** $180,000 - $1,225,000
- **Average Price:** ~$460,000

## Use Cases

1. **Price Prediction:** Build regression models to predict house prices
2. **Feature Engineering:** Explore and create new features
3. **Data Analysis:** Analyze relationships between features and prices
4. **Visualization:** Create plots and charts for data insights
5. **Educational:** Learn machine learning and data science concepts

## License

This dataset is provided by RSK World for educational and research purposes.

## Contact

For questions, support, or feedback:
- **Email:** help@rskworld.in, support@rskworld.in
- **Phone:** +91 93305 39277
- **Website:** https://rskworld.in

---

**Created by RSK World**
*Free Programming Resources & Source Code*

.gitignore

Raw Download

# Housing Price Prediction Dataset - .gitignore
# RSK World - Free Programming Resources & Source Code
# Website: https://rskworld.in
# Contact: help@rskworld.in, support@rskworld.in
# Phone: +91 93305 39277
# Founder: Molla Samser
# Designer & Tester: Rima Khatun

# Python
__pycache__/
*.py[cod]
*$py.class
*.so
.Python
env/
venv/
ENV/
build/
develop-eggs/
dist/
downloads/
eggs/
.eggs/
lib/
lib64/
parts/
sdist/
var/
wheels/
*.egg-info/
.installed.cfg
*.egg

# Jupyter Notebook
.ipynb_checkpoints
*.ipynb_checkpoints

# Visualization outputs
plots/
*.png
*.jpg
*.jpeg
*.pdf

# IDE
.vscode/
.idea/
*.swp
*.swo
*~

# OS
.DS_Store
Thumbs.db

# Data
*.zip

59 lines•714 B

text

predict_price.py

Raw Download

"""
Housing Price Prediction Dataset - Price Prediction Script
RSK World - Free Programming Resources & Source Code
Website: https://rskworld.in
Contact: help@rskworld.in, support@rskworld.in
Phone: +91 93305 39277
Founder: Molla Samser
Designer & Tester: Rima Khatun
Created: 2026
"""

import pandas as pd
import numpy as np
import joblib
import os
from sklearn.ensemble import RandomForestRegressor

class HousingPricePredictor:
    """Predict housing prices using trained models"""
    
    def __init__(self, model_path=None):
        """Initialize predictor with trained model"""
        if model_path and os.path.exists(model_path):
            self.model = joblib.load(model_path)
            print(f"Loaded model from: {model_path}")
        else:
            # Train a default model if no model provided
            print("Training default model...")
            self.train_default_model()
    
    def train_default_model(self):
        """Train a default Random Forest model"""
        df = pd.read_csv('housing_prices.csv')
        
        feature_columns = ['bedrooms', 'bathrooms', 'sqft_living', 'sqft_lot', 'floors',
                          'waterfront', 'view', 'condition', 'grade', 'sqft_above',
                          'sqft_basement', 'yr_built', 'yr_renovated', 'sqft_living15', 'sqft_lot15']
        
        current_year = 2026
        X = df[feature_columns].copy()
        X['house_age'] = current_year - X['yr_built']
        X['total_sqft'] = X['sqft_above'] + X['sqft_basement']
        
        y = df['price']
        
        self.model = RandomForestRegressor(n_estimators=100, random_state=42)
        self.model.fit(X, y)
        
        self.feature_columns = list(X.columns)
        print("Default model trained successfully!")
    
    def prepare_features(self, property_data):
        """Prepare features from property data dictionary"""
        current_year = 2026
        
        # Create feature array
        features = np.array([[
            property_data.get('bedrooms', 3),
            property_data.get('bathrooms', 2),
            property_data.get('sqft_living', 2000),
            property_data.get('sqft_lot', 8000),
            property_data.get('floors', 1),
            property_data.get('waterfront', 0),
            property_data.get('view', 0),
            property_data.get('condition', 3),
            property_data.get('grade', 7),
            property_data.get('sqft_above', 2000),
            property_data.get('sqft_basement', 0),
            property_data.get('yr_built', 2000),
            property_data.get('yr_renovated', 0),
            property_data.get('sqft_living15', 2000),
            property_data.get('sqft_lot15', 8000)
        ]])
        
        # Add engineered features
        house_age = current_year - features[0, 11]  # yr_built
        total_sqft = features[0, 9] + features[0, 10]  # sqft_above + sqft_basement
        
        features = np.append(features[0], [house_age, total_sqft])
        return features.reshape(1, -1)
    
    def predict(self, property_data):
        """Predict price for a property"""
        features = self.prepare_features(property_data)
        prediction = self.model.predict(features)[0]
        return prediction
    
    def predict_batch(self, properties_list):
        """Predict prices for multiple properties"""
        predictions = []
        for prop in properties_list:
            pred = self.predict(prop)
            predictions.append(pred)
        return predictions


def example_usage():
    """Example usage of the predictor"""
    print("="*60)
    print("Housing Price Prediction Example")
    print("RSK World - Free Programming Resources & Source Code")
    print("="*60)
    
    # Initialize predictor
    predictor = HousingPricePredictor()
    
    # Example property
    example_property = {
        'bedrooms': 3,
        'bathrooms': 2,
        'sqft_living': 2000,
        'sqft_lot': 8000,
        'floors': 2,
        'waterfront': 0,
        'view': 0,
        'condition': 3,
        'grade': 7,
        'sqft_above': 2000,
        'sqft_basement': 0,
        'yr_built': 2000,
        'yr_renovated': 0,
        'sqft_living15': 2000,
        'sqft_lot15': 8000
    }
    
    # Predict price
    predicted_price = predictor.predict(example_property)
    
    print(f"\nExample Property:")
    for key, value in example_property.items():
        print(f"  {key}: {value}")
    
    print(f"\nPredicted Price: ${predicted_price:,.2f}")
    print("\n" + "="*60)


if __name__ == "__main__":
    example_usage()

140 lines•4.6 KB

python

Theme Settings

Color Scheme

Display Options

Font Size

README.md