https://github.com/tasninanika/callifornia-housing-price-prediction-svr

Support Vector Regression (SVR) is a type of Support Vector Machine used for predicting continuous values.
https://github.com/tasninanika/callifornia-housing-price-prediction-svr

matplotlib numpy pandas python3 scikit-learn seaborn svm-regression

Last synced: 3 months ago
JSON representation

Support Vector Regression (SVR) is a type of Support Vector Machine used for predicting continuous values.

• Host: GitHub
• URL: https://github.com/tasninanika/callifornia-housing-price-prediction-svr
• Owner: tasninanika
• Created: 2025-06-27T17:56:03.000Z (5 months ago)
• Default Branch: main
• Last Pushed: 2025-06-28T09:03:44.000Z (5 months ago)
• Last Synced: 2025-06-29T08:39:34.910Z (5 months ago)
• Topics: matplotlib, numpy, pandas, python3, scikit-learn, seaborn, svm-regression
• Language: Jupyter Notebook
• Homepage:
• Size: 158 KB
• Stars: 1
• Watchers: 0
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# 🏡 California Housing Price Prediction using SVR

This project uses **Support Vector Regression (SVR)** from `scikit-learn` to predict house prices based on features from the **California Housing Dataset**. The goal is to build a regression model that can estimate median house values across various districts in California.



  

  

  

  

  

  



---

## 🧠 What is Support Vector Regression?

**Support Vector Regression (SVR)** is a type of Support Vector Machine used for predicting continuous values. It tries to fit the best line or curve within a threshold (margin of tolerance) so that the majority of data points fall inside that margin.

---

## 🏘️ About the Dataset

We use the **California Housing Dataset** from `sklearn.datasets.fetch_california_housing`. It contains real estate data collected from California districts.

### 📌 Features:

| Column Name             | Description                                     |

|-------------------------|-------------------------------------------------|

| `MedInc`                | Median income in block                         |

| `HouseAge`              | Median house age in block                      |

| `AveRooms`              | Average number of rooms per household          |

| `AveBedrms`             | Average number of bedrooms per household       |

| `Population`            | Block population                               |

| `AveOccup`             | Average number of household members            |

| `Latitude`              | Block latitude                                 |

| `Longitude`             | Block longitude                                |

🎯 **Target Column**: `MedHouseVal` – Median house value (in $100,000s)

---

## 🚀 Project Workflow

1. Load the California Housing dataset using `fetch_california_housing()`

2. Split data into training and test sets

3. Train an SVR model using a kernel (like `'linear'` or `'rbf'`)

4. Predict on test data

5. Evaluate model performance using R² Score and MSE

6. Visualize predictions vs actual values