/House_Price_Prediction-Vidhi_Bhatt

Primary LanguageJupyter NotebookMIT LicenseMIT

House Price Prediction

This project predicts the prices of houses located in the cities of the US, with the help of essential features.

Dataset

The dataset which is used here, is collected from Kaggle website. Here is the link of the dataset : https://www.kaggle.com/shree1992/housedata

Goal

The goal of this project is to make a prediction model which will predict the prices of the houses using different parameters.

What have I done?

  1. Importing all the required libraries. Check requirements.txt.
  2. Upload the dataset and the Google Collab file.
  3. Exploratory Data Analysis
  4. Data Processing
  5. Prediction Models
    • Linear Regression
    • Random Forest Regression
    • Lasso Regression
    • OLS Regression
    • Ridge Regression
    • Bayesian Regression
    • ElasticNet Regression
    • Model Comparison
  6. Conclusion

Libraries used

  1. Numpy
  2. Pandas
  3. Matplotlib
  4. Sklearn
  5. Seaborn

Exploratory Data Analysis

  1. Pairplot

  1. Distplot

  1. Average price of houses depending on no. of bedrooms

  1. Pearon Correaltion matrix

Conclusion

Models:

Model-Name Training Accuracy Testing Accuracy
Linear Regresssion 40% 52%
Random Forest 88% 15%
Lasso Regresssion 39% 52%
  • Therefore, Random Forest works the best for the following dataset.

Author

Code Contributed by Vidhi Bhatt, 2021 @VidhiBhatt01 #GWOC21