README.md

Repo for the Kaggle "House Price Advanced"

• Problem definition
• Overview & Workflow
• Afterthoughts
• Resources that helped me learn

Problem definition

Train a regression model to predict house pricing using historical data. More details are described here.

Overview & Workflow

For this project I decided to use regression models, specifically random forests.

• EDA

  • using pipeline to handle missing values, transform numerical and categorical features, feature engineer, drop unwanted features:

  

• Model & learning curve

  

Afterthoughts

The most important thing I learned and applied in this project is using sklearn pipeline.

Resources

1. House Prices - all done via pipeline by Alexander Scarlat MD
2. ML Data Pipelines with Custom Transformers in Python by Sam T
3. End-to-end Machine Learning project on predicting housing prices using Regression by Gurupratap S Matharu
4. Feature Transformation for Machine Learning, a Beginners Guide by Rebecca Vickery
5. Strategies for working with discrete, categorical data by Dipanjan (DJ) Sarkar
6. Feature Engineering with sklearn Pipelines by FilipK
7. Transformation & Scaling of Numeric Features: Intuition by Manu Sharma
8. Categorical Data by Dipanjan (DJ) Sarkar
9. Normality Testing - Skewness and Kurtosis
10. Python Inheritance
11. Python Objects and Classes