The objective of this work is to predict the sale price of each house. For each Id in the test set, the value of the SalePrice variable is predicted. The data used consists of 79 explanatory variables that describe (almost) all aspects of residential houses in Ames, Iowa. In the jupyter notebook file, the following operations were carried out:
- EDA
- Treatment of missing values
- Dimensionality reduction
- Convert values
- Creation of new features
- Model algorithms
- Algorithm training
- Stacking
- Cross validation
- Model Selection
The following graphs emerge from the code in the repository:
Missing values: 
