Exploring and Structuring Data

Data preparation is important to understand and analyze the data at hand, and structure it to facilitate this analysis. It is also an essential phase in the model creation process.

Data exploration allows you to:

  • Make data easier to interpret through filtering and grouping operations;

  • Reshape your data tables to facilitate subsequent analysis;

  • Join different data sources into a single table;

  • Detect and remove data and features you do not want to include in your model;

  • Enrich your tables by adding new features computed from the original data;

  • Manage missing information.

The data exploration operations you can perform in the Factory are: