Data Exploration

Which of the following states an accurate comparison between parts of data exploration and parts of data wrangling?

Incorrect. Feature selection is the second part of data exploration, which involves selecting features (variables, or columns) of interest. Filtration is a wrangling activity that involves selecting rows or observations rather than features.

Exactly! Feature engineering is the third part of data exploration, and it involves the creation of new features from existing features. This is quite similar to both the extraction and aggregation activities of data wrangling.

No, that's not right. EDA is the first step in data exploration. It involves summary statistics about variables, and correlations between variables. Extraction is a wrangling activity that involves calculating new features from existing features.

Exploratory data analysis is similar to extraction

Feature selection is similar to filtration

Feature engineering is similar to aggregation