A data profiling report consolidates exploratory data analysis into a shareable interactive HTML file. It summarizes a dataset’s structure, missingness, distributions, categorical variables, and correlations. section 17.4.2
A generated report can include:
- Dataset dimensions, variable types, missing values, complete rows, observations, and memory usage. section 17.4.2
- Visual views of structure, missingness, histograms, QQ plots, density plots, correlations, and categorical frequencies. section 17.4.2
- Grouped bar charts, such as categorical distributions organized by month. section 17.4.2
Profiling NBA betting data
After wrangling the oddsdf3 dataset, run create_report(oddsdf3) to generate a standalone interactive report. The dataset contains 1,230 rows, 14 columns, seven discrete columns, seven continuous columns, and no missing values. section 17.4.2
create_report(oddsdf3)
Run the DataExplorer report-generation command for the prepared dataset. section 17.4.2
