How to plot graphs & look for inconsistencies?

How to adjust the font of the axis labels? How to load the graphs in a documents (report, article et…)?
Data usually comes very dirty. What are the method to clean it from duplicates? inconsistency (person who has 20 years experience and is 24 years old etc…)?

1 Like

That is why data cleaning is a whole subject on its own. It can be a laborious process.

Use a combination of logical conditions, and the functions our lecturer mention supplied to you by pandas such as where or unique or nunique.

Study the pandas documentation to make your work easier

1 Like

One good way is to plot graphs & look for inconsistencies.

For example, if a 20-year old person claims to have 2 years of experience, you’ll be able to detect this easily using a scatter plot between the two columns.

Similarly, histograms and bar charts are useful for finding inconsistent values or distributions.