Most Used Python Commands for Data Cleaning

Cleaning data isn't the most glamorous part of the data science....but it's the part that makes everything else possible.

Before you build fancy models or create beautiful dashboard , you need clean, reliable data.

That's where Pyhton (and especially Pandas) comes in handy. Here are some of the most - used commands I rely on working with messy datasets:

• Peek into your data with head(), info(), describe()

• Handle missing values using isnull(), dropna(), fillna()

• Transform and clean columns with drop_duplicates(), rename(), astype(), replace()

• Filter and select exactly what you need with loc[] and conditions

• Analyze with groupby(), sort_values(), value_counts()

• Merge, join, or append Dataframes to bring everything together

Next time you are stuck with messy data, keep this cheat sheet handy!