Combined Data Cleansing

Combined Data Cleansing
Description	It is a data preprocessing task to fix data quality issues and enhance data quality. You can perform several operations on any categorical or numerical data.
Why to use	Data Preprocessing to Remove Whitespaces Line Breaks Null Rows and Columns Numbers from Strings Alphabets from Numbers Punctuations and Special Characters Modify casing in case of Textual Data
When to use	When you want to remove any deformity or anomaly in the data.	When not to use	When the data is clean and already preprocessed
Prerequisites	-
Input	Unclean data	Output	Cleansed Data
Statistical Methods used	-	Limitations	-

The table below describes the various data cleansing methods and their corresponding sub-methods.

Method	Sub-Method	Description
Remove Unwanted Characters	Remove leading and trailing whitespaces	Remove any extra whitespace(s) before or after a string, word, or number.
	Remove tabs, line breaks, and duplicate whitespaces	Remove any extra tabs, line breaks, or repeated whitespaces in a string.
	Remove all whitespaces	Remove leading, trailing, in-between or duplicate whitespaces.
	Remove letters	Remove alphabet(s) from a string or a number
	Remove numbers	Remove a number(s) from strings or words
	Remove punctuations	Remove all punctuation marks from strings, words, or numbers
Modify Case	Upper Case	Convert all letters or words in a string to upper case.
	Lower Case	Convert all letters or words in a string to lower case.
	Title Case	Capitalize each word in a phrase or a sentence.
Replace Null Data	Replace with blanks (string columns)	Replace any null string value in a cell with a blank space. It renders an empty cell.
Replace Null Data	Replace with zero (numeric columns)	Replace any null value in a numerical column with zero (0).
Remove Null Data	Remove Null Rows	Remove all rows with a null value in any column
	Remove Null Rows	Only remove rows that have a null value in every column
	Remove Null Columns	Remove all columns with a null value in any row
	Remove Null Columns	Only remove columns that have a null value in every row