Data Overview

The data used in this project exists in the ‘world_layoffs’ database that contains one table, ‘layoffs’, which consists of 2,361 records of global company employee layoffs. Each record is a specific period that the company had laid off a number of their employees. The ‘layoffs’ table is made up of nine columns.

Data Cleaning on Company's Layoff

My data cleaning process consists of four different steps to ensure the quality of data being worked with. This also helps maximize run-time efficiency. Removing any duplicate records. Standardizing data fields. Removing or filling in null or blank values. Eliminating any columns not required for analysis. Before performing any data manipulation to my original ‘layoffs’ table, I have created a staging table to work with. This table, ‘layoffs_staging’, is a direct copy of my original raw data table but, changes made to this data will not affect the root table. This step ensures that any mistakes or data deletion will not affect our original data in the ‘layoffs’ table..