DATA CLEANING PROJECT IN SQL
---------------------------------------------------------------------------------------------------------
-------------------------------DATA CLEANING BASIC PROJECT
--------DATA MIGRATION------------TRANSFORMATION ON THE SOURCE SIDE---
---------------------------------------------------------------------------------------------------------
-2.1 Checking for duplicates.----------
--2.2 Dealing with missing data and Nulls
--2.3 Dealing with wrong categorical data
--2.4 Type conversion
---------------------------------------------------------------------------------------------------------
---------------------------------------------------------------------------------------------------------
CREATE TABLE EMPLOYEES
(
EMPLOYEE_ID INT,
EMPLOYEE_NAME VARCHAR(100),
DEPARTMENT_ID INT,
GENDER VARCHAR(10),
SALARY VARCHAR(100),--------------
HIRE_DATE DATE
)
--INSERT INTO EMPLOYEES VALUES(1,'JANVI',3,'F',80000,'2022-02-05')
--INSERT INTO EMPLOYEES VALUES(2,'HARSHIT',1,'m',100000,'2022-03-10')
--INSERT INTO EMPLOYEES VALUES(3,'HARSHIT',1,'M',100000,'2022-03-10')
--INSERT INTO EMPLOYEES VALUES(4,'NEHA',3,'F',75000,'2050-05-10')
--INSERT INTO EMPLOYEES VALUES(5,'Charlie',2,'Male',70000,'2022-05-12')
--INSERT INTO EMPLOYEES VALUES(6,'David',1,'F',68000,'2022-07-25')
--INSERT INTO EMPLOYEES VALUES(7,'Eva',3,'',60000,'2022-06-18')
--INSERT INTO EMPLOYEES VALUES(8,'Frank',NULL,'F',60000,'2022-09-05')
--INSERT INTO EMPLOYEES VALUES(9,'Richa',2,'Female',50000,'2022-02-20')
--INSERT INTO EMPLOYEES VALUES(10,'RIcha',2,'female',50000,'2022-02-20')
--INSERT INTO EMPLOYEES VALUES(11,'Meghal',1,'M',60000,'2022-01-15')
--INSERT INTO EMPLOYEES VALUES(12,'Meghal',1,'m',60000,'2022-01-15')
--INSERT INTO EMPLOYEES VALUES(13,'Meghal',1,'m',60000,'2022-01-15')
--INSERT INTO EMPLOYEES VALUES(14,'Sophie',2,NULL,44000,'2022-08-30')
CREATE TABLE DEPARTMENTS
(
DEPARTMENT_ID INT,
DEPARTMENT_NAME VARCHAR(100)
)
--INSERT INTO DEPARTMENTS VALUES(1,'Human Resources')
--INSERT INTO DEPARTMENTS VALUES(2,'Marketing')
--INSERT INTO DEPARTMENTS VALUES(3,'Finances')
---------------------------------------------------------------------------------------------------------
SELECT * FROM EMPLOYEES
--------FULLY TRANSFORMED TABLE AND YOU CAN LOAD THIS TABLE INTO THE FINAL DESTINATION TABLE.
---------------------------------------------------------------------------------------------------------
--2.1 Checking for duplicates.
--2.2 Dealing with missing data and Nulls
--2.3 Dealing with wrong categorical data
--2.4 Type conversion