commit

Author: PinkMean

EmployeeReport_DataCleaning/DATA CLEANING.sql

@@ -0,0 +1,51 @@
+-- Select all records from employeedata in the empreport
+SELECT * FROM empreport.employeedata; 
+
+-- If the uodate not working input this code but after back again this is for safety reasonn
+SET sql_safe_updates = 0; 
+
+
+-- Change column name from 'ID' to 'Employee_ID' and adjust data type
+ALTER TABLE employeedata
+CHANGE COLUMN ID Employee_ID VARCHAR(15) NULL;
+
+-- Display column details to check data types before altering
+DESCRIBE employeedata;
+
+SELECT Birth_Date from employeedata;
+
+-- Update and format 'Birth_Date' from MM/DD/YYYY and MM-DD-YYYY to YYYY-MM-DD
+UPDATE empreport.employeedata
+SET Birth_Date = CASE 
+	WHEN Birth_Date Like '%/%' THEN date_format(STR_TO_DATE(Birth_Date, '%m/%d/%Y'), '%Y/%m/%d')
+    WHEN Birth_Date Like '%-%' THEN date_format(STR_TO_DATE(Birth_Date, '%m-%d-%Y'), '%Y-%m-%d')
+ELSE NULL
+END;
+
+-- Modify 'Birth_Date' column to DATE type after ensuring data is properly formatted
+ALTER TABLE empreport.employeedata
+MODIFY COLUMN Birth_Date DATE;
+
+-- Add an 'Age' column calculated from 'Birth_Date'
+ALTER TABLE employeedata ADD COLUMN Age int;
+
+-- Calculate age based on 'Birth_Date' using current date
+UPDATE empreport.employeedata
+SET Age = TIMESTAMPDIFF(YEAR, Birth_Date, CURDATE());
+
+-- Display birth dates and corresponding ages to verify correctness
+SELECT Birth_Date, Age FROM empreport.employeedata;
+
+-- Find the youngest and oldest employees in the dataset
+SELECT 
+    MIN(Age) AS Youngest_Age,
+    MAX(Age) AS Oldest_Age
+FROM empreport.employeedata;
+
+-- Select employees over 60 years old to view their first name, age, and birth date
+SELECT First_Name, Age, Birth_Date 
+FROM empreport.employeedata 
+WHERE Age > 60;
+
+-- Re-enable safe updates after maintenance
+SET sql_safe_updates = 1;

EmployeeReport_DataVisulization/Average_Salary.csv

@@ -0,0 +1,9 @@
+Job_Title,Average_Salary
+"BI Data Analyst",77182
+"Business Data Analyst",69200
+"Compliance Data Analyst",45000
+"Data Analyst",94430
+"Financial Data Analyst",80300
+"Marketing Data Analyst",200000
+"Sales Data Analyst",60000
+"Staff Data Analyst",97499

EmployeeReport_DataVisulization/Company Size Salary.csv

@@ -0,0 +1,4 @@
+Company_Size,Minimum_Salary,Maximum_Salary,Average_Salary
+M,15000,166000,86720
+L,17000,180000,83958
+S,36000,200000,87889

EmployeeReport_DataVisulization/Employee Salary Analysis and Visualization.sql

@@ -0,0 +1,52 @@
+-- Employee Salary Analysis and Visualization
+
+-- Select all records from employeedata in the empreport
+SELECT * FROM empreport.employeedata;
+
+-- 1. What is the total number of employees, and how many are there in each job title?
+-- This helps to understand the distribution of employees across different roles.
+-- Use a Card and Matrix Chart to easily count the total number of employees and the count in each job title.
+SELECT Job_Title, COUNT(*) AS Employee_Count
+FROM empreport.employeedata
+GROUP BY Job_Title;
+
+-- 2. What is the average salary by Job title?
+-- This highlight compensation trends across different positions.
+SELECT Job_Title, ROUND(AVG(Salary), 0) AS Average_Salary
+FROM EmployeeData
+GROUP BY Job_Title
+ORDER BY Job_Title ASC;
+
+-- 3. What is the distribution of experience levels within the company?
+-- Understanding the distribution of experience can aid in planning for training and development.
+-- Use a Pie Chart to show the proportion of each experience level within the company, providing a quick view of the distribution.
+-- Use a Stacked Bar Chart to compare average salaries side-by-side for males and females across various job roles or departments.
+SELECT Experience_Level, COUNT(*) AS Count
+FROM EmployeeData
+GROUP BY Experience_Level;
+
+-- 4. What are the common work settings and their salaries?
+-- This can show if remote work settings influence salaries differently.
+-- Clustered Column Chart show average salaries for different work settings and show the count of employees in each setting.
+SELECT Work_Setting, ROUND (AVG(Salary), 0) AS Average_Salary, COUNT(*) AS Employee_Count
+FROM EmployeeData
+GROUP BY Work_Setting;
+
+-- 5. How does employee distribution vary by location?
+-- Identifying if certain locations have more employees can influence regional policies.
+-- Use a Treemap chart to show the distribution across different regions.
+SELECT Location, COUNT(*) AS Employee_Count
+FROM EmployeeData
+GROUP BY Location;
+
+
+-- 6. What is the salary range within each company size category?
+-- Examining how salary ranges differ between small, medium, and large companies.
+-- Display the distribution of salaries, highlighting the median, quartiles, and outliers within each company size category.
+SELECT Company_Size, 
+       MIN(Salary) AS Minimum_Salary, 
+       MAX(Salary) AS Maximum_Salary, 
+       ROUND(AVG(Salary), 0) AS Average_Salary
+FROM EmployeeData
+GROUP BY Company_Size;
+

EmployeeReport_DataVisulization/Employee Salary Report.pbix

@@ -0,0 +1,12 @@
+Location,Employee_Count
+"United States",37
+Poland,1
+Canada,2
+India,1
+Russia,1
+Ghana,1
+Nigeria,3
+"United Kingdom",1
+"Saudi Arabia",1
+Netherlands,1
+Kenya,1

EmployeeReport_DataVisulization/Employee Salary Report.pdf

@@ -0,0 +1,5 @@
+Experience_Level,Count
+Entry-level,18
+Senior,13
+Mid-level,17
+Executive,2

EmployeeReport_DataVisulization/Employee_Location.csv

@@ -0,0 +1,9 @@
+Job_Title,Employee_Count
+"Data Analyst",23
+"Business Data Analyst",5
+"Financial Data Analyst",5
+"Marketing Data Analyst",1
+"Staff Data Analyst",2
+"Sales Data Analyst",1
+"Compliance Data Analyst",2
+"BI Data Analyst",11

EmployeeReport_DataVisulization/Experience_Level.csv

@@ -0,0 +1,4 @@
+Work_Setting,Average_Salary,Employee_Count
+In-person,80169,17
+Remote,94964,28
+Hybrid,58300,5