There are more than 250000 records with 14 features excluding target variable i.e. Total_Compensation.

Data Dictionary

OGC: Organization Group Code - Org Group is a group of Departments. For example, the Public Protection Org Group includes departments such as the Police, Fire, Adult Probation, District Attorney, and Sheriff.
OG: Organization Group names
DC: Department Code - Departments are the primary organizational unit used by the City and County of San Francisco. Examples include Recreation and Parks, Public Works, and the Police Department.
Dept: Department name
UC: Union Code - Unions represent employees in collective bargaining agreements. A job belongs to one union, although some jobs are unrepresented (usually temporarily).
Union: Union names
JF: Job Family - Job Family combines similar Jobs into meaningful groups.
Job: Job name
EI: Employee Identifier
Salaries: Salary of the employee
Overtime: Amounts paid to City employees working in excess of 40 hours per week.
H/D: Health/Dental - City-paid premiums to health and dental insurance plans covering City employees. To protect confidentiality as legally required, pro-rated citywide averages are presented in lieu of employee-specific health and dental benefits.
YT: Year Type - Fiscal (July through June) or Calendar (January through December)
Total_Compensation: The final compensation i.e. the sum of all salaries and benefits paid to City employees.

How to download and read the dataset?

The dataset can be downloaded from this link: https://drive.google.com/drive/folders/1pK1SfMozordl5JNiQn4qPd--8eu8bdE2?usp=sharing
After you have downloaded the dataset, you can read the dataset in your jupyter notebook using the read_csv() function. Provide the appropriate path of the data located on your machine. For example, if the data is located in the same location where you are executing your jupyter notebook, you can read the dataset as:
train_data = pd.read_csv('train_set.csv')

Saving Prediction File & Sample Submission

You can find more details on how to save a prediction file here: https://discuss.dphi.tech/t/how-to-submit-predictions/548

Sample submission: You should submit a CSV file with a header row and the sample submission can be found below:

Compensation

107525

11359

6121

9728

162448
.
.
.

Note that the header name should be ‘Compensation’ else it will throw an evaluation error.

Notebook Submission

Steps to follow to submit your notebook:

Go to the Notebook section on this challenge page
Click on the 'Upload Notebook' button on top left corner as shown in the image below:
Make sure to make the visibility of your notebook as 'public' while uploading the notebook.
Provide Notebook Title, Summary, add some tags, go to next, chose a file and click on Upload.

Acknowledgement

The data is sourced from DataSF (San Francisco). The San Francisco Controller's Office maintains a database of the salary and benefits paid to City employees.

Data Sprint #33: Employee Compensation

Challenge Starts

Registration Ends

Challenge Ends