# Grading Rubric 

The bulk of the grade will be determined by the contents of your kernel notebook, including: (1) the creation of a single structured CSV file and data dictionary that contains all of the information from the plain text job postings; and (2) the quality of the insights and data-driven recommendations that you make to the City of LA.  

The possible elements contained within each job bulletin are described in Kaggle_data_dictionary.csv, Sample job class export template.csv, and Job_titles.csv. If competitors extract additional data elements, they should provide an updated data dictionary, which builds on the one provided but includes at a minimum greater detail about allowable values, additionally identified variables, data types, and explanatory notes as appropriate.


**Performances will be scored on:**

 - Accuracy (5 points)

 - Documentation (5 points)

 - Recommendation (5 points)


**Accuracy (5 points):**

 - Did the user convert the folder of job postings into a structured CSV?

 - Job class structures will be evaluated on how accurately each prepared field matches manually-structured fields for a randomized set of classes. 

**Documentation (5 points):**

 - Does the user follow good coding practices?

 - Useful comments

 - Description of coding language used/modules used

 - Are the modules open sourced? (prefer open sourced modules)

 - Documentation of script automation. (Fully-automated scripts are preferred)

 - Does the user document their methodology? 

 - Is there documentation about how the solution was evaluated?

 - Is there documentation about the pros and cons of their solution?


**Recommendation (5 points)**

 - Did the authors use the structured data to make an original insight?

 - Did the authors identify and communicate details about something that they discovered in the data?

 - Did the authors make an actionable recommendation to the City of LA?

 - Did the authors make effective use of data visualizations to communicate their recommendations to the City of LA? 

 - Do the recommendations give helpful solutions to one or more of the following issues?

 -  - (1) identify language that can bias the pool of applicants

 -  - (2) improve the diversity and quality of the applicant pool; and/or 

 -  - (3) increase the discoverability of promotional pathways