qlpsco / machine_learning_final_project Goto Github PK

Download the 2017, 2018, and 2019 data for anonymized LCA application here: https://www.foreignlaborcert.doleta.gov/performancedata.cfm (navidate to "Disclosure Data", then LCA programs).

Convert datasets into dataframes and pickle them with the following naming convention: df[YEAR].pkl (ie df2019.pkl).

Visualizations used in report can be found and generated in Histograms_cs.ipynb and Wage and SOC graphs.ipynb.

The Jupyter Notebook final_project_v2.ipynb has all of the preprocessing and modelling steps required for modelling. Run from the beginning.