This repo includes 5 '.ipynb' file:
a. Absenteeism_project(Part 1) cleans the original data-Absenteeism_data.csv by Pandas, then stores the cleaned dataset in Absenteeism_preprocessed.csv
b. Absenteeism_project(Part 2) standardizes numerial variables & training model
c. Absenteeism_project(Part 3) simplifies the model by removing 3 irrelevant/less relavant variables, then saves the model for deployment by using pickle
d. Absenteeism_Project(Part 4) creates a module, then downloads as .py file for later use
e. Absenteeism_BI Analyst part uses new dataset-Absenteeism_new_data.csv to predict absentees, then stores the predictions in Absenteeism_predictions.csv for visualization in Tableau