This repository contains all the final codes that were used to produce the results.
00a_ExtractDump.ipynb - Contains Webscrapping code
00b_Parse HTML.ipynb - Contains code to parse HTML Scrapped
00c_Cleanup Missing Values.ipynb - Contains code to clean up missing values
01_data_prep_scrapped_data.ipynb - Contains data prep and feature engineering codes
02a_Exploratory-Full Data.ipynb - Contains the exploratory analysis for full data set (Women's category)
02b_Exploratory-womens 5 core.ipynb - Contains exploratory analysis for 5-core data set (Women's category)
03a_Advanced_BPR_Women_5core.ipynb - Contains the HBPR implementation and evaluation on Women's 5 core data
03b_Advanced_BPR_Cellphones_5core.ipynb - Contains the HBPR implementation and evaluation on Cellphone 5 core data
04_model_code - TensorFlow implementations
Capstone Poster.pdf: Final deliverable - Poster with summary of the project
Capstone Presentation.pdf: Final deliverable - Final presentation presented
Capstone Final Report.pdf: Final deliverable - Final report of the project
All final and intermediate files as well as presentations and reports are stored in a shared teamdrive ala Google Drive. The name of the teamdrive is Sharknado. Google Team Drives do not allow for linking directly and appear within a user's Google Drive once access is granted. Access Requests can be granted by any Sharknado team member as well as Dr. Ilkay Altantas (altintas@sdsc.edu) and Kevin Coakley (kcoakley@eng.ucsd.edu)