/Essex-CE888

Data Science & Decision Making Project Work

Primary LanguageJupyter Notebook

Essex-CE888

This repository stores work done for CE888-Data Science & Decision Making module.

Dependency

  • Python 2.7.14 :: Anaconda custom (64-bit)

  • Pandas 1.4.1

  • matplotlib: 2.1.0

Folder Structure

  • assignment1-seq2seq - contains the jupyter notebook for the sequence2sequence translation assignment. For the work Spider dataset is used. As part of the initial analysis the notebook contains details of exploratory data analysis done on the dataset.

  • Assignment-2 - contains the jupyter notebook for the sequence2sequence translation assignment 2. The notebook has the entire code which includes data preprocessing, simulation of different models. I understand that in the assignment we were asked to provide a python script instead and use jupyter notebook only for data illustrations but due to paucity of time I couldn’t convert the code into a python script. Pardon me for that.

  • Dataset - contains JSON files used as input for training and testing the model

Citation

The dataset is annotated by 11 college students from Yale University. Follow this link to their Github repository.