alextzhao/psychedelicNLP

EAS 499: Senior Thesis for University of Pennsylvania; Dimensions of Non-ordinary Subjective Experiences: Natural Language Processing of Transcendent Experience Reports

Dimensions of Non Ordinary Experiences: Natural Language Processing of Transcendent Experience Reports

EAS 499: Senior Thesis

University of Pennsylvania, Fall 2019

Author: Alex Tianheng Zhao

alexzhao@seas.upenn.edu
Department of Computer and Information, School of Engineering and Applied Science, University of Pennsylvania
Department of Statistics, The Wharton School, University of Pennsylvania
🌐personal website, github, linkedin, ORCID

Max Mintz, PhD

mintz@cis.upenn.edu
Coordinator, Senior Thesis Program, Department of Computer and Information Science
University of Pennsylvania

Thesis Advisors

Chris Callison-Burch, PhD
ccb@upenn.edu
Department of Computer and Information Science (SEAS), University of Pennsylvania

Lyle Ungar, PhD
ungar@cis.upenn.edu
Department of Computer and Information Science; additional appoints in the Departments of Bioengineering (SEAS); Genomics and Computational Biology (Penn Medicine); Operations, Informations, and Decisions (Wharton); Psychology (SAS), University of Pennsylvania

Useful Links:

• Thesis Related:
  • Thesis Master Document
  • Thesis Scratch Paper
  • Thesis Codebase
  • Thesis Interactive Jupyter Notebook
• Helpful Tutorials and Tips
  • Excellent Series from Towards Data Science:
    • A Practitioner's Guide to Natural Language Processing (Part I): Processing & Understanding Text
    • Feature Engineering: Continuous Numeric Data
    • Feature Engineering: Categorical Data
    • Feature Engineering: Text Data Basics
    • Feature Engineering: Text Data Advanced
  • A few userful things to know about machine learning
  • LDA: Excellent Talk by Christine Doig on Topic Models
  • Markdown Cheatsheet
  • Using R and Python together; python, R dataframe interoperability; R and python pipelining
  • Translate dplyr to pandas
  • Basic pandas tutorial
  • Recommended dependencies for pandas
  • Pandas: Working with Text Data
  • sklearn reference: handy documentation, and provides broad-strokes ontology for machine learning techniques
  • Introduction to Machine Learning with sklearn
  • Sample pipeline for text feature extraction and evaluation: using sklearn
  • Comparison of performances of different classifiers: from sklearn, super cool
  • TODO: Citing sklearn
  • Contributing to sklearn
  • Manually Creating a table of contents
  • Automaticaly Creating Table of Contents
  • Python Data Science Handbook: Free Jupyter Notebooks
  • Configuring jupyter notebook with extensions
• Publishing my thesis:
  • Jupyter Notebook Viewer

• Notes to self:
  • ~/opt/anaconda3/lib/python3.7/site-packages/jupyter_contrib_nbextensions/nbextensions/toc2 path to nbextensions toc2
  • fixing nbextensions