the main script for this repo is in ted.py
. at the bottom are a few method calls you can uncomment to run different simple analyses:
surprise_analysis
collocates_analysis
laugh_rate_analysis
subdirectory data
contains files from this dataset:
https://www.kaggle.com/rounakbanik/ted-talks
ted_main.csv
with key fields:
- title
- tags
- url
transcripts.csv
with fields:
- transcript
- url