GitHub - pfeyz/formulae-project

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 53 Commits
Absolute difference scores.ipynb		Absolute difference scores.ipynb
Count function words.ipynb		Count function words.ipynb
Manchester Analysis.ipynb		Manchester Analysis.ipynb
Morisita Example Distributions.ipynb		Morisita Example Distributions.ipynb
Morisita Function-Content Split.ipynb		Morisita Function-Content Split.ipynb
Morisita vs Cosine, Pearson, Spearman.ipynb		Morisita vs Cosine, Pearson, Spearman.ipynb
Morisita.ipynb		Morisita.ipynb
Pearson.ipynb		Pearson.ipynb
README.txt		README.txt
Spearman.ipynb		Spearman.ipynb
Top Bigram Variance.ipynb		Top Bigram Variance.ipynb
Top Types.ipynb		Top Types.ipynb
Zero counts.ipynb		Zero counts.ipynb
analyze.py		analyze.py
dataset.py		dataset.py
filtered_parent_ngrams.py		filtered_parent_ngrams.py
function-words.txt		function-words.txt
functionword_tagger.py		functionword_tagger.py
main.py		main.py
parent_child_ngrams.py		parent_child_ngrams.py
requirements.txt		requirements.txt
similarity.py		similarity.py
utils.py		utils.py

Repository files navigation

Setup:

  $ pip install -r requirements.txt

Usage:

see number of utterance per speaker:

  $ python main.py speakerstats 01a.xml 01b.xml
  INV 231
  CHI 846
  MOT 1224

output all bigrams in files:

  $ python main.py allgrams 01a.xml 01b.xml
  at Parent
  Parent Lastname
  Lastname 's
  's house
  house with
  with Child
  Child Lastname
  Lastname and
  ...

output all trigrams in files, limiting to specific speakers:

  $ python main.py allgrams -n 3 -s CHI,MOT 01a.xml 01b.xml
  that 's okay
  February first nineteen
  first nineteen eighty
  nineteen eighty four
  she just turned
  just turned two
  ...