Merge pull request #58 from nickduran/update-newversion-branch

Update newversion branch

.gitignore

@@ -8,7 +8,8 @@ dist
 *.ipynb_checkpoints
 *.pyc
 MANIFEST
-doc/_build
-doc/modules/generated
+docs/
 *.DS_Store
 build/
+sandbox/
+venv/

MANIFEST.in

@@ -1,6 +1,32 @@
-recursive-include *.py
-recursive-include *.txt
-recursive-include align *.md
-graft doc
-graft doc/_static
-graft doc/_templates
+# include src/align/data/*.txt
+# include src/align/data/*.md
+# recursive-include *.py
+# recursive-include *.txt
+# recursive-include align *.md
+# graft doc 
+# graft doc/_static
+# graft doc/_templates
+
+
+# added by check-manifest
+# recursive-include doc *.bat
+# recursive-include doc *.buildinfo
+# recursive-include doc *.css
+# recursive-include doc *.doctree
+# recursive-include doc *.eot
+# recursive-include doc *.html
+# recursive-include doc *.inv
+# recursive-include doc *.js
+# recursive-include doc *.pickle
+# recursive-include doc *.png
+# recursive-include doc *.py
+# recursive-include doc *.rst
+# recursive-include doc *.svg
+# recursive-include doc *.ttf
+# recursive-include doc *.txt
+# recursive-include doc *.woff
+# recursive-include doc *.woff2
+# recursive-include doc Makefile
+# recursive-include examples *.ipynb
+recursive-include src *.md
+recursive-include src *.txt

README.md

@@ -1,49 +1,53 @@
-# ALIGN, a computational tool for multi-level language analysis (optimized for Python 3)
+# ALIGN, a computational tool for multi-level language analysis (optimized for Python 3.10)
 
 `align` is a Python library for extracting quantitative, reproducible
 metrics of multi-level alignment between two speakers in naturalistic
 language corpora. The method was introduced in "ALIGN: Analyzing
 Linguistic Interactions with Generalizable techNiques" (Duran, Paxton, &
 Fusaroli, 2019; Psychological Methods).
+
 <!--
 ## Try out `align` with Binder
 
 Interested in seeing how `align` works, but not sure if you want to install it
 yet? Try it out through Binder. Click the "launch" button to get a complete
 cloud environment to try out the ALIGN pipeline on our Python tutorials (the CHILDES
   tutorial is currently the only one fully operational). The process for Binder to launch may
-  take several minutes.  
+  take several minutes.
 
 [![Binder](https://mybinder.org/badge.svg)](https://mybinder.org/v2/gh/nickduran/align-linguistic-alignment/master)
 -->
+
 ## Installation
 
-`align` may downloaded directly using `pip`.
+`align` may be downloaded directly using `pip`.
 
 To download the stable version released on PyPI:
+
 ```
 pip install align
 ```
 
 To download directly from our GitHub repo:
+
 ```
 pip install git+https://github.com/nickduran/align-linguistic-alignment.git
 ```
 
 ## Additional tools required for some `align` options
 
 The Google News pre-trained word2vec vectors (`GoogleNews-vectors-negative300.bin`)
-and the Stanford part-of-speech tagger (`stanford-postagger-full-2018-10-16`)
+and the Stanford part-of-speech tagger (`stanford-postagger-full-2020-11-17`)
 are required for some optional `align` parameters but must be downloaded
 separately.
 
-* Google News: https://code.google.com/archive/p/word2vec/ (page) or
-https://drive.google.com/file/d/0B7XkCwpI5KDYNlNUTTlSS21pQmM/edit?usp=sharing
-(direct download)
+- Google News: https://code.google.com/archive/p/word2vec/ (page) or
+  https://drive.google.com/file/d/0B7XkCwpI5KDYNlNUTTlSS21pQmM/edit?usp=sharing
+  (direct download)
 
-* Stanford POS tagger: https://nlp.stanford.edu/software/tagger.shtml#Download (page)
-or https://nlp.stanford.edu/software/stanford-postagger-full-2018-10-16.zip
-(direct download)
+- Stanford POS tagger: https://nlp.stanford.edu/software/tagger.shtml#Download (page)
+  or https://nlp.stanford.edu/software/stanford-tagger-4.2.0.zip
+  (direct download)
 
 ## Tutorials
 
@@ -57,26 +61,27 @@ that helps streamline workflows. A major advantage is that Anaconda also makes i
 to set up unique Python environments - which may be necessary to run `align`
 and the tutorials given `align` is currently optimized for Python 3.
 
-* **Jupyter Notebook 1: CHILDES**
-    * This tutorial walks users through an analysis of conversations from a
-      single English corpus from the CHILDES database (MacWhinney,
-      2000)---specifically, Kuczaj’s Abe corpus (Kuczaj, 1976). We analyze the
-      last 20 conversations in the corpus in order to explore how ALIGN can be
-      used to track multi-level linguistic alignment between a parent and child
-      over time, which may be of interest to developmental language researchers.
-      Specifically, we explore how alignment between a parent and a child
-      changes over a brief span of developmental trajectory.
-
-* **Jupyter Notebook 2: Devil's Advocate**
-    * This tutorial walks users throught the analysis reported in (Duran,
-      Paxton, & Fusaroli, 2019). The corpus consists of 94 written
-      transcripts of conversations, lasting eight minutes each, collected from
-      an experimental study of truthful and deceptive communication. The goal
-      of the study was to examine interpersonal linguistic alignment between
-      dyads across two conversations where participants either agreed or
-      disagreed with each other (as a randomly assigned between-dyads condition)
-      and where one of the conversations involved the truth and the other
-      deception (as a within-subjects condition).
+- **Jupyter Notebook 1: CHILDES**
+
+  - This tutorial walks users through an analysis of conversations from a
+    single English corpus from the CHILDES database (MacWhinney,
+    2000)---specifically, Kuczaj’s Abe corpus (Kuczaj, 1976). We analyze the
+    last 20 conversations in the corpus in order to explore how ALIGN can be
+    used to track multi-level linguistic alignment between a parent and child
+    over time, which may be of interest to developmental language researchers.
+    Specifically, we explore how alignment between a parent and a child
+    changes over a brief span of developmental trajectory.
+
+- **Jupyter Notebook 2: Devil's Advocate**
+  - This tutorial walks users throught the analysis reported in (Duran,
+    Paxton, & Fusaroli, 2019). The corpus consists of 94 written
+    transcripts of conversations, lasting eight minutes each, collected from
+    an experimental study of truthful and deceptive communication. The goal
+    of the study was to examine interpersonal linguistic alignment between
+    dyads across two conversations where participants either agreed or
+    disagreed with each other (as a randomly assigned between-dyads condition)
+    and where one of the conversations involved the truth and the other
+    deception (as a within-subjects condition).
 
 We are in the process of adding more tutorials and would welcome additional
 tutorials by interested contributors.
@@ -85,31 +90,33 @@ tutorials by interested contributors.
 
 If you find the package useful, please cite our manuscript:
 
->Duran, N., Paxton, A., & Fusaroli, R. (2019). ALIGN: Analyzing
->    Linguistic Interactions with Generalizable techNiques. *Psychological Methods*. http://dynamicog.org/papers/
+> Duran, N., Paxton, A., & Fusaroli, R. (2019). ALIGN: Analyzing
+> Linguistic Interactions with Generalizable techNiques. _Psychological Methods_. http://dynamicog.org/papers/
 
 ## Licensing of example data
 
-* **CHILDES**
-    * Example corpus "Kuczaj Corpus" by Stan Kuczaj is licensed under a
-      Creative Commons Attribution-ShareAlike 3.0 Unported License
-      (https://childes.talkbank.org/access/Eng-NA/Kuczaj.html):
-
-    > Kuczaj, S. (1977). The acquisition of regular and irregular past tense
-    >     forms. *Journal of Verbal Learning and Verbal Behavior, 16*, 589–600.
-
-* **Devil's Advocate**
-    * The complete de-identified dataset of raw conversational transcripts
-      is hosted on a secure protected-access repository provided by the
-      Inter-university Consortium for Political and Social Research
-      (ICPSR). Please click on the link to access: http://dx.doi.org/10.3886/ICPSR37124.v1.
-      Due to the requirements of our IRB, please note that users interested in
-      obtaining these data must complete a Restricted Data Use Agreement, specify
-      the reason for the request, and obtain IRB approval or notice of exemption for their research.
-
-     > Duran, Nicholas, Alexandra Paxton, and Riccardo
-     >  Fusaroli. Conversational Transcripts of Truthful and
-     >  Deceptive Speech Involving Controversial Topics,
-     >  Central California, 2012. ICPSR37124-v1. Ann Arbor,
-     >  MI: Inter-university Consortium for Political and
-     >  Social Research [distributor], 2018-08-29.
+- **CHILDES**
+
+  - Example corpus "Kuczaj Corpus" by Stan Kuczaj is licensed under a
+    Creative Commons Attribution-ShareAlike 3.0 Unported License
+    (https://childes.talkbank.org/access/Eng-NA/Kuczaj.html):
+
+  > Kuczaj, S. (1977). The acquisition of regular and irregular past tense
+  > forms. _Journal of Verbal Learning and Verbal Behavior, 16_, 589–600.
+
+- **Devil's Advocate**
+
+  - The complete de-identified dataset of raw conversational transcripts
+    is hosted on a secure protected-access repository provided by the
+    Inter-university Consortium for Political and Social Research
+    (ICPSR). Please click on the link to access: http://dx.doi.org/10.3886/ICPSR37124.v1.
+    Due to the requirements of our IRB, please note that users interested in
+    obtaining these data must complete a Restricted Data Use Agreement, specify
+    the reason for the request, and obtain IRB approval or notice of exemption for their research.
+
+  > Duran, Nicholas, Alexandra Paxton, and Riccardo
+  > Fusaroli. Conversational Transcripts of Truthful and
+  > Deceptive Speech Involving Controversial Topics,
+  > Central California, 2012. ICPSR37124-v1. Ann Arbor,
+  > MI: Inter-university Consortium for Political and
+  > Social Research [distributor], 2018-08-29.

doc/Makefile

@@ -1,10 +1,10 @@
 # Minimal makefile for Sphinx documentation
 #
 
-# You can set these variables from the command line.
-SPHINXOPTS    =
-SPHINXBUILD   = python -msphinx
-SPHINXPROJ    = ALIGN
+# You can set these variables from the command line, and also
+# from the environment for the first two.
+SPHINXOPTS    ?=
+SPHINXBUILD   ?= sphinx-build
 SOURCEDIR     = .
 BUILDDIR      = _build
 
@@ -17,4 +17,4 @@ help:
 # Catch-all target: route all unknown targets to Sphinx using the new
 # "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
 %: Makefile
-	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)

doc/_build/html/.buildinfo

@@ -0,0 +1,4 @@
+# Sphinx build info version 1
+# This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
+config: 92fb6c56a78588f6ece5cb0d20061f36
+tags: 645f666f9bcd5a90fca523b33c5a78b7

doc/_build/html/_sources/calculate_alignment.rst.txt

@@ -0,0 +1,7 @@
+calculate\_alignment module
+===========================
+
+.. automodule:: calculate_alignment
+   :members:
+   :undoc-members:
+   :show-inheritance:

doc/_build/html/_sources/index.rst.txt

@@ -0,0 +1,22 @@
+.. ALIGN documentation master file, created by
+   sphinx-quickstart on Mon Jul  4 09:14:01 2022.
+   You can adapt this file completely to your liking, but it should at least
+   contain the root `toctree` directive.
+
+Welcome to ALIGN's documentation!
+=================================
+
+.. toctree::
+   :maxdepth: 2
+   :caption: Contents:
+
+   modules
+
+
+
+Indices and tables
+==================
+
+* :ref:`genindex`
+* :ref:`modindex`
+* :ref:`search`

doc/_build/html/_sources/modules.rst.txt

@@ -0,0 +1,8 @@
+align
+=====
+
+.. toctree::
+   :maxdepth: 4
+
+   calculate_alignment
+   prepare_transcripts

doc/_build/html/_sources/prepare_transcripts.rst.txt

@@ -0,0 +1,7 @@
+prepare\_transcripts module
+===========================
+
+.. automodule:: prepare_transcripts
+   :members:
+   :undoc-members:
+   :show-inheritance: