Skip to content

Commit

Permalink
reformat paper
Browse files Browse the repository at this point in the history
  • Loading branch information
Rankin_summer authored and Rankin_summer committed Jun 26, 2020
1 parent 35c2fff commit 5c1fdb7
Show file tree
Hide file tree
Showing 15 changed files with 2,285 additions and 283 deletions.
Binary file modified .DS_Store
Binary file not shown.
Binary file added bloatectomy_paper.pdf
Binary file not shown.
1 change: 0 additions & 1 deletion build.sh

This file was deleted.

38 changes: 38 additions & 0 deletions meta.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,38 @@
{% set name = "bloatectomy" %}
{% set version = "0.0.12" %}

package:
name: "{{ name|lower }}"
version: "{{ version }}"

source:
url: "https://pypi.io/packages/source/{{ name[0] }}/{{ name }}/{{ name }}-{{ version }}.tar.gz"
sha256: 4f84db2264a3e337b13bde94c1154e1e46f9efaa3c501b26b5ee67f095f73363

build:
number: 0
script: "{{ PYTHON }} -m pip install . -vv"

requirements:
host:
- pip
- python
run:
- python

test:
imports:
- bloatectomy

about:
home: "https://github.com/MIT-LCP/bloatectomy"
license: GPL-3.0-or-later
license_family: GPL3
license_file: LICENSE
summary: "Bloatectomy: a method for the identification and removal of duplicate text in the bloated notes of electronic health records and other documents."
doc_url:
dev_url:

extra:
recipe-maintainers:
- 1fmusic
Binary file added paper/.DS_Store
Binary file not shown.
107 changes: 107 additions & 0 deletions paper/bloatectomy_paper.aux
Original file line number Diff line number Diff line change
@@ -0,0 +1,107 @@
\relax
\providecommand\hyper@newdestlabel[2]{}
\providecommand\HyperFirstAtBeginDocument{\AtBeginDocument}
\HyperFirstAtBeginDocument{\ifx\hyper@anchor\@undefined
\global\let\oldcontentsline\contentsline
\gdef\contentsline#1#2#3#4{\oldcontentsline{#1}{#2}{#3}}
\global\let\oldnewlabel\newlabel
\gdef\newlabel#1#2{\newlabelxx{#1}#2}
\gdef\newlabelxx#1#2#3#4#5#6{\oldnewlabel{#1}{{#2}{#3}}}
\AtEndDocument{\ifx\hyper@anchor\@undefined
\let\contentsline\oldcontentsline
\let\newlabel\oldnewlabel
\fi}
\fi}
\global\let\hyper@last\relax
\gdef\HyperFirstAtBeginDocument#1{#1}
\providecommand\HyField@AuxAddToFields[1]{}
\providecommand\HyField@AuxAddToCoFields[2]{}
\citation{mimiciii}
\citation{mimiciiidata}
\citation{physionet}
\@writefile{toc}{\contentsline {chapter}{Bloatectomy}{0}{}}
\@writefile{toc}{\contentsline {title}{Bloatectomy:}{1}{chapter.1}\protected@file@percent }
\@writefile{toc}{\authcount {3}}
\@writefile{toc}{\contentsline {author}{Summer K Rankin$^{*}$\unskip {} \and Roselie Bright\unskip {} \and Katherine Dowdy\unskip {}}{1}{chapter.1}\protected@file@percent }
\@writefile{toc}{\contentsline {section}{\numberline {1}Introduction}{1}{section.1.1}\protected@file@percent }
\citation{Dean:2018}
\citation{Cohen:2013}
\@writefile{lof}{\contentsline {figure}{\numberline {1}{\ignorespaces \textbf {Graphical Abstract}}}{2}{figure.1.1}\protected@file@percent }
\newlabel{abstract}{{1}{2}{\textbf {Graphical Abstract}}{figure.1.1}{}}
\@writefile{lof}{\contentsline {figure}{\numberline {2}{\ignorespaces \textbf {Progressively longer nurse\IeC {\textquoteright }s notes over one shift.} In this figure, we used a manual method to highlight identical sentences with unique colors. The original sentences are in bold font as well. This and similar figures in this document are purposely small and low resolution to provide further patient and provider privacy protection without disturbing our point about duplicate text.}}{2}{figure.1.2}\protected@file@percent }
\newlabel{notes1}{{2}{2}{\textbf {Progressively longer nurse’s notes over one shift.} In this figure, we used a manual method to highlight identical sentences with unique colors. The original sentences are in bold font as well. This and similar figures in this document are purposely small and low resolution to provide further patient and provider privacy protection without disturbing our point about duplicate text}{figure.1.2}{}}
\@writefile{lof}{\contentsline {figure}{\numberline {3}{\ignorespaces \textbf { Example of two physicians\IeC {\textquoteright } notes from the same time period.} In this figure, we used a manual method to highlight identical sentences with unique colors. The original sentences are in bold font as well.}}{3}{figure.1.3}\protected@file@percent }
\newlabel{notes2}{{3}{3}{\textbf { Example of two physicians’ notes from the same time period.} In this figure, we used a manual method to highlight identical sentences with unique colors. The original sentences are in bold font as well}{figure.1.3}{}}
\citation{Su:2008}
\citation{copyfind}
\citation{Ceglarek:2013}
\citation{Thielke:2007}
\citation{Wrenn:2010}
\citation{Altschul:1990}
\citation{Cohen:2013}
\citation{Cohen:2013}
\citation{Gabriel:2018}
\citation{Lancichinetti:2015}
\citation{Cohen:2014}
\citation{Zhang:2011}
\citation{Welch:1984}
\citation{python3}
\@writefile{toc}{\contentsline {section}{\numberline {2}Duplicate Detection}{5}{section.1.2}\protected@file@percent }
\@writefile{lof}{\contentsline {figure}{\numberline {4}{\ignorespaces \emph {High-level flowchart of the Bloatectomy method.}}}{5}{figure.1.4}\protected@file@percent }
\newlabel{flowchart}{{4}{5}{\emph {High-level flowchart of the Bloatectomy method.}}{figure.1.4}{}}
\@writefile{toc}{\contentsline {subsection}{\numberline {2.1}Document Selection}{5}{subsection.1.2.1}\protected@file@percent }
\@writefile{toc}{\contentsline {subsection}{\numberline {2.2}Code and Example}{5}{subsection.1.2.2}\protected@file@percent }
\@writefile{toc}{\contentsline {subsubsection}{Create Sentence Tokens}{6}{section*.3}\protected@file@percent }
\@writefile{lof}{\contentsline {figure}{\numberline {5}{\ignorespaces \emph {The regular expression used for the first tokenization.}}}{6}{figure.1.5}\protected@file@percent }
\newlabel{regex1}{{5}{6}{\emph {The regular expression used for the first tokenization.}}{figure.1.5}{}}
\@writefile{lot}{\contentsline {table}{\numberline {1}{\ignorespaces Tokens after first tokenization}}{7}{table.1.1}\protected@file@percent }
\@writefile{toc}{\contentsline {subsubsection}{Create List Token}{7}{section*.4}\protected@file@percent }
\@writefile{lof}{\contentsline {figure}{\numberline {6}{\ignorespaces \emph {The regular expression used to calculate the second tokenization.}}}{7}{figure.1.6}\protected@file@percent }
\newlabel{regex2}{{6}{7}{\emph {The regular expression used to calculate the second tokenization.}}{figure.1.6}{}}
\@writefile{lot}{\contentsline {table}{\numberline {2}{\ignorespaces Tokens after second tokenization}}{8}{table.1.2}\protected@file@percent }
\@writefile{toc}{\contentsline {subsubsection}{Assign Either New or Old Hash Number}{8}{section*.5}\protected@file@percent }
\@writefile{lot}{\contentsline {table}{\numberline {3}{\ignorespaces Hash Table of Tokens}}{9}{table.1.3}\protected@file@percent }
\@writefile{toc}{\contentsline {subsubsection}{Use the Hash Table of Tokens}{9}{section*.6}\protected@file@percent }
\@writefile{lot}{\contentsline {table}{\numberline {4}{\ignorespaces Marked Table of Tokens}}{10}{table.1.4}\protected@file@percent }
\@writefile{lof}{\contentsline {figure}{\numberline {7}{\ignorespaces \emph { Highlighted duplicates in the output from the example text.} }}{10}{figure.1.7}\protected@file@percent }
\newlabel{output}{{7}{10}{\emph { Highlighted duplicates in the output from the example text.}}{figure.1.7}{}}
\@writefile{toc}{\contentsline {subsection}{\numberline {2.3}Parameter Adjustments}{10}{subsection.1.2.3}\protected@file@percent }
\@writefile{toc}{\contentsline {section}{\numberline {3}Results}{11}{section.1.3}\protected@file@percent }
\@writefile{lof}{\contentsline {figure}{\numberline {8}{\ignorespaces \emph { The same nurse\IeC {\textquoteright }s notes from \ref {notes1}, after Bloatectomy.} }}{11}{figure.1.8}\protected@file@percent }
\newlabel{output_notes1}{{8}{11}{\emph { The same nurse’s notes from \ref {notes1}, after Bloatectomy.}}{figure.1.8}{}}
\@writefile{lof}{\contentsline {figure}{\numberline {9}{\ignorespaces \emph { The same physicians' notes from \ref {notes2}, after Bloatectomy.} }}{11}{figure.1.9}\protected@file@percent }
\newlabel{output_notes2}{{9}{11}{\emph { The same physicians' notes from \ref {notes2}, after Bloatectomy.}}{figure.1.9}{}}
\@writefile{toc}{\contentsline {section}{\numberline {4}Conclusions}{12}{section.1.4}\protected@file@percent }
\@writefile{toc}{\contentsline {section}{\numberline {5}Installation}{12}{section.1.5}\protected@file@percent }
\@writefile{toc}{\contentsline {section}{\numberline {6}Examples}{12}{section.1.6}\protected@file@percent }
\@writefile{toc}{\contentsline {section}{\numberline {7}Parameters}{14}{section.1.7}\protected@file@percent }
\@writefile{toc}{\contentsline {subsubsection}{Acknowledgements}{15}{section*.7}\protected@file@percent }
\@writefile{toc}{\contentsline {subsubsection}{Funding}{15}{section*.8}\protected@file@percent }
\@writefile{toc}{\contentsline {subsubsection}{Conflict of Interest}{15}{section*.9}\protected@file@percent }
\bibcite{Dean:2018}{1}
\bibcite{March:2016}{2}
\bibcite{Tsou:2017}{3}
\bibcite{Corwin:2004}{4}
\bibcite{Cohen:2013}{5}
\bibcite{Cohen:2014}{6}
\bibcite{Ceglarek:2013}{7}
\bibcite{Carson:2012}{8}
\bibcite{copyfind}{9}
\bibcite{aws}{10}
\bibcite{Altschul:1990}{11}
\bibcite{mimiciii}{12}
\bibcite{mimiciiidata}{13}
\@writefile{toc}{\contentsline {subsubsection}{Disclaimer}{16}{section*.10}\protected@file@percent }
\@writefile{toc}{\contentsline {subsubsection}{Data Availability}{16}{section*.11}\protected@file@percent }
\bibcite{physionet}{14}
\bibcite{python3}{15}
\bibcite{Lancichinetti:2015}{16}
\bibcite{Mckinney:2010}{17}
\bibcite{Meystre:2008}{18}
\bibcite{Mikolov:2013}{19}
\bibcite{Su:2008}{20}
\bibcite{Thielke:2007}{21}
\bibcite{Welch:1984}{22}
\bibcite{Wrenn:2010}{23}
\bibcite{Zhang:2011}{24}
\bibcite{Gabriel:2018}{25}
3 changes: 3 additions & 0 deletions paper/bloatectomy_paper.bbl
Original file line number Diff line number Diff line change
@@ -0,0 +1,3 @@
\begin{thebibliography}{}

\end{thebibliography}
55 changes: 55 additions & 0 deletions paper/bloatectomy_paper.blg
Original file line number Diff line number Diff line change
@@ -0,0 +1,55 @@
This is BibTeX, Version 0.99d (TeX Live 2019)
Capacity: max_strings=100000, hash_size=100000, hash_prime=85009
The top-level auxiliary file: bloatectomy_paper.aux
The style file: plain.bst
I couldn't open database file bloatecomy_paper.bib
---line 63 of file bloatectomy_paper.aux
: \bibdata{bloatecomy_paper
: }
I'm skipping whatever remains of this command
I found no database files---while reading file bloatectomy_paper.aux
Warning--I didn't find a database entry for "mimiciii"
Warning--I didn't find a database entry for "mimiciiidata"
Warning--I didn't find a database entry for "physionet"
You've used 0 entries,
2118 wiz_defined-function locations,
500 strings with 4052 characters,
and the built_in function-call counts, 18 in all, are:
= -- 0
> -- 0
< -- 0
+ -- 0
- -- 0
* -- 2
:= -- 7
add.period$ -- 0
call.type$ -- 0
change.case$ -- 0
chr.to.int$ -- 0
cite$ -- 0
duplicate$ -- 0
empty$ -- 1
format.name$ -- 0
if$ -- 1
int.to.chr$ -- 0
int.to.str$ -- 0
missing$ -- 0
newline$ -- 3
num.names$ -- 0
pop$ -- 0
preamble$ -- 1
purify$ -- 0
quote$ -- 0
skip$ -- 1
stack$ -- 0
substring$ -- 0
swap$ -- 0
text.length$ -- 0
text.prefix$ -- 0
top$ -- 0
type$ -- 0
warning$ -- 0
while$ -- 0
width$ -- 0
write$ -- 2
(There were 2 error messages)
20 changes: 20 additions & 0 deletions paper/bloatectomy_paper.out
Original file line number Diff line number Diff line change
@@ -0,0 +1,20 @@
\BOOKMARK [0][-]{chapter.1}{Bloatectomy:}{}% 1
\BOOKMARK [1][-]{section.1.1}{Introduction}{chapter.1}% 2
\BOOKMARK [1][-]{section.1.2}{Duplicate Detection}{chapter.1}% 3
\BOOKMARK [2][-]{subsection.1.2.1}{Document Selection}{section.1.2}% 4
\BOOKMARK [2][-]{subsection.1.2.2}{Code and Example}{section.1.2}% 5
\BOOKMARK [3][-]{section*.3}{Create Sentence Tokens}{subsection.1.2.2}% 6
\BOOKMARK [3][-]{section*.4}{Create List Token}{subsection.1.2.2}% 7
\BOOKMARK [3][-]{section*.5}{Assign Either New or Old Hash Number}{subsection.1.2.2}% 8
\BOOKMARK [3][-]{section*.6}{Use the Hash Table of Tokens}{subsection.1.2.2}% 9
\BOOKMARK [2][-]{subsection.1.2.3}{Parameter Adjustments}{section.1.2}% 10
\BOOKMARK [1][-]{section.1.3}{Results}{chapter.1}% 11
\BOOKMARK [1][-]{section.1.4}{Conclusions}{chapter.1}% 12
\BOOKMARK [1][-]{section.1.5}{Installation}{chapter.1}% 13
\BOOKMARK [1][-]{section.1.6}{Examples}{chapter.1}% 14
\BOOKMARK [1][-]{section.1.7}{Parameters}{chapter.1}% 15
\BOOKMARK [2][-]{section*.7}{Acknowledgements}{section.1.7}% 16
\BOOKMARK [3][-]{section*.8}{Funding}{section*.7}% 17
\BOOKMARK [3][-]{section*.9}{Conflict of Interest}{section*.7}% 18
\BOOKMARK [3][-]{section*.10}{Disclaimer}{section*.7}% 19
\BOOKMARK [3][-]{section*.11}{Data Availability}{section*.7}% 20
Binary file added paper/bloatectomy_paper.synctex.gz
Binary file not shown.
Loading

0 comments on commit 5c1fdb7

Please sign in to comment.