From 69b3a4f63f41299410595d4490c361da4ad5cd7a Mon Sep 17 00:00:00 2001
From: Kathryn Hempstalk <khempstalk@tmmac001879.trademe.local>
Date: Fri, 2 Mar 2018 15:57:08 +1300
Subject: [PATCH 1/2] Updated module to be installable, rearranged files.

---
 .DS_Store                                     | Bin 0 -> 6148 bytes
 MANIFEST.in                                   |   1 +
 README.md                                     |  28 ++++++++++++++++--
 __init__.py                                   |   1 +
 data/.DS_Store                                | Bin 0 -> 6148 bytes
 data/stoplists/.DS_Store                      | Bin 0 -> 6148 bytes
 .../stoplists/FoxStoplist.txt                 |   0
 .../stoplists/FrenchStoplist.txt              |   0
 .../stoplists/SmartStoplist.txt               |   0
 .../stoplists/SpanishStoplist.txt             |   0
 rake.py                                       |  10 +++----
 rake_tutorial.py                              |   2 +-
 setup.py                                      |  15 ++++++++++
 13 files changed, 49 insertions(+), 8 deletions(-)
 create mode 100644 .DS_Store
 create mode 100644 MANIFEST.in
 create mode 100644 __init__.py
 create mode 100644 data/.DS_Store
 create mode 100644 data/stoplists/.DS_Store
 rename FoxStoplist.txt => data/stoplists/FoxStoplist.txt (100%)
 rename FrenchStoplist.txt => data/stoplists/FrenchStoplist.txt (100%)
 rename SmartStoplist.txt => data/stoplists/SmartStoplist.txt (100%)
 rename SpanishStoplist.txt => data/stoplists/SpanishStoplist.txt (100%)
 create mode 100644 setup.py

diff --git a/.DS_Store b/.DS_Store
new file mode 100644
index 0000000000000000000000000000000000000000..66d21f7f2956eaf43865532a3ef230b4a9759552
GIT binary patch
literal 6148
zcmeHKJxc>Y5PcI*Nl-AQU~{F7g0;;h<cfecnqG5B3gI*XFQDBu)`DQ+PZ0c%`et_x
zmrHC#!VJv5-MxAH@%Fg61t8t|_!MXZXwnrMEf#A`pR2D}BlPSL#f>rU=hIP^PqUR+
z>-e7v=-F)}!yLEBQ9VC>CC=zaU(Vd}BaAUbfnnvGHSVJpw~q_-F~Bj-IqnD(+~a}e
z3Av9bYV1$4Un{e;aETNh^f*dN&Ru<7@=V5ih0%1Q7u>~+@iRQtX6P{ftrEY-bxg=9
zaQ(BRbv!vF@1??H)65hw1x$erP=GmGt-0&bN>jiTFa;J0==UL}D<%O;kM7gK!d(G~
z5xbqSu0Mpzi3279OOJd)6Hg_2s)Q?scsl#z5SIijJ$gDMTs|bsEa8SCZg!3zyKqS2
z(MnUm6j)YZ%QxGa|I^>^|H~w6nF6N3Mkyds@2c13mO^e_*_`Iun0`Z7)40;(g2IYR
g#f;Tdd_Z@`{#Yx-Bw*>0Jv93fa57k73jC=8-yRuWCjbBd

literal 0
HcmV?d00001

diff --git a/MANIFEST.in b/MANIFEST.in
new file mode 100644
index 0000000..e0f334d
--- /dev/null
+++ b/MANIFEST.in
@@ -0,0 +1 @@
+include data/stoplists/*
diff --git a/README.md b/README.md
index f9e103a..803d7af 100644
--- a/README.md
+++ b/README.md
@@ -1,6 +1,30 @@
-RAKE
-====
+# RAKE
+---
 
 A Python implementation of the Rapid Automatic Keyword Extraction (RAKE) algorithm as described in: Rose, S., Engel, D., Cramer, N., & Cowley, W. (2010). Automatic Keyword Extraction from Individual Documents. In M. W. Berry & J. Kogan (Eds.), Text Mining: Theory and Applications: John Wiley & Sons.
 
 The source code is released under the MIT License.
+
+## Installing rake
+
+To install rake as a package, run:
+
+`python setup.py install`
+
+## Example use
+
+```python
+from nlp_rake import rake
+
+stoppath = 'data/stoplists/SmartStoplist.txt'
+
+rake_object = rake.Rake(stoppath, 5, 3, 4)
+
+sample_file = open("data/docs/fao_test/w2167e.txt", 'r', encoding="iso-8859-1")
+text = sample_file.read()
+
+keywords = rake_object.run(text)
+
+# 3. print results
+print("Keywords:", keywords)
+```
diff --git a/__init__.py b/__init__.py
new file mode 100644
index 0000000..d333644
--- /dev/null
+++ b/__init__.py
@@ -0,0 +1 @@
+import rake
diff --git a/data/.DS_Store b/data/.DS_Store
new file mode 100644
index 0000000000000000000000000000000000000000..40be868e1b40aa70e1c9b22a55b164770e1fd8a1
GIT binary patch
literal 6148
zcmeHKJ8A<l5S>X}IHYlzQdjT|gxQ?HjY$>Qg(To*7i?E<bg~>H=kc3Q!Y)>kB7_iT
zKzbw1N7@G~X^4n7r*2KOBBCXlAd6BFnXZ~{+<5_H&9SF9I?$00`<F_hzc?j(ztcSr
zG}2`M>uo#q<7CSfuYPEn?sRO4KHl5&?x~)uAG&XNjjvZLP8JU}7zhS}fnXpQ_%Q}>
zXNxTF4WkbRf`MS*ivc+w5}IIkEQWe?pwkinD9>mW=u%5aOmfVQ#Sj(<TPV;%*-H$z
zaLgz7%Z|m+!il~3U|;#Ocwt=~`IEX6XT#`&fnZ?Hz^x5ea{oW#m#G%{^N<(?1Hr&Q
zV}KXUw%OpL{BFJaJh^KV+B2Gn_!Utg&}WYT4CEYnP@~zC=<v&q#Za=yyoLkgA)tgr
J7YzIY0~cQoFY^EZ

literal 0
HcmV?d00001

diff --git a/data/stoplists/.DS_Store b/data/stoplists/.DS_Store
new file mode 100644
index 0000000000000000000000000000000000000000..d661515a1243a2d52ac3cf57223f412484a26fdc
GIT binary patch
literal 6148
zcmeHKO-sW-5Pe&FsCY2y#pC`0!G91+6+HJ3Xsci$Hl>ZwWB$3m`Jfo0mmpGP24>#w
zW@eIo8!{OHY5M+r3lsn*RKd|H%{L;~MSC*xl`%1Cjs`V0sIbDW=N${j$bg*PIqrFG
zd(83m{2JVFzDM&=)yqXyFX&l(bVN6F$>=R!u*MRv19Mz3?hQ}O(+tdT#kdVKto7X+
z`W(l2Lh($&Krj#t{5}J$*&>rO!?3|XFc1tJ7?AHnrV5sht)YH8XtV_&%5S6!$I?qk
zOm-|CTSH!<Bnu^4Xz~^#Svc3T`<0HZp@k!P^O5|{$vc#!cW3^r?ntF!*kB+S=rV9(
z(?aV1-Ov4hHz;PoKrryH7)ayUd^Y8lytei>C$%<HAE_eZ*BTx|IM7l|Un#}cR28mg
W84ydy){rZd_z_SV!UO|<%D^XUKyCW~

literal 0
HcmV?d00001

diff --git a/FoxStoplist.txt b/data/stoplists/FoxStoplist.txt
similarity index 100%
rename from FoxStoplist.txt
rename to data/stoplists/FoxStoplist.txt
diff --git a/FrenchStoplist.txt b/data/stoplists/FrenchStoplist.txt
similarity index 100%
rename from FrenchStoplist.txt
rename to data/stoplists/FrenchStoplist.txt
diff --git a/SmartStoplist.txt b/data/stoplists/SmartStoplist.txt
similarity index 100%
rename from SmartStoplist.txt
rename to data/stoplists/SmartStoplist.txt
diff --git a/SpanishStoplist.txt b/data/stoplists/SpanishStoplist.txt
similarity index 100%
rename from SpanishStoplist.txt
rename to data/stoplists/SpanishStoplist.txt
diff --git a/rake.py b/rake.py
index 07801fa..4e047e0 100644
--- a/rake.py
+++ b/rake.py
@@ -1,6 +1,6 @@
 # Implementation of RAKE - Rapid Automatic Keyword Extraction algorithm
 # as described in:
-# Rose, S., D. Engel, N. Cramer, and W. Cowley (2010). 
+# Rose, S., D. Engel, N. Cramer, and W. Cowley (2010).
 # Automatic keyword extraction from individual documents.
 # In M. W. Berry and J. Kogan (Eds.), Text Mining: Applications and Theory.unknown: John Wiley and Sons, Ltd.
 #
@@ -25,7 +25,7 @@
 from collections import Counter
 
 debug = False
-test = True
+test = False
 
 
 def is_number(s):
@@ -270,13 +270,13 @@ def run(self, text):
         return sorted_keywords
 
 
-if test:
+if test and __name__ == '__main__':
     text = "Compatibility of systems of linear constraints over the set of natural numbers. Criteria of compatibility of a system of linear Diophantine equations, strict inequations, and nonstrict inequations are considered. Upper bounds for components of a minimal set of solutions and algorithms of construction of minimal generating sets of solutions for all types of systems are given. These criteria and the corresponding algorithms for constructing a minimal supporting set of solutions can be used in solving all the considered types of systems and systems of mixed types."
 
     # Split text into sentences
     sentenceList = split_sentences(text)
     # stoppath = "FoxStoplist.txt" #Fox stoplist contains "numbers", so it will not find "natural numbers" like in Table 1.1
-    stoppath = "SmartStoplist.txt"  # SMART stoplist misses some of the lower-scoring keywords in Figure 1.5, which means that the top 1/3 cuts off one of the 4.0 score words in Table 1.1
+    stoppath = "data/stoplists/SmartStoplist.txt"  # SMART stoplist misses some of the lower-scoring keywords in Figure 1.5, which means that the top 1/3 cuts off one of the 4.0 score words in Table 1.1
     stopwordpattern = build_stop_word_regex(stoppath)
 
     # generate candidate keywords
@@ -296,6 +296,6 @@ def run(self, text):
     if debug: print(totalKeywords)
     print(sortedKeywords[0:(totalKeywords // 3)])
 
-    rake = Rake("SmartStoplist.txt")
+    rake = Rake("data/stoplists/SmartStoplist.txt")
     keywords = rake.run(text)
     print(keywords)
diff --git a/rake_tutorial.py b/rake_tutorial.py
index 222542f..3692201 100644
--- a/rake_tutorial.py
+++ b/rake_tutorial.py
@@ -8,7 +8,7 @@
 import io
 
 # EXAMPLE ONE - SIMPLE
-stoppath = "SmartStoplist.txt"
+stoppath = "data/stoplists/SmartStoplist.txt"
 
 # 1. initialize RAKE by providing a path to a stopwords file
 rake_object = rake.Rake(stoppath, 5, 3, 4)
diff --git a/setup.py b/setup.py
new file mode 100644
index 0000000..39f0564
--- /dev/null
+++ b/setup.py
@@ -0,0 +1,15 @@
+#!/usr/bin/env python
+
+from setuptools import setup
+
+setup(name='nlp_rake',
+      version='1.0',
+      description='Rapid Automatic Keyword Extraction (RAKE) algorithm',
+      long_description='A Python implementation of the Rapid Automatic Keyword Extraction (RAKE) algorithm as described in: Rose, S., Engel, D., Cramer, N., & Cowley, W. (2010). Automatic Keyword Extraction from Individual Documents. In M. W. Berry & J. Kogan (Eds.), Text Mining: Theory and Applications: John Wiley & Sons.',
+      author='zelandiya, aneesha',
+      url='https://www.python.org/sigs/distutils-sig/',
+      packages=['nlp_rake'],
+      package_dir={'nlp_rake': './'},
+      package_data={'nlp_rake': ['data/']},
+      include_package_data = True,
+     )

From eccade611ce9b520978a4b002203c57eb8d2236f Mon Sep 17 00:00:00 2001
From: Kathryn Hempstalk <khempstalk@tmmac001879.trademe.local>
Date: Fri, 2 Mar 2018 16:14:44 +1300
Subject: [PATCH 2/2] Cleaned up files.

---
 .DS_Store      | Bin 6148 -> 0 bytes
 .gitignore     |   1 +
 data/.DS_Store | Bin 6148 -> 0 bytes
 3 files changed, 1 insertion(+)
 delete mode 100644 .DS_Store
 delete mode 100644 data/.DS_Store

diff --git a/.DS_Store b/.DS_Store
deleted file mode 100644
index 66d21f7f2956eaf43865532a3ef230b4a9759552..0000000000000000000000000000000000000000
GIT binary patch
literal 0
HcmV?d00001

literal 6148
zcmeHKJxc>Y5PcI*Nl-AQU~{F7g0;;h<cfecnqG5B3gI*XFQDBu)`DQ+PZ0c%`et_x
zmrHC#!VJv5-MxAH@%Fg61t8t|_!MXZXwnrMEf#A`pR2D}BlPSL#f>rU=hIP^PqUR+
z>-e7v=-F)}!yLEBQ9VC>CC=zaU(Vd}BaAUbfnnvGHSVJpw~q_-F~Bj-IqnD(+~a}e
z3Av9bYV1$4Un{e;aETNh^f*dN&Ru<7@=V5ih0%1Q7u>~+@iRQtX6P{ftrEY-bxg=9
zaQ(BRbv!vF@1??H)65hw1x$erP=GmGt-0&bN>jiTFa;J0==UL}D<%O;kM7gK!d(G~
z5xbqSu0Mpzi3279OOJd)6Hg_2s)Q?scsl#z5SIijJ$gDMTs|bsEa8SCZg!3zyKqS2
z(MnUm6j)YZ%QxGa|I^>^|H~w6nF6N3Mkyds@2c13mO^e_*_`Iun0`Z7)40;(g2IYR
g#f;Tdd_Z@`{#Yx-Bw*>0Jv93fa57k73jC=8-yRuWCjbBd

diff --git a/.gitignore b/.gitignore
index a2dd459..50bf877 100644
--- a/.gitignore
+++ b/.gitignore
@@ -10,6 +10,7 @@ __pycache__/
 
 # Distribution / packaging
 .Python
+.DS_STORE
 env/
 bin/
 build/
diff --git a/data/.DS_Store b/data/.DS_Store
deleted file mode 100644
index 40be868e1b40aa70e1c9b22a55b164770e1fd8a1..0000000000000000000000000000000000000000
GIT binary patch
literal 0
HcmV?d00001

literal 6148
zcmeHKJ8A<l5S>X}IHYlzQdjT|gxQ?HjY$>Qg(To*7i?E<bg~>H=kc3Q!Y)>kB7_iT
zKzbw1N7@G~X^4n7r*2KOBBCXlAd6BFnXZ~{+<5_H&9SF9I?$00`<F_hzc?j(ztcSr
zG}2`M>uo#q<7CSfuYPEn?sRO4KHl5&?x~)uAG&XNjjvZLP8JU}7zhS}fnXpQ_%Q}>
zXNxTF4WkbRf`MS*ivc+w5}IIkEQWe?pwkinD9>mW=u%5aOmfVQ#Sj(<TPV;%*-H$z
zaLgz7%Z|m+!il~3U|;#Ocwt=~`IEX6XT#`&fnZ?Hz^x5ea{oW#m#G%{^N<(?1Hr&Q
zV}KXUw%OpL{BFJaJh^KV+B2Gn_!Utg&}WYT4CEYnP@~zC=<v&q#Za=yyoLkgA)tgr
J7YzIY0~cQoFY^EZ