Merge pull request aneesha#9 from drkatnz/master

Added setup.py to make module easily installable

.gitignore

@@ -10,6 +10,7 @@ __pycache__/
 
 # Distribution / packaging
 .Python
+.DS_STORE
 env/
 bin/
 build/

MANIFEST.in

@@ -0,0 +1 @@
+include data/stoplists/*

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)
+```

__init__.py

@@ -0,0 +1 @@
+import rake

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)

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)

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,
+     )