Skip to content

Update to Python 3 version on stringcomp.py file #27

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Update to Python 3 version on stringcomp.py file #27

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
c313bb4
Updated to Python 3 & string style reformed
dmartmillan Aug 4, 2020
9e9b714
Replaced paper URL, it was broken
dmartmillan Aug 4, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
26 changes: 14 additions & 12 deletions nltk_contrib/stringcomp.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,7 @@ def stringcomp (fx, fy):
This is an implementation of the string comparison algorithm (also known
as "string similarity") published by Qi Xiao Yang, Sung Sam Yuan, Li Zhao,
Lu Chun and Sun Peng in a paper called "Faster Algorithm of String
Comparison" ( http://front.math.ucdavis.edu/0112.6022 ). Please note that,
Comparison" ( https://arxiv.org/abs/cs/0112022 ). Please note that,
however, this implementation presents some relevant differences that
will lead to different numerical results (read the comments for more
details).
Expand Down Expand Up @@ -74,7 +74,7 @@ def stringcomp (fx, fy):
index = fy.find(pattern)
if index != -1:
ssnc += (2.*length)**2
if fx_removed == False:
if not fx_removed:
fx = fx[:i] + fx[i+length:]
fx_removed = True
fy = fy[:index] + fy[index+length:]
Expand All @@ -89,20 +89,22 @@ def stringcomp (fx, fy):


def demo ():
print "Comparison between 'python' and 'python': %.2f" % stringcomp("python", "python")
print "Comparison between 'python' and 'Python': %.2f" % stringcomp("python", "Python")
print "Comparison between 'NLTK' and 'NTLK': %.2f" % stringcomp("NLTK", "NTLK")
print "Comparison between 'abc' and 'def': %.2f" % stringcomp("abc", "def")

print "Word most similar to 'australia' in list ['canada', 'brazil', 'egypt', 'thailand', 'austria']:"
max_score = 0.0 ; best_match = None
print("Comparison between 'python' and 'python': {0:0.2f}".format(stringcomp("python", "python")))
print("Comparison between 'python' and 'Python': {0:0.2f}".format(stringcomp("python", "Python")))
print("Comparison between 'NLTK' and 'NTLK': {0:0.2f}".format(stringcomp("NLTK", "NTLK")))
print("Comparison between 'abc' and 'def': {0:0.2f}".format(stringcomp("abc", "def")))

print("Word most similar to 'australia' in list ['canada', 'brazil', 'egypt', 'thailand', 'austria']:")
max_score = 0.0
best_match = None
for country in ["canada", "brazil", "egypt", "thailand", "austria"]:
score = stringcomp("australia", country)
if score > max_score:
best_match = country
max_score = score
print "(comparison between 'australia' and '%s': %.2f)" % (country, score)
print "Word most similar to 'australia' is '%s' (score: %.2f)" % (best_match, max_score)

print("(comparison between 'australia' and '{0}': {1:0.2f})".format(country, score))
print("Word most similar to 'australia' is '{0}' (score: {1:0.2f})".format(best_match, max_score))


if __name__ == "__main__":
demo()