class MangleVerbs(object):
def __init__(self):
self.syllables = CountSyllables()
def filterVerbs(self):
fileName = open("verbs.txt", "r")
data = fileName.read()
fileName.close()
data = data.split("\n")
fileName2 = open("dict.txt", "r")
commonWords = fileName2.read()
fileName2.close()
commonWords = commonWords.split("\n")
output = open("output.txt", "w")
for word in data:
word = word.strip().lower()
number = self.syllables.count(word)
#print word, number
if number == -1:
number = self.syllables.oldCount(word)
if number == 1:
if word in commonWords:
print "killed: ", word
continue
output.write(word + "\n")
print "added: ", word
output.close()
class Lawrence(object):
def __init__(self):
self.cs = CountSyllables()
self.instances = []
def ss(self):
# sum of squares
c = self.mean()
ss = sum((x - c) **2 for x in self.instances)
return ss
def stdev(self):
# standard deviation
n = len(self.instances)
if n < 2:
return 0
ss = self.ss()
pvar = ss / n
return pvar ** 0.5
def mean(self):
count = len(self.instances)
sum = 0.0
for num in self.instances:
sum += num
return sum / count
def fleschKincaid(self, wordCount, syllableCount):
x = (206.835 - ((1.015 * wordCount) / 1)) - (((84.6 * syllableCount) / wordCount))
return x
def loopSentence(self, text):
self.instances = []
sentences = text.lower().split('.')
for sentence in sentences:
if len(sentence) < 1: continue
words = sentence.split(' ')
wordCount = len(words)
syllableCount = 0
for word in words:
syllableCount += self.cs.count(word)
self.instances += [self.fleschKincaid(wordCount, syllableCount)]
class SyllableIt(TagIt):
"""
Extracts syllable counts from either side of a key word.
"""
def __init__(self):
self.syllable = CountSyllables()
def addTags(self, sentence=["here", "is", "a", "word"], factors=5):
""""
Buffer a list of (word, tag) with NAs of any factor
[(x1,y1), (x2,y2)], 1 ----> [(na,na), (x1,y1), (x2,y2), (na,na)]
"""
newVars = []
for i in range(factors):
newVars += ["na"]
sentence += newVars
newVars += sentence
return newVars
def extractTags(self, sentence, keys, factors):
"""
Return the words around a key
["na", "I", "run", "na"], "run", 1 -----> ["I", "run", "na"]
"""
listOfTags = []
count = 0
for i in sentence:
if i in keys:
iterNum = 0
#Get words before key
for z in range(factors):
listOfTags += [
str(
self.getSyllable(sentence[(count - factors) +
iterNum]))
]
iterNum += 1
iterNum = 1
for z in range(factors):
listOfTags += [
str(self.getSyllable(sentence[count + iterNum]))
]
iterNum += 1
return listOfTags
count += 1
return listOfTags
def processWords(self,
sentence="I can not take it much farther.",
keys=["further", "farther"],
factors=5):
"""Turns a sentence into a list of syllables with buffer of N factors"""
#Tag sentence
X = sentence.lower().split(" ")
X = [x[0] for x in self.tagSentence(sentence)]
#Add NAs to front and back
X = self.addTags(X, factors)
#Reduce to a list of tags
return self.extractTags(X, keys, factors)
def getSyllable(self, word):
return self.syllable.count(word)
def __init__(self):
self.syllable = CountSyllables()
def __init__(self): self.syllables = CountSyllables()
def __init__(self):
self.cs = CountSyllables()
self.instances = []