def avgWordLengthBucketed(text):
tokens = Tokenize.byWordAlphaOnly(text)
sum = 0
count = 0
for token in tokens:
sum += len(token)
count +=1
numericValue = int(sum/count)
bucketLabel = "Long" if numericValue > 6 else "Medium" if numericValue > 4 else "Short"
return {"AVG word Length" : bucketLabel}
def avgWordLengthBucketed(text):
tokens = Tokenize.byWordAlphaOnly(text)
sum = 0
count = 0
for token in tokens:
sum += len(token)
count += 1
numericValue = int(sum / count)
bucketLabel = "Long" if numericValue > 6 else "Medium" if numericValue > 4 else "Short"
return {"AVG word Length": bucketLabel}
def avgWordLength(text):
text = " ".join(text)
tokens = Tokenize.byWordAlphaOnly(text)
sum = 0
count = 0
tokens = list(set(tokens))
for token in tokens:
if token.isalpha():
sum += len(token)
count += 1
return {"AVG word Length": int(sum / count)}
def avgWordLength(text):
text = " ".join(text)
tokens = Tokenize.byWordAlphaOnly(text)
sum = 0
count = 0
tokens = list(set(tokens))
for token in tokens:
if token.isalpha():
sum += len(token)
count +=1
return {"AVG word Length" : int(sum/count)}
def feature(text):
text = " ".join(text)
tokens = Tokenize.byWord(text)
words=[]
if stem:
words = Tokenize.byWordStem(text)
else:
words = Tokenize.byWordAlphaOnly(text)
fd = Ngrams.getNgramFreqDist(words,n)
topM = sorted([item for item in fd.items()],key=lambda x:x[1], reverse=True)[:m]
vector = {}
for i in range(len(topM)):
vector["word#"+str(i)+" "+str(n)+"gramW"] = topM[i][0]
return vector
def feature(text):
text = " ".join(text)
tokens = Tokenize.byWord(text)
words = []
if stem:
words = Tokenize.byWordStem(text)
else:
words = Tokenize.byWordAlphaOnly(text)
fd = Ngrams.getNgramFreqDist(words, n)
topM = sorted([item for item in fd.items()],
key=lambda x: x[1],
reverse=True)[:m]
vector = {}
for i in range(len(topM)):
vector["word#" + str(i) + " " + str(n) + "gramW"] = topM[i][0]
return vector
def wordLengthDist(text):
text = " ".join(text)
words = Tokenize.byWordAlphaOnly(text)
vector = {}
total = 0
for i in range(1,11):
vector["%ofwords"+str(i)+"long"] = 0
count = 0
words = list(set(words))
for word in words:
if len(word) < 10:
vector["%ofwords"+str(len(word))+"long"] += 1
else:
vector["%ofwords"+str(10)+"long"] += 1
total +=1
for i in range(1,11):
vector["%ofwords"+str(i)+"long"] = int(100*vector["%ofwords"+str(i)+"long"]/total)
return vector
def wordLengthDist(text):
text = " ".join(text)
words = Tokenize.byWordAlphaOnly(text)
vector = {}
total = 0
for i in range(1, 11):
vector["%ofwords" + str(i) + "long"] = 0
count = 0
words = list(set(words))
for word in words:
if len(word) < 10:
vector["%ofwords" + str(len(word)) + "long"] += 1
else:
vector["%ofwords" + str(10) + "long"] += 1
total += 1
for i in range(1, 11):
vector["%ofwords" + str(i) + "long"] = int(
100 * vector["%ofwords" + str(i) + "long"] / total)
return vector
