def createDocumentVector(fileObj, tfRawD):
fileContent = FileReader(fileObj).content
fileContent = ''.join(map(lambda x: ' ' if x != '.' and ord(x) < 48 or 57 < ord(x) < 65 else x, list(fileContent)))
words = fileContent.strip().split()
length = len(words)
uniqueWordsInDoc = set()
for word in words:
word = modify_word(word)
if word:
uniqueWordsInDoc.add(word)
if word not in tfRawD:
tfRawD[word] = 1
else:
tfRawD[word] += 1
return uniqueWordsInDoc, words, length, tfRawD
def createTopicVector(fileObj, T, tfRaw):
fileContent = FileReader(fileObj).content
fileContent = ''.join(map(lambda x: ' ' if x != '.' and ord(x) < 48 or 57 < ord(x) < 65 else x, list(fileContent)))
words = fileContent.strip().split()
length = len(words)
DVector = set()
T.extend(words)
for word in words:
word = modify_word(word)
if word:
DVector.add(word)
if word not in tfRaw:
tfRaw[word] = 1
else:
tfRaw[word] += 1
return DVector, length
def createDocumentVector(fileObj, tfRawD):
fileContent = FileReader(fileObj).content
fileContent = ''.join(
map(
lambda x: ' '
if x != '.' and ord(x) < 48 or 57 < ord(x) < 65 else x,
list(fileContent)))
words = fileContent.strip().split()
length = len(words)
uniqueWordsInDoc = set()
for word in words:
word = modify_word(word)
if word:
uniqueWordsInDoc.add(word)
if word not in tfRawD:
tfRawD[word] = 1
else:
tfRawD[word] += 1
return uniqueWordsInDoc, words, length, tfRawD
def createTopicVector(fileObj, T, tfRaw):
fileContent = FileReader(fileObj).content
fileContent = ''.join(
map(
lambda x: ' '
if x != '.' and ord(x) < 48 or 57 < ord(x) < 65 else x,
list(fileContent)))
words = fileContent.strip().split()
length = len(words)
DVector = set()
T.extend(words)
for word in words:
word = modify_word(word)
if word:
DVector.add(word)
if word not in tfRaw:
tfRaw[word] = 1
else:
tfRaw[word] += 1
return DVector, length
