def mostUsed(fileName, top=10):
fileData = taxonomy.readFile(fileName)
section = [taxonomy.sanitize(word) for word in fileData.split()]
wordCounts = {word: 0 for word in section}
for word in section:
wordCounts[word] += 1
allWords = [{'label': word, 'value': wordCounts[word]} \
for word in wordCounts]
allWords = sorted(allWords, key=lambda x: x['value'], reverse=True)
topWords = allWords[:top]
return topWords
def mostUsed(fileName, top=10):
fileData = taxonomy.readFile(fileName)
section = [taxonomy.sanitize(word) for word in fileData.split()]
wordCounts = {word: 0 for word in section}
for word in section:
wordCounts[word] += 1
allWords = [{'label': word, 'value': wordCounts[word]} \
for word in wordCounts]
allWords = sorted(allWords, key=lambda x: x['value'], reverse=True)
topWords = allWords[:top]
return topWords
def main():
allLines = taxonomy.readFile(args.args.file)
num = 1
sentences = [sentence.strip() for sentence in allLines.split('.')]
graphSentenceLength(sentences)
graphSentenceWordUse(sentences)
graphSentenceWordUse(sentences, top=5)
for sentence in sentences:
if len(sentence) > 0:
alreadyDone = taxonomy.word(num)
if alreadyDone == None:
handleSentence(sentence, num)
num += 1
graphSentencePartsOfSpeech(sentences)
def main():
allLines = taxonomy.readFile(args.args.file)
num = 1
sentences = [sentence.strip() for sentence in allLines.split('.')]
for sentence in sentences:
if len(sentence) > 0:
alreadyDone = taxonomy.word(num)
if alreadyDone == None or \
not 'independent' in alreadyDone or \
not 'dependent' in alreadyDone:
handleSentence(sentence, num)
num += 1
graphSentenceClauses(sentences)
graphSentenceKinds(sentences)
def main():
allLines = taxonomy.readFile(args.args.file)
num = 1
sentences = [sentence.strip() for sentence in allLines.split('.')]
for sentence in sentences:
if len(sentence) > 0:
alreadyDone = taxonomy.word(num)
if alreadyDone == None or \
not 'independent' in alreadyDone or \
not 'dependent' in alreadyDone:
handleSentence(sentence, num)
num += 1
graphSentenceClauses(sentences)
graphSentenceKinds(sentences)
def main():
allLines = taxonomy.readFile(args.args.file)
num = 1
sentences = [sentence.strip() for sentence in allLines.split('.')]
graphSentenceLength(sentences)
graphSentenceWordUse(sentences)
graphSentenceWordUse(sentences, top=5)
for sentence in sentences:
if len(sentence) > 0:
alreadyDone = taxonomy.word(num)
if alreadyDone == None:
handleSentence(sentence, num)
num += 1
graphSentencePartsOfSpeech(sentences)
def main():
allLines = taxonomy.readFile(args.args.file)
sentences = [sentence.strip() for sentence in allLines.split('.')]
graphAllPuntuation(sentences)
