Пример #1
0
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)
Пример #2
0
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)
Пример #3
0
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)
Пример #4
0
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)
Пример #5
0
def handleSentence(sentence, num):
    sentence = sentence.strip()
    words = sentence.split()
    wordTypes = []
    for i in xrange(0, len(words)):
        clearScreen()
        before = ' '.join(words[:i]) + ' '
        if i == 0:
            before = ''
        display = before + colorama.Fore.RED + words[i] \
            + colorama.Style.RESET_ALL + ' ' + ' '.join(words[i + 1:])
        word = taxonomy.sanitize(words[i])
        info = taxonomy.word(word)
        print info['definition']
        print ''
        del info['definition']
        del info['_id']
        print info
        print ''
        for j in xrange(1, len(taxonomy.TYPES)):
            print j, taxonomy.TYPES[j - 1]
        print ''
        print display
        print ''
        res = inp('What kind of word is this? ')
        if res == '':
            res = info['type'][-1]
        else:
            res = taxonomy.TYPES[int(res) - 1]
        wordTypes.append(res)
        if 'type' in info and isinstance(info['type'], list) and \
            not res in info['type']:
            info['type'].append(res)
        else:
            info['type'] = [res]
        mongo.coll.update_one({'_id': word}, {'$set': {'type': info['type']}}, \
            upsert=False)
    try:
        mongo.coll.insert_one({
            '_id': num,
            'sentence': words,
            'types': wordTypes
        })
    except Exception as e:
        print e
        time.sleep(1)
Пример #6
0
def graphSentenceClauses(sentences):
    num = len(sentences) + 1
    chart = pygal.StackedBar(print_labels=True)
    chart.title = 'Sentence Clauses'
    chart.x_labels = map(str, range(1, num))
    allClauses = {clause: [] for clause in CLAUSE_KINDS}
    for i in xrange(1, num):
        sentence = taxonomy.word(i)
        for clause in CLAUSE_KINDS:
            if sentence[clause] != 0:
                sentence[clause] = {'value': sentence[clause], 'label': str(sentence[clause])}
            else:
                sentence[clause] = {'value': sentence[clause], 'label': ''}
            allClauses[clause].append(sentence[clause])
    for clause in allClauses:
        chart.add(clause, allClauses[clause])
    fileName = chart.title.lower().replace(' ', '_')
    chart.render_to_png(taxonomy.outdir(fileName + '.png'))
Пример #7
0
def graphSentenceKinds(sentences):
    num = len(sentences) + 1
    chart = pygal.StackedBar()
    chart.title = 'Kinds Of Sentences'
    chart.x_labels = map(str, range(1, num))
    allKinds = {kind: [] for kind in SENTENCE_KINDS}
    for i in xrange(1, num):
        sentence = taxonomy.word(i)
        for kind in SENTENCE_KINDS:
            if sentence['dependent'] == SENTENCE_KINDS[kind]['dependent'] and \
                sentence['independent'] == SENTENCE_KINDS[kind]['independent']:
                sentenceKind = {'value': 1, 'label': kind}
            else:
                sentenceKind = {'value': 0, 'label': ''}
            allKinds[kind].append(sentenceKind)
    for kind in allKinds:
        chart.add(kind, allKinds[kind])
    fileName = chart.title.lower().replace(' ', '_')
    chart.render_to_png(taxonomy.outdir(fileName + '.png'))
Пример #8
0
def graphSentenceKinds(sentences):
    num = len(sentences) + 1
    chart = pygal.StackedBar()
    chart.title = 'Kinds Of Sentences'
    chart.x_labels = map(str, range(1, num))
    allKinds = {kind: [] for kind in SENTENCE_KINDS}
    for i in xrange(1, num):
        sentence = taxonomy.word(i)
        for kind in SENTENCE_KINDS:
            if sentence['dependent'] == SENTENCE_KINDS[kind]['dependent'] and \
                sentence['independent'] == SENTENCE_KINDS[kind]['independent']:
                sentenceKind = {'value': 1, 'label': kind}
            else:
                sentenceKind = {'value': 0, 'label': ''}
            allKinds[kind].append(sentenceKind)
    for kind in allKinds:
        chart.add(kind, allKinds[kind])
    fileName = chart.title.lower().replace(' ', '_')
    chart.render_to_png(taxonomy.outdir(fileName + '.png'))
Пример #9
0
def handleSentence(sentence, num):
    sentence = sentence.strip()
    words = sentence.split()
    wordTypes = []
    for i in xrange(0, len(words)):
        clearScreen()
        before = ' '.join(words[:i]) + ' '
        if i == 0:
            before = ''
        display = before + colorama.Fore.RED + words[i] \
            + colorama.Style.RESET_ALL + ' ' + ' '.join(words[i + 1:])
        word = taxonomy.sanitize(words[i])
        info = taxonomy.word(word)
        print info['definition']
        print ''
        del info['definition']
        del info['_id']
        print info
        print ''
        for j in xrange(1, len(taxonomy.TYPES)):
            print j, taxonomy.TYPES[j - 1]
        print ''
        print display
        print ''
        res = inp('What kind of word is this? ')
        if res == '':
            res = info['type'][-1]
        else:
            res = taxonomy.TYPES[int(res) - 1]
        wordTypes.append(res)
        if 'type' in info and isinstance(info['type'], list) and \
            not res in info['type']:
            info['type'].append(res)
        else:
            info['type'] = [res]
        mongo.coll.update_one({'_id': word}, {'$set': {'type': info['type']}}, \
            upsert=False)
    try:
        mongo.coll.insert_one({'_id': num, 'sentence': words, 'types': wordTypes})
    except Exception as e:
        print e
        time.sleep(1)
Пример #10
0
def graphSentencePartsOfSpeech(sentences):
    num = len(sentences) + 1
    chart = pygal.StackedBar(print_labels=True)
    chart.title = 'Parts of Speech In Sentences'
    chart.x_labels = map(str, range(1, num))
    allParts = {part: [] for part in taxonomy.TYPES}
    for i in xrange(1, num):
        sentence = taxonomy.word(i)
        counts = {part: 0 for part in taxonomy.TYPES}
        for wordType in sentence['types']:
            counts[wordType] += 1
        for part in counts:
            if counts[part] != 0:
                counts[part] = {'value': counts[part], 'label': str(counts[part])}
            else:
                counts[part] = {'value': counts[part], 'label': ''}
            allParts[part].append(counts[part])
    for part in allParts:
        chart.add(part, allParts[part])
    fileName = chart.title.lower().replace(' ', '_')
    chart.render_to_png(taxonomy.outdir(fileName + '.png'))
Пример #11
0
def graphSentenceClauses(sentences):
    num = len(sentences) + 1
    chart = pygal.StackedBar(print_labels=True)
    chart.title = 'Sentence Clauses'
    chart.x_labels = map(str, range(1, num))
    allClauses = {clause: [] for clause in CLAUSE_KINDS}
    for i in xrange(1, num):
        sentence = taxonomy.word(i)
        for clause in CLAUSE_KINDS:
            if sentence[clause] != 0:
                sentence[clause] = {
                    'value': sentence[clause],
                    'label': str(sentence[clause])
                }
            else:
                sentence[clause] = {'value': sentence[clause], 'label': ''}
            allClauses[clause].append(sentence[clause])
    for clause in allClauses:
        chart.add(clause, allClauses[clause])
    fileName = chart.title.lower().replace(' ', '_')
    chart.render_to_png(taxonomy.outdir(fileName + '.png'))
Пример #12
0
def main():
    word = args.args.word
    try:
        word = int(word)
    except Exception as e:
        pass
    info = taxonomy.word(word)
    if 'definition' in info:
        definition = info['definition']
        del info['definition']
        print definition
        print ''
    print info
    print ''
    print info['_id']
    if args.args.set != '':
        to = args.args.to
        try:
            to = int(to)
        except Exception as e:
            pass
        mongo.coll.update_one({'_id': info['_id']}, \
            {'$set': {args.args.set: to}}, \
            upsert=False)
Пример #13
0
def main():
    word = args.args.word
    try:
        word = int(word)
    except Exception as e:
        pass
    info = taxonomy.word(word)
    if 'definition' in info:
        definition = info['definition']
        del info['definition']
        print definition
        print ''
    print info
    print ''
    print info['_id']
    if args.args.set != '':
        to = args.args.to
        try:
            to = int(to)
        except Exception as e:
            pass
        mongo.coll.update_one({'_id': info['_id']}, \
            {'$set': {args.args.set: to}}, \
            upsert=False)
Пример #14
0
def graphSentencePartsOfSpeech(sentences):
    num = len(sentences) + 1
    chart = pygal.StackedBar(print_labels=True)
    chart.title = 'Parts of Speech In Sentences'
    chart.x_labels = map(str, range(1, num))
    allParts = {part: [] for part in taxonomy.TYPES}
    for i in xrange(1, num):
        sentence = taxonomy.word(i)
        counts = {part: 0 for part in taxonomy.TYPES}
        for wordType in sentence['types']:
            counts[wordType] += 1
        for part in counts:
            if counts[part] != 0:
                counts[part] = {
                    'value': counts[part],
                    'label': str(counts[part])
                }
            else:
                counts[part] = {'value': counts[part], 'label': ''}
            allParts[part].append(counts[part])
    for part in allParts:
        chart.add(part, allParts[part])
    fileName = chart.title.lower().replace(' ', '_')
    chart.render_to_png(taxonomy.outdir(fileName + '.png'))