Python WordCloud.process_text方法代码示例

# 需要导入模块: from wordcloud import WordCloud [as 别名]
# 或者: from wordcloud.WordCloud import process_text [as 别名]
def test_unicode_stopwords():
    wc_unicode = WordCloud(stopwords=[u'Beautiful'])
    try:
        words_unicode = wc_unicode.process_text(unicode(THIS))
    except NameError:  # PY3
        words_unicode = wc_unicode.process_text(THIS)

    wc_str = WordCloud(stopwords=['Beautiful'])
    words_str = wc_str.process_text(str(THIS))

    assert_true(words_unicode == words_str)

# 需要导入模块: from wordcloud import WordCloud [as 别名]
# 或者: from wordcloud.WordCloud import process_text [as 别名]
def test_generate_from_frequencies():
    # test that generate_from_frequencies() takes input argument dicts
    wc = WordCloud(max_words=50)
    words = wc.process_text(THIS)
    result = wc.generate_from_frequencies(words)

    assert_true(isinstance(result, WordCloud))

# 需要导入模块: from wordcloud import WordCloud [as 别名]
# 或者: from wordcloud.WordCloud import process_text [as 别名]
def test_process_text():
    # test that process function returns a dict
    wc = WordCloud(max_words=50)
    result = wc.process_text(THIS)

    # check for proper return type
    assert_true(isinstance(result, dict))

# 需要导入模块: from wordcloud import WordCloud [as 别名]
# 或者: from wordcloud.WordCloud import process_text [as 别名]
def test_generate_from_frequencies():
    # test that generate_from_frequencies() takes input argument of class
    # 'dict_items'
    wc = WordCloud(max_words=50)
    words = wc.process_text(THIS)
    items = words.items()
    result = wc.generate_from_frequencies(items)

    assert_true(isinstance(result, WordCloud))

# 需要导入模块: from wordcloud import WordCloud [as 别名]
# 或者: from wordcloud.WordCloud import process_text [as 别名]
def writeFreq(text, outFile, words):
    """
    Writes frequencies of words into the specified file
    """

    excludewords = STOPWORDS.copy()
    
    for word in words:
        excludewords.add(word)
    
    wordcloud = WordCloud(max_words=NUM_OF_WORDS, stopwords=excludewords)
    freqList  = wordcloud.process_text(text)

    for item in freqList:
        outFile.write(item[0] + ',' + str(item[1]) + '\n')

# 需要导入模块: from wordcloud import WordCloud [as 别名]
# 或者: from wordcloud.WordCloud import process_text [as 别名]
def test_stopwords_lowercasing():
    # test that capitalized stopwords work.
    wc = WordCloud(stopwords=["Beautiful"])
    processed = wc.process_text(THIS)
    words = [count[0] for count in processed]
    assert_true("Beautiful" not in words)

# 需要导入模块: from wordcloud import WordCloud [as 别名]
# 或者: from wordcloud.WordCloud import process_text [as 别名]
def test_process_text_regexp_parameter():
    # test that word processing is influenced by `regexp`
    wc = WordCloud(max_words=50, regexp=r'\w{5}')
    words = wc.process_text(THIS)

    assert_false('than' in words)

# 需要导入模块: from wordcloud import WordCloud [as 别名]
# 或者: from wordcloud.WordCloud import process_text [as 别名]
def test_min_word_length():
    wc_numbers = WordCloud(min_word_length=5)
    wc = wc_numbers.process_text(THIS)
    word_lengths = [len(word) for word in wc.keys()]

    assert min(word_lengths) == 5

# 需要导入模块: from wordcloud import WordCloud [as 别名]
# 或者: from wordcloud.WordCloud import process_text [as 别名]
def test_include_numbers():
    wc_numbers = WordCloud(include_numbers=True)
    wc = wc_numbers.process_text(THIS)

    assert '14' in wc.keys()

# 需要导入模块: from wordcloud import WordCloud [as 别名]
# 或者: from wordcloud.WordCloud import process_text [as 别名]
df = pd.read_csv('music_message.csv', header=None)

text = ''
for line in df[2]:
    text += ' '.join(jieba.cut(line, cut_all=False))
backgroud_Image = plt.imread('job.jpg')
stopwords = set('')
stopwords.update(['封面', 'none介绍', '介绍', '歌单', '歌曲', '我们', '自己', '没有', '就是', '可以', '知道', '一起', '不是', '因为', '什么', '时候', '还是', '如果', '不要', '那些', '那么', '那个', '所有', '一样', '一直', '不会', '现在', '他们', '这样', '最后', '这个', '只是', '有些', '其实', '开始', '曾经', '所以', '不能', '你们', '已经', '后来', '一切', '一定', '这些', '一些', '只有', '还有'])

wc = WordCloud(
    background_color='white',
    mask=backgroud_Image,
    font_path='C:\Windows\Fonts\STZHONGS.TTF',
    max_words=2000,
    max_font_size=150,
    random_state=30,
    stopwords=stopwords
)
wc.generate_from_text(text)
# 看看词频高的有哪些,把无用信息去除
process_word = WordCloud.process_text(wc, text)
sort = sorted(process_word.items(), key=lambda e:e[1], reverse=True)
print(sort[:50])
img_colors = ImageColorGenerator(backgroud_Image)
wc.recolor(color_func=img_colors)
plt.imshow(wc)
plt.axis('off')
wc.to_file("活着.jpg")
print('生成词云成功!')

# 需要导入模块: from wordcloud import WordCloud [as 别名]
# 或者: from wordcloud.WordCloud import process_text [as 别名]
    seed = int(sys.argv[0])
except:
    seed = 0



wc = WordCloud(max_words=10000,
               stopwords=stopwords,
               margin=5,
               random_state=seed,
               height=height,
               max_font_size=max_font_size,
               width=width,
               prefer_horizontal=0.75)

freqs = wc.process_text(text)


freqs = [freqs[1::2],
         freqs[::2]]


count = [0, 0]



for i in range(min([len(x) for x in freqs])):
    if((len(freqs[0][i][0]) > len(freqs[1][i][0]) and count[0] > count[1]) or
       (len(freqs[0][i][0]) < len(freqs[1][i][0]) and count[0] < count[1])):
        freqs[0][i], freqs[1][i] = freqs[1][i], freqs[0][i]
        print("Swapped %d" % i, freqs[0][i], freqs[1][i], count)

# 需要导入模块: from wordcloud import WordCloud [as 别名]
# 或者: from wordcloud.WordCloud import process_text [as 别名]
__author__ = "Nick"

from os import path
import matplotlib.pyplot as plt
from wordcloud import WordCloud, STOPWORDS

text = open("Alice.txt").read()

wc = WordCloud(background_color="white", max_words=100, stopwords=STOPWORDS.add("said"))
wc.generate(text)

print(wc.process_text(text=text))

plt.imshow(wc)
plt.axis("off")
plt.show()