def wrd_cld(toks):
'''Function to visualize word frequency using tokens and is particular to findings of the
corpus used in the toxic words challenge from Kaggle.
toks - tokens rendered from tokinization'''
import string
import nltk
from nltk.corpus import stopwords
from nltk import word_tokenize
import matplotlib.pyplot as plt
# Get all the stop words in the English language
stopwords_list = stopwords.words('english')
#remove punctuation
stopwords_list += list(string.punctuation)
##adding adhoc all strings that don't appear to contribute, added 'article, page and wikipedia' iteratively as
##these are parts of most comment strings
stopwords_list += ("''","``", "'s", "\\n\\n" , '...', 'i\\','\\n',
'•', "i", 'the', "'m", 'i\\', "'ve", "don\\'t",
"'re", "\\n\\ni", "it\\", "'ll", 'you\\', "'d", "n't",
'’', 'article', 'page', 'wikipedia')
import wordcloud
from wordcloud import WordCloud
wordcloud = WordCloud(stopwords=stopwords_list,collocations=False)
wordcloud.generate(','.join(toks))
plt.figure(figsize = (12, 12), facecolor = None)
plt.imshow(wordcloud)
plt.axis('off')
def draw_cloud(dataframe, column):
# Join the different processed titles together.
long_string = ','.join(list(dataframe[column]))
# Create a WordCloud object
wordcloud = WordCloud(background_color="white", max_words=5000, contour_width=6, contour_color='steelblue')
# Generate a word cloud
wordcloud.generate(long_string)
# Visualize the word cloud
return wordcloud.to_image()
def get_wordcloud(image,font,sw,word,result):
wordcloud = WordCloud(scale=15, font_path=font, mask=image, stopwords=sw, background_color='white',
max_words=80000,max_font_size=10, random_state=42)
wordcloud.generate(word)
img_colors = ImageColorGenerator(image)
plt.imshow(wordcloud.recolor(color_func=img_colors))
plt.imshow(wordcloud)
plt.axis('off')
plt.show()
wordcloud.to_file(result)
print('Task Done!')
def data_visualisation(data):
#word cloud
genre = data['genres'].str.split('|')
str2 = ','.join(str(i) for i in genre)
print(str2)
wordcloud = WordCloud()
wordcloud.generate(str2)
plt.figure()
plt.max_words = 200
plt.imshow(wordcloud, interpolation="bilinear")
plt.axis("off")
plt.show()
def generate_wordcloud(logo_image,text, stopwords_list, portal, today, path):
custom_mask = np.array(Image.open(logo_image))
wordcloud = WordCloud(stopwords = stopwords_list, background_color="white",mask=custom_mask)
wordcloud.generate(text)
image_colors = ImageColorGenerator(custom_mask)
wordcloud.recolor(color_func=image_colors)
plt.figure(figsize=(10,10))
plt.imshow(wordcloud, interpolation="bilinear")
plt.axis("off")
plt.savefig( path + "/wordclouds/wordcloud_"+portal+"_"+today+".png")
def generateWordCloud(corpus: str, cmap: str) -> wordcloud:
"""
Return a Word Cloud object generated from the corpus and color map parameter.
"""
wordcloud = WordCloud(background_color='black',
width=800,
height=400,
colormap=cmap,
max_words=180,
contour_width=3,
max_font_size=80,
contour_color='steelblue',
random_state=0)
wordcloud.generate(corpus)
plt.imshow(wordcloud, interpolation='bilinear')
plt.axis("off")
plt.figure()
return wordcloud
# Visualisation is key to understanding whether we are still on the right track! In addition, # it allows us to verify whether we need additional preprocessing before further analyzing the text data. # Import the wordcloud library import wordcloud # Join the different processed titles together. s = " " long_string = s.join(papers['title_processed']) # print (long_string) # Create a WordCloud object wordcloud = wordcloud.WordCloud() # Generate a word cloud wordcloud.generate(long_string) # Visualize the word cloud wordcloud.to_image() import matplotlib.pyplot as plt plt.figure() plt.imshow(wordcloud, interpolation="bilinear") plt.show() # ## 6. Prepare the text for LDA analysis #The main text analysis method that we will use is latent Dirichlet allocation (LDA). # LDA is able to perform topic detection on large document sets, determining what the main 'topics' are in a large unlabeled set of texts. # A 'topic' is a collection of words that tend to co-occur often. # The hypothesis is that LDA might be able to clarify what the different topics in the research titles are. # These topics can then be used as a starting point for further analysis.</p>
import tweepy
import wordcloud
from Credentialstwitter import *
from wordcloud import WordCloud, STOPWORDS
import matplotlib.pyplot as plt
auth = tweepy.OAuthHandler(ConsumerKey, ConsumerSecret)
api = tweepy.API(auth)
text = " "
tweets = api.user_timeline(screen_name="maiconkusterkkk",
count=1000,
include_rts=False,
tweet_mode="extended")
for tweet in tweets:
#print(tweet.full_text)
text = text + " " + tweet.full_text
wordcloud = WordCloud(width=1920, height=1200)
STOPWORDS.update(["hppt", "https", "co", "da","de","em","na","se","às","como","que", "para", "os", "dos", "das", "assim", "quais","feira","um", "uma", "mais", "ao", "por","pelo","pela",\
"como", "nosso", "nossa", "zu", "das", "zu","die","der","dem","und","auf","ein","nicht","von","wie","wird", "daß", "dass","mit","für", "Sie","sie","er","noch","vor","ist", "bei",\
"wenn", "sich", "den", "hat", "des", "diese", "diesen", "dieses", "dieser", "über", "eine", "einer", "einen", "eines", "auch", "es", "werden", "auch", "im", "als", "uns", "sehr",\
"aber", "einem", "zur", "nun", "mehr", "zum", "durch", "sind", "kann", "man", "aus", "nur", "haben", "will", "é" ])
wordcloud.generate(text)
plt.imshow(wordcloud)
plt.axis("off")
plt.show()
import matplotlib.pyplot as plt
# import os
# pwd = os.getcwd()
# print(pwd)
file_ad = r"439-黄帝内经太素[204].txt"
str = open(file_ad, encoding='gb2312')
with str as f:
data = f.read()
pattern = re.compile('(?<=\[)[^\[.]+?(?=\])')
search = pattern.findall(data)
# print(search)
if search:
for group in search:
seg_list = jieba.cut(group, cut_all=False)
print(",".join(seg_list))
# wordcloud = WordCloud(max_font_size=40, relative_scaling=.5)
wordcloud = WordCloud(font_path=u'./static/simheittf/simhei.ttf',
background_color="black",
margin=5,
width=1800,
height=800)
wordcloud = wordcloud.generate(seg_list)
plt.figure()
plt.imshow(wordcloud)
plt.axis("off")
plt.show()