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 create_word_cloud(x="result.png"):
f = open("word_repeat_word_cloud", encoding="utf8")
text = f.read()
stopwords = add_stop_words(['نیست'])
stopwords = add_stop_words(['هست'])
stopwords = add_stop_words(['میکنیم'])
stopwords = add_stop_words(['کردند'])
stopwords = add_stop_words(['کنید'])
stopwords = add_stop_words(['میکنند'])
stopwords = add_stop_words(['کردم'])
stopwords = add_stop_words(['کردیم'])
stopwords = add_stop_words(['داریم'])
stopwords = add_stop_words(['کرده'])
stopwords = add_stop_words(['کرد'])
stopwords = add_stop_words(['میکند'])
stopwords = add_stop_words(['میکنم'])
stopwords = add_stop_words(['هستیم'])
stopwords = add_stop_words(['کردید'])
stopwords = add_stop_words(['کنیم'])
stopwords = add_stop_words(['کنند'])
stopwords = add_stop_words(['باشیم'])
stopwords = add_stop_words(['کند'])
stopwords = add_stop_words(['کند'])
stopwords = add_stop_words(['میشود'])
stopwords = add_stop_words(['میشویم'])
stopwords = add_stop_words(['میشوید'])
stopwords = add_stop_words(['اینها'])
# Generate a word cloud image
wordcloud = PersianWordCloud(only_persian=True,
max_words=300,
margin=0,
width=1000,
height=1000,
min_font_size=1,
collocations=False,
max_font_size=500,
stopwords=stopwords,
background_color="black").generate(text)
# Display the generated image:
image = wordcloud.to_image()
image.show()
image.save(x)
f.close()
def genwordcloud(fulltext):
try:
wordcloud = WordCloud(max_font_size=60,
max_words=30,
background_color="white",
collocations=False).generate(fulltext)
# wordcloud.recolor (color_func=color_func, random_state=3)
image = wordcloud.to_image()
output = io.BytesIO()
image.save(output, format="PNG")
print(hostname,
now(),
'/wordcloud: Generated wordcloud image.',
file=sys.stderr)
return output.getvalue()
except:
print(hostname,
now(),
'/wordcloud: Error generating wordcloud image.',
file=sys.stderr)
return None
# 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> #LDA does not work directly on text data. First, it is necessary to convert the documents into a simple vector representation. # This representation will then be used by LDA to determine the topics. # Each entry of a 'document vector' will correspond with the number of times a word occurred in the document.