from wordcloud import WordCloud from csvcols import get_column import matplotlib.pyplot as plt import sys categories = get_column(sys.argv[1], col=1) wordcloud = WordCloud(width=1800, height=1400, max_words=10000, random_state=1, relative_scaling=0.25) wordcloud.fit_words(categories.most_common(len(categories))) plt.imshow(wordcloud) plt.axis("off") wordcloud.to_file("SFPD-wordcloud.png") plt.show()
from cloud import WordCloud from csvcols import get_column import matplotlib.pyplot as plt import sys categories = get_column(sys.argv[1], col=1) wordcloud = WordCloud(width=1800, height=1400, max_words=10000, random_state=1, relative_scaling=0.25) wordcloud.fit_words(categories.most_common(len(categories))) plt.imshow(wordcloud) plt.axis("off") wordcloud.to_file("SFPD-wordcloud.png") plt.show()
from wordcloud import WordCloud from csvcols import get_column import matplotlib.pyplot as plt import sys neighborhoods = get_column(sys.argv[1], col=6) wordcloud = WordCloud(width=1800, height=1400, max_words=10000, random_state=1, relative_scaling=0.25) wordcloud.fit_words(neighborhoods.most_common(len(neighborhoods))) plt.imshow(wordcloud) plt.axis("off") wordcloud.to_file("SFPD-hood-wordcloud.png") plt.show()
import sys from csvcols import get_column categories = get_column(sys.argv[1], col=1) descriptions = get_column(sys.argv[1], col=2) for c, n in categories.most_common(len(categories)): print "%6d %s" % (n, c) for d, n in descriptions.most_common(len(descriptions)): print "%6d %s" % (n, d)