diff --git a/英文.py b/英文.py new file mode 100644 index 0000000..7fea9f9 --- /dev/null +++ b/英文.py @@ -0,0 +1,41 @@ + +import numpy as np +from wordcloud import WordCloud +import matplotlib.pyplot as plt +from wordcloud import STOPWORDS +def getTxt(): + txt = open(r'C:\jieba-python\英文\xxx.txt').read() + txt = txt.lower() + for ch in '!"@#$%^&*()+,-./:;<=>?@[\\]_`~{|}': + txt = txt.replace(ch, ' ') + return txt +hamletTxt = getTxt() +words = hamletTxt.split() +counts = {} +for word in words: + counts[word] = counts.get(word,0) + 1 +for word in list(STOPWORDS): + counts.pop(word, 0) + items = list(counts.items()) + items.sort(key = lambda x:x[1], reverse = True) +infos, counts = [], [] +for i in range(10): + word, count = items[i] + infos.append(word) + counts.append(count) + print('{0:<10}{1:>5}'.format(word, count)) +plt.bar(range(len(infos)), counts, width=0.8) +plt.xticks(list(range(0, 10)), infos, fontsize=12) +for a, b in zip(np.arange(len(infos)), counts): + plt.text(a, b, '%d' % b, ha='center', va='bottom', fontsize=12) +plt.savefig(r'C:\jieba-python\英文\tb1.png', dpi=300, bbox_inches='tight') +text_y = open(r"C:\jieba-python\英文\xxx.txt").read() +wordcloud = WordCloud(width=800, height=600,background_color="white", max_words=2000) +ax = wordcloud.generate(text_y) +width,height = 24, 14 +plt.figure() +plt.figure(figsize=(width,height)) +plt.imshow(ax, interpolation='bilinear') +plt.axis('off') +plt.show() +wordcloud.to_file("C:\jieba-python\英文\\xxx.png")