詞頻統計

# utf-8
# 打開英文演講的txt文檔
s_words = {'own', 'the', 'and', 'that', 'this', 'it', 'my', 'when', 'but', 'so', 'where', 'an', 'a'}
sep = ''',.?!:」'「;][ ’'''
with open("dream.txt") as fd:
    words = fd.readlines()
    for i in sep:
        # print(i)
        words = str(words).replace(i, '\n').lower()
tr_words = words.lower().split()
# for w in wordset:
#     print(w)
worddit = {}
for j in tr_words:
    worddit[j] = tr_words.count(j)
diclist = list(worddit.items())
diclist.sort(key=lambda x: x[1], reverse=True)
for d in diclist[0:10]:
    print(d)
wordset = set(tr_words) - s_words
tr_words = list(wordset)
diclist = list(worddit.items())
diclist.sort(key=lambda x: x[1])  #lamba定義了一個匿名函數，只對x[1]進行排序操做
# for d in diclist[0:10]:
#     print(d)

fd.close()