Initial commit: Python learning project with examples and exercises
This commit is contained in:
@@ -0,0 +1,18 @@
|
||||
#e10.3CalThreeKingdoms.py
|
||||
from jieba import*
|
||||
excludes = {} #{"将军","却说","丞相"}
|
||||
txt = open("三国演义.txt", "r", encoding='utf_8').read()
|
||||
words = lcut(txt) #jieba
|
||||
counts = {}
|
||||
for word in words:
|
||||
if len(word) == 1: #排除单个字符的分词结果
|
||||
continue
|
||||
else:
|
||||
counts[word] = counts.get(word,0) + 1
|
||||
for word in excludes:
|
||||
del(counts[word])
|
||||
items = list(counts.items())
|
||||
items.sort(key=lambda x:x[1], reverse=True)
|
||||
for i in range(15):
|
||||
word, count = items[i]
|
||||
print ("{0:<10}{1:>5}".format(word, count))
|
||||
@@ -0,0 +1,27 @@
|
||||
#e10.4CalThreeKingdoms.py
|
||||
import jieba
|
||||
excludes = {"将军","却说","荆州","二人","不可","不能","如此"}
|
||||
txt = open("三国演义.txt", "r", encoding='utf-8').read()
|
||||
words = jieba.lcut(txt)
|
||||
counts = {}
|
||||
for word in words:
|
||||
if len(word) == 1:
|
||||
continue
|
||||
elif word == "诸葛亮" or word == "孔明曰":
|
||||
rword = "孔明"
|
||||
elif word == "关公" or word == "云长":
|
||||
rword = "关羽"
|
||||
elif word == "玄德" or word == "玄德曰":
|
||||
rword = "刘备"
|
||||
elif word == "孟德" or word == "丞相":
|
||||
rword = "曹操"
|
||||
else:
|
||||
rword = word
|
||||
counts[rword] = counts.get(rword,0) + 1
|
||||
for word in excludes:
|
||||
del(counts[word])
|
||||
items = list(counts.items())
|
||||
items.sort(key=lambda x:x[1], reverse=True)
|
||||
for i in range(5):
|
||||
word, count = items[i]
|
||||
print ("{0:<10}{1:>5}".format(word, count))
|
||||
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user