一
1.集合类型定义及其操作：
集合用{}表示，元素用逗号分隔，无序，唯一
集合操作符：
|：并
-：减
&：交
^ ：补
<= <：判断子集关系
>= >：判断包含关系
|=：
-=：
&=：
^=：
集合处理方法：
S.add(x) 字面意思
S.discard(x) 移除S中元素x，若不在，不报错
S.remove(x) 移除S中元素x，若不在，产生KeyError异常
S.clear(x) 移除S中所有元素
S.pop(x) 随机返回S的一个元素，更新S，若S为空产生KeyError异常
S.copy()
len(S)
x in S
x not in S
set(x)
集合类型应用场景：
包含关系比较
元素去重
2.序列类型及其操作：
定义：一维元素向量，元素类型可以不同
比如字符串
序列操作符：in, not in,s+t,s*n,s[i],s[i:j:k]
函数：len(s),min(s),max(s),s.index(x)或s.index(x,i,j),返回序列s从i开始到j位置中第一次出现x的位置，s.count(x)，返回s中出现x的总次数
元组类型及其操作：一旦创建不能被更改，tuple()
列表类型及其操作：可以随意修改，使用[]或list()创建
ls[i] = x
ls[i:j:k] = lt
del s[i],del ls[i:j:k]删除
ls += lt
ls *= n
ls.append(x) 在列表ls最后增加一个元素x
ls.clear()
ls.copy()
ls.insert(i,x)
ls.pop(i) 取出并删除
ls.remove(x) 删除第一个x
ls.reverse() 将ls中的元素反转
3.序列类型应用场景：
item遍历
4.sorted排序
二
基本统计值实例
#CalStatisticsV1.py
def getNum():
nums = []
iNumStr = input("请输入数字(回车退出)：")
while iNumStr !="":
nums.append(eval(iNumStr))
iNumStr = input("请输入数字(回车退出)：")
return nums def mean(numbers):
s = 0.0
for num in numbers:
s = s+num
return s / len(numbers) def dev(numbers,mean):
sdev = 0.0
for num in numbers:
sdev = sdev + (num-mean)**2
return pow(sdev / (len(numbers)-1),0.5) def median(numbers):
sorted(numbers)
size = len(numbers)
if size % 2 == 0:
med = (numbers[size//2-1]+numbers[size//2])/2
else:
med = numbers[size//2]
return med n = getNum()
m = mean(n)
print("平均值:{},方差:{:.2},中位数:{}".format(m,dev(n,m),median(n)))
三、字典类型
映射是键和值的对应
采用{}和dict()创建，键值对用冒号:表示
d = {"C":"B","M":"H","F":"B"}
>>> d
{'C': 'B', 'M': 'H', 'F': 'B'}
>>> d["C"]
del d[k] 删除字典d中键k对应的数据值
k in d 判断键k是否在字典中
d.keys() 返回字典d中所有的键信息
d.values() 返回字典d中所有的值信息
d.items() 返回字典d中所有的键值对信息
>>> d = {"中国":"北京","美国":"华盛顿","法国":"巴黎"}
>>> "中国" in d
True
>>> d.keys()
dict_keys(['中国', '美国', '法国'])
>>> d.values()
dict_values(['北京', '华盛顿', '巴黎'])
d.get(k,<default>) 键k存在，则返回相应的值，不在，则返回<default>值
d.pop(k,<default>) 键k存在，则取出相应的值，不在，则返回<default>值
d.popitem() 随机从字典d中取出一个键值对，以元组形式返回
d.clear() 删除所有键值对
len(d) 返回字典d中元素的个数
>>> d.get("中国","*堡")
'北京'
>>> d.get("日本","*堡")
'*堡'
>>> d.popitem()
('法国', '巴黎')
定义空字典 ：d = {}
向d增加两个键值对元素：d["a"] = 1;d["b"] = 2
字典类型应用场景：
四、jieba库
Microsoft Windows [版本 10.0.17134.648]
(c) Microsoft Corporation。保留所有权利。 C:\Users\ASUS>pip install jieba
Collecting jieba
Downloading https://files.pythonhosted.org/packages/71/46/c6f9179f73b818d5827202ad1c4a94e371a29473b7f043b736b4dab6b8cd/jieba-0.39.zip (7.3MB)
% |████████▌ | .9MB 19kB/s eta ::32Exception:
Traceback (most recent call last):
File "c:\users\asus\appdata\local\programs\python\python37-32\lib\site-packages\pip\_vendor\urllib3\response.py", line , in _error_catcher
yield
File "c:\users\asus\appdata\local\programs\python\python37-32\lib\site-packages\pip\_vendor\urllib3\response.py", line , in read
data = self._fp.read(amt)
File "c:\users\asus\appdata\local\programs\python\python37-32\lib\site-packages\pip\_vendor\cachecontrol\filewrapper.py", line , in read
data = self.__fp.read(amt)
File "c:\users\asus\appdata\local\programs\python\python37-32\lib\http\client.py", line , in read
n = self.readinto(b)
File "c:\users\asus\appdata\local\programs\python\python37-32\lib\http\client.py", line , in readinto
n = self.fp.readinto(b)
File "c:\users\asus\appdata\local\programs\python\python37-32\lib\socket.py", line , in readinto
return self._sock.recv_into(b)
File "c:\users\asus\appdata\local\programs\python\python37-32\lib\ssl.py", line , in recv_into
return self.read(nbytes, buffer)
File "c:\users\asus\appdata\local\programs\python\python37-32\lib\ssl.py", line , in read
return self._sslobj.read(len, buffer)
socket.timeout: The read operation timed out During handling of the above exception, another exception occurred: Traceback (most recent call last):
File "c:\users\asus\appdata\local\programs\python\python37-32\lib\site-packages\pip\_internal\cli\base_command.py", line , in main
status = self.run(options, args)
File "c:\users\asus\appdata\local\programs\python\python37-32\lib\site-packages\pip\_internal\commands\install.py", line , in run
resolver.resolve(requirement_set)
File "c:\users\asus\appdata\local\programs\python\python37-32\lib\site-packages\pip\_internal\resolve.py", line , in resolve
self._resolve_one(requirement_set, req)
File "c:\users\asus\appdata\local\programs\python\python37-32\lib\site-packages\pip\_internal\resolve.py", line , in _resolve_one
abstract_dist = self._get_abstract_dist_for(req_to_install)
File "c:\users\asus\appdata\local\programs\python\python37-32\lib\site-packages\pip\_internal\resolve.py", line , in _get_abstract_dist_for
self.require_hashes
File "c:\users\asus\appdata\local\programs\python\python37-32\lib\site-packages\pip\_internal\operations\prepare.py", line , in prepare_linked_requirement
progress_bar=self.progress_bar
File "c:\users\asus\appdata\local\programs\python\python37-32\lib\site-packages\pip\_internal\download.py", line , in unpack_url
progress_bar=progress_bar
File "c:\users\asus\appdata\local\programs\python\python37-32\lib\site-packages\pip\_internal\download.py", line , in unpack_http_url
progress_bar)
File "c:\users\asus\appdata\local\programs\python\python37-32\lib\site-packages\pip\_internal\download.py", line , in _download_http_url
_download_url(resp, link, content_file, hashes, progress_bar)
File "c:\users\asus\appdata\local\programs\python\python37-32\lib\site-packages\pip\_internal\download.py", line , in _download_url
hashes.check_against_chunks(downloaded_chunks)
File "c:\users\asus\appdata\local\programs\python\python37-32\lib\site-packages\pip\_internal\utils\hashes.py", line , in check_against_chunks
for chunk in chunks:
File "c:\users\asus\appdata\local\programs\python\python37-32\lib\site-packages\pip\_internal\download.py", line , in written_chunks
for chunk in chunks:
File "c:\users\asus\appdata\local\programs\python\python37-32\lib\site-packages\pip\_internal\utils\ui.py", line , in iter
for x in it:
File "c:\users\asus\appdata\local\programs\python\python37-32\lib\site-packages\pip\_internal\download.py", line , in resp_read
decode_content=False):
File "c:\users\asus\appdata\local\programs\python\python37-32\lib\site-packages\pip\_vendor\urllib3\response.py", line , in stream
data = self.read(amt=amt, decode_content=decode_content)
File "c:\users\asus\appdata\local\programs\python\python37-32\lib\site-packages\pip\_vendor\urllib3\response.py", line , in read
raise IncompleteRead(self._fp_bytes_read, self.length_remaining)
File "c:\users\asus\appdata\local\programs\python\python37-32\lib\contextlib.py", line , in __exit__
self.gen.throw(type, value, traceback)
File "c:\users\asus\appdata\local\programs\python\python37-32\lib\site-packages\pip\_vendor\urllib3\response.py", line , in _error_catcher
raise ReadTimeoutError(self._pool, None, 'Read timed out.')
pip._vendor.urllib3.exceptions.ReadTimeoutError: HTTPSConnectionPool(host='files.pythonhosted.org', port=): Read timed out.
You are using pip version 18.1, however version 19.0. is available.
You should consider upgrading via the 'python -m pip install --upgrade pip' command. C:\Users\ASUS>python -m pip install --upgrade pip
Collecting pip
Downloading https://files.pythonhosted.org/packages/d8/f3/413bab4ff08e1fc4828dfc59996d721917df8e8583ea85385d51125dceff/pip-19.0.3-py2.py3-none-any.whl (1.4MB)
% |████████████████████████████████| .4MB 20kB/s
Installing collected packages: pip
Found existing installation: pip 18.1
Uninstalling pip-18.1:
Successfully uninstalled pip-18.1
Successfully installed pip-19.0. C:\Users\ASUS>pip install jieba
Collecting jieba
Downloading https://files.pythonhosted.org/packages/71/46/c6f9179f73b818d5827202ad1c4a94e371a29473b7f043b736b4dab6b8cd/jieba-0.39.zip (7.3MB)
% |████████████████████████████████| .3MB 445kB/s
Installing collected packages: jieba
Running setup.py install for jieba ... done
Successfully installed jieba-0.39 C:\Users\ASUS>
精确模式：把文本精确地切分开，不存在冗余单词
全模式：有冗余
搜索引擎模式：在精确模式基础上，对长词再次切分
函数：
jieba.lcut(s) ，精确模式，返回一个列表类型的分词结果
jieba.lcut(s,cut_all=True) ，全模式，返回一个列表类型的分词结果,存在冗余
jieba.lcut_for_search(s) ，搜索引擎模式，返回一个列表类型的分词结果,存在冗余
jieba.add_word(w) 向分词词典增加新词w
>>> import jieba
>>> jieba.lcut("中国是一个伟大的国家")
Building prefix dict from the default dictionary ...
Dumping model to file cache C:\Users\ASUS\AppData\Local\Temp\jieba.cache
Loading model cost 1.139 seconds.
Prefix dict has been built succesfully.
['中国', '是', '一个', '伟大', '的', '国家']
>>> jieba.lcut("中国是一个伟大的国家")
['中国', '是', '一个', '伟大', '的', '国家']
>>> jieba.lcut("中国是一个伟大的国家",cut_all=True)
['中国', '国是', '一个', '伟大', '的', '国家']
>>> jieba.lcut_for_search("*是伟大的")
['中华', '华人', '人民', '共和', '*', '*', '是', '伟大', '的']
五、“文本词频统计”实例
#CalHamletV1.py
def getText():
txt = open("hamlet.txt","r").read() #读取文本
txt = txt.lower()
for ch in '~!@#$%^&*()_+{}:"<>?[];,./-=':
txt = txt.replace(ch," ")
return txt hamletTxt = getText()
words = hamletTxt.split()
counts = {}
for word in words:
counts[word] = counts.get(word,0)+1 #统计词频
items = list(counts.items())
items.sort(key=lambda x:x[1],reverse=True) #降序排列
for i in range(10):
word,count = items[i]
print("{0:<10}{1:>5}".format(word,count))
#CalThreeKingdomsV1.py
import jieba
txt = open("threekingdoms.txt","r",encoding="utf-8").read()
words = jieba.lcut(txt)
counts = {}
for word in words:
if len(word)==1:
continue
else:
counts[word] = counts.get(word,0)+1
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))
运行遇到问题，直接评论即可
#CalThreeKingdomsV2.py
import jieba
excludes= {"将军","却说","荆州","二人","不可","不能","如此","商议","如何","军士"}
txt = open("threekingdoms.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=="丞相曰" or word=="丞相" or word=="主公":
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(15):
word,count = items[i]
print("{0:<10}{1:>5}".format(word,count))