1.Python标准库GUI界面（turtle）
1.1turtle的简单实用
turtle的简单使用
import turtle as t
t.done()
t.color('blue')
- 绘制NEUSOFT
- 水平左移
- 抬笔
t.penup()
t.goto(-260, 0)
t.pd()
1.2绘制N
t.left(90)
t.forward(80)
t.right(145)
1.3简写
t.fd(100)
t.lt(145)
t.fd(80)
1.4绘制O
t.penup()
t.goto(200, 40)
t.pd()
t.circle(30, 180)
1.5 绘制 S
t.penup()
t.goto(120, 50)
t.pd()
t.circle(22,270)
2.python常用数据类型
列表: 与c语言中的数组很相似， 只不过可以存储不同类型的数据
优点：灵活 ，缺点： 效率低
定义方式 []
hero_name = ['鲁班七号', '安琪拉', '李白', '刘备']
输出
print(hero_name)
遍历
for hero in hero_name:
print(hero)
3.常见操作
3.1列表的访问
列表名[索引]
print(hero_name[2])
3. 2添加 append
hero_name.append('后羿')
print('添加后的列表', hero_name)
3.3修改
hero_name[1] = 1000
print('修改后的列表',hero_name)
3.4删除
del hero_name[1]
print('删除后的列表',hero_name)
5.字典 (dict java hashmap)
- key-value数据结构
- 定义形式 {}
info = {'name':'李四', 'age':34, 'addr':'重庆市渝北区'}
print(len(info))
print(info)
5.1字典的访问
print(info['name'])
5.2修改
info['addr'] = '北京市朝阳区'
print('修改后字典',info)
5.3增加
info['sex'] = 'female'
print('增加后字典',info)
5.4获取字典中所有的键
print(info.keys())
5.5获取字典中所有的z值
print(info.values())
5.6获取字典中所有的key-value
print(info.items())
d = [('name', '李四'), ('age', 34), ('addr', '北京市朝阳区'), ('sex', 'female')]
d1 = dict(d)
print(d1)
5.7遍历字典
for k, v in info.items():
print(k, v)
集合
- 无序，不重复
set1 = {'zhangsan', 'lisi', 222}
print(type(set1))
- 遍历
for x in set1:
print(x)
掌握python常用数据类型和语法
- 列表的排序
li = []
for i in range(10):
li.append(i)
print(li)
from random import shuffle
shuffle(li)
print('随机打乱的列表', li)
li.sort(reverse=True)
print('排序后的列表', li)
stu_info = [
{"name":'zhangsan', "age":18},
{"name":'lisi', "age":30},
{"name":'wangwu', "age":99},
{"name":'tiaqi', "age":3},
]
print('排序前', stu_info)
- def 函数名(参数):
# 函数体
def sort_by_age(x):
return x['age']
# key= 函数名 --- 按照什么进行排序
# 根据年龄大小进行正序排序
stu_info.sort(key=sort_by_age, reverse=True)
print('排序后', stu_info)
- 练习
根据元组第二个元素进行正序排序
name_info_list = [
('张三',4500),
('李四',9900),
('王五',2000),
('赵六',5500),
]
def sort_by_grade(i):
return i[1]
# 根据元组第二个元素进行正序排序
name_info_list.sort(key=sort_by_grade)
print(name_info_list)
- 例子
def say_hello(name):
print('hello, {}'.format(name))
say_hello('重庆师范')
6.本地文件读取
- python中使用open内置函数进行文件读取
f = open(file='./novel/threekingdom.txt', mode='r', encoding='utf-8')
data = f.read()
f.close()
data = open(file='./novel/threekingdom.txt', mode='r', encoding='utf-8').read()
print(data)
- with as 上下文管理器 不用手动关闭流
with open('./novel/threekingdom.txt', 'r', encoding='utf-8') as f:
data = f.read()
print(data)
- 写入
txt = 'i like python'
with open('python.txt','w', encoding='utf-8') as f:
f.write(txt)
text = """<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<title>Title</title>
</head>
<body>
<h1>重庆师范欢迎你</h1>
</body>
</html>"""
print(text)
with open('chongqingshifan.html','w', encoding='utf-8') as f:
f.write(text)
中文分词 jieba
PyCharm IDE中，可以直接引入各种工具包。jieba中文分词工具包安装非常方便。
1、打开Pycharm，点击左上角 >>File >>Settings。
2、在settings界面中点击Project :（项目名称） >>Project interpreter 。或者在左上角搜索框里输入“project interpreter”搜索定位。
3、>>点击右绿色“+”号，添加Package。
4、在可用包界面中，输入"jieba"搜索，找到jieba，点击下方“Install …”安装。
5、验证是否安装成功。再次打开Project interpreter（ File >>Settings>>Project :（项目名称） >> Project interpreter），看到列表中已有Package“jieba”。表明安装成功。
- 安装jieba分词库
- 指定国内镜像安装
- 1.在用户目录下新建pip文件夹
- 2.新建pip.ini文件
- 添加
"""
[global]
index-url = http://mirrors.aliyun.com/pypi/simple/
[install]
trusted-host=mirrors.aliyun.com
"""
# pip install jieba
# 导入jieba分词
import jieba
# 三种分词模式
seg = "我来到北京清华大学"
# 精确模式 精确分词
seg_list = jieba.lcut(seg)
print(seg_list)
# 全模式 找出所有可能的分词结果 冗余性大
seg_list1 = jieba.lcut(seg,cut_all=True)
print(seg_list1)
# 搜索引擎模式
seg_list2 = jieba.lcut_for_search(seg)
print(seg_list2)
#
text = '小明硕士毕业于中国科学院计算所，后在日本京都大学深造'
seg_list4 = jieba.lcut(text,cut_all=True)
print(seg_list4)
# 搜索引擎模式 先执行精确模式，在对其中的长词进行处理
seg_list5 = jieba.lcut_for_search(text)
print(seg_list5)
# nlp
import jieba
# 三国演义小说分词
# 读取三国演义小说
with open('./novel/threekingdom.txt','r', encoding='utf-8') as f:
words = f.read()
print(len(words)) # 字数 55万
words_list = jieba.lcut(words)
print(len(words_list)) # 分词后的词语数 35万
print(words_list)
词云的展示
- 安装
- pip install wordcloud
- 本地安装python库
# 导入词云 WordCloud类
from wordcloud import WordCloud
import jieba
import imageio
# 绘制词云
# text = 'He was an old man who fished alone in a skiff in the Gulf Stream and he had gone eighty-four days now without taking a fish. In the first forty days a boy had been with him. But after forty days without a fish the boy’s parents had told him that the old man was now definitely and finally salao, which is the worst form of unlucky, and the boy had gone at their orders in another boat which caught three good fish the first week. It made the boy sad to see the old man come in each day with his skiff empty and he always went down to help him carry either the coiled lines or the gaff and harpoon and the sail that was furled around the mast. The sail was patched with flour sacks and, furled, it looked like the flag of permanent defeat.'
# wc = WordCloud().generate(text)
# wc.to_file('老人与海.png')
三国演义小说词云绘制
# 三国演义小说分词
# 读取三国演义小说
mask = imageio.imread('./china.jpg')
with open('./novel/threekingdom.txt','r', encoding='utf-8') as f:
words = f.read()
# print(len(words)) # 字数 55万
words_list = jieba.lcut(words)
# print(len(words_list)) # 分词后的词语数 35万
print(words_list)
# 将words_list转化成字符串
novel_words = " ".join(words_list)
print(novel_words)
# WordCloud()里面设置参数
wc = WordCloud(
font_path='msyh.ttc',
background_color='white',
width=800,
height=600,
mask=mask
).generate(novel_words)
wc.to_file('三国词云.png')
效果图
image
