#%% md

### **Series**

#%%

import numpy as np
import pandas as pd

#%%

# 通过numpy数组创建
print(np.random.rand(5))
# 转成Serise()
s = pd.Series(np.random.rand(5))
print(s, type(s))  # <class 'pandas.core.series.Series'>
print('-'*30)
print(s.index.tolist())  # 获取索引
print('-'*30)
print(s.values)  # 获取值
print(s.dtype)  # 查看元素类型

#%%

# 通过字典去进行获取
dic = {"red":100,"black":500,"green":300,"pink":900}
s1 = pd.Series(dic)
print(s1)

#%% md

### **series的索引及切片**

#%%

se1 = pd.Series(data=[1,2,3,4],index=['a','b','c','d'])
print(se1)
# 通过位置索引去2
# print(se1[1])
# 通过标签索引去2
# print(se1['b'])
# 同时取2和3
print(se1[1:3])
print('-'*30)
print(se1['b':'c'])  # 能取到结束标签

#%% md

### **series常见操作**

#%%

s = pd.Series(np.random.rand(50))  # 随机生成50个实数，范围0-1之间
# print(s)
# print(s.head())  # 只查看前几行，默认前五行
print(s.tail())  # 只查看后几行，默认后五行

#%%

# Series对齐
s1 = pd.Series(np.random.rand(3), index = ['Jack','Marry','Wilia'])
s2 = pd.Series(np.random.rand(3), index = ['Wang','Wilia','Marry'])
print(s1)
print('-'*30)
print(s2)
print('-'*30)
# 在相同索引位置数据可以计算
print(s1 + s2)

#%%

# drop()删除
s = pd.Series(np.random.rand(5), index = list('abcde'))  # index 设置自定义标签
print(s)
print('-'*30)
print(s.drop('b'))  # 删除下标为b的数据

#%%

# 添加
s1 = pd.Series(np.random.rand(5))
print(s1)
print('-'*30)
# 类似字典：键本身不存在时，添加
s1[5] = 99
print(s1)
print('-'*30)
# 修改
s1[3] = 188
print(s1)
print('-'*30)
s1.index = ['a','b','c','d','e','f']
print(s1)

#%% md

### **DataFrame**

#%%

# 二维数组创建
df1 = pd.DataFrame(np.random.randint(0,20,(4,5)), index = ['h','k','o','p'], columns = ['a','b','c','d','e'])
print(df1)

#%%

# 字典创建
data1 = {
    'a':[1,2,3],
    'b':[3,4,5],
    'c':[5,6,7]
}
print(data1)
print('-'*30)
df2 = pd.DataFrame(data1)
print(df2)

#%%

# 由字典组成的列表创建
data2 = [{'one':1,'two':2},{'one':3,'two':4,'three':5}]
df3 = pd.DataFrame(data2)
print(df3)

#%%

# 由字典组成的字典创建
data3 = {
    'Jack':{'math':90,'english':89,'art':78},
    'Marry':{'math':82,'english':95,'art':92},
    'Tom':{'math':78,'english':67}
}
df4 = pd.DataFrame(data3)
print(df4)

#%% md

### **DataFrame()对象常用属性**

#%%

data = {
    'name':['Jack','Tom','Marry'],
    'age':[18,19,20],
    'gender':['F','M','W']
       }
df = pd.DataFrame(data,index=['a','b','c'])
print(df)
print('-'*30)
# 查看行和列
print(df.shape)  # (3, 3)
# 获取行索引
print(df.index.tolist())
# 获取列索引
print(df.columns.tolist())
print('-'*30)
# 获取值
print(df.values, type(df.values))  # <class 'numpy.ndarray'>
print('-'*30)
# 获取前两行
print(df.head(2))
print('-'*30)
# 获取后两行
print(df.tail(2))
print('-'*30)
# 取age数据
print(df['age'])
# 取19
# 如果同时要涉及行和列，最好使用loc或iloc
# df.loc通过标签索引行数据
print(df.loc['b','age'])
# df.iloc通过位置索引行数据
print(df.iloc[1,1])

#%% md

### **排序**

#%%

# 值排序
data = {
    'name':['Jack','Tom','Marry'],
    'age':[18,19,20],
    'gender':['F','M','W']
       }
df = pd.DataFrame(data,index=['a','b','c'])
print(df)
print('-'*30)
# 按age列进行排序，ascending=False表示降序
print(df.sort_values(by='age',ascending=False))


#%%

# 按索引进行排序
df1 = pd.DataFrame(np.random.rand(16).reshape(4,4)*100,
                  index = [5,4,3,2],
                  columns = ['a','b','c','d'])
print(df1)
print('-'*30)
print(df1.sort_index())

#%% md

### **布尔索引**

#%%

df = pd.DataFrame(np.random.rand(16).reshape(4,4)*100,
                  index = [5,4,3,2],
                  columns = ['a','b','c','d'])
print(df)
print(df['a']>20)  # True False
print(df[df['a']>20])  # df['a']>20表示筛选的条件

#%% md

### **爬取天气数据保存为DataFrame格式**

#%%

import requests
from lxml import etree

#%%

url = 'https://weather.cma.cn/'
headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36'
}
res = requests.get(url,headers=headers)
content = res.content.decode('utf-8')
# print(content)
tree = etree.HTML(content)
a_s = tree.xpath('//div[@id="HOT"]/a')
lst = []
for a in a_s[1:]:
    dic = {}
    dic['排名'] = a.xpath('./div[@class="rank"]/text()')[0].strip()
    dic['城市'] = a.xpath('./div[@class="sname"]/text()')[0].strip()
    dic['省份'] = a.xpath('./div[@class="pname"]/text()')[0].strip()
    dic['最高温度'] = a.xpath('./div[@class="value"]/text()')[0].strip()
    lst.append(dic)
print(lst)
df = pd.DataFrame(lst)
print(df)

#%%

df = pd.DataFrame(np.random.random(size=(6,4)),
                  index=['a','b','c','d','e','f'],
                  columns=['one','two','three','four'])
# 显示前三行
print(df.head(3))
print('-'*30)
# 查看行索引
print(df.index.tolist())
print('-'*30)
# 查看所以值
print(df.values)
# 取下标为1和2的行
print('-'*30)
print(df.iloc[1:3])
print('-'*30)
# 多列多行
print(df)
print('-'*30)
# 对c列进行按值升序排列
print(df.sort_values(by="three",ascending=True))