pandas基础

import pandas as pd

#定义字典
mydataset={
    'sites':["Goodle","Runoob","Wiki"],
    'number':[1,2,3]
}
#将字典转换为DataFrame，才能处理
mydf=pd.DataFrame(mydataset)
print(mydf)

#将列表转换为series
a=[1,2,3]
mysr=pd.Series(a,name="number")
print(mysr)
print(mysr[1])

#制定series的索引值
a=["Google","Runoob","Wiki"]
myvar=pd.Series(a,index=["x","y","z"])
print(myvar)

#通过字典创建索引
sites={1:"Google",2:"Runoob",3:"Wiki"}
myvar=pd.Series(sites)
print(myvar)

#去部分索引
sites={1:"Google",2:"Runoob",3:"Wiki"}
myvar=pd.Series(sites,index=[1,2])
print(myvar)

#ndarrays创建
data=[['Google',10],['Runoob',12],['Wiki',13]]
df=pd.DataFrame(data,columns=['Site','Age'],dtype=float)
print(df)

#字典中创建列名
data={'Site':['Google','Runoob','Wiki'],'Age':[10,12,13]}
df=pd.DataFrame(data)
print(df)

#使用字典创建
data=[{'a':1,'b':2},{'a':5,'b':10,'c':20}]
df=pd.DataFrame(data)
print("dd:",df)
print()

#返回指定行数据
data={"calories":[420,380,390],"duration":[50,40,45]}
    #数据载入到DataFrame对象
df=pd.DataFrame(data)
    #返回全部
print(df)
    #返回第一行
print("第一行",df.loc[0])
    #返回第二行
print("第二行",df.loc[1])

#返回多行数据
data={"calories":[420,380,390],"duration":[50,40,45]}
    #数据载入到DataFrame对象
df=pd.DataFrame(data)
    # #返回第一行和第二行
print(df.loc[[0,1]])

#指定索引值
data={"calories":[420,380,390],"duration":[50,40,45]}
df=pd.DataFrame(data,index=["day1","day2","day3"])
print(df)

#指定索引
data={"calories":[420,380,390],"duration":[50,40,45]}
df=pd.DataFrame(data,index=["day1","day2","day3"])
    #指定索引
print(df.loc["day2"])

pandasCSV

import pandas as pd
#读取csv文件为DataFrame
df=pd.read_csv('./nba.csv',encoding='GDK')
print(df)

#将DataFrame保存为csv，编码为utf-8
df.to_csv('./nba2.csv',encoding='utf-8')

#自定义DataFrame存为csv文件
#三个字段name，site，age
nme=["goodle","runoob","taobao","wiki"]
st=["www.goole.com","www.runoob.com","www.taobao.com","www.wikipedia.org"]
ag=[90,40,80,98]
#字典
dict={'name':nme,'site':st,'age':ag}
df=pd.DataFrame(dict)
#保存dataframe
df.to_csv('site.csv')

#查看DataFrame的前三行
print(df.head(3))
#查看DataFram的后三行
print(df.tail(3))
#打印DataFram的信息
print(df.info())

import pandas as pd
#读取json文件为DATAFram
json=pd.read_json('./sites.json')
print(json)

#定义数据保存为json
s={
    "col1":{"row1":1,"row2":2,"row3":3},
    "col2":{"row1":"x","row2":"y","row3":"z"}
}
#将数据转换为DataFrame
df=pd.DataFrame(s)
#保存DataFrame为json
df.to_json('s.json')

#读取网站中的文件转换为DataFrame
URL='https://static.runoob.com/download/sites.json'
df=pd.read_json(URL)
print(df)

#读取json文件
nq=pd.read_json('./neiqian.json')
print(nq)