Pandas入门之三：DataFrame

已信任
Jupyter 服务器: 本地
Python 3: Idle

[2]



import pandas as pd
import numpy as np



[-]




[3]



# pd.DataFrame(data,index,columns,dtype)
# 创建空的DataFrame
df = pd.DataFrame()
df
[4]



# 通过列表创建
data = [1,2,3,4,5,6]
df = pd.DataFrame(data)
df
0
0    1
1    2
2    3
3    4
4    5
5    6
[5]



# 2列数据：名字，年龄
data = [['xiaoming', 10],['xiaochen',13]]
df = pd.DataFrame(data, columns=['username','age'])
df
username    age
0    xiaoming    10
1    xiaochen    13
[6]



# 字典创建
data ={
    'username':['小黑','小白','小刘'],
    'income':[1000,2000,3000]
}
df = pd.DataFrame(data,index=[1,2,3])
df
username    income
1    小黑    1000
2    小白    2000
3    小刘    3000
[7]



d = {
    'one':pd.Series([1,2,3],index=['a','b','c']),
    'two':pd.Series([1,2,3,4],index=['a','b','c','d'])
}
df = pd.DataFrame(d)
df
one    two
a    1.0    1
b    2.0    2
c    3.0    3
d    NaN    4
[8]



df['one']# 获取1列的方式，通过列名
a    1.0
b    2.0
c    3.0
d    NaN
Name: one, dtype: float64
[9]



# 增加列
df['three'] = pd.Series([4,5,6],index=['a','b','c'])
df
one    two    three
a    1.0    1    4.0
b    2.0    2    5.0
c    3.0    3    6.0
d    NaN    4    NaN
[10]



df['four'] = df['one']+df['three']
df
one    two    three    four
a    1.0    1    4.0    5.0
b    2.0    2    5.0    7.0
c    3.0    3    6.0    9.0
d    NaN    4    NaN    NaN
[11]



# 删除列
del df['four']
df
one    two    three
a    1.0    1    4.0
b    2.0    2    5.0
c    3.0    3    6.0
d    NaN    4    NaN
[12]



df.pop('two')
df
one    three
a    1.0    4.0
b    2.0    5.0
c    3.0    6.0
d    NaN    NaN
[13]



# 标签选择行
df.loc['a']
one      1.0
three    4.0
Name: a, dtype: float64
[16]



# 通过顺序选择行
df.iloc[1]# 选择第2行
one      2.0
three    5.0
Name: b, dtype: float64
[17]



# 切片,选择行
df[0:2]
one    three
a    1.0    4.0
b    2.0    5.0
[18]



df
one    three
a    1.0    4.0
b    2.0    5.0
c    3.0    6.0
d    NaN    NaN
[19]



# 添加行
df2 = pd.DataFrame([[2,5], [5,6]],columns=['one','three'])
df2
one    three
0    2    5
1    5    6
[22]



df = df.append(df2)
df
one    three
a    1.0    4.0
b    2.0    5.0
c    3.0    6.0
d    NaN    NaN
0    2.0    5.0
1    5.0    6.0
0    2.0    5.0
1    5.0    6.0
[23]



# 删除行
df.drop(0)
one    three
a    1.0    4.0
b    2.0    5.0
c    3.0    6.0
d    NaN    NaN
1    5.0    6.0
1    5.0    6.0
[-]