[TOC]
# Series对象
## 查
~~~
import pandas as pd
data = [10, 11, 12]
index = ['a', 'b', 'c']
# 构造一个Series结构
s = pd.Series(data = data, index = index)
# 也支持索引和分片s[0],s[0:2]
print(s)
~~~
输出
~~~
a 10
b 11
c 12
dtype: int64
~~~
**也可以根据bool来查询**
~~~
import pandas as pd
data = [10, 11, 12]
index = ['a', 'b', 'c']
# 构造一个Series结构
s = pd.Series(data = data, index = index)
mask=[True, False, True]
print(s[mask])
~~~
输出
~~~
a 10
c 12
dtype: int64
~~~
**也可以根据Ioc和iloc来查询**
~~~
import pandas as pd
data = [10, 11, 12]
index = ['a', 'b', 'c']
# 构造一个Series结构
s = pd.Series(data = data, index = index)
print(s.loc['b'])
print(s.iloc[1])
~~~
输出
~~~
11
11
~~~
## 改
**拷贝改**
~~~
import pandas as pd
data = [10, 11, 12]
index = ['a', 'b', 'c']
# 构造一个Series结构
s = pd.Series(data = data, index = index)
s1 = s.copy()
s1['a'] = 100
print(s1)
~~~
输出
~~~
a 100
b 11
c 12
dtype: int64
~~~
**replace改**
~~~
import pandas as pd
data = [10, 11, 12]
index = ['a', 'b', 'c']
# 构造一个Series结构
s = pd.Series(data = data, index = index)
# inplace为false表示不会在原始基础上改,true会
replace = s.replace(to_replace=10, value=101, inplace=False)
print(replace)
~~~
输出
~~~
a 101
b 11
c 12
dtype: int64
~~~
**改索引**
~~~
import pandas as pd
data = [10, 11, 12]
index = ['a', 'b', 'c']
# 构造一个Series结构
s = pd.Series(data=data, index=index)
print(s.index)
s.index = ['a', 'b', 'd']
print(s)
~~~
输出
~~~
Index(['a', 'b', 'c'], dtype='object')
a 10
b 11
d 12
dtype: int64
~~~
**更改索引**
~~~
import pandas as pd
data = [10, 11, 12]
index = ['a', 'b', 'c']
# 构造一个Series结构
s = pd.Series(data=data, index=index)
s.rename(index={'a': 'A'}, inplace=True)
print(s)
~~~
输出
~~~
A 10
b 11
c 12
dtype: int64
~~~
## 增
**把2个合并**
~~~
import pandas as pd
data = [10, 11, 12]
index = ['a', 'b', 'c']
# 构造一个Series结构
s = pd.Series(data=data, index=index)
series = pd.Series(data=[100, 110], index=['h', 'k'])
# ignore_index=False表示保留原来的索引,不保留索引变为0,1,2
append = s.append(series, ignore_index=False)
print(append)
~~~
输出
~~~
a 10
b 11
c 12
h 100
k 110
dtype: int64
~~~
**新增一项**
~~~
import pandas as pd
data = [10, 11, 12]
index = ['a', 'b', 'c']
# 构造一个Series结构
s = pd.Series(data=data, index=index)
s['j'] = 500
print(s)
~~~
输出
~~~
a 10
b 11
c 12
j 500
dtype: int64
~~~
## 删
**删除一行**
~~~
import pandas as pd
data = [10, 11, 12]
index = ['a', 'b', 'c']
# 构造一个Series结构
s = pd.Series(data=data, index=index)
del s['a']
print(s)
~~~
输出
~~~
b 11
c 12
dtype: int64
~~~
**删除多行**
~~~
import pandas as pd
data = [10, 11, 12]
index = ['a', 'b', 'c']
# 构造一个Series结构
s = pd.Series(data=data, index=index)
# inplace为True,原来的值会改变,否则原来值不会改变要变量接收结果
s.drop(['b', 'c'], inplace=True)
print(s)
~~~
输出
~~~
a 10
dtype: int64
~~~
# DataFrame
## 创建
~~~
import pandas as pd
# 数据
data = [[1, 2, 3], [4, 5, 6]]
# 索引
index = ['a', 'b']
# 列名
columns = ['A', 'B', 'C']
df = pd.DataFrame(data=data, index=index, columns=columns)
print(df)
~~~
输出
~~~
A B C
a 1 2 3
b 4 5 6
~~~
## 查询
**查询某一列**
~~~
print(df['A'])
~~~
输出
~~~
a 1
b 4
Name: A, dtype: int64
~~~
**查询某个索引**
用iloc
~~~
print(df.iloc[0])
~~~
输出
~~~
A 1
B 2
C 3
Name: a, dtype: int64
~~~
用loc
~~~
print(df.loc['a'])
~~~
输出
~~~
A 1
B 2
C 3
Name: a, dtype: int64
~~~
**索引和列定位一个数据**
~~~
print(df.loc['a']['A'])
~~~
输出
~~~
1
~~~
## 更改
**更改某个值**
~~~
df.loc['a']['A'] = 150
print(df)
~~~
输出
~~~
A B C
a 150 2 3
b 4 5 6
~~~
**更改索引**
~~~
df.index = ['f', 'g']
print(df)
~~~
输出
~~~
A B C
f 1 2 3
g 4 5 6
~~~
## 增加
**增加一列**
~~~
df.loc['c'] = [1, 2, 3]
print(df)
~~~
输出
~~~
A B C
a 1 2 3
b 4 5 6
c 1 2 3
~~~
**合并2个DataFrame**
~~~
import pandas as pd
# 数据
data = [[1, 2, 3], [4, 5, 6]]
# 索引
index = ['a', 'b']
# 列名
columns = ['A', 'B', 'C']
# 创建个DataFrame结构
df = pd.DataFrame(data=data, index=index, columns=columns)
df2 = pd.DataFrame(data=data, index=['j', 'k'], columns = columns)
# 默认axis为0,按照样本拼接,也可以指定为1,但是没有的值会显示NaN
df3 = pd.concat([df, df2], axis=0)
print(df3)
~~~
输出
~~~
A B C
a 1 2 3
b 4 5 6
j 1 2 3
k 4 5 6
~~~
**增加一列**
~~~
# 增加列
df['Tang'] = [10, 11]
print(df)
~~~
输出
~~~
A B C Tang
a 1 2 3 10
b 4 5 6 11
~~~
## 删除
**删除一个索引**
~~~
# 删除一个索引
df.drop(['a'], axis=0, inplace=True)
print(df)
~~~
输出
~~~
A B C
b 4 5 6
~~~
**删除一列**
~~~
# 删除一个列
del df['A']
print(df)
~~~
输出
~~~
B C
a 2 3
b 5 6
~~~
**删除多个列**
~~~
df.drop(['A', 'B'], axis=1, inplace=True)
print(df)
~~~
输出
~~~
C
a 3
b 6
~~~
