python之pandas.concat

文章目录

• 1 函数原型
• 2 常用的参数含义
• 3 举例

1 函数原型

pd.concat(objs, axis=0, join='outer', join_axes=None, ignore_index=False,
          keys=None, levels=None, names=None, verify_integrity=False,
          copy=True)

2 常用的参数含义

1. obj：为Series、DataFrame、Pannel对象的序列或映射。
2. axis：默认为0,。是沿着连接的轴
3. join：{“inner”, “outer”}，是为内连接和外连接。
4. keys：使用传递的键值，作为最外才能够构建层次索引。如果为多索引，应该使用元组。

3 举例

• 效果如下图所示
  

• 代码

import pandas as pd

df1 = pd.DataFrame({'A': ['A0', 'A1', 'A2', 'A3'],
                    'B': ['B0', 'B1', 'B2', 'B3'],
                    'C': ['C0', 'C1', 'C2', 'C3'],
                    'D': ['D0', 'D1', 'D2', 'D3']},
                   index=[0, 1, 2, 3])
print(df1)

df2 = pd.DataFrame({'A': ['A4', 'A5', 'A6', 'A7'],
                    'B': ['B4', 'B5', 'B6', 'B7'],
                    'C': ['C4', 'C5', 'C6', 'C7'],
                    'D': ['D4', 'D5', 'D6', 'D7']},
                   index=[4, 5, 6, 7])
print(df2)

df3 = pd.DataFrame({'A': ['A8', 'A9', 'A10', 'A11'],
                    'B': ['B8', 'B9', 'B10', 'B11'],
                    'C': ['C8', 'C9', 'C10', 'C11'],
                    'D': ['D8', 'D9', 'D10', 'D11']},
                   index=[8, 9, 10, 11])
print(df3)

frames = [df1, df2, df3]
print("frames:\n", frames)

result = pd.concat(frames)  # 默认axis=0
print("result:\n", result)

• 扩展1：如果指定keys

result_1 = pd.concat(frames, keys=['x', 'y', 'z'])
print("result_1:\n", result_1)

• 输出：

result_1:
         A    B    C    D
x 0    A0   B0   C0   D0
  1    A1   B1   C1   D1
  2    A2   B2   C2   D2
  3    A3   B3   C3   D3
y 4    A4   B4   C4   D4
  5    A5   B5   C5   D5
  6    A6   B6   C6   D6
  7    A7   B7   C7   D7
z 8    A8   B8   C8   D8
  9    A9   B9   C9   D9
  10  A10  B10  C10  D10
  11  A11  B11  C11  D11

• 扩展2：如果使用join

import pandas as pd

df1 = pd.DataFrame({'A': ['A0', 'A1', 'A2', 'A3'],
                    'B': ['B0', 'B1', 'B2', 'B3'],
                    'C': ['C0', 'C1', 'C2', 'C3'],
                    'D': ['D0', 'D1', 'D2', 'D3']},
                   index=[0, 1, 2, 3])
print(df1)

df2 = pd.DataFrame({'A': ['A4', 'A5', 'A6', 'A7'],
                    'B': ['B4', 'B5', 'B6', 'B7'],
                    'C': ['C4', 'C5', 'C6', 'C7'],
                    'D': ['D4', 'D5', 'D6', 'D7']},
                   index=[4, 5, 6, 7])
print(df2)

df3 = pd.DataFrame({'A': ['A8', 'A9', 'A10', 'A11'],
                    'B': ['B8', 'B9', 'B10', 'B11'],
                    'C': ['C8', 'C9', 'C10', 'C11'],
                    'D': ['D8', 'D9', 'D10', 'D11']},
                   index=[8, 9, 10, 11])
print(df3)



frames = [df1, df2, df3]
print("frames:\n", frames)

result = pd.concat(frames)  # 默认axis=0
print("result:\n", result)

result_1 = pd.concat(frames, keys=['x', 'y', 'z'])
print("result_1:\n", result_1)

df4 = pd.DataFrame({'B': ['B2', 'B3', 'B6', 'B7'],
                    'D': ['D2', 'D3', 'D6', 'D7'],
                    'F': ['F2', 'F3', 'F6', 'F7']},
                   index=[2, 3, 6, 7])

result_2 = pd.concat([df1, df4], axis=1)
result_3 = pd.concat([df1, df4], axis=1, join='inner')
print("join前：\n", result_2)
print("join后：\n", result_3)