拥有不同列的DataFrame的行连接 concat 函数
from pandas import read_csv,concat,Series,DataFrame
#DataFrame
s1 = read_csv("concat_1.csv")
s2 = read_csv("concat_2.csv")
s3 = read_csv("concat_3.csv")
print("-----------s1-----------------")
print(s1)
print("------------s2----------------")
print(s2)
print("-------------s3---------------")
print(s3)
#修改列表名称
s1.columns = ["A","B","C","D"]
s2.columns = ["E","F","G","H"]
s3.columns = ["A","C","F","H"]
print("-----------s1-----------------")
print(s1)
print("------------s2----------------")
print(s2)
print("------------s3----------------")
print(s3)
print("-----------默认的合并 sort=True--------------")
print(concat([s1,s2,s3],sort=True))
print("-------------s1s2s3 join=inner---------------")
print(concat([s1,s2,s3],join="inner"))
print("-------------s1s3 join=inner---------------")
print(concat([s1,s3],join="inner"))
print("-------------s2s3---------------")
print(concat([s2,s3],join="inner"))output
-----------s1-----------------
A B C D
0 a0 b0 c0 d0
1 a1 b1 c1 d1
2 a2 b2 c2 d2
3 a3 b3 c3 d3
------------s2----------------
A B C D
0 a4 b4 c4 d4
1 a5 b5 c5 d5
2 a6 b6 c6 d6
3 a7 b7 c7 d7
-------------s3---------------
A B C D
0 a8 b8 c8 d8
1 a9 b9 c9 d9
2 a10 b10 c10 d10
3 a11 b11 c11 d11
-----------s1-----------------
A B C D
0 a0 b0 c0 d0
1 a1 b1 c1 d1
2 a2 b2 c2 d2
3 a3 b3 c3 d3
------------s2----------------
E F G H
0 a4 b4 c4 d4
1 a5 b5 c5 d5
2 a6 b6 c6 d6
3 a7 b7 c7 d7
------------s3----------------
A C F H
0 a8 b8 c8 d8
1 a9 b9 c9 d9
2 a10 b10 c10 d10
3 a11 b11 c11 d11
-----------默认的合并 sort=True--------------
A B C D E F G H
0 a0 b0 c0 d0 NaN NaN NaN NaN
1 a1 b1 c1 d1 NaN NaN NaN NaN
2 a2 b2 c2 d2 NaN NaN NaN NaN
3 a3 b3 c3 d3 NaN NaN NaN NaN
0 NaN NaN NaN NaN a4 b4 c4 d4
1 NaN NaN NaN NaN a5 b5 c5 d5
2 NaN NaN NaN NaN a6 b6 c6 d6
3 NaN NaN NaN NaN a7 b7 c7 d7
0 a8 NaN b8 NaN NaN c8 NaN d8
1 a9 NaN b9 NaN NaN c9 NaN d9
2 a10 NaN b10 NaN NaN c10 NaN d10
3 a11 NaN b11 NaN NaN c11 NaN d11
-------------s1s2s3 join=inner---------------
Empty DataFrame
Columns: []
Index: [0, 1, 2, 3, 0, 1, 2, 3, 0, 1, 2, 3]
-------------s1s3 join=inner---------------
A C
0 a0 c0
1 a1 c1
2 a2 c2
3 a3 c3
0 a8 b8
1 a9 b9
2 a10 b10
3 a11 b11
-------------sss---------------
F H
0 b4 d4
1 b5 d5
2 b6 d6
3 b7 d7
0 c8 d8
1 c9 d9
2 c10 d10
3 c11 d11
Process finished with exit code 0
源码
def concat(objs, axis=0, join=’outer’, join_axes=None, ignore_index=False,
keys=None, levels=None, names=None, verify_integrity=False,
sort=None, copy=True):
def concat(objs, axis=0, join='outer', join_axes=None, ignore_index=False,
keys=None, levels=None, names=None, verify_integrity=False,
sort=None, copy=True):
"""
Parameters
----------
objs : a sequence or mapping of Series, DataFrame, or Panel objects
If a dict is passed, the sorted keys will be used as the `keys`
argument, unless it is passed, in which case the values will be
selected (see below). Any None objects will be dropped silently unless
they are all None in which case a ValueError will be raised
axis : {0/'index', 1/'columns'}, default 0
The axis to concatenate along
join : {'inner', 'outer'}, default 'outer'
How to handle indexes on other axis(es)
join_axes : list of Index objects
Specific indexes to use for the other n - 1 axes instead of performing
inner/outer set logic
ignore_index : boolean, default False
If True, do not use the index values along the concatenation axis. The
resulting axis will be labeled 0, ..., n - 1. This is useful if you are
concatenating objects where the concatenation axis does not have
meaningful indexing information. Note the index values on the other
axes are still respected in the join.
keys : sequence, default None
If multiple levels passed, should contain tuples. Construct
hierarchical index using the passed keys as the outermost level
levels : list of sequences, default None
Specific levels (unique values) to use for constructing a
MultiIndex. Otherwise they will be inferred from the keys
names : list, default None
Names for the levels in the resulting hierarchical index
verify_integrity : boolean, default False
Check whether the new concatenated axis contains duplicates. This can
be very expensive relative to the actual data concatenation
sort : boolean, default None
Sort non-concatenation axis if it is not already aligned when `join`
is 'outer'. The current default of sorting is deprecated and will
change to not-sorting in a future version of pandas.
Explicitly pass ``sort=True`` to silence the warning and sort.
Explicitly pass ``sort=False`` to silence the warning and not sort.
This has no effect when ``join='inner'``, which already preserves
the order of the non-concatenation axis.
.. versionadded:: 0.23.0
copy : boolean, default True
If False, do not copy data unnecessarily
Returns
-------
concatenated : object, type of objs
When concatenating all ``Series`` along the index (axis=0), a
``Series`` is returned. When ``objs`` contains at least one
``DataFrame``, a ``DataFrame`` is returned. When concatenating along
the columns (axis=1), a ``DataFrame`` is returned.
Notes
-----
The keys, levels, and names arguments are all optional.
A walkthrough of how this method fits in with other tools for combining
pandas objects can be found `here
` __.
See Also
--------
Series.append
DataFrame.append
DataFrame.join
DataFrame.merge
Examples
Combine two ``Series``.
----------------------------
>>> s1 = pd.Series(['a', 'b'])
>>> s2 = pd.Series(['c', 'd'])
>>> pd.concat([s1, s2])
0 a
1 b
0 c
1 d
dtype: object
ignore_index=True
-------------------------------------
Clear the existing index and reset it in the result
by setting the ``ignore_index`` option to ``True``.
>>> pd.concat([s1, s2], ignore_index=True)
0 a
1 b
2 c
3 d
dtype: object
keys=['s1', 's2',]
--------------------------------------
Add a hierarchical index at the outermost level of
the data with the ``keys`` option.
>>> pd.concat([s1, s2], keys=['s1', 's2',])
s1 0 a
1 b
s2 0 c
1 d
dtype: object
Label the index keys you create with the ``names`` option.
>>> pd.concat([s1, s2], keys=['s1', 's2'],
... names=['Series name', 'Row ID'])
Series name Row ID
s1 0 a
1 b
s2 0 c
1 d
dtype: object
Combine two ``DataFrame`` objects with identical columns.
>>> df1 = pd.DataFrame([['a', 1], ['b', 2]],
... columns=['letter', 'number'])
>>> df1
letter number
0 a 1
1 b 2
>>> df2 = pd.DataFrame([['c', 3], ['d', 4]],
... columns=['letter', 'number'])
>>> df2
letter number
0 c 3
1 d 4
>>> pd.concat([df1, df2])
letter number
0 a 1
1 b 2
0 c 3
1 d 4
Combine ``DataFrame`` objects with overlapping columns
and return everything. Columns outside the intersection will
be filled with ``NaN`` values.
>>> df3 = pd.DataFrame([['c', 3, 'cat'], ['d', 4, 'dog']],
... columns=['letter', 'number', 'animal'])
>>> df3
letter number animal
0 c 3 cat
1 d 4 dog
>>> pd.concat([df1, df3])
animal letter number
0 NaN a 1
1 NaN b 2
0 cat c 3
1 dog d 4
join="inner"
------------------------------
Combine ``DataFrame`` objects with overlapping columns
and return only those that are shared by passing ``inner`` to
the ``join`` keyword argument.
>>> pd.concat([df1, df3], join="inner")
letter number
0 a 1
1 b 2
0 c 3
1 d 4
axis=1
---------------------------------
Combine ``DataFrame`` objects horizontally along the x axis by
passing in ``axis=1``.
>>> df4 = pd.DataFrame([['bird', 'polly'], ['monkey', 'george']],
... columns=['animal', 'name'])
>>> pd.concat([df1, df4], axis=1)
letter number animal name
0 a 1 bird polly
1 b 2 monkey george
Prevent the result from including duplicate index values with the
``verify_integrity`` option.
>>> df5 = pd.DataFrame([1], index=['a'])
>>> df5
0
a 1
>>> df6 = pd.DataFrame([2], index=['a'])
>>> df6
0
a 2
>>> pd.concat([df5, df6], verify_integrity=True)
Traceback (most recent call last):
...
ValueError: Indexes have overlapping values: ['a']
"""
op = _Concatenator(objs, axis=axis, join_axes=join_axes,
ignore_index=ignore_index, join=join,
keys=keys, levels=levels, names=names,
verify_integrity=verify_integrity,
copy=copy, sort=sort)
return op.get_result()