合併DataFrame - 1/2¶

In [1]:

import numpy as np
import pandas as pd

import numpy as np import pandas as pd

In [2]:

df1 =  pd.DataFrame([['a', 1], ['b', 2]], columns=['col1', 'col2'], index=['row1', 'row2'])

df1 = pd.DataFrame([['a', 1], ['b', 2]], columns=['col1', 'col2'], index=['row1', 'row2'])

In [4]:

df2 =  pd.DataFrame([['c', 3], ['d', 4]], columns=['col1', 'col2'], index=['row1', 'row2'])

df2 = pd.DataFrame([['c', 3], ['d', 4]], columns=['col1', 'col2'], index=['row1', 'row2'])

In [5]:

df3 =  pd.DataFrame([['e', 1, 100], ['f', 2, 200]], columns=['col1', 'col2', 'col3'], index=['row1', 'row2'])

df3 = pd.DataFrame([['e', 1, 100], ['f', 2, 200]], columns=['col1', 'col2', 'col3'], index=['row1', 'row2'])

In [14]:

df4 =  pd.DataFrame([['g', 3, 300], ['h', 4, 400]], columns=['col1', 'col2', 'col3'])

df4 = pd.DataFrame([['g', 3, 300], ['h', 4, 400]], columns=['col1', 'col2', 'col3'])

In [3]:

df1

df1

Out[3]:

	col1	col2
row1	a	1
row2	b	2

In [6]:

df2

df2

Out[6]:

	col1	col2
row1	c	3
row2	d	4

In [7]:

df3

df3

Out[7]:

	col1	col2	col3
row1	e	1	100
row2	f	2	200

In [16]:

df4

df4

Out[16]:

	col1	col2	col3
0	g	3	300
1	h	4	400

.concat()¶

沿著特定軸向合併DataFrame。

https://pandas.pydata.org/docs/reference/api/pandas.concat.html

In [8]:

pd.concat([df1, df2])

pd.concat([df1, df2])

Out[8]:

	col1	col2
row1	a	1
row2	b	2
row1	c	3
row2	d	4

In [9]:

pd.concat([df1, df2], ignore_index=True)

pd.concat([df1, df2], ignore_index=True)

Out[9]:

	col1	col2
0	a	1
1	b	2
2	c	3
3	d	4

In [10]:

pd.concat([df1, df3])

pd.concat([df1, df3])

Out[10]:

	col1	col2	col3
row1	a	1	NaN
row2	b	2	NaN
row1	e	1	100.0
row2	f	2	200.0

In [11]:

pd.concat([df1, df3], join="inner")

pd.concat([df1, df3], join="inner")

Out[11]:

	col1	col2
row1	a	1
row2	b	2
row1	e	1
row2	f	2

In [13]:

pd.concat([df1, df2], axis=1)

pd.concat([df1, df2], axis=1)

Out[13]:

	col1	col2	col1	col2
row1	a	1	c	3
row2	b	2	d	4

In [15]:

pd.concat([df1, df4], axis=1)

pd.concat([df1, df4], axis=1)

Out[15]:

	col1	col2	col1	col2	col3
row1	a	1.0	NaN	NaN	NaN
row2	b	2.0	NaN	NaN	NaN
0	NaN	NaN	g	3.0	300.0
1	NaN	NaN	h	4.0	400.0

.append()¶

將一個DataFrame附加到另一個之後。

.append()之後會被汰換掉，之後用.concat()就好了，不要再用.append()。

https://pandas.pydata.org/pandas-docs/version/1.3/reference/api/pandas.DataFrame.append.html

In [17]:

df1.append(df2)

df1.append(df2)

<ipython-input-17-8ab0723181fb>:1: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.
  df1.append(df2)

Out[17]:

	col1	col2
row1	a	1
row2	b	2
row1	c	3
row2	d	4

In [21]:

df1.append(df2, verify_integrity=True)

df1.append(df2, verify_integrity=True)

<ipython-input-21-f4f92554bbfd>:1: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.
  df1.append(df2, verify_integrity=True)

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-21-f4f92554bbfd> in <cell line: 1>()
----> 1 df1.append(df2, verify_integrity=True)

/usr/local/lib/python3.10/dist-packages/pandas/core/frame.py in append(self, other, ignore_index, verify_integrity, sort)
   9766         )
   9767 
-> 9768         return self._append(other, ignore_index, verify_integrity, sort)
   9769 
   9770     def _append(

/usr/local/lib/python3.10/dist-packages/pandas/core/frame.py in _append(self, other, ignore_index, verify_integrity, sort)
   9806             to_concat = [self, other]
   9807 
-> 9808         result = concat(
   9809             to_concat,
   9810             ignore_index=ignore_index,

/usr/local/lib/python3.10/dist-packages/pandas/util/_decorators.py in wrapper(*args, **kwargs)
    329                     stacklevel=find_stack_level(),
    330                 )
--> 331             return func(*args, **kwargs)
    332 
    333         # error: "Callable[[VarArg(Any), KwArg(Any)], Any]" has no

/usr/local/lib/python3.10/dist-packages/pandas/core/reshape/concat.py in concat(objs, axis, join, ignore_index, keys, levels, names, verify_integrity, sort, copy)
    366     1   3   4
    367     """
--> 368     op = _Concatenator(
    369         objs,
    370         axis=axis,

/usr/local/lib/python3.10/dist-packages/pandas/core/reshape/concat.py in __init__(self, objs, axis, join, keys, levels, names, ignore_index, verify_integrity, copy, sort)
    561         self.copy = copy
    562 
--> 563         self.new_axes = self._get_new_axes()
    564 
    565     def get_result(self):

/usr/local/lib/python3.10/dist-packages/pandas/core/reshape/concat.py in _get_new_axes(self)
    631     def _get_new_axes(self) -> list[Index]:
    632         ndim = self._get_result_dim()
--> 633         return [
    634             self._get_concat_axis if i == self.bm_axis else self._get_comb_axis(i)
    635             for i in range(ndim)

/usr/local/lib/python3.10/dist-packages/pandas/core/reshape/concat.py in <listcomp>(.0)
    632         ndim = self._get_result_dim()
    633         return [
--> 634             self._get_concat_axis if i == self.bm_axis else self._get_comb_axis(i)
    635             for i in range(ndim)
    636         ]

/usr/local/lib/python3.10/dist-packages/pandas/_libs/properties.pyx in pandas._libs.properties.CachedProperty.__get__()

/usr/local/lib/python3.10/dist-packages/pandas/core/reshape/concat.py in _get_concat_axis(self)
    695             )
    696 
--> 697         self._maybe_check_integrity(concat_axis)
    698 
    699         return concat_axis

/usr/local/lib/python3.10/dist-packages/pandas/core/reshape/concat.py in _maybe_check_integrity(self, concat_index)
    703             if not concat_index.is_unique:
    704                 overlap = concat_index[concat_index.duplicated()].unique()
--> 705                 raise ValueError(f"Indexes have overlapping values: {overlap}")
    706 
    707 

ValueError: Indexes have overlapping values: Index(['row1', 'row2'], dtype='object')

In [18]:

df1.append(df2, ignore_index=True)

df1.append(df2, ignore_index=True)

<ipython-input-18-992fb3fde170>:1: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.
  df1.append(df2, ignore_index=True)

Out[18]:

	col1	col2
0	a	1
1	b	2
2	c	3
3	d	4

In [19]:

df1.append(df3)

df1.append(df3)

<ipython-input-19-8d783e85260f>:1: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.
  df1.append(df3)

Out[19]:

	col1	col2	col3
row1	a	1	NaN
row2	b	2	NaN
row1	e	1	100.0
row2	f	2	200.0

In [20]:

df1.append(df4)

df1.append(df4)

<ipython-input-20-2eeefe8b6e74>:1: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.
  df1.append(df4)

Out[20]:

	col1	col2	col3
row1	a	1	NaN
row2	b	2	NaN
0	g	3	300.0
1	h	4	400.0

.join()¶

會根據index把DataFrame合併在一起。

https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.join.html

In [22]:

df1

df1

Out[22]:

	col1	col2
row1	a	1
row2	b	2

In [23]:

df2

df2

Out[23]:

	col1	col2
row1	c	3
row2	d	4

In [24]:

df1.join(df2)

df1.join(df2)

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-24-f8069890b6d0> in <cell line: 1>()
----> 1 df1.join(df2)

/usr/local/lib/python3.10/dist-packages/pandas/core/frame.py in join(self, other, on, how, lsuffix, rsuffix, sort, validate)
   9977         5  K1  A5   B1
   9978         """
-> 9979         return self._join_compat(
   9980             other,
   9981             on=on,

/usr/local/lib/python3.10/dist-packages/pandas/core/frame.py in _join_compat(self, other, on, how, lsuffix, rsuffix, sort, validate)
  10016                     validate=validate,
  10017                 )
> 10018             return merge(
  10019                 self,
  10020                 other,

/usr/local/lib/python3.10/dist-packages/pandas/core/reshape/merge.py in merge(left, right, how, on, left_on, right_on, left_index, right_index, sort, suffixes, copy, indicator, validate)
    122         validate=validate,
    123     )
--> 124     return op.get_result(copy=copy)
    125 
    126 

/usr/local/lib/python3.10/dist-packages/pandas/core/reshape/merge.py in get_result(self, copy)
    773         join_index, left_indexer, right_indexer = self._get_join_info()
    774 
--> 775         result = self._reindex_and_concat(
    776             join_index, left_indexer, right_indexer, copy=copy
    777         )

/usr/local/lib/python3.10/dist-packages/pandas/core/reshape/merge.py in _reindex_and_concat(self, join_index, left_indexer, right_indexer, copy)
    727         right = self.right[:]
    728 
--> 729         llabels, rlabels = _items_overlap_with_suffix(
    730             self.left._info_axis, self.right._info_axis, self.suffixes
    731         )

/usr/local/lib/python3.10/dist-packages/pandas/core/reshape/merge.py in _items_overlap_with_suffix(left, right, suffixes)
   2456 
   2457     if not lsuffix and not rsuffix:
-> 2458         raise ValueError(f"columns overlap but no suffix specified: {to_rename}")
   2459 
   2460     def renamer(x, suffix):

ValueError: columns overlap but no suffix specified: Index(['col1', 'col2'], dtype='object')

In [25]:

df1.join(df2, lsuffix='_df1', rsuffix='_df2')

df1.join(df2, lsuffix='_df1', rsuffix='_df2')

Out[25]:

	col1_df1	col2_df1	col1_df2	col2_df2
row1	a	1	c	3
row2	b	2	d	4

In [26]:

df2.columns = ['col3', 'col4']

df2.columns = ['col3', 'col4']

In [27]:

df1.join(df2)

df1.join(df2)

Out[27]:

	col1	col2	col3	col4
row1	a	1	c	3
row2	b	2	d	4