import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
|
|
s = pd.Series([1,3,5,np.nan,6,8]); s
0 1 1 3 2 5 3 NaN 4 6 5 8 dtype: object 0 1 1 3 2 5 3 NaN 4 6 5 8 dtype: object |
dates = pd.date_range('2013-01-01', '2013-01-06')
|
|
dates
<class 'pandas.tseries.index.DatetimeIndex'> [2013-01-01 00:00:00, ..., 2013-01-06 00:00:00] Length: 6, Freq: D, Timezone: None <class 'pandas.tseries.index.DatetimeIndex'> [2013-01-01 00:00:00, ..., 2013-01-06 00:00:00] Length: 6, Freq: D, Timezone: None |
df = pd.DataFrame(np.random.randn(6,4),index=dates,columns=list('ABCD')); df
A B C D 2013-01-01 0.329222 -1.027603 0.045742 -0.005040 2013-01-02 -2.131626 -2.990553 -0.918132 -1.119217 2013-01-03 -0.967064 -0.270507 -1.142525 0.030026 2013-01-04 -1.971963 0.634871 0.977957 0.762491 2013-01-05 -0.423241 0.099963 -0.193580 0.585892 2013-01-06 -1.911004 -0.472659 0.745064 -0.614818 [6 rows x 4 columns] A B C D 2013-01-01 0.329222 -1.027603 0.045742 -0.005040 2013-01-02 -2.131626 -2.990553 -0.918132 -1.119217 2013-01-03 -0.967064 -0.270507 -1.142525 0.030026 2013-01-04 -1.971963 0.634871 0.977957 0.762491 2013-01-05 -0.423241 0.099963 -0.193580 0.585892 2013-01-06 -1.911004 -0.472659 0.745064 -0.614818 [6 rows x 4 columns] |
df2 = pd.DataFrame({ 'A' : 1.,
'B' : pd.Timestamp('20130102'),
'C' : pd.Series(1, index=list(range(4)), dtype='float32'),
'D' : np.array([3] * 4, dtype='int32'),
'E' : 'foo' })
|
|
df2
A B C D E 0 1.00000000000000 2013-01-02 00:00:00 1 3 foo 1 1.00000000000000 2013-01-02 00:00:00 1 3 foo 2 1.00000000000000 2013-01-02 00:00:00 1 3 foo 3 1.00000000000000 2013-01-02 00:00:00 1 3 foo [4 rows x 5 columns] A B C D E 0 1.00000000000000 2013-01-02 00:00:00 1 3 foo 1 1.00000000000000 2013-01-02 00:00:00 1 3 foo 2 1.00000000000000 2013-01-02 00:00:00 1 3 foo 3 1.00000000000000 2013-01-02 00:00:00 1 3 foo [4 rows x 5 columns] |
df2.dtypes
A object B datetime64[ns] C float32 D int32 E object dtype: object A object B datetime64[ns] C float32 D int32 E object dtype: object |
df.head()
A B C D 2013-01-01 0.329222 -1.027603 0.045742 -0.005040 2013-01-02 -2.131626 -2.990553 -0.918132 -1.119217 2013-01-03 -0.967064 -0.270507 -1.142525 0.030026 2013-01-04 -1.971963 0.634871 0.977957 0.762491 2013-01-05 -0.423241 0.099963 -0.193580 0.585892 [5 rows x 4 columns] A B C D 2013-01-01 0.329222 -1.027603 0.045742 -0.005040 2013-01-02 -2.131626 -2.990553 -0.918132 -1.119217 2013-01-03 -0.967064 -0.270507 -1.142525 0.030026 2013-01-04 -1.971963 0.634871 0.977957 0.762491 2013-01-05 -0.423241 0.099963 -0.193580 0.585892 [5 rows x 4 columns] |
df.tail(3)
A B C D 2013-01-04 -1.971963 0.634871 0.977957 0.762491 2013-01-05 -0.423241 0.099963 -0.193580 0.585892 2013-01-06 -1.911004 -0.472659 0.745064 -0.614818 [3 rows x 4 columns] A B C D 2013-01-04 -1.971963 0.634871 0.977957 0.762491 2013-01-05 -0.423241 0.099963 -0.193580 0.585892 2013-01-06 -1.911004 -0.472659 0.745064 -0.614818 [3 rows x 4 columns] |
df.index
<class 'pandas.tseries.index.DatetimeIndex'> [2013-01-01 00:00:00, ..., 2013-01-06 00:00:00] Length: 6, Freq: D, Timezone: None <class 'pandas.tseries.index.DatetimeIndex'> [2013-01-01 00:00:00, ..., 2013-01-06 00:00:00] Length: 6, Freq: D, Timezone: None |
df.values
array([[ 0.3292223 , -1.02760341, 0.04574179, -0.00503985],
[-2.13162621, -2.99055305, -0.91813208, -1.11921746],
[-0.96706357, -0.27050684, -1.14252505, 0.03002641],
[-1.97196316, 0.63487149, 0.97795723, 0.76249148],
[-0.42324079, 0.09996291, -0.19358013, 0.58589231],
[-1.91100396, -0.47265915, 0.74506379, -0.61481822]])
array([[ 0.3292223 , -1.02760341, 0.04574179, -0.00503985],
[-2.13162621, -2.99055305, -0.91813208, -1.11921746],
[-0.96706357, -0.27050684, -1.14252505, 0.03002641],
[-1.97196316, 0.63487149, 0.97795723, 0.76249148],
[-0.42324079, 0.09996291, -0.19358013, 0.58589231],
[-1.91100396, -0.47265915, 0.74506379, -0.61481822]])
|
df.describe()
A B C D count 6.000000 6.000000 6.000000 6.000000 mean -1.179279 -0.671081 -0.080912 -0.060111 std 0.996287 1.265457 0.855586 0.711977 min -2.131626 -2.990553 -1.142525 -1.119217 25% -1.956723 -0.888867 -0.736994 -0.462374 50% -1.439034 -0.371583 -0.073919 0.012493 75% -0.559196 0.007345 0.570233 0.446926 max 0.329222 0.634871 0.977957 0.762491 [8 rows x 4 columns] A B C D count 6.000000 6.000000 6.000000 6.000000 mean -1.179279 -0.671081 -0.080912 -0.060111 std 0.996287 1.265457 0.855586 0.711977 min -2.131626 -2.990553 -1.142525 -1.119217 25% -1.956723 -0.888867 -0.736994 -0.462374 50% -1.439034 -0.371583 -0.073919 0.012493 75% -0.559196 0.007345 0.570233 0.446926 max 0.329222 0.634871 0.977957 0.762491 [8 rows x 4 columns] |
df.T
2013-01-01 2013-01-02 2013-01-03 2013-01-04 2013-01-05 2013-01-06 A 0.329222 -2.131626 -0.967064 -1.971963 -0.423241 -1.911004 B -1.027603 -2.990553 -0.270507 0.634871 0.099963 -0.472659 C 0.045742 -0.918132 -1.142525 0.977957 -0.193580 0.745064 D -0.005040 -1.119217 0.030026 0.762491 0.585892 -0.614818 [4 rows x 6 columns] 2013-01-01 2013-01-02 2013-01-03 2013-01-04 2013-01-05 2013-01-06 A 0.329222 -2.131626 -0.967064 -1.971963 -0.423241 -1.911004 B -1.027603 -2.990553 -0.270507 0.634871 0.099963 -0.472659 C 0.045742 -0.918132 -1.142525 0.977957 -0.193580 0.745064 D -0.005040 -1.119217 0.030026 0.762491 0.585892 -0.614818 [4 rows x 6 columns] |
# sageでは、axis=1の操作ができない
# df.sort_index(axis=1, ascending=False)
df.T.sort_index(ascending=False).T
D C B A 2013-01-01 -0.005040 0.045742 -1.027603 0.329222 2013-01-02 -1.119217 -0.918132 -2.990553 -2.131626 2013-01-03 0.030026 -1.142525 -0.270507 -0.967064 2013-01-04 0.762491 0.977957 0.634871 -1.971963 2013-01-05 0.585892 -0.193580 0.099963 -0.423241 2013-01-06 -0.614818 0.745064 -0.472659 -1.911004 [6 rows x 4 columns] D C B A 2013-01-01 -0.005040 0.045742 -1.027603 0.329222 2013-01-02 -1.119217 -0.918132 -2.990553 -2.131626 2013-01-03 0.030026 -1.142525 -0.270507 -0.967064 2013-01-04 0.762491 0.977957 0.634871 -1.971963 2013-01-05 0.585892 -0.193580 0.099963 -0.423241 2013-01-06 -0.614818 0.745064 -0.472659 -1.911004 [6 rows x 4 columns] |
df.sort(columns='B')
A B C D 2013-01-02 -2.131626 -2.990553 -0.918132 -1.119217 2013-01-01 0.329222 -1.027603 0.045742 -0.005040 2013-01-06 -1.911004 -0.472659 0.745064 -0.614818 2013-01-03 -0.967064 -0.270507 -1.142525 0.030026 2013-01-05 -0.423241 0.099963 -0.193580 0.585892 2013-01-04 -1.971963 0.634871 0.977957 0.762491 [6 rows x 4 columns] A B C D 2013-01-02 -2.131626 -2.990553 -0.918132 -1.119217 2013-01-01 0.329222 -1.027603 0.045742 -0.005040 2013-01-06 -1.911004 -0.472659 0.745064 -0.614818 2013-01-03 -0.967064 -0.270507 -1.142525 0.030026 2013-01-05 -0.423241 0.099963 -0.193580 0.585892 2013-01-04 -1.971963 0.634871 0.977957 0.762491 [6 rows x 4 columns] |
html.table(df.values.tolist(), header=df.columns.tolist())
|
df['A']
2013-01-01 0.329222 2013-01-02 -2.131626 2013-01-03 -0.967064 2013-01-04 -1.971963 2013-01-05 -0.423241 2013-01-06 -1.911004 Freq: D, Name: A, dtype: float64 2013-01-01 0.329222 2013-01-02 -2.131626 2013-01-03 -0.967064 2013-01-04 -1.971963 2013-01-05 -0.423241 2013-01-06 -1.911004 Freq: D, Name: A, dtype: float64 |
#df[0:3]
df.iloc[0:3,]
A B C D 2013-01-01 0.329222 -1.027603 0.045742 -0.005040 2013-01-02 -2.131626 -2.990553 -0.918132 -1.119217 2013-01-03 -0.967064 -0.270507 -1.142525 0.030026 [3 rows x 4 columns] A B C D 2013-01-01 0.329222 -1.027603 0.045742 -0.005040 2013-01-02 -2.131626 -2.990553 -0.918132 -1.119217 2013-01-03 -0.967064 -0.270507 -1.142525 0.030026 [3 rows x 4 columns] |
df['2013-01-02':'2013-01-04']
A B C D 2013-01-02 -2.131626 -2.990553 -0.918132 -1.119217 2013-01-03 -0.967064 -0.270507 -1.142525 0.030026 2013-01-04 -1.971963 0.634871 0.977957 0.762491 [3 rows x 4 columns] A B C D 2013-01-02 -2.131626 -2.990553 -0.918132 -1.119217 2013-01-03 -0.967064 -0.270507 -1.142525 0.030026 2013-01-04 -1.971963 0.634871 0.977957 0.762491 [3 rows x 4 columns] |
#df.loc[dates[0]]
df.ix[0]
A 0.370320 B 0.110648 C -0.609493 D 0.965530 Name: 0, dtype: float64 A 0.370320 B 0.110648 C -0.609493 D 0.965530 Name: 0, dtype: float64 |
df.loc[:,['A', 'B']]
A B 2013-01-01 0.329222 -1.027603 2013-01-02 -2.131626 -2.990553 2013-01-03 -0.967064 -0.270507 2013-01-04 -1.971963 0.634871 2013-01-05 -0.423241 0.099963 2013-01-06 -1.911004 -0.472659 [6 rows x 2 columns] A B 2013-01-01 0.329222 -1.027603 2013-01-02 -2.131626 -2.990553 2013-01-03 -0.967064 -0.270507 2013-01-04 -1.971963 0.634871 2013-01-05 -0.423241 0.099963 2013-01-06 -1.911004 -0.472659 [6 rows x 2 columns] |
df.loc['20130102':'20130104', ['A', 'B']]
A B 2013-01-02 -2.131626 -2.990553 2013-01-03 -0.967064 -0.270507 2013-01-04 -1.971963 0.634871 [3 rows x 2 columns] A B 2013-01-02 -2.131626 -2.990553 2013-01-03 -0.967064 -0.270507 2013-01-04 -1.971963 0.634871 [3 rows x 2 columns] |
df.loc['20130102',['A', 'B']]
A -2.131626 B -2.990553 Name: 2013-01-02 00:00:00, dtype: float64 A -2.131626 B -2.990553 Name: 2013-01-02 00:00:00, dtype: float64 |
#df.loc[dates[0], 'A']
df.loc['20130101', 'A']
0.32922229678262199 0.32922229678262199 |
#df.at[dates[0], 'A']
Traceback (click to the left of this block for traceback) ... AttributeError: 'numpy.datetime64' object has no attribute 'name' Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "_sage_input_361.py", line 10, in <module>
exec compile(u'open("___code___.py","w").write("# -*- coding: utf-8 -*-\\n" + _support_.preparse_worksheet_cell(base64.b64decode("I2RmLmF0W2RhdGVzWzBdLCAnQSddCmRmLml4W2RhdGVzWzBdLCAnQSdd"),globals())+"\\n"); execfile(os.path.abspath("___code___.py"))
File "", line 1, in <module>
File "/tmp/tmpqpchms/___code___.py", line 3, in <module>
exec compile(u"df.ix[dates[_sage_const_0 ], 'A']" + '\n', '', 'single')
File "", line 1, in <module>
File "/usr/local/sage-6.0/local/lib/python2.7/site-packages/pandas-0.13.0-py2.7-linux-x86_64.egg/pandas/tseries/index.py", line 1369, in __getitem__
return self._simple_new(result, self.name, new_offset, self.tz)
File "/usr/local/sage-6.0/local/lib/python2.7/site-packages/pandas-0.13.0-py2.7-linux-x86_64.egg/pandas/tseries/index.py", line 446, in _simple_new
result.name = name
AttributeError: 'numpy.datetime64' object has no attribute 'name'
|
#df.iloc[3]
df.ix[3]
A -1.672190 B -1.078498 C 0.843426 D -1.578764 Name: 3, dtype: float64 A -1.672190 B -1.078498 C 0.843426 D -1.578764 Name: 3, dtype: float64 |
df.iloc[3:5, 0:2]
A B 2013-01-04 -1.971963 0.634871 2013-01-05 -0.423241 0.099963 [2 rows x 2 columns] A B 2013-01-04 -1.971963 0.634871 2013-01-05 -0.423241 0.099963 [2 rows x 2 columns] |
df.iloc[1:3, :]
A B C D 2013-01-02 -2.131626 -2.990553 -0.918132 -1.119217 2013-01-03 -0.967064 -0.270507 -1.142525 0.030026 [2 rows x 4 columns] A B C D 2013-01-02 -2.131626 -2.990553 -0.918132 -1.119217 2013-01-03 -0.967064 -0.270507 -1.142525 0.030026 [2 rows x 4 columns] |
df.iloc[:, 1:3]
B C 2013-01-01 -1.027603 0.045742 2013-01-02 -2.990553 -0.918132 2013-01-03 -0.270507 -1.142525 2013-01-04 0.634871 0.977957 2013-01-05 0.099963 -0.193580 2013-01-06 -0.472659 0.745064 [6 rows x 2 columns] B C 2013-01-01 -1.027603 0.045742 2013-01-02 -2.990553 -0.918132 2013-01-03 -0.270507 -1.142525 2013-01-04 0.634871 0.977957 2013-01-05 0.099963 -0.193580 2013-01-06 -0.472659 0.745064 [6 rows x 2 columns] |
#df.iloc[1,1]
df.ix[1,1]
0.036577458005332408 0.036577458005332408 |
df.iat[1, 1]
Traceback (click to the left of this block for traceback) ... ValueError: iAt based indexing can only have integer indexers Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "_sage_input_272.py", line 10, in <module>
exec compile(u'open("___code___.py","w").write("# -*- coding: utf-8 -*-\\n" + _support_.preparse_worksheet_cell(base64.b64decode("ZGYuaWF0WzEsIDFd"),globals())+"\\n"); execfile(os.path.abspath("___code___.py"))
File "", line 1, in <module>
File "/tmp/tmpv2oWCb/___code___.py", line 3, in <module>
exec compile(u'df.iat[_sage_const_1 , _sage_const_1 ]
File "", line 1, in <module>
File "/usr/local/sage-6.0/local/lib/python2.7/site-packages/pandas-0.13.0-py2.7-linux-x86_64.egg/pandas/core/indexing.py", line 1257, in __getitem__
key = self._convert_key(key)
File "/usr/local/sage-6.0/local/lib/python2.7/site-packages/pandas-0.13.0-py2.7-linux-x86_64.egg/pandas/core/indexing.py", line 1289, in _convert_key
raise ValueError("iAt based indexing can only have integer "
ValueError: iAt based indexing can only have integer indexers
|
x = list('abcdef')
|
|
x[4:10]
['e', 'f'] ['e', 'f'] |
x[8:10]
[] [] |
df.iloc[:, 8:10]
Traceback (click to the left of this block for traceback) ... IndexError: out-of-bounds on slice (start) Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "_sage_input_276.py", line 10, in <module>
exec compile(u'open("___code___.py","w").write("# -*- coding: utf-8 -*-\\n" + _support_.preparse_worksheet_cell(base64.b64decode("ZGYuaWxvY1s6LCA4OjEwXQ=="),globals())+"\\n"); execfile(os.path.abspath("___code___.py"))
File "", line 1, in <module>
File "/tmp/tmpkjSKsW/___code___.py", line 3, in <module>
exec compile(u'df.iloc[:, _sage_const_8 :_sage_const_10 ]
File "", line 1, in <module>
File "/usr/local/sage-6.0/local/lib/python2.7/site-packages/pandas-0.13.0-py2.7-linux-x86_64.egg/pandas/core/indexing.py", line 1018, in __getitem__
return self._getitem_tuple(key)
File "/usr/local/sage-6.0/local/lib/python2.7/site-packages/pandas-0.13.0-py2.7-linux-x86_64.egg/pandas/core/indexing.py", line 1190, in _getitem_tuple
retval = getattr(retval, self.name)._getitem_axis(key, axis=i)
File "/usr/local/sage-6.0/local/lib/python2.7/site-packages/pandas-0.13.0-py2.7-linux-x86_64.egg/pandas/core/indexing.py", line 1210, in _getitem_axis
return self._get_slice_axis(key, axis=axis)
File "/usr/local/sage-6.0/local/lib/python2.7/site-packages/pandas-0.13.0-py2.7-linux-x86_64.egg/pandas/core/indexing.py", line 1202, in _get_slice_axis
typ='iloc')
File "/usr/local/sage-6.0/local/lib/python2.7/site-packages/pandas-0.13.0-py2.7-linux-x86_64.egg/pandas/core/indexing.py", line 75, in _slice
typ=typ)
File "/usr/local/sage-6.0/local/lib/python2.7/site-packages/pandas-0.13.0-py2.7-linux-x86_64.egg/pandas/core/frame.py", line 1836, in _slice
slobj, axis=axis, raise_on_error=raise_on_error)
File "/usr/local/sage-6.0/local/lib/python2.7/site-packages/pandas-0.13.0-py2.7-linux-x86_64.egg/pandas/core/internals.py", line 2516, in get_slice
_check_slice_bounds(slobj, new_axes[axis])
File "/usr/local/sage-6.0/local/lib/python2.7/site-packages/pandas-0.13.0-py2.7-linux-x86_64.egg/pandas/core/indexing.py", line 1523, in _check_slice_bounds
raise IndexError("out-of-bounds on slice (start)")
IndexError: out-of-bounds on slice (start)
|
df[df.A > 0]
A B C D 2013-01-01 0.329222 -1.027603 0.045742 -0.00504 [1 rows x 4 columns] A B C D 2013-01-01 0.329222 -1.027603 0.045742 -0.00504 [1 rows x 4 columns] |
df[df > 0]
A B C D 2013-01-01 0.329222 NaN 0.045742 NaN 2013-01-02 NaN NaN NaN NaN 2013-01-03 NaN NaN NaN 0.030026 2013-01-04 NaN 0.634871 0.977957 0.762491 2013-01-05 NaN 0.099963 NaN 0.585892 2013-01-06 NaN NaN 0.745064 NaN [6 rows x 4 columns] A B C D 2013-01-01 0.329222 NaN 0.045742 NaN 2013-01-02 NaN NaN NaN NaN 2013-01-03 NaN NaN NaN 0.030026 2013-01-04 NaN 0.634871 0.977957 0.762491 2013-01-05 NaN 0.099963 NaN 0.585892 2013-01-06 NaN NaN 0.745064 NaN [6 rows x 4 columns] |
s1 = pd.Series([1,2,3,4,5,6],index=pd.date_range('20130102', '20130107'))
|
|
s1
2013-01-02 1 2013-01-03 2 2013-01-04 3 2013-01-05 4 2013-01-06 5 2013-01-07 6 Freq: D, dtype: object 2013-01-02 1 2013-01-03 2 2013-01-04 3 2013-01-05 4 2013-01-06 5 2013-01-07 6 Freq: D, dtype: object |
df['F'] = s1
|
|
df.at[dates[0], 'A']
Traceback (click to the left of this block for traceback) ... AttributeError: 'numpy.datetime64' object has no attribute 'name' Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "_sage_input_282.py", line 10, in <module>
exec compile(u'open("___code___.py","w").write("# -*- coding: utf-8 -*-\\n" + _support_.preparse_worksheet_cell(base64.b64decode("ZGYuYXRbZGF0ZXNbMF0sICdBJ10="),globals())+"\\n"); execfile(os.path.abspath("___code___.py"))
File "", line 1, in <module>
File "/tmp/tmpCRl5v1/___code___.py", line 3, in <module>
exec compile(u"df.at[dates[_sage_const_0 ], 'A']" + '\n', '', 'single')
File "", line 1, in <module>
File "/usr/local/sage-6.0/local/lib/python2.7/site-packages/pandas-0.13.0-py2.7-linux-x86_64.egg/pandas/tseries/index.py", line 1369, in __getitem__
return self._simple_new(result, self.name, new_offset, self.tz)
File "/usr/local/sage-6.0/local/lib/python2.7/site-packages/pandas-0.13.0-py2.7-linux-x86_64.egg/pandas/tseries/index.py", line 446, in _simple_new
result.name = name
AttributeError: 'numpy.datetime64' object has no attribute 'name'
|
df.iat[0,1]
Traceback (click to the left of this block for traceback) ... ValueError: iAt based indexing can only have integer indexers Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "_sage_input_283.py", line 10, in <module>
exec compile(u'open("___code___.py","w").write("# -*- coding: utf-8 -*-\\n" + _support_.preparse_worksheet_cell(base64.b64decode("ZGYuaWF0WzAsMV0="),globals())+"\\n"); execfile(os.path.abspath("___code___.py"))
File "", line 1, in <module>
File "/tmp/tmp2NmQDZ/___code___.py", line 3, in <module>
exec compile(u'df.iat[_sage_const_0 ,_sage_const_1 ]
File "", line 1, in <module>
File "/usr/local/sage-6.0/local/lib/python2.7/site-packages/pandas-0.13.0-py2.7-linux-x86_64.egg/pandas/core/indexing.py", line 1257, in __getitem__
key = self._convert_key(key)
File "/usr/local/sage-6.0/local/lib/python2.7/site-packages/pandas-0.13.0-py2.7-linux-x86_64.egg/pandas/core/indexing.py", line 1289, in _convert_key
raise ValueError("iAt based indexing can only have integer "
ValueError: iAt based indexing can only have integer indexers
|
df
A B C D F 2013-01-01 0.329222 -1.027603 0.045742 -0.005040 NaN 2013-01-02 -2.131626 -2.990553 -0.918132 -1.119217 1 2013-01-03 -0.967064 -0.270507 -1.142525 0.030026 2 2013-01-04 -1.971963 0.634871 0.977957 0.762491 3 2013-01-05 -0.423241 0.099963 -0.193580 0.585892 4 2013-01-06 -1.911004 -0.472659 0.745064 -0.614818 5 [6 rows x 5 columns] A B C D F 2013-01-01 0.329222 -1.027603 0.045742 -0.005040 NaN 2013-01-02 -2.131626 -2.990553 -0.918132 -1.119217 1 2013-01-03 -0.967064 -0.270507 -1.142525 0.030026 2 2013-01-04 -1.971963 0.634871 0.977957 0.762491 3 2013-01-05 -0.423241 0.099963 -0.193580 0.585892 4 2013-01-06 -1.911004 -0.472659 0.745064 -0.614818 5 [6 rows x 5 columns] |
df.loc[:,'D'] = np.array([5] * len(df))
|
|
df
A B C D F 2013-01-01 0.329222 -1.027603 0.045742 5 NaN 2013-01-02 -2.131626 -2.990553 -0.918132 5 1 2013-01-03 -0.967064 -0.270507 -1.142525 5 2 2013-01-04 -1.971963 0.634871 0.977957 5 3 2013-01-05 -0.423241 0.099963 -0.193580 5 4 2013-01-06 -1.911004 -0.472659 0.745064 5 5 [6 rows x 5 columns] A B C D F 2013-01-01 0.329222 -1.027603 0.045742 5 NaN 2013-01-02 -2.131626 -2.990553 -0.918132 5 1 2013-01-03 -0.967064 -0.270507 -1.142525 5 2 2013-01-04 -1.971963 0.634871 0.977957 5 3 2013-01-05 -0.423241 0.099963 -0.193580 5 4 2013-01-06 -1.911004 -0.472659 0.745064 5 5 [6 rows x 5 columns] |
df2 = df.copy()
df2[df2 > 0] = -df2
Traceback (click to the left of this block for traceback) ... TypeError: Cannot do boolean setting on mixed-type frame Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "_sage_input_287.py", line 10, in <module>
exec compile(u'open("___code___.py","w").write("# -*- coding: utf-8 -*-\\n" + _support_.preparse_worksheet_cell(base64.b64decode("ZGYyID0gZGYuY29weSgpCmRmMltkZjIgPiAwXSA9IC1kZjI="),globals())+"\\n"); execfile(os.path.abspath("___code___.py"))
File "", line 1, in <module>
File "/tmp/tmpQ7mx4G/___code___.py", line 4, in <module>
exec compile(u'df2[df2 > _sage_const_0 ] = -df2
File "", line 1, in <module>
File "/usr/local/sage-6.0/local/lib/python2.7/site-packages/pandas-0.13.0-py2.7-linux-x86_64.egg/pandas/core/frame.py", line 1860, in __setitem__
self._setitem_frame(key, value)
File "/usr/local/sage-6.0/local/lib/python2.7/site-packages/pandas-0.13.0-py2.7-linux-x86_64.egg/pandas/core/frame.py", line 1896, in _setitem_frame
'Cannot do boolean setting on mixed-type frame')
TypeError: Cannot do boolean setting on mixed-type frame
|
df2[df2 > 0]
A B C D F 2013-01-01 0.329222 NaN 0.045742 5 NaN 2013-01-02 NaN NaN NaN 5 1 2013-01-03 NaN NaN NaN 5 2 2013-01-04 NaN 0.634871 0.977957 5 3 2013-01-05 NaN 0.099963 NaN 5 4 2013-01-06 NaN NaN 0.745064 5 5 [6 rows x 5 columns] A B C D F 2013-01-01 0.329222 NaN 0.045742 5 NaN 2013-01-02 NaN NaN NaN 5 1 2013-01-03 NaN NaN NaN 5 2 2013-01-04 NaN 0.634871 0.977957 5 3 2013-01-05 NaN 0.099963 NaN 5 4 2013-01-06 NaN NaN 0.745064 5 5 [6 rows x 5 columns] |
df2
A B C D F 2013-01-01 0.329222 -1.027603 0.045742 5 NaN 2013-01-02 -2.131626 -2.990553 -0.918132 5 1 2013-01-03 -0.967064 -0.270507 -1.142525 5 2 2013-01-04 -1.971963 0.634871 0.977957 5 3 2013-01-05 -0.423241 0.099963 -0.193580 5 4 2013-01-06 -1.911004 -0.472659 0.745064 5 5 [6 rows x 5 columns] A B C D F 2013-01-01 0.329222 -1.027603 0.045742 5 NaN 2013-01-02 -2.131626 -2.990553 -0.918132 5 1 2013-01-03 -0.967064 -0.270507 -1.142525 5 2 2013-01-04 -1.971963 0.634871 0.977957 5 3 2013-01-05 -0.423241 0.099963 -0.193580 5 4 2013-01-06 -1.911004 -0.472659 0.745064 5 5 [6 rows x 5 columns] |
df1 = df.reindex(index=dates[0:4], columns=list(df.columns) + ['E'])
|
|
#df1.loc[dates[0]:dates[1], 'E')
df1.loc['20130101':'20130102', : )
Traceback (click to the left of this block for traceback) ... SyntaxError: invalid syntax Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "_sage_input_291.py", line 10, in <module>
exec compile(u'open("___code___.py","w").write("# -*- coding: utf-8 -*-\\n" + _support_.preparse_worksheet_cell(base64.b64decode("I2RmMS5sb2NbZGF0ZXNbMF06ZGF0ZXNbMV0sICdFJykKZGYxLmxvY1snMjAxMzAxMDEnOicyMDEzMDEwMicsIDogKQ=="),globals())+"\\n"); execfile(os.path.abspath("___code___.py"))
File "", line 1, in <module>
File "/tmp/tmpIhpBkb/___code___.py", line 3
df1.loc['20130101':'20130102', : )
^
SyntaxError: invalid syntax
|
df1.loc['20130101':'20130102', 'E'] = 1
|
|
df1
A B C D F E 2013-01-01 0.329222 -1.027603 0.045742 5 NaN 1 2013-01-02 -2.131626 -2.990553 -0.918132 5 1 1 2013-01-03 -0.967064 -0.270507 -1.142525 5 2 NaN 2013-01-04 -1.971963 0.634871 0.977957 5 3 NaN [4 rows x 6 columns] A B C D F E 2013-01-01 0.329222 -1.027603 0.045742 5 NaN 1 2013-01-02 -2.131626 -2.990553 -0.918132 5 1 1 2013-01-03 -0.967064 -0.270507 -1.142525 5 2 NaN 2013-01-04 -1.971963 0.634871 0.977957 5 3 NaN [4 rows x 6 columns] |
df1.dropna(how='any')
A B C D F E 2013-01-02 -2.131626 -2.990553 -0.918132 5 1 1 [1 rows x 6 columns] A B C D F E 2013-01-02 -2.131626 -2.990553 -0.918132 5 1 1 [1 rows x 6 columns] |
df1.fillna(value=5)
A B C D F E 2013-01-01 0.329222 -1.027603 0.045742 5 5 1 2013-01-02 -2.131626 -2.990553 -0.918132 5 1 1 2013-01-03 -0.967064 -0.270507 -1.142525 5 2 5 2013-01-04 -1.971963 0.634871 0.977957 5 3 5 [4 rows x 6 columns] A B C D F E 2013-01-01 0.329222 -1.027603 0.045742 5 5 1 2013-01-02 -2.131626 -2.990553 -0.918132 5 1 1 2013-01-03 -0.967064 -0.270507 -1.142525 5 2 5 2013-01-04 -1.971963 0.634871 0.977957 5 3 5 [4 rows x 6 columns] |
pd.isnull(df1)
A B C D F E 2013-01-01 False False False False True False 2013-01-02 False False False False False False 2013-01-03 False False False False False True 2013-01-04 False False False False False True [4 rows x 6 columns] A B C D F E 2013-01-01 False False False False True False 2013-01-02 False False False False False False 2013-01-03 False False False False False True 2013-01-04 False False False False False True [4 rows x 6 columns] |
df.mean()
A -1.179279 B -0.671081 C -0.080912 D 5.000000 F 3.000000 dtype: float64 A -1.179279 B -0.671081 C -0.080912 D 5.000000 F 3.000000 dtype: float64 |
#df.mean(1)
df.T.mean()
2013-01-01 1.086840 2013-01-02 -0.008062 2013-01-03 0.923981 2013-01-04 1.528173 2013-01-05 1.696628 2013-01-06 1.672280 Freq: D, dtype: float64 2013-01-01 1.086840 2013-01-02 -0.008062 2013-01-03 0.923981 2013-01-04 1.528173 2013-01-05 1.696628 2013-01-06 1.672280 Freq: D, dtype: float64 |
s = pd.Series([1,3,5,np.nan,6,8],index=dates).shift(2); s
2013-01-01 NaN 2013-01-02 NaN 2013-01-03 1 2013-01-04 3 2013-01-05 5 2013-01-06 NaN Freq: D, dtype: object 2013-01-01 NaN 2013-01-02 NaN 2013-01-03 1 2013-01-04 3 2013-01-05 5 2013-01-06 NaN Freq: D, dtype: object |
df.sub(s, axis='index')
A B C D F 2013-01-01 NaN NaN NaN NaN NaN 2013-01-02 NaN NaN NaN NaN NaN 2013-01-03 -1.967064 -1.270507 -2.142525 4 1 2013-01-04 -4.971963 -2.365129 -2.022043 2 0 2013-01-05 -5.423241 -4.900037 -5.19358 0 -1 2013-01-06 NaN NaN NaN NaN NaN [6 rows x 5 columns] A B C D F 2013-01-01 NaN NaN NaN NaN NaN 2013-01-02 NaN NaN NaN NaN NaN 2013-01-03 -1.967064 -1.270507 -2.142525 4 1 2013-01-04 -4.971963 -2.365129 -2.022043 2 0 2013-01-05 -5.423241 -4.900037 -5.19358 0 -1 2013-01-06 NaN NaN NaN NaN NaN [6 rows x 5 columns] |
df.apply(np.cumsum)
A B C D F 2013-01-01 0.329222 -1.027603 0.045742 5 NaN 2013-01-02 -1.802404 -4.018156 -0.872390 10 1 2013-01-03 -2.769467 -4.288663 -2.014915 15 3 2013-01-04 -4.741431 -3.653792 -1.036958 20 6 2013-01-05 -5.164671 -3.553829 -1.230538 25 10 2013-01-06 -7.075675 -4.026488 -0.485474 30 15 [6 rows x 5 columns] A B C D F 2013-01-01 0.329222 -1.027603 0.045742 5 NaN 2013-01-02 -1.802404 -4.018156 -0.872390 10 1 2013-01-03 -2.769467 -4.288663 -2.014915 15 3 2013-01-04 -4.741431 -3.653792 -1.036958 20 6 2013-01-05 -5.164671 -3.553829 -1.230538 25 10 2013-01-06 -7.075675 -4.026488 -0.485474 30 15 [6 rows x 5 columns] |
df.apply(lambda x: x.max() - x.min())
A 2.460849 B 3.625425 C 2.120482 D 0 F 4 dtype: object A 2.460849 B 3.625425 C 2.120482 D 0 F 4 dtype: object |
s = pd.Series(np.random.randint(0,7,size=10)); s
0 6 1 2 2 6 3 0 4 5 5 6 6 3 7 2 8 2 9 5 dtype: int64 0 6 1 2 2 6 3 0 4 5 5 6 6 3 7 2 8 2 9 5 dtype: int64 |
s.value_counts()
6 3 2 3 5 2 3 1 0 1 dtype: int64 6 3 2 3 5 2 3 1 0 1 dtype: int64 |
s = pd.Series(['A', 'B', 'C', 'Aaba', 'Baca', np.nan, 'CABA', 'dog', 'cat'])
s.str.lower()
0 a 1 b 2 c 3 aaba 4 baca 5 NaN 6 caba 7 dog 8 cat dtype: object 0 a 1 b 2 c 3 aaba 4 baca 5 NaN 6 caba 7 dog 8 cat dtype: object |
df = pd.DataFrame(np.random.randn(10, 4)); df
0 1 2 3 0 1.928492 1.118287 -2.519915 -0.732903 1 -0.255994 -0.874783 -0.112143 -0.550197 2 0.020601 0.191504 1.031185 0.173446 3 -0.190841 -1.545637 1.370097 0.628026 4 0.339714 -0.241329 1.591237 -0.114874 5 0.065372 1.231525 1.482569 -0.328469 6 -0.359970 0.849471 -1.130912 -1.500106 7 0.457768 -1.622407 -0.736991 0.392162 8 0.794101 1.042252 1.713021 2.795153 9 -0.689289 -0.517617 0.665668 -0.286480 [10 rows x 4 columns] 0 1 2 3 0 1.928492 1.118287 -2.519915 -0.732903 1 -0.255994 -0.874783 -0.112143 -0.550197 2 0.020601 0.191504 1.031185 0.173446 3 -0.190841 -1.545637 1.370097 0.628026 4 0.339714 -0.241329 1.591237 -0.114874 5 0.065372 1.231525 1.482569 -0.328469 6 -0.359970 0.849471 -1.130912 -1.500106 7 0.457768 -1.622407 -0.736991 0.392162 8 0.794101 1.042252 1.713021 2.795153 9 -0.689289 -0.517617 0.665668 -0.286480 [10 rows x 4 columns] |
pieces = [df[:3], df[3:7], df[7:]]; pieces
[ 0 1 2 3 0 1.928492 1.118287 -2.519915 -0.732903 1 -0.255994 -0.874783 -0.112143 -0.550197 2 0.020601 0.191504 1.031185 0.173446 [3 rows x 4 columns], 0 1 2 3 3 -0.190841 -1.545637 1.370097 0.628026 4 0.339714 -0.241329 1.591237 -0.114874 5 0.065372 1.231525 1.482569 -0.328469 6 -0.359970 0.849471 -1.130912 -1.500106 [4 rows x 4 columns], 0 1 2 3 7 0.457768 -1.622407 -0.736991 0.392162 8 0.794101 1.042252 1.713021 2.795153 9 -0.689289 -0.517617 0.665668 -0.286480 [3 rows x 4 columns]] [ 0 1 2 3 0 1.928492 1.118287 -2.519915 -0.732903 1 -0.255994 -0.874783 -0.112143 -0.550197 2 0.020601 0.191504 1.031185 0.173446 [3 rows x 4 columns], 0 1 2 3 3 -0.190841 -1.545637 1.370097 0.628026 4 0.339714 -0.241329 1.591237 -0.114874 5 0.065372 1.231525 1.482569 -0.328469 6 -0.359970 0.849471 -1.130912 -1.500106 [4 rows x 4 columns], 0 1 2 3 7 0.457768 -1.622407 -0.736991 0.392162 8 0.794101 1.042252 1.713021 2.795153 9 -0.689289 -0.517617 0.665668 -0.286480 [3 rows x 4 columns]] |
pd.concat(pieces)
0 1 2 3 0 1.928492 1.118287 -2.519915 -0.732903 1 -0.255994 -0.874783 -0.112143 -0.550197 2 0.020601 0.191504 1.031185 0.173446 3 -0.190841 -1.545637 1.370097 0.628026 4 0.339714 -0.241329 1.591237 -0.114874 5 0.065372 1.231525 1.482569 -0.328469 6 -0.359970 0.849471 -1.130912 -1.500106 7 0.457768 -1.622407 -0.736991 0.392162 8 0.794101 1.042252 1.713021 2.795153 9 -0.689289 -0.517617 0.665668 -0.286480 [10 rows x 4 columns] 0 1 2 3 0 1.928492 1.118287 -2.519915 -0.732903 1 -0.255994 -0.874783 -0.112143 -0.550197 2 0.020601 0.191504 1.031185 0.173446 3 -0.190841 -1.545637 1.370097 0.628026 4 0.339714 -0.241329 1.591237 -0.114874 5 0.065372 1.231525 1.482569 -0.328469 6 -0.359970 0.849471 -1.130912 -1.500106 7 0.457768 -1.622407 -0.736991 0.392162 8 0.794101 1.042252 1.713021 2.795153 9 -0.689289 -0.517617 0.665668 -0.286480 [10 rows x 4 columns] |
left = pd.DataFrame({'key': ['foo', 'foo'], 'lval': [1, 2]})
right = pd.DataFrame({'key': ['foo', 'foo'], 'rval': [3, 4]})
left
key lval 0 foo 1 1 foo 2 [2 rows x 2 columns] key lval 0 foo 1 1 foo 2 [2 rows x 2 columns] |
right
key rval 0 foo 3 1 foo 4 [2 rows x 2 columns] key rval 0 foo 3 1 foo 4 [2 rows x 2 columns] |
pd.merge(left, right, on='key')
key lval rval 0 foo 1 3 1 foo 1 4 2 foo 2 3 3 foo 2 4 [4 rows x 3 columns] key lval rval 0 foo 1 3 1 foo 1 4 2 foo 2 3 3 foo 2 4 [4 rows x 3 columns] |
df = pd.DataFrame(np.random.randn(8, 4), columns=['A', 'B', 'C', 'D']); df
A B C D 0 0.370320 0.110648 -0.609493 0.965530 1 -0.036627 0.036577 -1.005085 0.379531 2 -0.203456 -0.676061 -0.699941 -0.462796 3 -1.672190 -1.078498 0.843426 -1.578764 4 -0.471450 -0.018858 -1.428270 -1.296049 5 0.971352 0.181037 -0.014627 -0.077370 6 -0.008730 0.574746 -0.546932 -0.345956 7 0.945161 -0.912941 1.247042 -1.055882 [8 rows x 4 columns] A B C D 0 0.370320 0.110648 -0.609493 0.965530 1 -0.036627 0.036577 -1.005085 0.379531 2 -0.203456 -0.676061 -0.699941 -0.462796 3 -1.672190 -1.078498 0.843426 -1.578764 4 -0.471450 -0.018858 -1.428270 -1.296049 5 0.971352 0.181037 -0.014627 -0.077370 6 -0.008730 0.574746 -0.546932 -0.345956 7 0.945161 -0.912941 1.247042 -1.055882 [8 rows x 4 columns] |
# s = df.iloc[3]
s = df.ix[3]; s
A -1.672190 B -1.078498 C 0.843426 D -1.578764 Name: 3, dtype: float64 A -1.672190 B -1.078498 C 0.843426 D -1.578764 Name: 3, dtype: float64 |
df.append(s, ignore_index=True)
A B C D 0 0.370320 0.110648 -0.609493 0.965530 1 -0.036627 0.036577 -1.005085 0.379531 2 -0.203456 -0.676061 -0.699941 -0.462796 3 -1.672190 -1.078498 0.843426 -1.578764 4 -0.471450 -0.018858 -1.428270 -1.296049 5 0.971352 0.181037 -0.014627 -0.077370 6 -0.008730 0.574746 -0.546932 -0.345956 7 0.945161 -0.912941 1.247042 -1.055882 8 -1.672190 -1.078498 0.843426 -1.578764 [9 rows x 4 columns] A B C D 0 0.370320 0.110648 -0.609493 0.965530 1 -0.036627 0.036577 -1.005085 0.379531 2 -0.203456 -0.676061 -0.699941 -0.462796 3 -1.672190 -1.078498 0.843426 -1.578764 4 -0.471450 -0.018858 -1.428270 -1.296049 5 0.971352 0.181037 -0.014627 -0.077370 6 -0.008730 0.574746 -0.546932 -0.345956 7 0.945161 -0.912941 1.247042 -1.055882 8 -1.672190 -1.078498 0.843426 -1.578764 [9 rows x 4 columns] |
df = pd.DataFrame({ 'A' : ['foo', 'bar', 'foo', 'bar',
'foo', 'bar', 'foo', 'foo'],
'B' : ['one', 'one', 'two', 'three',
'two', 'two', 'one', 'three'],
'C' : np.random.randn(8),
'D' : np.random.randn(8) })
|
|
df
A B C D 0 foo one -0.462028 -0.557120 1 bar one 0.516956 -0.565886 2 foo two -0.250218 -0.132476 3 bar three -0.672271 1.173194 4 foo two 0.415148 0.557836 5 bar two -1.517287 0.178196 6 foo one 1.391643 -1.248932 7 foo three -0.396384 -1.506650 [8 rows x 4 columns] A B C D 0 foo one -0.462028 -0.557120 1 bar one 0.516956 -0.565886 2 foo two -0.250218 -0.132476 3 bar three -0.672271 1.173194 4 foo two 0.415148 0.557836 5 bar two -1.517287 0.178196 6 foo one 1.391643 -1.248932 7 foo three -0.396384 -1.506650 [8 rows x 4 columns] |
df.groupby('A').sum()
C D A bar -1.672603 0.785505 foo 0.698161 -2.887342 [2 rows x 2 columns] C D A bar -1.672603 0.785505 foo 0.698161 -2.887342 [2 rows x 2 columns] |
df.groupby(['A', 'B']).sum()
C D
A B
bar one 0.516956 -0.565886
three -0.672271 1.173194
two -1.517287 0.178196
foo one 0.929615 -1.806052
three -0.396384 -1.506650
two 0.164930 0.425360
[6 rows x 2 columns]
C D
A B
bar one 0.516956 -0.565886
three -0.672271 1.173194
two -1.517287 0.178196
foo one 0.929615 -1.806052
three -0.396384 -1.506650
two 0.164930 0.425360
[6 rows x 2 columns]
|
tuples = zip( ['bar', 'bar', 'baz', 'baz', 'foo', 'foo', 'qux', 'qux'],
['one', 'two', 'one', 'two', 'one', 'two', 'one', 'two']); tuples
[('bar', 'one'), ('bar', 'two'), ('baz', 'one'), ('baz', 'two'), ('foo',
'one'), ('foo', 'two'), ('qux', 'one'), ('qux', 'two')]
[('bar', 'one'), ('bar', 'two'), ('baz', 'one'), ('baz', 'two'), ('foo', 'one'), ('foo', 'two'), ('qux', 'one'), ('qux', 'two')]
|
index = pd.MultiIndex.from_tuples(tuples, names=['first', 'second'])
|
|
df2 = pd.DataFrame(np.random.randn(8, 2), index=index, columns=['A', 'B']); df2
A B
first second
bar one -1.138084 0.045845
two -0.721766 -0.766594
baz one -0.102921 0.458671
two -0.624306 -1.613681
foo one 0.843396 0.989673
two 0.259121 -1.407217
qux one 0.643975 -0.127660
two 0.081298 0.231508
[8 rows x 2 columns]
A B
first second
bar one -1.138084 0.045845
two -0.721766 -0.766594
baz one -0.102921 0.458671
two -0.624306 -1.613681
foo one 0.843396 0.989673
two 0.259121 -1.407217
qux one 0.643975 -0.127660
two 0.081298 0.231508
[8 rows x 2 columns]
|
#df2 = df2[:4]
|
|
stacked = df2.stack(); stacked
first second
bar one A -1.138084
B 0.045845
two A -0.721766
B -0.766594
baz one A -0.102921
B 0.458671
two A -0.624306
B -1.613681
foo one A 0.843396
B 0.989673
two A 0.259121
B -1.407217
qux one A 0.643975
B -0.127660
two A 0.081298
B 0.231508
dtype: float64
first second
bar one A -1.138084
B 0.045845
two A -0.721766
B -0.766594
baz one A -0.102921
B 0.458671
two A -0.624306
B -1.613681
foo one A 0.843396
B 0.989673
two A 0.259121
B -1.407217
qux one A 0.643975
B -0.127660
two A 0.081298
B 0.231508
dtype: float64
|
stacked.unstack()
A B
first second
bar one -1.138084 0.045845
two -0.721766 -0.766594
baz one -0.102921 0.458671
two -0.624306 -1.613681
foo one 0.843396 0.989673
two 0.259121 -1.407217
qux one 0.643975 -0.127660
two 0.081298 0.231508
[8 rows x 2 columns]
A B
first second
bar one -1.138084 0.045845
two -0.721766 -0.766594
baz one -0.102921 0.458671
two -0.624306 -1.613681
foo one 0.843396 0.989673
two 0.259121 -1.407217
qux one 0.643975 -0.127660
two 0.081298 0.231508
[8 rows x 2 columns]
|
#stacked.unstack(1)
stacked.unstack('second')
second one two
first
bar A -0.721294 1.497937
B 0.095341 -0.236623
baz A -1.341615 -1.367798
B -0.323850 0.899221
foo A -0.458022 0.142316
B 0.936772 0.197030
qux A -0.902071 0.627089
B -1.144674 0.599214
[8 rows x 2 columns]
second one two
first
bar A -0.721294 1.497937
B 0.095341 -0.236623
baz A -1.341615 -1.367798
B -0.323850 0.899221
foo A -0.458022 0.142316
B 0.936772 0.197030
qux A -0.902071 0.627089
B -1.144674 0.599214
[8 rows x 2 columns]
|
#stacked.unstack(0)
stacked.unstack('first')
first bar baz foo qux
second
one A -0.721294 -1.341615 -0.458022 -0.902071
B 0.095341 -0.323850 0.936772 -1.144674
two A 1.497937 -1.367798 0.142316 0.627089
B -0.236623 0.899221 0.197030 0.599214
[4 rows x 4 columns]
first bar baz foo qux
second
one A -0.721294 -1.341615 -0.458022 -0.902071
B 0.095341 -0.323850 0.936772 -1.144674
two A 1.497937 -1.367798 0.142316 0.627089
B -0.236623 0.899221 0.197030 0.599214
[4 rows x 4 columns]
|
df = pd.DataFrame({ 'A' : ['one', 'one', 'two', 'three'] * 3,
'B' : ['A', 'B', 'C'] * 4,
'C' : ['foo', 'foo', 'foo', 'bar', 'bar', 'bar'] * 2,
'D' : np.random.randn(12),
'E' : np.random.randn(12)})
|
|
df
A B C D E 0 one A foo -0.575791 1.237530 1 one B foo -0.878026 -2.105447 2 two C foo 0.358016 -1.244665 3 three A bar -1.554278 2.092796 4 one B bar -0.361680 -0.612601 5 one C bar 0.996817 -0.342134 6 two A foo 0.315994 0.053370 7 three B foo 0.365110 -1.792427 8 one C foo 0.267303 1.612153 9 one A bar -0.481900 0.101901 10 two B bar 0.934088 -0.738267 11 three C bar -0.356125 -1.344649 [12 rows x 5 columns] A B C D E 0 one A foo -0.575791 1.237530 1 one B foo -0.878026 -2.105447 2 two C foo 0.358016 -1.244665 3 three A bar -1.554278 2.092796 4 one B bar -0.361680 -0.612601 5 one C bar 0.996817 -0.342134 6 two A foo 0.315994 0.053370 7 three B foo 0.365110 -1.792427 8 one C foo 0.267303 1.612153 9 one A bar -0.481900 0.101901 10 two B bar 0.934088 -0.738267 11 three C bar -0.356125 -1.344649 [12 rows x 5 columns] |
pd.pivot_table(df, values='D', rows=['A', 'B'], cols = ['C'])
C bar foo
A B
one A -0.481900 -0.575791
B -0.361680 -0.878026
C 0.996817 0.267303
three A -1.554278 NaN
B NaN 0.365110
C -0.356125 NaN
two A NaN 0.315994
B 0.934088 NaN
C NaN 0.358016
[9 rows x 2 columns]
C bar foo
A B
one A -0.481900 -0.575791
B -0.361680 -0.878026
C 0.996817 0.267303
three A -1.554278 NaN
B NaN 0.365110
C -0.356125 NaN
two A NaN 0.315994
B 0.934088 NaN
C NaN 0.358016
[9 rows x 2 columns]
|
#rng = pd.date_range('1/1/2012', period=100, freq='S')
rng = pd.date_range('2013-01-01', '2013-03-01', freq='S')
|
|
ts = pd.Series(np.random.randint(0, 500, len(rng)), index=rng)
|
|
ts.resample('5Min', how='sum')
2013-01-01 00:00:00 73259 2013-01-01 00:05:00 77648 2013-01-01 00:10:00 76375 2013-01-01 00:15:00 77739 2013-01-01 00:20:00 78859 2013-01-01 00:25:00 75512 2013-01-01 00:30:00 72930 2013-01-01 00:35:00 74449 2013-01-01 00:40:00 74204 2013-01-01 00:45:00 74762 2013-01-01 00:50:00 72786 2013-01-01 00:55:00 77871 2013-01-01 01:00:00 71174 2013-01-01 01:05:00 76263 2013-01-01 01:10:00 66631 ... 2013-02-28 22:50:00 74266 2013-02-28 22:55:00 71942 2013-02-28 23:00:00 74738 2013-02-28 23:05:00 74001 2013-02-28 23:10:00 74506 2013-02-28 23:15:00 72185 2013-02-28 23:20:00 73015 2013-02-28 23:25:00 74474 2013-02-28 23:30:00 76912 2013-02-28 23:35:00 74203 2013-02-28 23:40:00 73931 2013-02-28 23:45:00 71752 2013-02-28 23:50:00 69154 2013-02-28 23:55:00 74418 2013-03-01 00:00:00 135 Freq: 5T, Length: 16993 2013-01-01 00:00:00 73259 2013-01-01 00:05:00 77648 2013-01-01 00:10:00 76375 2013-01-01 00:15:00 77739 2013-01-01 00:20:00 78859 2013-01-01 00:25:00 75512 2013-01-01 00:30:00 72930 2013-01-01 00:35:00 74449 2013-01-01 00:40:00 74204 2013-01-01 00:45:00 74762 2013-01-01 00:50:00 72786 2013-01-01 00:55:00 77871 2013-01-01 01:00:00 71174 2013-01-01 01:05:00 76263 2013-01-01 01:10:00 66631 ... 2013-02-28 22:50:00 74266 2013-02-28 22:55:00 71942 2013-02-28 23:00:00 74738 2013-02-28 23:05:00 74001 2013-02-28 23:10:00 74506 2013-02-28 23:15:00 72185 2013-02-28 23:20:00 73015 2013-02-28 23:25:00 74474 2013-02-28 23:30:00 76912 2013-02-28 23:35:00 74203 2013-02-28 23:40:00 73931 2013-02-28 23:45:00 71752 2013-02-28 23:50:00 69154 2013-02-28 23:55:00 74418 2013-03-01 00:00:00 135 Freq: 5T, Length: 16993 |
rng = pd.date_range('2013-01-01', '2013-01-05', freq='D')
ts = pd.Series(np.random.randn(len(rng)), rng)
ts
2013-01-01 -1.062925 2013-01-02 -1.662437 2013-01-03 -0.519298 2013-01-04 -0.393173 2013-01-05 -1.789035 Freq: D, dtype: float64 2013-01-01 -1.062925 2013-01-02 -1.662437 2013-01-03 -0.519298 2013-01-04 -0.393173 2013-01-05 -1.789035 Freq: D, dtype: float64 |
ts_utc = ts.tz_localize('UTC'); ts_utc
2013-01-01 00:00:00+00:00 -1.062925 2013-01-02 00:00:00+00:00 -1.662437 2013-01-03 00:00:00+00:00 -0.519298 2013-01-04 00:00:00+00:00 -0.393173 2013-01-05 00:00:00+00:00 -1.789035 Freq: D, dtype: float64 2013-01-01 00:00:00+00:00 -1.062925 2013-01-02 00:00:00+00:00 -1.662437 2013-01-03 00:00:00+00:00 -0.519298 2013-01-04 00:00:00+00:00 -0.393173 2013-01-05 00:00:00+00:00 -1.789035 Freq: D, dtype: float64 |
ts_utc.tz_convert('US/Eastern')
2012-12-31 19:00:00-05:00 -1.062925 2013-01-01 19:00:00-05:00 -1.662437 2013-01-02 19:00:00-05:00 -0.519298 2013-01-03 19:00:00-05:00 -0.393173 2013-01-04 19:00:00-05:00 -1.789035 Freq: D, dtype: float64 2012-12-31 19:00:00-05:00 -1.062925 2013-01-01 19:00:00-05:00 -1.662437 2013-01-02 19:00:00-05:00 -0.519298 2013-01-03 19:00:00-05:00 -0.393173 2013-01-04 19:00:00-05:00 -1.789035 Freq: D, dtype: float64 |
ts.to_period()
2013-01-01 -1.062925 2013-01-02 -1.662437 2013-01-03 -0.519298 2013-01-04 -0.393173 2013-01-05 -1.789035 Freq: D, dtype: float64 2013-01-01 -1.062925 2013-01-02 -1.662437 2013-01-03 -0.519298 2013-01-04 -0.393173 2013-01-05 -1.789035 Freq: D, dtype: float64 |
ts.plot()
<matplotlib.axes.AxesSubplot object at 0x1d0d6e90> <matplotlib.axes.AxesSubplot object at 0x1d0d6e90> |
plt.savefig('test.png')
|
|
|