def test_resample_panel(self):
rng = date_range("1/1/2000", "6/30/2000")
n = len(rng)
panel = Panel(
np.random.randn(3, n, 5),
items=["one", "two", "three"],
major_axis=rng,
minor_axis=["a", "b", "c", "d", "e"],
)
result = panel.resample("M", axis=1)
def p_apply(panel, f):
result = {}
for item in panel.items:
result[item] = f(panel[item])
return Panel(result, items=panel.items)
expected = p_apply(panel, lambda x: x.resample("M"))
tm.assert_panel_equal(result, expected)
panel2 = panel.swapaxes(1, 2)
result = panel2.resample("M", axis=2)
expected = p_apply(panel2, lambda x: x.resample("M", axis=1))
tm.assert_panel_equal(result, expected)
def test_resample_panel():
rng = date_range('1/1/2000', '6/30/2000')
n = len(rng)
with catch_warnings(record=True):
simplefilter("ignore", FutureWarning)
panel = Panel(np.random.randn(3, n, 5),
items=['one', 'two', 'three'],
major_axis=rng,
minor_axis=['a', 'b', 'c', 'd', 'e'])
result = panel.resample('M', axis=1).mean()
def p_apply(panel, f):
result = {}
for item in panel.items:
result[item] = f(panel[item])
return Panel(result, items=panel.items)
expected = p_apply(panel, lambda x: x.resample('M').mean())
tm.assert_panel_equal(result, expected)
panel2 = panel.swapaxes(1, 2)
result = panel2.resample('M', axis=2).mean()
expected = p_apply(panel2,
lambda x: x.resample('M', axis=1).mean())
tm.assert_panel_equal(result, expected)
def test_resample_panel():
rng = date_range('1/1/2000', '6/30/2000')
n = len(rng)
with catch_warnings(record=True):
simplefilter("ignore", FutureWarning)
panel = Panel(np.random.randn(3, n, 5),
items=['one', 'two', 'three'],
major_axis=rng,
minor_axis=['a', 'b', 'c', 'd', 'e'])
result = panel.resample('M', axis=1).mean()
def p_apply(panel, f):
result = {}
for item in panel.items:
result[item] = f(panel[item])
return Panel(result, items=panel.items)
expected = p_apply(panel, lambda x: x.resample('M').mean())
tm.assert_panel_equal(result, expected)
panel2 = panel.swapaxes(1, 2)
result = panel2.resample('M', axis=2).mean()
expected = p_apply(panel2,
lambda x: x.resample('M', axis=1).mean())
tm.assert_panel_equal(result, expected)
def test_resample_panel_numpy(self):
rng = date_range('1/1/2000', '6/30/2000')
n = len(rng)
panel = Panel(np.random.randn(3, n, 5),
items=['one', 'two', 'three'],
major_axis=rng,
minor_axis=['a', 'b', 'c', 'd', 'e'])
result = panel.resample('M', how=lambda x: x.mean(1), axis=1)
expected = panel.resample('M', how='mean', axis=1)
tm.assert_panel_equal(result, expected)
panel = panel.swapaxes(1, 2)
result = panel.resample('M', how=lambda x: x.mean(2), axis=2)
expected = panel.resample('M', how='mean', axis=2)
tm.assert_panel_equal(result, expected)
def test_resample_panel_numpy(self):
rng = date_range('1/1/2000', '6/30/2000')
n = len(rng)
panel = Panel(np.random.randn(3, n, 5),
items=['one', 'two', 'three'],
major_axis=rng,
minor_axis=['a', 'b', 'c', 'd', 'e'])
result = panel.resample('M', how=lambda x: x.mean(1), axis=1)
expected = panel.resample('M', how='mean', axis=1)
tm.assert_panel_equal(result, expected)
panel = panel.swapaxes(1, 2)
result = panel.resample('M', how=lambda x: x.mean(2), axis=2)
expected = panel.resample('M', how='mean', axis=2)
tm.assert_panel_equal(result, expected)
def first_difference(self):
"""
Compute first differences of variables
Returns
-------
diffs : PanelData
Differenced values
"""
diffs = self.panel.values
diffs = diffs[:, 1:] - diffs[:, :-1]
diffs = Panel(diffs, items=self.panel.items,
major_axis=self.panel.major_axis[1:],
minor_axis=self.panel.minor_axis)
diffs = diffs.swapaxes(1, 2).to_frame(filter_observations=False)
diffs = diffs.reindex(self._frame.index).dropna(how='any')
return PanelData(diffs)
def test_resample_panel_numpy():
rng = date_range('1/1/2000', '6/30/2000')
n = len(rng)
with catch_warnings(record=True):
panel = Panel(np.random.randn(3, n, 5),
items=['one', 'two', 'three'],
major_axis=rng,
minor_axis=['a', 'b', 'c', 'd', 'e'])
result = panel.resample('M', axis=1).apply(lambda x: x.mean(1))
expected = panel.resample('M', axis=1).mean()
tm.assert_panel_equal(result, expected)
panel = panel.swapaxes(1, 2)
result = panel.resample('M', axis=2).apply(lambda x: x.mean(2))
expected = panel.resample('M', axis=2).mean()
tm.assert_panel_equal(result, expected)
def test_resample_panel_numpy():
rng = date_range('1/1/2000', '6/30/2000')
n = len(rng)
with catch_warnings(record=True):
panel = Panel(np.random.randn(3, n, 5),
items=['one', 'two', 'three'],
major_axis=rng,
minor_axis=['a', 'b', 'c', 'd', 'e'])
result = panel.resample('M', axis=1).apply(lambda x: x.mean(1))
expected = panel.resample('M', axis=1).mean()
tm.assert_panel_equal(result, expected)
panel = panel.swapaxes(1, 2)
result = panel.resample('M', axis=2).apply(lambda x: x.mean(2))
expected = panel.resample('M', axis=2).mean()
tm.assert_panel_equal(result, expected)
def test_resample_panel_numpy(self):
rng = date_range("1/1/2000", "6/30/2000")
n = len(rng)
panel = Panel(
np.random.randn(3, n, 5),
items=["one", "two", "three"],
major_axis=rng,
minor_axis=["a", "b", "c", "d", "e"],
)
result = panel.resample("M", how=lambda x: x.mean(1), axis=1)
expected = panel.resample("M", how="mean", axis=1)
tm.assert_panel_equal(result, expected)
panel = panel.swapaxes(1, 2)
result = panel.resample("M", how=lambda x: x.mean(2), axis=2)
expected = panel.resample("M", how="mean", axis=2)
tm.assert_panel_equal(result, expected)
def test_resample_panel(self):
rng = date_range('1/1/2000', '6/30/2000')
n = len(rng)
panel = Panel(np.random.randn(3, n, 5),
items=['one', 'two', 'three'],
major_axis=rng,
minor_axis=['a', 'b', 'c', 'd', 'e'])
result = panel.resample('M', axis=1)
def p_apply(panel, f):
result = {}
for item in panel.items:
result[item] = f(panel[item])
return Panel(result, items=panel.items)
expected = p_apply(panel, lambda x: x.resample('M'))
tm.assert_panel_equal(result, expected)
panel2 = panel.swapaxes(1, 2)
result = panel2.resample('M', axis=2)
expected = p_apply(panel2, lambda x: x.resample('M', axis=1))
tm.assert_panel_equal(result, expected)
def test_resample_panel(self):
rng = date_range('1/1/2000', '6/30/2000')
n = len(rng)
panel = Panel(np.random.randn(3, n, 5),
items=['one', 'two', 'three'],
major_axis=rng,
minor_axis=['a', 'b', 'c', 'd', 'e'])
result = panel.resample('M', axis=1)
def p_apply(panel, f):
result = {}
for item in panel.items:
result[item] = f(panel[item])
return Panel(result, items=panel.items)
expected = p_apply(panel, lambda x: x.resample('M'))
tm.assert_panel_equal(result, expected)
panel2 = panel.swapaxes(1, 2)
result = panel2.resample('M', axis=2)
expected = p_apply(panel2, lambda x: x.resample('M', axis=1))
tm.assert_panel_equal(result, expected)
def response_as_panel(self, swap=False):
panel = Panel(self.response)
if swap:
panel = panel.swapaxes('items', 'minor')
return panel
def response_as_panel(self, swap=False):
panel = Panel(self.response)
if swap:
panel = panel.swapaxes('items', 'minor')
return panel
dict(
(stk, web.get_data_yahoo(
stk,"1/1/2011", "6/1/2014")
)for stk in ["AAPL","GOOG","MSFT","DELL"])
)
# pdata.to_frame().tail() # [2490 rows x 6 columns]
pdata
# indexes = date, cols = company ticker names
'''
<class 'pandas.core.panel.Panel'>
Dimensions: 4 (items) x 877 (major_axis) x 6 (minor_axis)
Items axis: AAPL to MSFT
Major_axis axis: 2011-01-03 00:00:00 to 2014-05-30 00:00:00
Minor_axis axis: Open to Adj Close
'''
pdata=pdata.swapaxes("items","minor")
pdata["Adj Close"].tail()
'''
AAPL DELL GOOG MSFT
Date
2014-05-23 86.58 NaN 552.70 39.34
2014-05-27 88.20 NaN 565.95 39.41
2014-05-28 87.97 NaN 561.68 39.23
2014-05-29 89.58 NaN 560.08 39.56
2014-05-30 89.24 NaN 559.89 40.15
'''
pdata.ix[:,"2013-02-15",:]
# select all data at specific date or
# range of dates
'''
Open High Low Close Volume Adj Close
def response_as_panel(self, swap=False):
panel = Panel(self.response)
if swap:
panel = panel.swapaxes("items", "minor")
return panel
def __init__(self, x, var_name='x', convert_dummies=True, drop_first=True):
self._var_name = var_name
self._convert_dummies = convert_dummies
self._drop_first = drop_first
if isinstance(x, PanelData):
x = x.dataframe
self._original = x
if isinstance(x, DataArray):
if x.ndim not in (2, 3):
raise ValueError('Only 2-d or 3-d DataArrays are supported')
x = x.to_pandas()
if isinstance(x, Series) and isinstance(x.index, pd.MultiIndex):
x = DataFrame(x)
elif isinstance(x, Series):
raise ValueError(
'Series can only be used with a 2-level MultiIndex')
if isinstance(x, (Panel, DataFrame)):
if isinstance(x, DataFrame):
if isinstance(x.index, pd.MultiIndex):
if len(x.index.levels) != 2:
raise ValueError('DataFrame input must have a '
'MultiIndex with 2 levels')
self._frame = x.copy()
else:
self._frame = DataFrame(
{var_name: x.T.stack(dropna=False)})
else:
self._frame = x.swapaxes(1,
2).to_frame(filter_observations=False)
elif isinstance(x, ndarray):
if not 2 <= x.ndim <= 3:
raise ValueError('2 or 3-d array required for numpy input')
if x.ndim == 2:
x = x[None, :, :]
k, t, n = x.shape
variables = [var_name] if k == 1 else [
var_name + '.{0}'.format(i) for i in range(k)
]
entities = ['entity.{0}'.format(i) for i in range(n)]
time = list(range(t))
x = x.astype(np.float64)
panel = Panel(x,
items=variables,
major_axis=time,
minor_axis=entities)
self._frame = panel.swapaxes(1,
2).to_frame(filter_observations=False)
else:
raise TypeError('Only ndarrays, DataFrames, Panels or DataArrays '
'supported.')
if convert_dummies:
self._frame = expand_categoricals(self._frame, drop_first)
self._frame = self._frame.astype(np.float64)
time_index = Series(self._frame.index.levels[1])
if not (is_numeric_dtype(time_index.dtype)
or is_datetime64_any_dtype(time_index.dtype)):
raise ValueError('The index on the time dimension must be either '
'numeric or date-like')
self._k, self._t, self._n = self.panel.shape
self._frame.index.levels[0].name = 'entity'
self._frame.index.levels[1].name = 'time'
# -*- coding: utf-8 -*-
import numpy as np
import pandas as pd
import pandas_datareader.data as web
from pandas import Series, DataFrame, Index, Panel
pdata = Panel(
dict((stk, web.get_data_yahoo(stk, '1/1/2016', '1/15/2016'))
for stk in ['AAPL', 'GOOG', 'BIDU', 'MSFT']))
print(pdata)
pdata = pdata.swapaxes('items', 'minor')
print(pdata)
print()
print("## access order: Item -> Major -> Minor:")
print(pdata['Adj Close'])
print(pdata[:, '1/5/2016', :]) # items as columns
print(pdata['Adj Close', '1/6/2016', :])
print()
print("## conversion between Panel and DataFrame:")
print("""### items as columns;
major, and minor as hierarchical index:""")
stacked1 = pdata.ix[:, '1/7/2016':, :].to_frame()
print("stacked1 ==>")
print(stacked1)
print()
stacked2 = pdata.ix[:, '1/7/2016':, 0:1].to_frame()
#stacked2 = pdata.ix[:, '1/7/2016':, 0].to_frame() # Error, not interval
# -*- coding: utf-8 -*-
import numpy as np
import pandas as pd
import pandas.io.data as web
from pandas import Series, DataFrame, Index, Panel
pdata = Panel(dict((stk, web.get_data_yahoo(stk, '1/1/2016', '1/15/2016')) for stk in ['AAPL', 'GOOG', 'BIDU', 'MSFT']))
print pdata
pdata = pdata.swapaxes('items', 'minor')
print pdata
print
print "访问顺序：# Item -> Major -> Minor"
print pdata['Adj Close']
print pdata[:, '1/5/2016', :]
print pdata['Adj Close', '1/6/2016', :]
print
print 'Panel与DataFrame相互转换'
stacked = pdata.ix[:, '1/7/2016':, :].to_frame()
print stacked
print stacked.to_panel()
