def setUp(self):
self.seriesd = common.getSeriesData()
self.tsd = common.getTimeSeriesData()
self.frame = self.klass(self.seriesd)
self.intframe = self.klass(dict((k, v.astype(int))
for k, v in self.seriesd.iteritems()))
self.tsframe = self.klass(self.tsd)
self.mixed_frame = self.frame.copy()
self.mixed_frame['foo'] = 'bar'
self.ts1 = common.makeTimeSeries()
self.ts2 = common.makeTimeSeries()[5:]
self.ts3 = common.makeTimeSeries()[-5:]
self.ts4 = common.makeTimeSeries()[1:-1]
self.ts_dict = {
'col1' : self.ts1,
'col2' : self.ts2,
'col3' : self.ts3,
'col4' : self.ts4,
}
self.empty = self.klass({})
self.unsortable = self.klass(
{'foo' : [1] * 1000,
datetime.today() : [1] * 1000,
'bar' : ['bar'] * 1000,
datetime.today() + timedelta(1) : ['bar'] * 1000},
index=np.arange(1000))
def datetime_frame():
"""
Fixture for DataFrame of floats with DatetimeIndex
Columns are ['A', 'B', 'C', 'D']
A B C D
2000-01-03 -1.122153 0.468535 0.122226 1.693711
2000-01-04 0.189378 0.486100 0.007864 -1.216052
2000-01-05 0.041401 -0.835752 -0.035279 -0.414357
2000-01-06 0.430050 0.894352 0.090719 0.036939
2000-01-07 -0.620982 -0.668211 -0.706153 1.466335
2000-01-10 -0.752633 0.328434 -0.815325 0.699674
2000-01-11 -2.236969 0.615737 -0.829076 -1.196106
... ... ... ... ...
2000-02-03 1.642618 -0.579288 0.046005 1.385249
2000-02-04 -0.544873 -1.160962 -0.284071 -1.418351
2000-02-07 -2.656149 -0.601387 1.410148 0.444150
2000-02-08 -1.201881 -1.289040 0.772992 -1.445300
2000-02-09 1.377373 0.398619 1.008453 -0.928207
2000-02-10 0.473194 -0.636677 0.984058 0.511519
2000-02-11 -0.965556 0.408313 -1.312844 -0.381948
[30 rows x 4 columns]
"""
return DataFrame(tm.getTimeSeriesData())
def setUp(self):
self.ts = tm.makeTimeSeries()
self.seriesd = tm.getSeriesData()
self.tsd = tm.getTimeSeriesData()
self.frame = DataFrame(self.seriesd)
self.tsframe = DataFrame(self.tsd)
self.df = df()
self.df_mixed_floats = 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.array(
np.random.randn(8), dtype='float32')})
self.mframe = mframe()
self.three_group = DataFrame(
{'A': ['foo', 'foo', 'foo', 'foo', 'bar', 'bar', 'bar', 'bar',
'foo', 'foo', 'foo'],
'B': ['one', 'one', 'one', 'two', 'one', 'one', 'one', 'two',
'two', 'two', 'one'],
'C': ['dull', 'dull', 'shiny', 'dull', 'dull', 'shiny', 'shiny',
'dull', 'shiny', 'shiny', 'shiny'],
'D': np.random.randn(11),
'E': np.random.randn(11),
'F': np.random.randn(11)})
def datetime_frame():
"""
Fixture for DataFrame of floats with DatetimeIndex
Columns are ['A', 'B', 'C', 'D']
"""
return DataFrame(tm.getTimeSeriesData())
def setUp(self):
self.seriesd = common.getSeriesData()
self.tsd = common.getTimeSeriesData()
self.frame = self.klass(self.seriesd)
self.intframe = self.klass(
dict((k, v.astype(int)) for k, v in self.seriesd.iteritems()))
self.tsframe = self.klass(self.tsd)
self.mixed_frame = self.frame.copy()
self.mixed_frame['foo'] = 'bar'
self.ts1 = common.makeTimeSeries()
self.ts2 = common.makeTimeSeries()[5:]
self.ts3 = common.makeTimeSeries()[-5:]
self.ts4 = common.makeTimeSeries()[1:-1]
self.ts_dict = {
'col1': self.ts1,
'col2': self.ts2,
'col3': self.ts3,
'col4': self.ts4,
}
self.empty = self.klass({})
self.unsortable = self.klass(
{
'foo': [1] * 1000,
datetime.today(): [1] * 1000,
'bar': ['bar'] * 1000,
datetime.today() + timedelta(1): ['bar'] * 1000
},
index=np.arange(1000))
def datetime_frame():
"""
Fixture for DataFrame of floats with DatetimeIndex
Columns are ['A', 'B', 'C', 'D']
A B C D
2000-01-03 -1.122153 0.468535 0.122226 1.693711
2000-01-04 0.189378 0.486100 0.007864 -1.216052
2000-01-05 0.041401 -0.835752 -0.035279 -0.414357
2000-01-06 0.430050 0.894352 0.090719 0.036939
2000-01-07 -0.620982 -0.668211 -0.706153 1.466335
2000-01-10 -0.752633 0.328434 -0.815325 0.699674
2000-01-11 -2.236969 0.615737 -0.829076 -1.196106
... ... ... ... ...
2000-02-03 1.642618 -0.579288 0.046005 1.385249
2000-02-04 -0.544873 -1.160962 -0.284071 -1.418351
2000-02-07 -2.656149 -0.601387 1.410148 0.444150
2000-02-08 -1.201881 -1.289040 0.772992 -1.445300
2000-02-09 1.377373 0.398619 1.008453 -0.928207
2000-02-10 0.473194 -0.636677 0.984058 0.511519
2000-02-11 -0.965556 0.408313 -1.312844 -0.381948
[30 rows x 4 columns]
"""
return DataFrame(tm.getTimeSeriesData())
def datetime_frame():
"""
Fixture for DataFrame of floats with DatetimeIndex
Columns are ['A', 'B', 'C', 'D']
"""
return DataFrame(tm.getTimeSeriesData())
def setup_method(self, method):
self.ts = tm.makeTimeSeries()
self.seriesd = tm.getSeriesData()
self.tsd = tm.getTimeSeriesData()
self.frame = DataFrame(self.seriesd)
self.tsframe = DataFrame(self.tsd)
self.df = 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)
})
self.df_mixed_floats = 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.array(np.random.randn(8), dtype='float32')
})
index = MultiIndex(levels=[['foo', 'bar', 'baz', 'qux'],
['one', 'two', 'three']],
labels=[[0, 0, 0, 1, 1, 2, 2, 3, 3, 3],
[0, 1, 2, 0, 1, 1, 2, 0, 1, 2]],
names=['first', 'second'])
self.mframe = DataFrame(np.random.randn(10, 3),
index=index,
columns=['A', 'B', 'C'])
self.three_group = DataFrame({
'A': [
'foo', 'foo', 'foo', 'foo', 'bar', 'bar', 'bar', 'bar', 'foo',
'foo', 'foo'
],
'B': [
'one', 'one', 'one', 'two', 'one', 'one', 'one', 'two', 'two',
'two', 'one'
],
'C': [
'dull', 'dull', 'shiny', 'dull', 'dull', 'shiny', 'shiny',
'dull', 'shiny', 'shiny', 'shiny'
],
'D':
np.random.randn(11),
'E':
np.random.randn(11),
'F':
np.random.randn(11)
})
def setUp(self):
self.ts = tm.makeTimeSeries()
self.seriesd = tm.getSeriesData()
self.tsd = tm.getTimeSeriesData()
self.frame = DataFrame(self.seriesd)
self.tsframe = DataFrame(self.tsd)
self.df = 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),
}
)
self.df_mixed_floats = 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.array(np.random.randn(8), dtype="float32"),
}
)
index = MultiIndex(
levels=[["foo", "bar", "baz", "qux"], ["one", "two", "three"]],
labels=[[0, 0, 0, 1, 1, 2, 2, 3, 3, 3], [0, 1, 2, 0, 1, 1, 2, 0, 1, 2]],
names=["first", "second"],
)
self.mframe = DataFrame(np.random.randn(10, 3), index=index, columns=["A", "B", "C"])
self.three_group = DataFrame(
{
"A": ["foo", "foo", "foo", "foo", "bar", "bar", "bar", "bar", "foo", "foo", "foo"],
"B": ["one", "one", "one", "two", "one", "one", "one", "two", "two", "two", "one"],
"C": ["dull", "dull", "shiny", "dull", "dull", "shiny", "shiny", "dull", "shiny", "shiny", "shiny"],
"D": np.random.randn(11),
"E": np.random.randn(11),
"F": np.random.randn(11),
}
)
def setup_method(self, method):
self.ts = tm.makeTimeSeries()
self.seriesd = tm.getSeriesData()
self.tsd = tm.getTimeSeriesData()
self.frame = DataFrame(self.seriesd)
self.tsframe = DataFrame(self.tsd)
self.df = df()
self.df_mixed_floats = 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.array(np.random.randn(8), dtype='float32')
})
self.mframe = mframe()
self.three_group = DataFrame({
'A': [
'foo', 'foo', 'foo', 'foo', 'bar', 'bar', 'bar', 'bar', 'foo',
'foo', 'foo'
],
'B': [
'one', 'one', 'one', 'two', 'one', 'one', 'one', 'two', 'two',
'two', 'one'
],
'C': [
'dull', 'dull', 'shiny', 'dull', 'dull', 'shiny', 'shiny',
'dull', 'shiny', 'shiny', 'shiny'
],
'D':
np.random.randn(11),
'E':
np.random.randn(11),
'F':
np.random.randn(11)
})
def setUp(self):
self.ts = tm.makeTimeSeries()
self.seriesd = tm.getSeriesData()
self.tsd = tm.getTimeSeriesData()
self.frame = DataFrame(self.seriesd)
self.tsframe = DataFrame(self.tsd)
self.df = 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)})
self.df_mixed_floats = 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.array(
np.random.randn(8), dtype='float32')})
index = MultiIndex(levels=[['foo', 'bar', 'baz', 'qux'], ['one', 'two',
'three']],
labels=[[0, 0, 0, 1, 1, 2, 2, 3, 3, 3],
[0, 1, 2, 0, 1, 1, 2, 0, 1, 2]],
names=['first', 'second'])
self.mframe = DataFrame(np.random.randn(10, 3), index=index,
columns=['A', 'B', 'C'])
self.three_group = DataFrame(
{'A': ['foo', 'foo', 'foo', 'foo', 'bar', 'bar', 'bar', 'bar',
'foo', 'foo', 'foo'],
'B': ['one', 'one', 'one', 'two', 'one', 'one', 'one', 'two',
'two', 'two', 'one'],
'C': ['dull', 'dull', 'shiny', 'dull', 'dull', 'shiny', 'shiny',
'dull', 'shiny', 'shiny', 'shiny'],
'D': np.random.randn(11),
'E': np.random.randn(11),
'F': np.random.randn(11)})
def setUp(self):
"""
Setup the dataframes used for the groupby tests derived from pandas
"""
self.dateRange = bdate_range('1/1/2005', periods=250)
self.stringIndex = Index([rands(8).upper() for x in range(250)])
self.groupId = Series([x[0] for x in self.stringIndex],
index=self.stringIndex)
self.groupDict = dict(
(k, v) for k, v in compat.iteritems(self.groupId))
self.columnIndex = Index(['A', 'B', 'C', 'D', 'E'])
randMat = np.random.randn(250, 5)
self.stringMatrix = DataFrame(randMat,
columns=self.columnIndex,
index=self.stringIndex)
self.timeMatrix = DataFrame(randMat,
columns=self.columnIndex,
index=self.dateRange)
self.ts = tm.makeTimeSeries()
self.seriesd = tm.getSeriesData()
self.tsd = tm.getTimeSeriesData()
self.frame = DataFrame(self.seriesd)
self.tsframe = DataFrame(self.tsd)
self.df = 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)
})
self.df_mixed_floats = 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.array(np.random.randn(8), dtype='float32')
})
index = MultiIndex(levels=[['foo', 'bar', 'baz', 'qux'],
['one', 'two', 'three']],
labels=[[0, 0, 0, 1, 1, 2, 2, 3, 3, 3],
[0, 1, 2, 0, 1, 1, 2, 0, 1, 2]],
names=['first', 'second'])
self.mframe = DataFrame(np.random.randn(10, 3),
index=index,
columns=['A', 'B', 'C'])
self.three_group = DataFrame({
'A': [
'foo', 'foo', 'foo', 'foo', 'bar', 'bar', 'bar', 'bar', 'foo',
'foo', 'foo'
],
'B': [
'one', 'one', 'one', 'two', 'one', 'one', 'one', 'two', 'two',
'two', 'one'
],
'C': [
'dull', 'dull', 'shiny', 'dull', 'dull', 'shiny', 'shiny',
'dull', 'shiny', 'shiny', 'shiny'
],
'D':
np.random.randn(11),
'E':
np.random.randn(11),
'F':
np.random.randn(11)
})
super(self.__class__, self).setUp()
def tsd():
return tm.getTimeSeriesData()
def _skip_if_no_xlsxwriter():
try:
import xlsxwriter # NOQA
except ImportError:
raise nose.SkipTest('xlsxwriter not installed, skipping')
def _skip_if_no_excelsuite():
_skip_if_no_xlrd()
_skip_if_no_xlwt()
_skip_if_no_openpyxl()
_seriesd = tm.getSeriesData()
_tsd = tm.getTimeSeriesData()
_frame = DataFrame(_seriesd)[:10]
_frame2 = DataFrame(_seriesd, columns=['D', 'C', 'B', 'A'])[:10]
_tsframe = tm.makeTimeDataFrame()[:5]
_mixed_frame = _frame.copy()
_mixed_frame['foo'] = 'bar'
class SharedItems(object):
def setUp(self):
self.dirpath = tm.get_data_path()
self.csv1 = os.path.join(self.dirpath, 'test1.csv')
self.csv2 = os.path.join(self.dirpath, 'test2.csv')
self.xls1 = os.path.join(self.dirpath, 'test.xls')
self.xlsx1 = os.path.join(self.dirpath, 'test.xlsx')
self.frame = _frame.copy()
def tsd():
return tm.getTimeSeriesData()
def tsframe():
return DataFrame(tm.getTimeSeriesData())
def setUp(self):
"""
Setup the dataframes used for the groupby tests derived from pandas
"""
self.dateRange = bdate_range('1/1/2005', periods=250)
self.stringIndex = Index([rands(8).upper() for x in range(250)])
self.groupId = Series([x[0] for x in self.stringIndex],
index=self.stringIndex)
self.groupDict = dict((k, v)
for k, v in compat.iteritems(self.groupId))
self.columnIndex = Index(['A', 'B', 'C', 'D', 'E'])
randMat = np.random.randn(250, 5)
self.stringMatrix = DataFrame(randMat, columns=self.columnIndex,
index=self.stringIndex)
self.timeMatrix = DataFrame(randMat, columns=self.columnIndex,
index=self.dateRange)
self.ts = tm.makeTimeSeries()
self.seriesd = tm.getSeriesData()
self.tsd = tm.getTimeSeriesData()
self.frame = DataFrame(self.seriesd)
self.tsframe = DataFrame(self.tsd)
self.df = 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)})
self.df_mixed_floats = 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.array(np.random.randn(8),
dtype='float32')})
index = MultiIndex(levels=[['foo', 'bar', 'baz', 'qux'],
['one', 'two', 'three']],
labels=[[0, 0, 0, 1, 1, 2, 2, 3, 3, 3],
[0, 1, 2, 0, 1, 1, 2, 0, 1, 2]],
names=['first', 'second'])
self.mframe = DataFrame(np.random.randn(10, 3), index=index,
columns=['A', 'B', 'C'])
self.three_group = DataFrame({'A': ['foo', 'foo', 'foo', 'foo',
'bar', 'bar', 'bar', 'bar',
'foo', 'foo', 'foo'],
'B': ['one', 'one', 'one', 'two',
'one', 'one', 'one', 'two',
'two', 'two', 'one'],
'C': ['dull', 'dull', 'shiny', 'dull',
'dull', 'shiny', 'shiny', 'dull',
'shiny', 'shiny', 'shiny'],
'D': np.random.randn(11),
'E': np.random.randn(11),
'F': np.random.randn(11)})
super(self.__class__, self).setUp()
def _skip_if_no_xlsxwriter():
try:
import xlsxwriter # NOQA
except ImportError:
raise nose.SkipTest('xlsxwriter not installed, skipping')
def _skip_if_no_excelsuite():
_skip_if_no_xlrd()
_skip_if_no_xlwt()
_skip_if_no_openpyxl()
_seriesd = tm.getSeriesData()
_tsd = tm.getTimeSeriesData()
_frame = DataFrame(_seriesd)[:10]
_frame2 = DataFrame(_seriesd, columns=['D', 'C', 'B', 'A'])[:10]
_tsframe = tm.makeTimeDataFrame()[:5]
_mixed_frame = _frame.copy()
_mixed_frame['foo'] = 'bar'
class SharedItems(object):
def setUp(self):
self.dirpath = tm.get_data_path()
self.csv1 = os.path.join(self.dirpath, 'test1.csv')
self.csv2 = os.path.join(self.dirpath, 'test2.csv')
self.xls1 = os.path.join(self.dirpath, 'test.xls')
self.xlsx1 = os.path.join(self.dirpath, 'test.xlsx')
self.frame = _frame.copy()
def tsframe():
return DataFrame(tm.getTimeSeriesData())
