def test_setitem(self):
# not sure what else to do here
series = self.frame['A'][::2]
self.frame['col5'] = series
self.assert_('col5' in self.frame)
common.assert_dict_equal(series,
self.frame['col5'],
compare_keys=False)
series = self.frame['A']
self.frame['col6'] = series
common.assert_dict_equal(series,
self.frame['col6'],
compare_keys=False)
self.assertRaises(Exception, self.frame.__setitem__,
randn(len(self.frame) + 1))
# set ndarray
arr = randn(len(self.frame))
self.frame['col9'] = arr
self.assert_((self.frame['col9'] == arr).all())
# set value, do out of order for DataMatrix
self.frame['col7'] = 5
assert ((self.frame['col7'] == 5).all())
self.frame['col8'] = 'foo'
assert ((self.frame['col8'] == 'foo').all())
smaller = self.frame[:2]
smaller['col10'] = ['1', '2']
self.assertEqual(smaller['col10'].dtype, np.object_)
self.assert_((smaller['col10'] == ['1', '2']).all())
def test_setitem(self):
# not sure what else to do here
series = self.frame['A'][::2]
self.frame['col5'] = series
self.assert_('col5' in self.frame)
common.assert_dict_equal(series, self.frame['col5'],
compare_keys=False)
series = self.frame['A']
self.frame['col6'] = series
common.assert_dict_equal(series, self.frame['col6'],
compare_keys=False)
self.assertRaises(Exception, self.frame.__setitem__,
randn(len(self.frame) + 1))
# set ndarray
arr = randn(len(self.frame))
self.frame['col9'] = arr
self.assert_((self.frame['col9'] == arr).all())
# set value, do out of order for DataMatrix
self.frame['col7'] = 5
assert((self.frame['col7'] == 5).all())
self.frame['col8'] = 'foo'
assert((self.frame['col8'] == 'foo').all())
smaller = self.frame[:2]
smaller['col10'] = ['1', '2']
self.assertEqual(smaller['col10'].dtype, np.object_)
self.assert_((smaller['col10'] == ['1', '2']).all())
def test_repr(self):
str(self.ts)
str(self.series)
str(self.series.astype(int))
str(self.objSeries)
str(Series(tm.randn(1000), index=np.arange(1000)))
str(Series(tm.randn(1000), index=np.arange(1000, 0, step=-1)))
# empty
str(self.empty)
# with NaNs
self.series[5:7] = np.NaN
str(self.series)
# with Nones
ots = self.ts.astype('O')
ots[::2] = None
repr(ots)
# various names
for name in [
'', 1, 1.2, 'foo',
u('\u03B1\u03B2\u03B3'),
'loooooooooooooooooooooooooooooooooooooooooooooooooooong',
('foo', 'bar', 'baz'), (1, 2), ('foo', 1, 2.3),
(u('\u03B1'), u('\u03B2'), u('\u03B3')), (u('\u03B1'), 'bar')
]:
self.series.name = name
repr(self.series)
biggie = Series(tm.randn(1000),
index=np.arange(1000),
name=('foo', 'bar', 'baz'))
repr(biggie)
# 0 as name
ser = Series(np.random.randn(100), name=0)
rep_str = repr(ser)
assert "Name: 0" in rep_str
# tidy repr
ser = Series(np.random.randn(1001), name=0)
rep_str = repr(ser)
assert "Name: 0" in rep_str
ser = Series(["a\n\r\tb"], name="a\n\r\td", index=["a\n\r\tf"])
assert "\t" not in repr(ser)
assert "\r" not in repr(ser)
assert "a\n" not in repr(ser)
# with empty series (#4651)
s = Series([], dtype=np.int64, name='foo')
self.assertEqual(repr(s), 'Series([], Name: foo, dtype: int64)')
s = Series([], dtype=np.int64, name=None)
self.assertEqual(repr(s), 'Series([], dtype: int64)')
def test_consolidate_ordering_issues(self):
self.mgr.set('f', randn(N))
self.mgr.set('d', randn(N))
self.mgr.set('b', randn(N))
self.mgr.set('g', randn(N))
cons = self.mgr.consolidate()
self.assertEquals(cons.nblocks, 1)
self.assert_(cons.blocks[0].items.equals(cons.items))
def test_consolidate_ordering_issues(self):
self.mgr.set('f', randn(N))
self.mgr.set('d', randn(N))
self.mgr.set('b', randn(N))
self.mgr.set('g', randn(N))
cons = self.mgr.consolidate()
self.assertEquals(cons.nblocks, 1)
self.assert_(cons.blocks[0].items.equals(cons.items))
def test_consolidate_ordering_issues(self):
self.mgr.set("f", randn(N))
self.mgr.set("d", randn(N))
self.mgr.set("b", randn(N))
self.mgr.set("g", randn(N))
self.mgr.set("h", randn(N))
cons = self.mgr.consolidate()
self.assertEqual(cons.nblocks, 1)
assert_almost_equal(cons.blocks[0].mgr_locs, np.arange(len(cons.items)))
def test_repr(self):
str(self.ts)
str(self.series)
str(self.series.astype(int))
str(self.objSeries)
str(Series(tm.randn(1000), index=np.arange(1000)))
str(Series(tm.randn(1000), index=np.arange(1000, 0, step=-1)))
# empty
str(self.empty)
# with NaNs
self.series[5:7] = np.NaN
str(self.series)
# with Nones
ots = self.ts.astype('O')
ots[::2] = None
repr(ots)
# various names
for name in ['', 1, 1.2, 'foo', u('\u03B1\u03B2\u03B3'),
'loooooooooooooooooooooooooooooooooooooooooooooooooooong',
('foo', 'bar', 'baz'), (1, 2), ('foo', 1, 2.3),
(u('\u03B1'), u('\u03B2'), u('\u03B3')),
(u('\u03B1'), 'bar')]:
self.series.name = name
repr(self.series)
biggie = Series(tm.randn(1000), index=np.arange(1000),
name=('foo', 'bar', 'baz'))
repr(biggie)
# 0 as name
ser = Series(np.random.randn(100), name=0)
rep_str = repr(ser)
assert "Name: 0" in rep_str
# tidy repr
ser = Series(np.random.randn(1001), name=0)
rep_str = repr(ser)
assert "Name: 0" in rep_str
ser = Series(["a\n\r\tb"], name="a\n\r\td", index=["a\n\r\tf"])
assert "\t" not in repr(ser)
assert "\r" not in repr(ser)
assert "a\n" not in repr(ser)
# with empty series (#4651)
s = Series([], dtype=np.int64, name='foo')
assert repr(s) == 'Series([], Name: foo, dtype: int64)'
s = Series([], dtype=np.int64, name=None)
assert repr(s) == 'Series([], dtype: int64)'
def test_consolidate_ordering_issues(self):
self.mgr.set('f', randn(N))
self.mgr.set('d', randn(N))
self.mgr.set('b', randn(N))
self.mgr.set('g', randn(N))
self.mgr.set('h', randn(N))
cons = self.mgr.consolidate()
self.assertEqual(cons.nblocks, 1)
assert_almost_equal(cons.blocks[0].mgr_locs,
np.arange(len(cons.items)))
def test_consolidate_ordering_issues(self):
self.mgr.set('f', randn(N))
self.mgr.set('d', randn(N))
self.mgr.set('b', randn(N))
self.mgr.set('g', randn(N))
self.mgr.set('h', randn(N))
cons = self.mgr.consolidate()
self.assertEquals(cons.nblocks, 1)
assert_almost_equal(cons.blocks[0].mgr_locs,
np.arange(len(cons.items)))
def test_merge(self):
avals = randn(2, 10)
bvals = randn(2, 10)
ref_cols = Index(['e', 'a', 'b', 'd', 'f'])
ablock = make_block(avals, ref_cols.get_indexer(['e', 'b']))
bblock = make_block(bvals, ref_cols.get_indexer(['a', 'd']))
merged = ablock.merge(bblock)
assert_almost_equal(merged.mgr_locs, [0, 1, 2, 3])
assert_almost_equal(merged.values[[0, 2]], avals)
assert_almost_equal(merged.values[[1, 3]], bvals)
def test_merge(self):
avals = randn(2, 10)
bvals = randn(2, 10)
ref_cols = Index(['e', 'a', 'b', 'd', 'f'])
ablock = make_block(avals, ref_cols.get_indexer(['e', 'b']))
bblock = make_block(bvals, ref_cols.get_indexer(['a', 'd']))
merged = ablock.merge(bblock)
assert_almost_equal(merged.mgr_locs, [0, 1, 2, 3])
assert_almost_equal(merged.values[[0, 2]], avals)
assert_almost_equal(merged.values[[1, 3]], bvals)
def test_merge(self):
avals = randn(2, 10)
bvals = randn(2, 10)
ref_cols = Index(["e", "a", "b", "d", "f"])
ablock = make_block(avals, ref_cols.get_indexer(["e", "b"]))
bblock = make_block(bvals, ref_cols.get_indexer(["a", "d"]))
merged = ablock.merge(bblock)
assert_almost_equal(merged.mgr_locs, [0, 1, 2, 3])
assert_almost_equal(merged.values[[0, 2]], avals)
assert_almost_equal(merged.values[[1, 3]], bvals)
def test_merge(self):
avals = randn(2, 10)
bvals = randn(2, 10)
ref_cols = Index(['e', 'a', 'b', 'd', 'f'])
ablock = make_block(avals, ref_cols.get_indexer(['e', 'b']))
bblock = make_block(bvals, ref_cols.get_indexer(['a', 'd']))
merged = ablock.merge(bblock)
tm.assert_numpy_array_equal(merged.mgr_locs.as_array,
np.array([0, 1, 2, 3], dtype=np.int64))
tm.assert_numpy_array_equal(merged.values[[0, 2]], np.array(avals))
tm.assert_numpy_array_equal(merged.values[[1, 3]], np.array(bvals))
def test_merge(self):
avals = randn(2, 10)
bvals = randn(2, 10)
ref_cols = Index(['e', 'a', 'b', 'd', 'f'])
ablock = make_block(avals, ref_cols.get_indexer(['e', 'b']))
bblock = make_block(bvals, ref_cols.get_indexer(['a', 'd']))
merged = ablock.merge(bblock)
tm.assert_numpy_array_equal(merged.mgr_locs.as_array,
np.array([0, 1, 2, 3], dtype=np.int64))
tm.assert_numpy_array_equal(merged.values[[0, 2]], np.array(avals))
tm.assert_numpy_array_equal(merged.values[[1, 3]], np.array(bvals))
def test_consolidate_ordering_issues(self):
self.mgr.set('f', randn(N))
self.mgr.set('d', randn(N))
self.mgr.set('b', randn(N))
self.mgr.set('g', randn(N))
self.mgr.set('h', randn(N))
# we have datetime/tz blocks in self.mgr
cons = self.mgr.consolidate()
self.assertEqual(cons.nblocks, 4)
cons = self.mgr.consolidate().get_numeric_data()
self.assertEqual(cons.nblocks, 1)
assert_almost_equal(cons.blocks[0].mgr_locs,
np.arange(len(cons.items)))
def test_consolidate_ordering_issues(self):
self.mgr.set('f', randn(N))
self.mgr.set('d', randn(N))
self.mgr.set('b', randn(N))
self.mgr.set('g', randn(N))
self.mgr.set('h', randn(N))
# we have datetime/tz blocks in self.mgr
cons = self.mgr.consolidate()
self.assertEqual(cons.nblocks, 4)
cons = self.mgr.consolidate().get_numeric_data()
self.assertEqual(cons.nblocks, 1)
assert_almost_equal(cons.blocks[0].mgr_locs,
np.arange(len(cons.items)))
def test_merge(self):
avals = randn(2, 10)
bvals = randn(2, 10)
ref_cols = ['e', 'a', 'b', 'd', 'f']
ablock = make_block(avals, ['e', 'b'], ref_cols)
bblock = make_block(bvals, ['a', 'd'], ref_cols)
merged = ablock.merge(bblock)
exvals = np.vstack((avals, bvals))
excols = ['e', 'b', 'a', 'd']
eblock = make_block(exvals, excols, ref_cols)
eblock = eblock.reindex_items_from(ref_cols)
assert_block_equal(merged, eblock)
def test_merge(self):
avals = randn(2, 10)
bvals = randn(2, 10)
ref_cols = ['e', 'a', 'b', 'd', 'f']
ablock = make_block(avals, ['e', 'b'], ref_cols)
bblock = make_block(bvals, ['a', 'd'], ref_cols)
merged = ablock.merge(bblock)
exvals = np.vstack((avals, bvals))
excols = ['e', 'b', 'a', 'd']
eblock = make_block(exvals, excols, ref_cols)
eblock = eblock.reindex_items_from(ref_cols)
assert_block_equal(merged, eblock)
def test_set_change_dtype(self):
self.mgr.set("baz", np.zeros(N, dtype=bool))
self.mgr.set("baz", np.repeat("foo", N))
self.assertEqual(self.mgr.get("baz").dtype, np.object_)
mgr2 = self.mgr.consolidate()
mgr2.set("baz", np.repeat("foo", N))
self.assertEqual(mgr2.get("baz").dtype, np.object_)
mgr2.set("quux", randn(N).astype(int))
self.assertEqual(mgr2.get("quux").dtype, np.int_)
mgr2.set("quux", randn(N))
self.assertEqual(mgr2.get("quux").dtype, np.float_)
def test_consolidate_ordering_issues(self):
self.mgr.set('f', randn(N))
self.mgr.set('d', randn(N))
self.mgr.set('b', randn(N))
self.mgr.set('g', randn(N))
self.mgr.set('h', randn(N))
# we have datetime/tz blocks in self.mgr
cons = self.mgr.consolidate()
self.assertEqual(cons.nblocks, 4)
cons = self.mgr.consolidate().get_numeric_data()
self.assertEqual(cons.nblocks, 1)
tm.assertIsInstance(cons.blocks[0].mgr_locs, lib.BlockPlacement)
tm.assert_numpy_array_equal(cons.blocks[0].mgr_locs.as_array,
np.arange(len(cons.items), dtype=np.int64))
def test_set_change_dtype(self, mgr):
mgr.set('baz', np.zeros(N, dtype=bool))
mgr.set('baz', np.repeat('foo', N))
assert mgr.get('baz').dtype == np.object_
mgr2 = mgr.consolidate()
mgr2.set('baz', np.repeat('foo', N))
assert mgr2.get('baz').dtype == np.object_
mgr2.set('quux', randn(N).astype(int))
assert mgr2.get('quux').dtype == np.int_
mgr2.set('quux', randn(N))
assert mgr2.get('quux').dtype == np.float_
def test_set_change_dtype(self, mgr):
mgr.set("baz", np.zeros(N, dtype=bool))
mgr.set("baz", np.repeat("foo", N))
assert mgr.get("baz").dtype == np.object_
mgr2 = mgr.consolidate()
mgr2.set("baz", np.repeat("foo", N))
assert mgr2.get("baz").dtype == np.object_
mgr2.set("quux", tm.randn(N).astype(int))
assert mgr2.get("quux").dtype == np.int_
mgr2.set("quux", tm.randn(N))
assert mgr2.get("quux").dtype == np.float_
def test_consolidate_ordering_issues(self, mgr):
mgr.set('f', randn(N))
mgr.set('d', randn(N))
mgr.set('b', randn(N))
mgr.set('g', randn(N))
mgr.set('h', randn(N))
# we have datetime/tz blocks in mgr
cons = mgr.consolidate()
assert cons.nblocks == 4
cons = mgr.consolidate().get_numeric_data()
assert cons.nblocks == 1
assert isinstance(cons.blocks[0].mgr_locs, BlockPlacement)
tm.assert_numpy_array_equal(cons.blocks[0].mgr_locs.as_array,
np.arange(len(cons.items), dtype=np.int64))
def test_set_change_dtype(self):
self.mgr.set('baz', np.zeros(N, dtype=bool))
self.mgr.set('baz', np.repeat('foo', N))
self.assert_(self.mgr.get('baz').dtype == np.object_)
mgr2 = self.mgr.consolidate()
mgr2.set('baz', np.repeat('foo', N))
self.assert_(mgr2.get('baz').dtype == np.object_)
mgr2.set('quux', randn(N).astype(int))
self.assert_(mgr2.get('quux').dtype == np.int64)
mgr2.set('quux', randn(N))
self.assert_(mgr2.get('quux').dtype == np.float_)
def test_consolidate_ordering_issues(self):
self.mgr.set('f', randn(N))
self.mgr.set('d', randn(N))
self.mgr.set('b', randn(N))
self.mgr.set('g', randn(N))
self.mgr.set('h', randn(N))
# we have datetime/tz blocks in self.mgr
cons = self.mgr.consolidate()
self.assertEqual(cons.nblocks, 4)
cons = self.mgr.consolidate().get_numeric_data()
self.assertEqual(cons.nblocks, 1)
tm.assertIsInstance(cons.blocks[0].mgr_locs, lib.BlockPlacement)
tm.assert_numpy_array_equal(cons.blocks[0].mgr_locs.as_array,
np.arange(len(cons.items), dtype=np.int64))
def test_consolidate_ordering_issues(self, mgr):
mgr.set('f', randn(N))
mgr.set('d', randn(N))
mgr.set('b', randn(N))
mgr.set('g', randn(N))
mgr.set('h', randn(N))
# we have datetime/tz blocks in mgr
cons = mgr.consolidate()
assert cons.nblocks == 4
cons = mgr.consolidate().get_numeric_data()
assert cons.nblocks == 1
assert isinstance(cons.blocks[0].mgr_locs, BlockPlacement)
tm.assert_numpy_array_equal(cons.blocks[0].mgr_locs.as_array,
np.arange(len(cons.items), dtype=np.int64))
def test_set_change_dtype(self):
self.mgr.set('baz', np.zeros(N, dtype=bool))
self.mgr.set('baz', np.repeat('foo', N))
self.assert_(self.mgr.get('baz').dtype == np.object_)
mgr2 = self.mgr.consolidate()
mgr2.set('baz', np.repeat('foo', N))
self.assert_(mgr2.get('baz').dtype == np.object_)
mgr2.set('quux', randn(N).astype(int))
self.assert_(mgr2.get('quux').dtype == np.int_)
mgr2.set('quux', randn(N))
self.assert_(mgr2.get('quux').dtype == np.float_)
def test_combine_first(self):
series = Series(common.makeIntIndex(20).astype(float),
index=common.makeIntIndex(20))
series_copy = series * 2
series_copy[::2] = np.NaN
# nothing used from the input
combined = series.combine_first(series_copy)
self.assert_(np.array_equal(combined, series))
# Holes filled from input
combined = series_copy.combine_first(series)
self.assert_(np.isfinite(combined).all())
self.assert_(np.array_equal(combined[::2], series[::2]))
self.assert_(np.array_equal(combined[1::2], series_copy[1::2]))
# mixed types
index = common.makeStringIndex(20)
floats = Series(common.randn(20), index=index)
strings = Series(common.makeStringIndex(10), index=index[::2])
combined = strings.combine_first(floats)
common.assert_dict_equal(strings, combined, compare_keys=False)
common.assert_dict_equal(floats[1::2], combined, compare_keys=False)
# corner case
s = Series([1., 2, 3], index=[0, 1, 2])
result = s.combine_first(Series([], index=[]))
assert_series_equal(s, result)
def test_constructor_dict_cast(self):
# cast float tests
test_data = {
'A': {
'1': 1,
'2': 2
},
'B': {
'1': '1',
'2': '2',
'3': '3'
},
}
frame = self.klass(test_data, dtype=float)
self.assertEqual(len(frame), 3)
self.assert_(frame['B'].dtype == np.float_)
self.assert_(frame['A'].dtype == np.float_)
frame = self.klass(test_data)
self.assertEqual(len(frame), 3)
self.assert_(frame['B'].dtype == np.object_)
self.assert_(frame['A'].dtype == np.float_)
# can't cast to float
test_data = {
'A': dict(zip(range(20), common.makeDateIndex(20))),
'B': dict(zip(range(15), randn(15)))
}
frame = self.klass(test_data, dtype=float)
self.assertEqual(len(frame), 20)
self.assert_(frame['A'].dtype == np.object_)
self.assert_(frame['B'].dtype == np.float_)
def test_combineFirst(self):
series = Series(common.makeIntIndex(20).astype(float),
index=common.makeIntIndex(20))
series_copy = series * 2
series_copy[::2] = np.NaN
# nothing used from the input
combined = series.combineFirst(series_copy)
self.assert_(np.array_equal(combined, series))
# Holes filled from input
combined = series_copy.combineFirst(series)
self.assert_(np.isfinite(combined).all())
self.assert_(np.array_equal(combined[::2], series[::2]))
self.assert_(np.array_equal(combined[1::2], series_copy[1::2]))
# mixed types
index = common.makeStringIndex(20)
floats = Series(common.randn(20), index=index)
strings = Series(common.makeStringIndex(10), index=index[::2])
combined = strings.combineFirst(floats)
common.assert_dict_equal(strings, combined, compare_keys=False)
common.assert_dict_equal(floats[1::2], combined, compare_keys=False)
# corner case
s = Series([1., 2, 3], index=[0, 1, 2])
result = s.combineFirst(Series([], index=[]))
assert_series_equal(s, result)
def test_combine_first(self):
values = tm.makeIntIndex(20).values.astype(float)
series = Series(values, index=tm.makeIntIndex(20))
series_copy = series * 2
series_copy[::2] = np.NaN
# nothing used from the input
combined = series.combine_first(series_copy)
tm.assert_series_equal(combined, series)
# Holes filled from input
combined = series_copy.combine_first(series)
assert np.isfinite(combined).all()
tm.assert_series_equal(combined[::2], series[::2])
tm.assert_series_equal(combined[1::2], series_copy[1::2])
# mixed types
index = tm.makeStringIndex(20)
floats = Series(tm.randn(20), index=index)
strings = Series(tm.makeStringIndex(10), index=index[::2])
combined = strings.combine_first(floats)
tm.assert_series_equal(strings, combined.loc[index[::2]])
tm.assert_series_equal(floats[1::2].astype(object),
combined.loc[index[1::2]])
# corner case
s = Series([1., 2, 3], index=[0, 1, 2])
result = s.combine_first(Series([], index=[]))
assert_series_equal(s, result)
def test_combine_first(self):
values = tm.makeIntIndex(20).values.astype(float)
series = Series(values, index=tm.makeIntIndex(20))
series_copy = series * 2
series_copy[::2] = np.NaN
# nothing used from the input
combined = series.combine_first(series_copy)
tm.assert_series_equal(combined, series)
# Holes filled from input
combined = series_copy.combine_first(series)
assert np.isfinite(combined).all()
tm.assert_series_equal(combined[::2], series[::2])
tm.assert_series_equal(combined[1::2], series_copy[1::2])
# mixed types
index = tm.makeStringIndex(20)
floats = Series(tm.randn(20), index=index)
strings = Series(tm.makeStringIndex(10), index=index[::2])
combined = strings.combine_first(floats)
tm.assert_series_equal(strings, combined.loc[index[::2]])
tm.assert_series_equal(floats[1::2].astype(object),
combined.loc[index[1::2]])
# corner case
s = Series([1., 2, 3], index=[0, 1, 2])
result = s.combine_first(Series([], index=[]))
assert_series_equal(s, result)
def test_constructor_dict_cast(self):
# cast float tests
test_data = {
'A' : {'1' : 1, '2' : 2},
'B' : {'1' : '1', '2' : '2', '3' : '3'},
}
frame = self.klass(test_data, dtype=float)
self.assertEqual(len(frame), 3)
self.assert_(frame['B'].dtype == np.float_)
self.assert_(frame['A'].dtype == np.float_)
frame = self.klass(test_data)
self.assertEqual(len(frame), 3)
self.assert_(frame['B'].dtype == np.object_)
self.assert_(frame['A'].dtype == np.float_)
# can't cast to float
test_data = {
'A' : dict(zip(range(20), common.makeDateIndex(20))),
'B' : dict(zip(range(15), randn(15)))
}
frame = self.klass(test_data, dtype=float)
self.assertEqual(len(frame), 20)
self.assert_(frame['A'].dtype == np.object_)
self.assert_(frame['B'].dtype == np.float_)
def test_repr(self):
# empty
foo = repr(self.empty)
# empty with index
frame = self.klass(index=np.arange(1000))
foo = repr(frame)
# small one
foo = repr(self.frame)
# big one
biggie = self.klass(np.zeros((1000, 4)),
columns=range(4),
index=range(1000))
foo = repr(biggie)
# mixed
foo = repr(self.mixed_frame)
# big mixed
biggie = self.klass(
{
'A': randn(1000),
'B': common.makeStringIndex(1000)
},
index=range(1000))
biggie['A'][:20] = np.NaN
biggie['B'][:20] = np.NaN
foo = repr(biggie)
# exhausting cases in DataMatrix.info
# columns but no index
no_index = self.klass(columns=[0, 1, 3])
foo = repr(no_index)
# no columns or index
buf = StringIO()
self.empty.info(buffer=buf)
# columns are not sortable
foo = repr(self.unsortable)
# do not fail!
self.frame.head(buffer=buf)
self.frame.tail(buffer=buf)
for i in range(5):
self.frame['foo%d' % i] = 1
self.frame.head(buffer=buf)
self.frame.tail(buffer=buf)
def test_dropEmptyRows(self):
N = len(self.frame.index)
mat = randn(N)
mat[:5] = np.NaN
frame = self.klass({'foo': mat}, index=self.frame.index)
smaller_frame = frame.dropEmptyRows()
self.assert_(np.array_equal(smaller_frame['foo'], mat[5:]))
smaller_frame = frame.dropEmptyRows(['foo'])
self.assert_(np.array_equal(smaller_frame['foo'], mat[5:]))
def test_dropEmptyRows(self):
N = len(self.frame.index)
mat = randn(N)
mat[:5] = np.NaN
frame = self.klass({'foo' : mat}, index=self.frame.index)
smaller_frame = frame.dropEmptyRows()
self.assert_(np.array_equal(smaller_frame['foo'], mat[5:]))
smaller_frame = frame.dropEmptyRows(['foo'])
self.assert_(np.array_equal(smaller_frame['foo'], mat[5:]))
def test_reindex_items(self):
def _check_cols(before, after, cols):
for col in cols:
assert_almost_equal(after.get(col), before.get(col))
# not consolidated
vals = randn(N)
self.mgr.set('g', vals)
reindexed = self.mgr.reindex_items(['g', 'c', 'a', 'd'])
self.assertEquals(reindexed.nblocks, 2)
assert_almost_equal(reindexed.get('g'), vals.squeeze())
_check_cols(self.mgr, reindexed, ['c', 'a', 'd'])
def test_reindex_items(self):
def _check_cols(before, after, cols):
for col in cols:
assert_almost_equal(after.get(col), before.get(col))
# not consolidated
vals = randn(N)
self.mgr.set('g', vals)
reindexed = self.mgr.reindex_items(['g', 'c', 'a', 'd'])
self.assertEquals(reindexed.nblocks, 2)
assert_almost_equal(reindexed.get('g'), vals.squeeze())
_check_cols(self.mgr, reindexed, ['c', 'a', 'd'])
def test_repr(self):
str(self.ts)
str(self.series)
str(self.series.astype(int))
str(self.objSeries)
str(Series(tm.randn(1000), index=np.arange(1000)))
# empty
str(self.empty)
# with NaNs
self.series[5:7] = np.NaN
str(self.series)
# tuple name, e.g. from hierarchical index
self.series.name = ('foo', 'bar', 'baz')
repr(self.series)
biggie = Series(tm.randn(1000), index=np.arange(1000),
name=('foo', 'bar', 'baz'))
repr(biggie)
def test_firstLastValid(self):
N = len(self.frame.index)
mat = randn(N)
mat[:5] = np.NaN
mat[-5:] = np.NaN
frame = self.klass({'foo' : mat}, index=self.frame.index)
index = frame._firstTimeWithValue()
self.assert_(index == frame.index[5])
index = frame._lastTimeWithValue()
self.assert_(index == frame.index[-6])
def test_dropIncompleteRows(self):
N = len(self.frame.index)
mat = randn(N)
mat[:5] = np.NaN
frame = self.klass({'foo' : mat}, index=self.frame.index)
frame['bar'] = 5
smaller_frame = frame.dropIncompleteRows()
self.assert_(np.array_equal(smaller_frame['foo'], mat[5:]))
samesize_frame = frame.dropIncompleteRows(specificColumns=['bar'])
self.assert_(samesize_frame.index.equals(self.frame.index))
def test_firstLastValid(self):
N = len(self.frame.index)
mat = randn(N)
mat[:5] = np.NaN
mat[-5:] = np.NaN
frame = self.klass({'foo': mat}, index=self.frame.index)
index = frame._firstTimeWithValue()
self.assert_(index == frame.index[5])
index = frame._lastTimeWithValue()
self.assert_(index == frame.index[-6])
def test_dropIncompleteRows(self):
N = len(self.frame.index)
mat = randn(N)
mat[:5] = np.NaN
frame = self.klass({'foo': mat}, index=self.frame.index)
frame['bar'] = 5
smaller_frame = frame.dropIncompleteRows()
self.assert_(np.array_equal(smaller_frame['foo'], mat[5:]))
samesize_frame = frame.dropIncompleteRows(specificColumns=['bar'])
self.assert_(samesize_frame.index.equals(self.frame.index))
def test_repr(self):
# empty
foo = repr(self.empty)
# empty with index
frame = self.klass(index=np.arange(1000))
foo = repr(frame)
# small one
foo = repr(self.frame)
# big one
biggie = self.klass(np.zeros((1000, 4)), columns=range(4),
index=range(1000))
foo = repr(biggie)
# mixed
foo = repr(self.mixed_frame)
# big mixed
biggie = self.klass({'A' : randn(1000),
'B' : common.makeStringIndex(1000)},
index=range(1000))
biggie['A'][:20] = np.NaN
biggie['B'][:20] = np.NaN
foo = repr(biggie)
# exhausting cases in DataMatrix.info
# columns but no index
no_index = self.klass(columns=[0, 1, 3])
foo = repr(no_index)
# no columns or index
buf = StringIO()
self.empty.info(buffer=buf)
# columns are not sortable
foo = repr(self.unsortable)
# do not fail!
self.frame.head(buffer=buf)
self.frame.tail(buffer=buf)
for i in range(5):
self.frame['foo%d' % i] = 1
self.frame.head(buffer=buf)
self.frame.tail(buffer=buf)
def test_repr(self):
str(self.ts)
str(self.series)
str(self.series.astype(int))
str(self.objSeries)
str(Series(common.randn(1000), index=np.arange(1000)))
# empty
str(self.empty)
# with NaNs
self.series[5:7] = np.NaN
str(self.series)
def test_repr(self):
str(self.ts)
str(self.series)
str(self.series.astype(int))
str(self.objSeries)
str(Series(common.randn(1000), index=np.arange(1000)))
# empty
str(self.empty)
# with NaNs
self.series[5:7] = np.NaN
str(self.series)
def test_toString(self):
# big mixed
biggie = self.klass({'A' : randn(1000),
'B' : common.makeStringIndex(1000)},
index=range(1000))
biggie['A'][:20] = np.NaN
biggie['B'][:20] = np.NaN
buf = StringIO()
biggie.toString(buffer=buf)
biggie.toString(buffer=buf, columns=['B', 'A'], colSpace=17)
biggie.toString(buffer=buf, columns=['B', 'A'],
formatters={'A' : lambda x: '%.1f' % x})
biggie.toString(buffer=buf, columns=['B', 'A'],
float_format=str)
frame = self.klass(index=np.arange(1000))
frame.toString(buffer=buf)
def test_toString(self):
# big mixed
biggie = self.klass(
{
'A': randn(1000),
'B': common.makeStringIndex(1000)
},
index=range(1000))
biggie['A'][:20] = np.NaN
biggie['B'][:20] = np.NaN
buf = StringIO()
biggie.toString(buffer=buf)
biggie.toString(buffer=buf, columns=['B', 'A'], colSpace=17)
biggie.toString(buffer=buf,
columns=['B', 'A'],
formatters={'A': lambda x: '%.1f' % x})
biggie.toString(buffer=buf, columns=['B', 'A'], float_format=str)
frame = self.klass(index=np.arange(1000))
frame.toString(buffer=buf)
def get_int32_ex(cols):
mat = randn(N, 1).astype(np.int32)
return make_block(mat.T, cols, TEST_COLS)
def get_int_ex(cols=['g'], dtype = np.int_):
mat = randn(N, 1).astype(dtype)
return make_block(mat.T, cols, TEST_COLS)
def get_dt_ex(cols=['h']):
mat = randn(N, 1).astype(int).astype('M8[ns]')
return make_block(mat.T, cols, TEST_COLS)
def get_int32_ex(cols):
mat = randn(N, 1).astype(np.int32)
return make_block(mat.T, cols, TEST_COLS)
def get_int_ex(cols=['g']):
mat = randn(N, 1).astype(int)
return make_block(mat.T, cols, TEST_COLS)
def get_dt_ex(cols=['h']):
mat = randn(N, 1).astype(int).astype('M8[ns]')
return make_block(mat.T, cols, TEST_COLS)
def test_repr(self, datetime_series, string_series, object_series):
str(datetime_series)
str(string_series)
str(string_series.astype(int))
str(object_series)
str(Series(tm.randn(1000), index=np.arange(1000)))
str(Series(tm.randn(1000), index=np.arange(1000, 0, step=-1)))
# empty
str(Series())
# with NaNs
string_series[5:7] = np.NaN
str(string_series)
# with Nones
ots = datetime_series.astype("O")
ots[::2] = None
repr(ots)
# various names
for name in [
"",
1,
1.2,
"foo",
"\u03B1\u03B2\u03B3",
"loooooooooooooooooooooooooooooooooooooooooooooooooooong",
("foo", "bar", "baz"),
(1, 2),
("foo", 1, 2.3),
("\u03B1", "\u03B2", "\u03B3"),
("\u03B1", "bar"),
]:
string_series.name = name
repr(string_series)
biggie = Series(tm.randn(1000),
index=np.arange(1000),
name=("foo", "bar", "baz"))
repr(biggie)
# 0 as name
ser = Series(np.random.randn(100), name=0)
rep_str = repr(ser)
assert "Name: 0" in rep_str
# tidy repr
ser = Series(np.random.randn(1001), name=0)
rep_str = repr(ser)
assert "Name: 0" in rep_str
ser = Series(["a\n\r\tb"], name="a\n\r\td", index=["a\n\r\tf"])
assert "\t" not in repr(ser)
assert "\r" not in repr(ser)
assert "a\n" not in repr(ser)
# with empty series (#4651)
s = Series([], dtype=np.int64, name="foo")
assert repr(s) == "Series([], Name: foo, dtype: int64)"
s = Series([], dtype=np.int64, name=None)
assert repr(s) == "Series([], dtype: int64)"
def get_int_ex(cols=['g']):
mat = randn(N, 1).astype(int)
return make_block(mat.T, cols, TEST_COLS)
