def testit():
for f, f2 in [(self.frame, self.frame2),
(self.mixed, self.mixed2)]:
f11 = f
f12 = f + 1
f21 = f2
f22 = f2 + 1
for op, op_str in [('gt', '>'), ('lt', '<'), ('ge', '>='),
('le', '<='), ('eq', '=='), ('ne', '!=')]:
op = getattr(operator, op)
result = expr._can_use_numexpr(op, op_str, f11, f12,
'evaluate')
self.assertNotEqual(result, f11._is_mixed_type)
result = expr.evaluate(op, op_str, f11, f12,
use_numexpr=True)
expected = expr.evaluate(op, op_str, f11, f12,
use_numexpr=False)
tm.assert_numpy_array_equal(result, expected.values)
result = expr._can_use_numexpr(op, op_str, f21, f22,
'evaluate')
self.assertFalse(result)
def test_constructor(self):
# explicit construction
index = Float64Index([1, 2, 3, 4, 5])
assert isinstance(index, Float64Index)
expected = np.array([1, 2, 3, 4, 5], dtype='float64')
tm.assert_numpy_array_equal(index.values, expected)
index = Float64Index(np.array([1, 2, 3, 4, 5]))
assert isinstance(index, Float64Index)
index = Float64Index([1., 2, 3, 4, 5])
assert isinstance(index, Float64Index)
index = Float64Index(np.array([1., 2, 3, 4, 5]))
assert isinstance(index, Float64Index)
assert index.dtype == float
index = Float64Index(np.array([1., 2, 3, 4, 5]), dtype=np.float32)
assert isinstance(index, Float64Index)
assert index.dtype == np.float64
index = Float64Index(np.array([1, 2, 3, 4, 5]), dtype=np.float32)
assert isinstance(index, Float64Index)
assert index.dtype == np.float64
# nan handling
result = Float64Index([np.nan, np.nan])
assert pd.isna(result.values).all()
result = Float64Index(np.array([np.nan]))
assert pd.isna(result.values).all()
result = Index(np.array([np.nan]))
assert pd.isna(result.values).all()
def test_conversions(data_missing):
# astype to object series
df = pd.DataFrame({'A': data_missing})
result = df['A'].astype('object')
expected = pd.Series(np.array([np.nan, 1], dtype=object), name='A')
tm.assert_series_equal(result, expected)
# convert to object ndarray
# we assert that we are exactly equal
# including type conversions of scalars
result = df['A'].astype('object').values
expected = np.array([np.nan, 1], dtype=object)
tm.assert_numpy_array_equal(result, expected)
for r, e in zip(result, expected):
if pd.isnull(r):
assert pd.isnull(e)
elif is_integer(r):
# PY2 can be int or long
assert r == e
assert is_integer(e)
else:
assert r == e
assert type(r) == type(e)
def test_equals(self):
# GH 13107
for tz in [None, 'UTC', 'US/Eastern', 'Asia/Tokyo']:
idx = pd.DatetimeIndex(['2011-01-01', '2011-01-02', 'NaT'])
assert idx.equals(idx)
assert idx.equals(idx.copy())
assert idx.equals(idx.asobject)
assert idx.asobject.equals(idx)
assert idx.asobject.equals(idx.asobject)
assert not idx.equals(list(idx))
assert not idx.equals(pd.Series(idx))
idx2 = pd.DatetimeIndex(['2011-01-01', '2011-01-02', 'NaT'],
tz='US/Pacific')
assert not idx.equals(idx2)
assert not idx.equals(idx2.copy())
assert not idx.equals(idx2.asobject)
assert not idx.asobject.equals(idx2)
assert not idx.equals(list(idx2))
assert not idx.equals(pd.Series(idx2))
# same internal, different tz
idx3 = pd.DatetimeIndex._simple_new(idx.asi8, tz='US/Pacific')
tm.assert_numpy_array_equal(idx.asi8, idx3.asi8)
assert not idx.equals(idx3)
assert not idx.equals(idx3.copy())
assert not idx.equals(idx3.asobject)
assert not idx.asobject.equals(idx3)
assert not idx.equals(list(idx3))
assert not idx.equals(pd.Series(idx3))
def test_properties(self, closed):
index = self.create_index(closed=closed)
assert len(index) == 10
assert index.size == 10
assert index.shape == (10, )
tm.assert_index_equal(index.left, Index(np.arange(10)))
tm.assert_index_equal(index.right, Index(np.arange(1, 11)))
tm.assert_index_equal(index.mid, Index(np.arange(0.5, 10.5)))
assert index.closed == closed
ivs = [Interval(l, r, closed) for l, r in zip(range(10), range(1, 11))]
expected = np.array(ivs, dtype=object)
tm.assert_numpy_array_equal(np.asarray(index), expected)
# with nans
index = self.create_index_with_nan(closed=closed)
assert len(index) == 10
assert index.size == 10
assert index.shape == (10, )
expected_left = Index([0, np.nan, 2, 3, 4, 5, 6, 7, 8, 9])
expected_right = expected_left + 1
expected_mid = expected_left + 0.5
tm.assert_index_equal(index.left, expected_left)
tm.assert_index_equal(index.right, expected_right)
tm.assert_index_equal(index.mid, expected_mid)
assert index.closed == closed
ivs = [Interval(l, r, closed) if notna(l) else np.nan
for l, r in zip(expected_left, expected_right)]
expected = np.array(ivs, dtype=object)
tm.assert_numpy_array_equal(np.asarray(index), expected)
def test_constructor_with_datetimelike(self):
# 12077
# constructor wwth a datetimelike and NaT
for dtl in [date_range('1995-01-01 00:00:00', periods=5, freq='s'),
date_range('1995-01-01 00:00:00', periods=5,
freq='s', tz='US/Eastern'),
timedelta_range('1 day', periods=5, freq='s')]:
s = Series(dtl)
c = Categorical(s)
expected = type(dtl)(s)
expected.freq = None
tm.assert_index_equal(c.categories, expected)
tm.assert_numpy_array_equal(c.codes, np.arange(5, dtype='int8'))
# with NaT
s2 = s.copy()
s2.iloc[-1] = NaT
c = Categorical(s2)
expected = type(dtl)(s2.dropna())
expected.freq = None
tm.assert_index_equal(c.categories, expected)
exp = np.array([0, 1, 2, 3, -1], dtype=np.int8)
tm.assert_numpy_array_equal(c.codes, exp)
result = repr(c)
assert 'NaT' in result
def test_simple(self):
x, y = list('ABC'), [1, 22]
result1, result2 = cartesian_product([x, y])
expected1 = np.array(['A', 'A', 'B', 'B', 'C', 'C'])
expected2 = np.array([1, 22, 1, 22, 1, 22])
tm.assert_numpy_array_equal(result1, expected1)
tm.assert_numpy_array_equal(result2, expected2)
def test_value_counts_inferred(self):
klasses = [Index, Series]
for klass in klasses:
s_values = ['a', 'b', 'b', 'b', 'b', 'c', 'd', 'd', 'a', 'a']
s = klass(s_values)
expected = Series([4, 3, 2, 1], index=['b', 'a', 'd', 'c'])
tm.assert_series_equal(s.value_counts(), expected)
if isinstance(s, Index):
exp = Index(np.unique(np.array(s_values, dtype=np.object_)))
tm.assert_index_equal(s.unique(), exp)
else:
exp = np.unique(np.array(s_values, dtype=np.object_))
tm.assert_numpy_array_equal(s.unique(), exp)
assert s.nunique() == 4
# don't sort, have to sort after the fact as not sorting is
# platform-dep
hist = s.value_counts(sort=False).sort_values()
expected = Series([3, 1, 4, 2], index=list('acbd')).sort_values()
tm.assert_series_equal(hist, expected)
# sort ascending
hist = s.value_counts(ascending=True)
expected = Series([1, 2, 3, 4], index=list('cdab'))
tm.assert_series_equal(hist, expected)
# relative histogram.
hist = s.value_counts(normalize=True)
expected = Series([.4, .3, .2, .1], index=['b', 'a', 'd', 'c'])
tm.assert_series_equal(hist, expected)
def test_interleave(self):
# interleave with object
result = self.tzframe.assign(D='foo').values
expected = np.array([[Timestamp('2013-01-01 00:00:00'),
Timestamp('2013-01-02 00:00:00'),
Timestamp('2013-01-03 00:00:00')],
[Timestamp('2013-01-01 00:00:00-0500',
tz='US/Eastern'),
pd.NaT,
Timestamp('2013-01-03 00:00:00-0500',
tz='US/Eastern')],
[Timestamp('2013-01-01 00:00:00+0100', tz='CET'),
pd.NaT,
Timestamp('2013-01-03 00:00:00+0100', tz='CET')],
['foo', 'foo', 'foo']], dtype=object).T
tm.assert_numpy_array_equal(result, expected)
# interleave with only datetime64[ns]
result = self.tzframe.values
expected = np.array([[Timestamp('2013-01-01 00:00:00'),
Timestamp('2013-01-02 00:00:00'),
Timestamp('2013-01-03 00:00:00')],
[Timestamp('2013-01-01 00:00:00-0500',
tz='US/Eastern'),
pd.NaT,
Timestamp('2013-01-03 00:00:00-0500',
tz='US/Eastern')],
[Timestamp('2013-01-01 00:00:00+0100', tz='CET'),
pd.NaT,
Timestamp('2013-01-03 00:00:00+0100',
tz='CET')]], dtype=object).T
tm.assert_numpy_array_equal(result, expected)
def _check(dtype):
obj = np.array(np.random.randn(20), dtype=dtype)
bins = np.array([6, 12, 20])
out = np.zeros((3, 4), dtype)
counts = np.zeros(len(out), dtype=np.int64)
labels = _ensure_int64(np.repeat(np.arange(3),
np.diff(np.r_[0, bins])))
func = getattr(groupby, 'group_ohlc_%s' % dtype)
func(out, counts, obj[:, None], labels)
def _ohlc(group):
if isna(group).all():
return np.repeat(nan, 4)
return [group[0], group.max(), group.min(), group[-1]]
expected = np.array([_ohlc(obj[:6]), _ohlc(obj[6:12]),
_ohlc(obj[12:])])
assert_almost_equal(out, expected)
tm.assert_numpy_array_equal(counts,
np.array([6, 6, 8], dtype=np.int64))
obj[:6] = nan
func(out, counts, obj[:, None], labels)
expected[0] = nan
assert_almost_equal(out, expected)
def test_include_na(self):
s = ['a', 'b', np.nan]
res = get_dummies(s, sparse=self.sparse)
exp = DataFrame({'a': {0: 1.0,
1: 0.0,
2: 0.0},
'b': {0: 0.0,
1: 1.0,
2: 0.0}})
assert_frame_equal(res, exp)
# Sparse dataframes do not allow nan labelled columns, see #GH8822
res_na = get_dummies(s, dummy_na=True, sparse=self.sparse)
exp_na = DataFrame({nan: {0: 0.0,
1: 0.0,
2: 1.0},
'a': {0: 1.0,
1: 0.0,
2: 0.0},
'b': {0: 0.0,
1: 1.0,
2: 0.0}}).reindex_axis(
['a', 'b', nan], 1)
# hack (NaN handling in assert_index_equal)
exp_na.columns = res_na.columns
assert_frame_equal(res_na, exp_na)
res_just_na = get_dummies([nan], dummy_na=True, sparse=self.sparse)
exp_just_na = DataFrame(Series(1.0, index=[0]), columns=[nan])
tm.assert_numpy_array_equal(res_just_na.values, exp_just_na.values)
def test_frame_non_unique_columns(self):
df = DataFrame([['a', 'b'], ['c', 'd']], index=[1, 2],
columns=['x', 'x'])
self.assertRaises(ValueError, df.to_json, orient='index')
self.assertRaises(ValueError, df.to_json, orient='columns')
self.assertRaises(ValueError, df.to_json, orient='records')
assert_frame_equal(df, read_json(df.to_json(orient='split'),
orient='split', dtype=False))
unser = read_json(df.to_json(orient='values'), orient='values')
tm.assert_numpy_array_equal(df.values, unser.values)
# GH4377; duplicate columns not processing correctly
df = DataFrame([['a', 'b'], ['c', 'd']], index=[
1, 2], columns=['x', 'y'])
result = read_json(df.to_json(orient='split'), orient='split')
assert_frame_equal(result, df)
def _check(df):
result = read_json(df.to_json(orient='split'), orient='split',
convert_dates=['x'])
assert_frame_equal(result, df)
for o in [[['a', 'b'], ['c', 'd']],
[[1.5, 2.5], [3.5, 4.5]],
[[1, 2.5], [3, 4.5]],
[[Timestamp('20130101'), 3.5],
[Timestamp('20130102'), 4.5]]]:
_check(DataFrame(o, index=[1, 2], columns=['x', 'x']))
def test_as_matrix_deprecated(self, float_frame):
# GH 18458
with tm.assert_produces_warning(FutureWarning):
cols = float_frame.columns.tolist()
result = float_frame.as_matrix(columns=cols)
expected = float_frame.values
tm.assert_numpy_array_equal(result, expected)
def test_compare_timedelta_ndarray(self):
# GH11835
periods = [Timedelta('0 days 01:00:00'), Timedelta('0 days 01:00:00')]
arr = np.array(periods)
result = arr[0] > arr
expected = np.array([False, False])
tm.assert_numpy_array_equal(result, expected)
def test_cast_scalar_to_array(self):
arr = cast_scalar_to_array((3, 2), 1, dtype=np.int64)
exp = np.ones((3, 2), dtype=np.int64)
tm.assert_numpy_array_equal(arr, exp)
arr = cast_scalar_to_array((3, 2), 1.1)
exp = np.empty((3, 2), dtype=np.float64)
exp.fill(1.1)
tm.assert_numpy_array_equal(arr, exp)
arr = cast_scalar_to_array((2, 3), Timestamp('2011-01-01'))
exp = np.empty((2, 3), dtype='datetime64[ns]')
exp.fill(np.datetime64('2011-01-01'))
tm.assert_numpy_array_equal(arr, exp)
# pandas dtype is stored as object dtype
obj = Timestamp('2011-01-01', tz='US/Eastern')
arr = cast_scalar_to_array((2, 3), obj)
exp = np.empty((2, 3), dtype=np.object)
exp.fill(obj)
tm.assert_numpy_array_equal(arr, exp)
obj = Period('2011-01-01', freq='D')
arr = cast_scalar_to_array((2, 3), obj)
exp = np.empty((2, 3), dtype=np.object)
exp.fill(obj)
tm.assert_numpy_array_equal(arr, exp)
def test_noright(self):
data = np.array([.2, 1.4, 2.5, 6.2, 9.7, 2.1, 2.575])
result, bins = cut(data, 4, right=False, retbins=True)
exp_codes = np.array([0, 0, 0, 2, 3, 0, 1], dtype=np.int8)
tm.assert_numpy_array_equal(result.codes, exp_codes)
exp = np.array([0.2, 2.575, 4.95, 7.325, 9.7095])
tm.assert_almost_equal(bins, exp)
def test_arraylike(self):
data = [.2, 1.4, 2.5, 6.2, 9.7, 2.1]
result, bins = cut(data, 3, retbins=True)
exp_codes = np.array([0, 0, 0, 1, 2, 0], dtype=np.int8)
tm.assert_numpy_array_equal(result.codes, exp_codes)
exp = np.array([0.1905, 3.36666667, 6.53333333, 9.7])
tm.assert_almost_equal(bins, exp)
def test_difference_base(self):
for name, idx in compat.iteritems(self.indices):
first = idx[2:]
second = idx[:4]
answer = idx[4:]
result = first.difference(second)
if isinstance(idx, CategoricalIndex):
pass
else:
self.assertTrue(tm.equalContents(result, answer))
# GH 10149
cases = [klass(second.values)
for klass in [np.array, Series, list]]
for case in cases:
if isinstance(idx, PeriodIndex):
msg = "can only call with other PeriodIndex-ed objects"
with tm.assertRaisesRegexp(ValueError, msg):
result = first.difference(case)
elif isinstance(idx, CategoricalIndex):
pass
elif isinstance(idx, (DatetimeIndex, TimedeltaIndex)):
self.assertEqual(result.__class__, answer.__class__)
tm.assert_numpy_array_equal(result.asi8, answer.asi8)
else:
result = first.difference(case)
self.assertTrue(tm.equalContents(result, answer))
if isinstance(idx, MultiIndex):
msg = "other must be a MultiIndex or a list of tuples"
with tm.assertRaisesRegexp(TypeError, msg):
result = first.difference([1, 2, 3])
def test_from_product_datetimeindex():
dt_index = date_range('2000-01-01', periods=2)
mi = pd.MultiIndex.from_product([[1, 2], dt_index])
etalon = construct_1d_object_array_from_listlike([(1, pd.Timestamp(
'2000-01-01')), (1, pd.Timestamp('2000-01-02')), (2, pd.Timestamp(
'2000-01-01')), (2, pd.Timestamp('2000-01-02'))])
tm.assert_numpy_array_equal(mi.values, etalon)
def test_map(self):
ci = pd.CategoricalIndex(list('ABABC'), categories=list('CBA'),
ordered=True)
result = ci.map(lambda x: x.lower())
exp = pd.Categorical(list('ababc'), categories=list('cba'),
ordered=True)
tm.assert_categorical_equal(result, exp)
ci = pd.CategoricalIndex(list('ABABC'), categories=list('BAC'),
ordered=False, name='XXX')
result = ci.map(lambda x: x.lower())
exp = pd.Categorical(list('ababc'), categories=list('bac'),
ordered=False)
tm.assert_categorical_equal(result, exp)
tm.assert_numpy_array_equal(ci.map(lambda x: 1),
np.array([1] * 5, dtype=np.int64))
# change categories dtype
ci = pd.CategoricalIndex(list('ABABC'), categories=list('BAC'),
ordered=False)
def f(x):
return {'A': 10, 'B': 20, 'C': 30}.get(x)
result = ci.map(f)
exp = pd.Categorical([10, 20, 10, 20, 30], categories=[20, 10, 30],
ordered=False)
tm.assert_categorical_equal(result, exp)
def test_numpy_argsort(self):
for k, ind in self.indices.items():
result = np.argsort(ind)
expected = ind.argsort()
tm.assert_numpy_array_equal(result, expected)
# these are the only two types that perform
# pandas compatibility input validation - the
# rest already perform separate (or no) such
# validation via their 'values' attribute as
# defined in pandas.indexes/base.py - they
# cannot be changed at the moment due to
# backwards compatibility concerns
if isinstance(type(ind), (CategoricalIndex, RangeIndex)):
msg = "the 'axis' parameter is not supported"
tm.assertRaisesRegexp(ValueError, msg,
np.argsort, ind, axis=1)
msg = "the 'kind' parameter is not supported"
tm.assertRaisesRegexp(ValueError, msg, np.argsort,
ind, kind='mergesort')
msg = "the 'order' parameter is not supported"
tm.assertRaisesRegexp(ValueError, msg, np.argsort,
ind, order=('a', 'b'))
def _check_axes_shape(self, axes, axes_num=None, layout=None,
figsize=None):
"""
Check expected number of axes is drawn in expected layout
Parameters
----------
axes : matplotlib Axes object, or its list-like
axes_num : number
expected number of axes. Unnecessary axes should be set to
invisible.
layout : tuple
expected layout, (expected number of rows , columns)
figsize : tuple
expected figsize. default is matplotlib default
"""
from pandas.plotting._matplotlib.tools import _flatten
if figsize is None:
figsize = self.default_figsize
visible_axes = self._flatten_visible(axes)
if axes_num is not None:
assert len(visible_axes) == axes_num
for ax in visible_axes:
# check something drawn on visible axes
assert len(ax.get_children()) > 0
if layout is not None:
result = self._get_axes_layout(_flatten(axes))
assert result == layout
tm.assert_numpy_array_equal(
visible_axes[0].figure.get_size_inches(),
np.array(figsize, dtype=np.float64))
def test_equals(self, freq):
# GH#13107
idx = pd.PeriodIndex(['2011-01-01', '2011-01-02', 'NaT'],
freq=freq)
assert idx.equals(idx)
assert idx.equals(idx.copy())
assert idx.equals(idx.astype(object))
assert idx.astype(object).equals(idx)
assert idx.astype(object).equals(idx.astype(object))
assert not idx.equals(list(idx))
assert not idx.equals(pd.Series(idx))
idx2 = pd.PeriodIndex(['2011-01-01', '2011-01-02', 'NaT'],
freq='H')
assert not idx.equals(idx2)
assert not idx.equals(idx2.copy())
assert not idx.equals(idx2.astype(object))
assert not idx.astype(object).equals(idx2)
assert not idx.equals(list(idx2))
assert not idx.equals(pd.Series(idx2))
# same internal, different tz
idx3 = pd.PeriodIndex._simple_new(idx.asi8, freq='H')
tm.assert_numpy_array_equal(idx.asi8, idx3.asi8)
assert not idx.equals(idx3)
assert not idx.equals(idx3.copy())
assert not idx.equals(idx3.astype(object))
assert not idx.astype(object).equals(idx3)
assert not idx.equals(list(idx3))
assert not idx.equals(pd.Series(idx3))
def test_get_value(self):
# GH 17717
p0 = pd.Period('2017-09-01')
p1 = pd.Period('2017-09-02')
p2 = pd.Period('2017-09-03')
idx0 = pd.PeriodIndex([p0, p1, p2])
input0 = np.array([1, 2, 3])
expected0 = 2
result0 = idx0.get_value(input0, p1)
assert result0 == expected0
idx1 = pd.PeriodIndex([p1, p1, p2])
input1 = np.array([1, 2, 3])
expected1 = np.array([1, 2])
result1 = idx1.get_value(input1, p1)
tm.assert_numpy_array_equal(result1, expected1)
idx2 = pd.PeriodIndex([p1, p2, p1])
input2 = np.array([1, 2, 3])
expected2 = np.array([1, 3])
result2 = idx2.get_value(input2, p1)
tm.assert_numpy_array_equal(result2, expected2)
def test_get_indexer(self):
# GH 17717
p1 = pd.Period('2017-09-01')
p2 = pd.Period('2017-09-04')
p3 = pd.Period('2017-09-07')
tp0 = pd.Period('2017-08-31')
tp1 = pd.Period('2017-09-02')
tp2 = pd.Period('2017-09-05')
tp3 = pd.Period('2017-09-09')
idx = pd.PeriodIndex([p1, p2, p3])
tm.assert_numpy_array_equal(idx.get_indexer(idx),
np.array([0, 1, 2], dtype=np.intp))
target = pd.PeriodIndex([tp0, tp1, tp2, tp3])
tm.assert_numpy_array_equal(idx.get_indexer(target, 'pad'),
np.array([-1, 0, 1, 2], dtype=np.intp))
tm.assert_numpy_array_equal(idx.get_indexer(target, 'backfill'),
np.array([0, 1, 2, -1], dtype=np.intp))
tm.assert_numpy_array_equal(idx.get_indexer(target, 'nearest'),
np.array([0, 0, 1, 2], dtype=np.intp))
res = idx.get_indexer(target, 'nearest',
tolerance=pd.Timedelta('1 day'))
tm.assert_numpy_array_equal(res,
np.array([0, 0, 1, -1], dtype=np.intp))
def test_groupby_categorical_no_compress(self):
data = Series(np.random.randn(9))
codes = np.array([0, 0, 0, 1, 1, 1, 2, 2, 2])
cats = Categorical.from_codes(codes, [0, 1, 2], ordered=True)
result = data.groupby(cats).mean()
exp = data.groupby(codes).mean()
exp.index = CategoricalIndex(exp.index, categories=cats.categories,
ordered=cats.ordered)
assert_series_equal(result, exp)
codes = np.array([0, 0, 0, 1, 1, 1, 3, 3, 3])
cats = Categorical.from_codes(codes, [0, 1, 2, 3], ordered=True)
result = data.groupby(cats).mean()
exp = data.groupby(codes).mean().reindex(cats.categories)
exp.index = CategoricalIndex(exp.index, categories=cats.categories,
ordered=cats.ordered)
assert_series_equal(result, exp)
cats = Categorical(["a", "a", "a", "b", "b", "b", "c", "c", "c"],
categories=["a", "b", "c", "d"], ordered=True)
data = DataFrame({"a": [1, 1, 1, 2, 2, 2, 3, 4, 5], "b": cats})
result = data.groupby("b").mean()
result = result["a"].values
exp = np.array([1, 2, 4, np.nan])
tm.assert_numpy_array_equal(result, exp)
def test_convert_sql_column_unicode(self):
arr = np.array([u('1.5'), None, u('3'), u('4.2')],
dtype=object)
result = lib.convert_sql_column(arr)
expected = np.array([u('1.5'), np.nan, u('3'), u('4.2')],
dtype=object)
tm.assert_numpy_array_equal(result, expected)
def test_rename_set_name(self):
s = Series(range(4), index=list('abcd'))
for name in ['foo', 123, 123., datetime(2001, 11, 11), ('foo',)]:
result = s.rename(name)
assert result.name == name
tm.assert_numpy_array_equal(result.index.values, s.index.values)
assert s.name is None
def test_cython_right_outer_join(self):
left = a_([0, 1, 2, 1, 2, 0, 0, 1, 2, 3, 3], dtype=np.int64)
right = a_([1, 1, 0, 4, 2, 2, 1], dtype=np.int64)
max_group = 5
rs, ls = libjoin.left_outer_join(right, left, max_group)
exp_ls = left.argsort(kind='mergesort')
exp_rs = right.argsort(kind='mergesort')
# 0 1 1 1
exp_li = a_([0, 1, 2, 3, 4, 5, 3, 4, 5, 3, 4, 5,
# 2 2 4
6, 7, 8, 6, 7, 8, -1])
exp_ri = a_([0, 0, 0, 1, 1, 1, 2, 2, 2, 3, 3, 3,
4, 4, 4, 5, 5, 5, 6])
exp_ls = exp_ls.take(exp_li)
exp_ls[exp_li == -1] = -1
exp_rs = exp_rs.take(exp_ri)
exp_rs[exp_ri == -1] = -1
tm.assert_numpy_array_equal(ls, exp_ls, check_dtype=False)
tm.assert_numpy_array_equal(rs, exp_rs, check_dtype=False)
def test_reindex_empty_index(self):
# See GH16770
c = CategoricalIndex([])
res, indexer = c.reindex(['a', 'b'])
tm.assert_index_equal(res, Index(['a', 'b']), exact=True)
tm.assert_numpy_array_equal(indexer,
np.array([-1, -1], dtype=np.intp))
def assert_as_array_equals(slc, asarray):
tm.assert_numpy_array_equal(
BlockPlacement(slc).as_array, np.asarray(asarray, dtype=np.int64)
)
def test_convert_non_hashable(self):
# GH13324
# make sure that we are handing non-hashables
arr = np.array([[10.0, 2], 1.0, "apple"])
result = lib.maybe_convert_numeric(arr, set(), False, True)
tm.assert_numpy_array_equal(result, np.array([np.nan, 1.0, np.nan]))
def test_reindex_empty_index(self):
# See GH16770
c = CategoricalIndex([])
res, indexer = c.reindex(['a', 'b'])
tm.assert_index_equal(res, Index(['a', 'b']), exact=True)
tm.assert_numpy_array_equal(indexer, np.array([-1, -1], dtype=np.intp))
def test_construction(self):
ci = self.create_index(categories=list('abcd'))
categories = ci.categories
result = Index(ci)
tm.assert_index_equal(result, ci, exact=True)
assert not result.ordered
result = Index(ci.values)
tm.assert_index_equal(result, ci, exact=True)
assert not result.ordered
# empty
result = CategoricalIndex(categories=categories)
tm.assert_index_equal(result.categories, Index(categories))
tm.assert_numpy_array_equal(result.codes, np.array([], dtype='int8'))
assert not result.ordered
# passing categories
result = CategoricalIndex(list('aabbca'), categories=categories)
tm.assert_index_equal(result.categories, Index(categories))
tm.assert_numpy_array_equal(result.codes,
np.array([0, 0, 1, 1, 2, 0], dtype='int8'))
c = pd.Categorical(list('aabbca'))
result = CategoricalIndex(c)
tm.assert_index_equal(result.categories, Index(list('abc')))
tm.assert_numpy_array_equal(result.codes,
np.array([0, 0, 1, 1, 2, 0], dtype='int8'))
assert not result.ordered
result = CategoricalIndex(c, categories=categories)
tm.assert_index_equal(result.categories, Index(categories))
tm.assert_numpy_array_equal(result.codes,
np.array([0, 0, 1, 1, 2, 0], dtype='int8'))
assert not result.ordered
ci = CategoricalIndex(c, categories=list('abcd'))
result = CategoricalIndex(ci)
tm.assert_index_equal(result.categories, Index(categories))
tm.assert_numpy_array_equal(result.codes,
np.array([0, 0, 1, 1, 2, 0], dtype='int8'))
assert not result.ordered
result = CategoricalIndex(ci, categories=list('ab'))
tm.assert_index_equal(result.categories, Index(list('ab')))
tm.assert_numpy_array_equal(
result.codes, np.array([0, 0, 1, 1, -1, 0], dtype='int8'))
assert not result.ordered
result = CategoricalIndex(ci, categories=list('ab'), ordered=True)
tm.assert_index_equal(result.categories, Index(list('ab')))
tm.assert_numpy_array_equal(
result.codes, np.array([0, 0, 1, 1, -1, 0], dtype='int8'))
assert result.ordered
result = pd.CategoricalIndex(ci, categories=list('ab'), ordered=True)
expected = pd.CategoricalIndex(ci,
categories=list('ab'),
ordered=True,
dtype='category')
tm.assert_index_equal(result, expected, exact=True)
# turn me to an Index
result = Index(np.array(ci))
assert isinstance(result, Index)
assert not isinstance(result, CategoricalIndex)
def test_order(self):
# with freq
idx1 = DatetimeIndex(['2011-01-01', '2011-01-02',
'2011-01-03'], freq='D', name='idx')
idx2 = DatetimeIndex(['2011-01-01 09:00', '2011-01-01 10:00',
'2011-01-01 11:00'], freq='H',
tz='Asia/Tokyo', name='tzidx')
for idx in [idx1, idx2]:
ordered = idx.sort_values()
tm.assert_index_equal(ordered, idx)
assert ordered.freq == idx.freq
ordered = idx.sort_values(ascending=False)
expected = idx[::-1]
tm.assert_index_equal(ordered, expected)
assert ordered.freq == expected.freq
assert ordered.freq.n == -1
ordered, indexer = idx.sort_values(return_indexer=True)
tm.assert_index_equal(ordered, idx)
tm.assert_numpy_array_equal(indexer, np.array([0, 1, 2]),
check_dtype=False)
assert ordered.freq == idx.freq
ordered, indexer = idx.sort_values(return_indexer=True,
ascending=False)
expected = idx[::-1]
tm.assert_index_equal(ordered, expected)
tm.assert_numpy_array_equal(indexer,
np.array([2, 1, 0]),
check_dtype=False)
assert ordered.freq == expected.freq
assert ordered.freq.n == -1
# without freq
for tz in self.tz:
idx1 = DatetimeIndex(['2011-01-01', '2011-01-03', '2011-01-05',
'2011-01-02', '2011-01-01'],
tz=tz, name='idx1')
exp1 = DatetimeIndex(['2011-01-01', '2011-01-01', '2011-01-02',
'2011-01-03', '2011-01-05'],
tz=tz, name='idx1')
idx2 = DatetimeIndex(['2011-01-01', '2011-01-03', '2011-01-05',
'2011-01-02', '2011-01-01'],
tz=tz, name='idx2')
exp2 = DatetimeIndex(['2011-01-01', '2011-01-01', '2011-01-02',
'2011-01-03', '2011-01-05'],
tz=tz, name='idx2')
idx3 = DatetimeIndex([pd.NaT, '2011-01-03', '2011-01-05',
'2011-01-02', pd.NaT], tz=tz, name='idx3')
exp3 = DatetimeIndex([pd.NaT, pd.NaT, '2011-01-02', '2011-01-03',
'2011-01-05'], tz=tz, name='idx3')
for idx, expected in [(idx1, exp1), (idx2, exp2), (idx3, exp3)]:
ordered = idx.sort_values()
tm.assert_index_equal(ordered, expected)
assert ordered.freq is None
ordered = idx.sort_values(ascending=False)
tm.assert_index_equal(ordered, expected[::-1])
assert ordered.freq is None
ordered, indexer = idx.sort_values(return_indexer=True)
tm.assert_index_equal(ordered, expected)
exp = np.array([0, 4, 3, 1, 2])
tm.assert_numpy_array_equal(indexer, exp, check_dtype=False)
assert ordered.freq is None
ordered, indexer = idx.sort_values(return_indexer=True,
ascending=False)
tm.assert_index_equal(ordered, expected[::-1])
exp = np.array([2, 1, 3, 4, 0])
tm.assert_numpy_array_equal(indexer, exp, check_dtype=False)
assert ordered.freq is None
def assert_block_equal(left, right):
tm.assert_numpy_array_equal(left.values, right.values)
assert left.dtype == right.dtype
assert isinstance(left.mgr_locs, BlockPlacement)
assert isinstance(right.mgr_locs, BlockPlacement)
tm.assert_numpy_array_equal(left.mgr_locs.as_array, right.mgr_locs.as_array)
def test_mgr_locs(self):
assert isinstance(self.fblock.mgr_locs, BlockPlacement)
tm.assert_numpy_array_equal(
self.fblock.mgr_locs.as_array, np.array([0, 2, 4], dtype=np.int64)
)
def test_eq(self, other):
idx = PeriodIndex(["2017", "2017", "2018"], freq="D")
expected = np.array([True, True, False])
result = idx == other
tm.assert_numpy_array_equal(result, expected)
def test_pi_cmp_nat(self, freq):
idx1 = PeriodIndex(["2011-01", "2011-02", "NaT", "2011-05"], freq=freq)
result = idx1 > Period("2011-02", freq=freq)
exp = np.array([False, False, False, True])
tm.assert_numpy_array_equal(result, exp)
result = Period("2011-02", freq=freq) < idx1
tm.assert_numpy_array_equal(result, exp)
result = idx1 == Period("NaT", freq=freq)
exp = np.array([False, False, False, False])
tm.assert_numpy_array_equal(result, exp)
result = Period("NaT", freq=freq) == idx1
tm.assert_numpy_array_equal(result, exp)
result = idx1 != Period("NaT", freq=freq)
exp = np.array([True, True, True, True])
tm.assert_numpy_array_equal(result, exp)
result = Period("NaT", freq=freq) != idx1
tm.assert_numpy_array_equal(result, exp)
idx2 = PeriodIndex(["2011-02", "2011-01", "2011-04", "NaT"], freq=freq)
result = idx1 < idx2
exp = np.array([True, False, False, False])
tm.assert_numpy_array_equal(result, exp)
result = idx1 == idx2
exp = np.array([False, False, False, False])
tm.assert_numpy_array_equal(result, exp)
result = idx1 != idx2
exp = np.array([True, True, True, True])
tm.assert_numpy_array_equal(result, exp)
result = idx1 == idx1
exp = np.array([True, True, False, True])
tm.assert_numpy_array_equal(result, exp)
result = idx1 != idx1
exp = np.array([False, False, True, False])
tm.assert_numpy_array_equal(result, exp)
def test_pi_cmp_period(self):
idx = period_range("2007-01", periods=20, freq="M")
result = idx < idx[10]
exp = idx.values < idx.values[10]
tm.assert_numpy_array_equal(result, exp)
def assert_array_dicts_equal(left, right):
for k, v in left.items():
tm.assert_numpy_array_equal(np.asarray(v), np.asarray(right[k]))
def test_comp_nat(self, dtype):
left = pd.PeriodIndex(
[pd.Period("2011-01-01"), pd.NaT,
pd.Period("2011-01-03")])
right = pd.PeriodIndex([pd.NaT, pd.NaT, pd.Period("2011-01-03")])
if dtype is not None:
left = left.astype(dtype)
right = right.astype(dtype)
result = left == right
expected = np.array([False, False, True])
tm.assert_numpy_array_equal(result, expected)
result = left != right
expected = np.array([True, True, False])
tm.assert_numpy_array_equal(result, expected)
expected = np.array([False, False, False])
tm.assert_numpy_array_equal(left == pd.NaT, expected)
tm.assert_numpy_array_equal(pd.NaT == right, expected)
expected = np.array([True, True, True])
tm.assert_numpy_array_equal(left != pd.NaT, expected)
tm.assert_numpy_array_equal(pd.NaT != left, expected)
expected = np.array([False, False, False])
tm.assert_numpy_array_equal(left < pd.NaT, expected)
tm.assert_numpy_array_equal(pd.NaT > left, expected)
def test_factorize_equivalence(self, data_for_grouping, na_sentinel):
l1, u1 = pd.factorize(data_for_grouping, na_sentinel=na_sentinel)
l2, u2 = data_for_grouping.factorize(na_sentinel=na_sentinel)
tm.assert_numpy_array_equal(l1, l2)
self.assert_extension_array_equal(u1, u2)
def test_unique_na_fill(arr, fill_value):
a = pd.SparseArray(arr, fill_value=fill_value).unique()
b = pd.Series(arr).unique()
assert isinstance(a, SparseArray)
a = np.asarray(a)
tm.assert_numpy_array_equal(a, b)
def test_get_indexer_backfill(self):
target = RangeIndex(10)
indexer = self.index.get_indexer(target, method='backfill')
expected = np.array([0, 1, 1, 2, 2, 3, 3, 4, 4, 5], dtype=np.intp)
tm.assert_numpy_array_equal(indexer, expected)
def test_coerce_outside_ns_bounds_one_valid(self):
arr = np.array(['1/1/1000', '1/1/2000'], dtype=object)
result, _ = tslib.array_to_datetime(arr, errors='coerce')
expected = [tslib.iNaT, '2000-01-01T00:00:00.000000000-0000']
tm.assert_numpy_array_equal(
result, np_array_datetime64_compat(expected, dtype='M8[ns]'))
def test_equals_op(self):
# GH9947, GH10637
index_a = self.create_index()
if isinstance(index_a, PeriodIndex):
pytest.skip("Skip check for PeriodIndex")
n = len(index_a)
index_b = index_a[0:-1]
index_c = index_a[0:-1].append(index_a[-2:-1])
index_d = index_a[0:1]
msg = "Lengths must match|could not be broadcast"
with pytest.raises(ValueError, match=msg):
index_a == index_b
expected1 = np.array([True] * n)
expected2 = np.array([True] * (n - 1) + [False])
tm.assert_numpy_array_equal(index_a == index_a, expected1)
tm.assert_numpy_array_equal(index_a == index_c, expected2)
# test comparisons with numpy arrays
array_a = np.array(index_a)
array_b = np.array(index_a[0:-1])
array_c = np.array(index_a[0:-1].append(index_a[-2:-1]))
array_d = np.array(index_a[0:1])
with pytest.raises(ValueError, match=msg):
index_a == array_b
tm.assert_numpy_array_equal(index_a == array_a, expected1)
tm.assert_numpy_array_equal(index_a == array_c, expected2)
# test comparisons with Series
series_a = Series(array_a)
series_b = Series(array_b)
series_c = Series(array_c)
series_d = Series(array_d)
with pytest.raises(ValueError, match=msg):
index_a == series_b
tm.assert_numpy_array_equal(index_a == series_a, expected1)
tm.assert_numpy_array_equal(index_a == series_c, expected2)
# cases where length is 1 for one of them
with pytest.raises(ValueError, match="Lengths must match"):
index_a == index_d
with pytest.raises(ValueError, match="Lengths must match"):
index_a == series_d
with pytest.raises(ValueError, match="Lengths must match"):
index_a == array_d
msg = "Can only compare identically-labeled Series objects"
with pytest.raises(ValueError, match=msg):
series_a == series_d
with pytest.raises(ValueError, match="Lengths must match"):
series_a == array_d
# comparing with a scalar should broadcast; note that we are excluding
# MultiIndex because in this case each item in the index is a tuple of
# length 2, and therefore is considered an array of length 2 in the
# comparison instead of a scalar
if not isinstance(index_a, MultiIndex):
expected3 = np.array([False] * (len(index_a) - 2) + [True, False])
# assuming the 2nd to last item is unique in the data
item = index_a[-2]
tm.assert_numpy_array_equal(index_a == item, expected3)
tm.assert_series_equal(series_a == item, Series(expected3))
def test_shift(self):
shifted = self.ts.shift(1)
unshifted = shifted.shift(-1)
tm.assert_index_equal(shifted.index, self.ts.index)
tm.assert_index_equal(unshifted.index, self.ts.index)
tm.assert_numpy_array_equal(unshifted.valid().values,
self.ts.values[:-1])
offset = BDay()
shifted = self.ts.shift(1, freq=offset)
unshifted = shifted.shift(-1, freq=offset)
assert_series_equal(unshifted, self.ts)
unshifted = self.ts.shift(0, freq=offset)
assert_series_equal(unshifted, self.ts)
shifted = self.ts.shift(1, freq='B')
unshifted = shifted.shift(-1, freq='B')
assert_series_equal(unshifted, self.ts)
# corner case
unshifted = self.ts.shift(0)
assert_series_equal(unshifted, self.ts)
# Shifting with PeriodIndex
ps = tm.makePeriodSeries()
shifted = ps.shift(1)
unshifted = shifted.shift(-1)
tm.assert_index_equal(shifted.index, ps.index)
tm.assert_index_equal(unshifted.index, ps.index)
tm.assert_numpy_array_equal(unshifted.valid().values, ps.values[:-1])
shifted2 = ps.shift(1, 'B')
shifted3 = ps.shift(1, BDay())
assert_series_equal(shifted2, shifted3)
assert_series_equal(ps, shifted2.shift(-1, 'B'))
self.assertRaises(ValueError, ps.shift, freq='D')
# legacy support
shifted4 = ps.shift(1, freq='B')
assert_series_equal(shifted2, shifted4)
shifted5 = ps.shift(1, freq=BDay())
assert_series_equal(shifted5, shifted4)
# 32-bit taking
# GH 8129
index = date_range('2000-01-01', periods=5)
for dtype in ['int32', 'int64']:
s1 = Series(np.arange(5, dtype=dtype), index=index)
p = s1.iloc[1]
result = s1.shift(periods=p)
expected = Series([np.nan, 0, 1, 2, 3], index=index)
assert_series_equal(result, expected)
# xref 8260
# with tz
s = Series(date_range('2000-01-01 09:00:00', periods=5,
tz='US/Eastern'), name='foo')
result = s - s.shift()
exp = Series(TimedeltaIndex(['NaT'] + ['1 days'] * 4), name='foo')
assert_series_equal(result, exp)
# incompat tz
s2 = Series(date_range('2000-01-01 09:00:00', periods=5,
tz='CET'), name='foo')
self.assertRaises(ValueError, lambda: s - s2)
def test_get_indexer_backfill(self):
target = Int64Index(np.arange(10))
indexer = self.index.get_indexer(target, method='backfill')
expected = np.array([0, 1, 1, 2, 2, 3, 3, 4, 4, 5])
tm.assert_numpy_array_equal(indexer, expected)
def test_get_indexer(self):
target = RangeIndex(10)
indexer = self.index.get_indexer(target)
expected = np.array([0, -1, 1, -1, 2, -1, 3, -1, 4, -1], dtype=np.intp)
tm.assert_numpy_array_equal(indexer, expected)
def test_block_internal(self):
idx = _make_index(4, np.array([2, 3], dtype=np.int32), kind='block')
assert isinstance(idx, BlockIndex)
self.assertEqual(idx.npoints, 2)
tm.assert_numpy_array_equal(idx.blocs, np.array([2], dtype=np.int32))
tm.assert_numpy_array_equal(idx.blengths, np.array([2],
dtype=np.int32))
idx = _make_index(4, np.array([], dtype=np.int32), kind='block')
assert isinstance(idx, BlockIndex)
self.assertEqual(idx.npoints, 0)
tm.assert_numpy_array_equal(idx.blocs, np.array([], dtype=np.int32))
tm.assert_numpy_array_equal(idx.blengths, np.array([], dtype=np.int32))
idx = _make_index(4,
np.array([0, 1, 2, 3], dtype=np.int32),
kind='block')
assert isinstance(idx, BlockIndex)
self.assertEqual(idx.npoints, 4)
tm.assert_numpy_array_equal(idx.blocs, np.array([0], dtype=np.int32))
tm.assert_numpy_array_equal(idx.blengths, np.array([4],
dtype=np.int32))
idx = _make_index(4, np.array([0, 2, 3], dtype=np.int32), kind='block')
assert isinstance(idx, BlockIndex)
self.assertEqual(idx.npoints, 3)
tm.assert_numpy_array_equal(idx.blocs, np.array([0, 2],
dtype=np.int32))
tm.assert_numpy_array_equal(idx.blengths,
np.array([1, 2], dtype=np.int32))
def test_numpy_array_equal_message(self):
if is_platform_windows():
pytest.skip("windows has incomparable line-endings "
"and uses L on the shape")
expected = """numpy array are different
numpy array shapes are different
\\[left\\]: \\(2,\\)
\\[right\\]: \\(3,\\)"""
with tm.assert_raises_regex(AssertionError, expected):
assert_numpy_array_equal(np.array([1, 2]), np.array([3, 4, 5]))
with tm.assert_raises_regex(AssertionError, expected):
assert_almost_equal(np.array([1, 2]), np.array([3, 4, 5]))
# scalar comparison
expected = """Expected type """
with tm.assert_raises_regex(AssertionError, expected):
assert_numpy_array_equal(1, 2)
expected = """expected 2\\.00000 but got 1\\.00000, with decimal 5"""
with tm.assert_raises_regex(AssertionError, expected):
assert_almost_equal(1, 2)
# array / scalar array comparison
expected = """numpy array are different
numpy array classes are different
\\[left\\]: ndarray
\\[right\\]: int"""
with tm.assert_raises_regex(AssertionError, expected):
# numpy_array_equal only accepts np.ndarray
assert_numpy_array_equal(np.array([1]), 1)
with tm.assert_raises_regex(AssertionError, expected):
assert_almost_equal(np.array([1]), 1)
# scalar / array comparison
expected = """numpy array are different
numpy array classes are different
\\[left\\]: int
\\[right\\]: ndarray"""
with tm.assert_raises_regex(AssertionError, expected):
assert_numpy_array_equal(1, np.array([1]))
with tm.assert_raises_regex(AssertionError, expected):
assert_almost_equal(1, np.array([1]))
expected = """numpy array are different
numpy array values are different \\(66\\.66667 %\\)
\\[left\\]: \\[nan, 2\\.0, 3\\.0\\]
\\[right\\]: \\[1\\.0, nan, 3\\.0\\]"""
with tm.assert_raises_regex(AssertionError, expected):
assert_numpy_array_equal(np.array([np.nan, 2, 3]),
np.array([1, np.nan, 3]))
with tm.assert_raises_regex(AssertionError, expected):
assert_almost_equal(np.array([np.nan, 2, 3]),
np.array([1, np.nan, 3]))
expected = """numpy array are different
numpy array values are different \\(50\\.0 %\\)
\\[left\\]: \\[1, 2\\]
\\[right\\]: \\[1, 3\\]"""
with tm.assert_raises_regex(AssertionError, expected):
assert_numpy_array_equal(np.array([1, 2]), np.array([1, 3]))
with tm.assert_raises_regex(AssertionError, expected):
assert_almost_equal(np.array([1, 2]), np.array([1, 3]))
expected = """numpy array are different
numpy array values are different \\(50\\.0 %\\)
\\[left\\]: \\[1\\.1, 2\\.000001\\]
\\[right\\]: \\[1\\.1, 2.0\\]"""
with tm.assert_raises_regex(AssertionError, expected):
assert_numpy_array_equal(np.array([1.1, 2.000001]),
np.array([1.1, 2.0]))
# must pass
assert_almost_equal(np.array([1.1, 2.000001]), np.array([1.1, 2.0]))
expected = """numpy array are different
numpy array values are different \\(16\\.66667 %\\)
\\[left\\]: \\[\\[1, 2\\], \\[3, 4\\], \\[5, 6\\]\\]
\\[right\\]: \\[\\[1, 3\\], \\[3, 4\\], \\[5, 6\\]\\]"""
with tm.assert_raises_regex(AssertionError, expected):
assert_numpy_array_equal(np.array([[1, 2], [3, 4], [5, 6]]),
np.array([[1, 3], [3, 4], [5, 6]]))
with tm.assert_raises_regex(AssertionError, expected):
assert_almost_equal(np.array([[1, 2], [3, 4], [5, 6]]),
np.array([[1, 3], [3, 4], [5, 6]]))
expected = """numpy array are different
numpy array values are different \\(25\\.0 %\\)
\\[left\\]: \\[\\[1, 2\\], \\[3, 4\\]\\]
\\[right\\]: \\[\\[1, 3\\], \\[3, 4\\]\\]"""
with tm.assert_raises_regex(AssertionError, expected):
assert_numpy_array_equal(np.array([[1, 2], [3, 4]]),
np.array([[1, 3], [3, 4]]))
with tm.assert_raises_regex(AssertionError, expected):
assert_almost_equal(np.array([[1, 2], [3, 4]]),
np.array([[1, 3], [3, 4]]))
# allow to overwrite message
expected = """Index are different
Index shapes are different
\\[left\\]: \\(2,\\)
\\[right\\]: \\(3,\\)"""
with tm.assert_raises_regex(AssertionError, expected):
assert_numpy_array_equal(np.array([1, 2]),
np.array([3, 4, 5]),
obj='Index')
with tm.assert_raises_regex(AssertionError, expected):
assert_almost_equal(np.array([1, 2]),
np.array([3, 4, 5]),
obj='Index')
def test_rank_na_option(self):
rankdata = pytest.importorskip('scipy.stats.rankdata')
self.frame['A'][::2] = np.nan
self.frame['B'][::3] = np.nan
self.frame['C'][::4] = np.nan
self.frame['D'][::5] = np.nan
# bottom
ranks0 = self.frame.rank(na_option='bottom')
ranks1 = self.frame.rank(1, na_option='bottom')
fvals = self.frame.fillna(np.inf).values
exp0 = np.apply_along_axis(rankdata, 0, fvals)
exp1 = np.apply_along_axis(rankdata, 1, fvals)
tm.assert_almost_equal(ranks0.values, exp0)
tm.assert_almost_equal(ranks1.values, exp1)
# top
ranks0 = self.frame.rank(na_option='top')
ranks1 = self.frame.rank(1, na_option='top')
fval0 = self.frame.fillna((self.frame.min() - 1).to_dict()).values
fval1 = self.frame.T
fval1 = fval1.fillna((fval1.min() - 1).to_dict()).T
fval1 = fval1.fillna(np.inf).values
exp0 = np.apply_along_axis(rankdata, 0, fval0)
exp1 = np.apply_along_axis(rankdata, 1, fval1)
tm.assert_almost_equal(ranks0.values, exp0)
tm.assert_almost_equal(ranks1.values, exp1)
# descending
# bottom
ranks0 = self.frame.rank(na_option='top', ascending=False)
ranks1 = self.frame.rank(1, na_option='top', ascending=False)
fvals = self.frame.fillna(np.inf).values
exp0 = np.apply_along_axis(rankdata, 0, -fvals)
exp1 = np.apply_along_axis(rankdata, 1, -fvals)
tm.assert_almost_equal(ranks0.values, exp0)
tm.assert_almost_equal(ranks1.values, exp1)
# descending
# top
ranks0 = self.frame.rank(na_option='bottom', ascending=False)
ranks1 = self.frame.rank(1, na_option='bottom', ascending=False)
fval0 = self.frame.fillna((self.frame.min() - 1).to_dict()).values
fval1 = self.frame.T
fval1 = fval1.fillna((fval1.min() - 1).to_dict()).T
fval1 = fval1.fillna(np.inf).values
exp0 = np.apply_along_axis(rankdata, 0, -fval0)
exp1 = np.apply_along_axis(rankdata, 1, -fval1)
tm.assert_numpy_array_equal(ranks0.values, exp0)
tm.assert_numpy_array_equal(ranks1.values, exp1)
def test_get_indexer(self):
target = Int64Index(np.arange(10))
indexer = self.index.get_indexer(target)
expected = np.array([0, -1, 1, -1, 2, -1, 3, -1, 4, -1])
tm.assert_numpy_array_equal(indexer, expected)
def test_convert_downcast_int64(self):
from pandas._libs.parsers import na_values
arr = np.array([1, 2, 7, 8, 10], dtype=np.int64)
expected = np.array([1, 2, 7, 8, 10], dtype=np.int8)
# default argument
result = lib.downcast_int64(arr, na_values)
tm.assert_numpy_array_equal(result, expected)
result = lib.downcast_int64(arr, na_values, use_unsigned=False)
tm.assert_numpy_array_equal(result, expected)
expected = np.array([1, 2, 7, 8, 10], dtype=np.uint8)
result = lib.downcast_int64(arr, na_values, use_unsigned=True)
tm.assert_numpy_array_equal(result, expected)
# still cast to int8 despite use_unsigned=True
# because of the negative number as an element
arr = np.array([1, 2, -7, 8, 10], dtype=np.int64)
expected = np.array([1, 2, -7, 8, 10], dtype=np.int8)
result = lib.downcast_int64(arr, na_values, use_unsigned=True)
tm.assert_numpy_array_equal(result, expected)
arr = np.array([1, 2, 7, 8, 300], dtype=np.int64)
expected = np.array([1, 2, 7, 8, 300], dtype=np.int16)
result = lib.downcast_int64(arr, na_values)
tm.assert_numpy_array_equal(result, expected)
int8_na = na_values[np.int8]
int64_na = na_values[np.int64]
arr = np.array([int64_na, 2, 3, 10, 15], dtype=np.int64)
expected = np.array([int8_na, 2, 3, 10, 15], dtype=np.int8)
result = lib.downcast_int64(arr, na_values)
tm.assert_numpy_array_equal(result, expected)
def test_lookup_array(self):
for kind in ['integer', 'block']:
idx = _make_index(4, np.array([2, 3], dtype=np.int32), kind=kind)
res = idx.lookup_array(np.array([-1, 0, 2], dtype=np.int32))
exp = np.array([-1, -1, 0], dtype=np.int32)
tm.assert_numpy_array_equal(res, exp)
res = idx.lookup_array(np.array([4, 2, 1, 3], dtype=np.int32))
exp = np.array([-1, 0, -1, 1], dtype=np.int32)
tm.assert_numpy_array_equal(res, exp)
idx = _make_index(4, np.array([], dtype=np.int32), kind=kind)
res = idx.lookup_array(np.array([-1, 0, 2, 4], dtype=np.int32))
exp = np.array([-1, -1, -1, -1], dtype=np.int32)
idx = _make_index(4,
np.array([0, 1, 2, 3], dtype=np.int32),
kind=kind)
res = idx.lookup_array(np.array([-1, 0, 2], dtype=np.int32))
exp = np.array([-1, 0, 2], dtype=np.int32)
tm.assert_numpy_array_equal(res, exp)
res = idx.lookup_array(np.array([4, 2, 1, 3], dtype=np.int32))
exp = np.array([-1, 2, 1, 3], dtype=np.int32)
tm.assert_numpy_array_equal(res, exp)
idx = _make_index(4,
np.array([0, 2, 3], dtype=np.int32),
kind=kind)
res = idx.lookup_array(np.array([2, 1, 3, 0], dtype=np.int32))
exp = np.array([1, -1, 2, 0], dtype=np.int32)
tm.assert_numpy_array_equal(res, exp)
res = idx.lookup_array(np.array([1, 4, 2, 5], dtype=np.int32))
exp = np.array([-1, -1, 1, -1], dtype=np.int32)
tm.assert_numpy_array_equal(res, exp)
def test_convert_sql_column_unicode(self):
arr = np.array([u('1.5'), None, u('3'), u('4.2')], dtype=object)
result = lib.convert_sql_column(arr)
expected = np.array([u('1.5'), np.nan, u('3'), u('4.2')], dtype=object)
tm.assert_numpy_array_equal(result, expected)
def test_argsort(idx):
result = idx.argsort()
expected = idx.values.argsort()
tm.assert_numpy_array_equal(result, expected)
def test_convert_sql_column_strings(self):
arr = np.array(['1.5', None, '3', '4.2'], dtype=object)
result = lib.convert_sql_column(arr)
expected = np.array(['1.5', np.nan, '3', '4.2'], dtype=object)
tm.assert_numpy_array_equal(result, expected)
def test_convert_sql_column_decimals(self):
from decimal import Decimal
arr = np.array([Decimal('1.5'), None, Decimal('3'), Decimal('4.2')])
result = lib.convert_sql_column(arr)
expected = np.array([1.5, np.nan, 3, 4.2], dtype='f8')
tm.assert_numpy_array_equal(result, expected)