def test_numpy_transpose(self):
for obj in self.objs:
tm.assert_equal(np.transpose(obj), obj)
with pytest.raises(ValueError, match=self.errmsg):
np.transpose(obj, axes=1)
def assert_invalid_comparison(left, right, box):
"""
Assert that comparison operations with mismatched types behave correctly.
Parameters
----------
left : np.ndarray, ExtensionArray, Index, or Series
right : object
box : {pd.DataFrame, pd.Series, pd.Index, pd.array, tm.to_array}
"""
# Not for tznaive-tzaware comparison
# Note: not quite the same as how we do this for tm.box_expected
xbox = box if box not in [Index, array] else np.array
def xbox2(x):
# Eventually we'd like this to be tighter, but for now we'll
# just exclude PandasArray[bool]
if isinstance(x, PandasArray):
return x._ndarray
return x
result = xbox2(left == right)
expected = xbox(np.zeros(result.shape, dtype=np.bool_))
tm.assert_equal(result, expected)
result = xbox2(right == left)
tm.assert_equal(result, expected)
result = xbox2(left != right)
tm.assert_equal(result, ~expected)
result = xbox2(right != left)
tm.assert_equal(result, ~expected)
msg = "|".join([
"Invalid comparison between",
"Cannot compare type",
"not supported between",
"invalid type promotion",
(
# GH#36706 npdev 1.20.0 2020-09-28
r"The DTypes <class 'numpy.dtype\[datetime64\]'> and "
r"<class 'numpy.dtype\[int64\]'> do not have a common DType. "
"For example they cannot be stored in a single array unless the "
"dtype is `object`."),
])
with pytest.raises(TypeError, match=msg):
left < right
with pytest.raises(TypeError, match=msg):
left <= right
with pytest.raises(TypeError, match=msg):
left > right
with pytest.raises(TypeError, match=msg):
left >= right
with pytest.raises(TypeError, match=msg):
right < left
with pytest.raises(TypeError, match=msg):
right <= left
with pytest.raises(TypeError, match=msg):
right > left
with pytest.raises(TypeError, match=msg):
right >= left
def test_nat_arithmetic_td64_vector(op_name, box):
# see gh-19124
vec = box(["1 day", "2 day"], dtype="timedelta64[ns]")
box_nat = box([NaT, NaT], dtype="timedelta64[ns]")
tm.assert_equal(_ops[op_name](vec, NaT), box_nat)
def test_apply_as_index_constant_lambda(as_index, expected):
# GH 13217
df = DataFrame({"a": [1, 1, 2, 2], "b": [1, 1, 2, 2], "c": [1, 1, 1, 1]})
result = df.groupby(["a", "b"], as_index=as_index).apply(lambda x: 1)
tm.assert_equal(result, expected)
def test_constructor_unwraps_index(self, index):
if isinstance(index, pd.MultiIndex):
raise pytest.skip("MultiIndex has no ._data")
a = index
b = type(a)(a)
tm.assert_equal(a._data, b._data)
def test_rank_object_first(self, frame_or_series, na_option, ascending, expected):
obj = frame_or_series(["foo", "foo", None, "foo"])
result = obj.rank(method="first", na_option=na_option, ascending=ascending)
expected = frame_or_series(expected)
tm.assert_equal(result, expected)
def test_numpy_zero_dim_ndarray(other):
arr = integer_array([1, None, 2])
result = arr + np.array(other)
expected = arr + other
tm.assert_equal(result, expected)
def test_transpose(index_or_series_obj):
obj = index_or_series_obj
tm.assert_equal(obj.transpose(), obj)
def test_ufunc_coercions(self, holder):
idx = holder([1, 2, 3, 4, 5], name="x")
box = pd.Series if holder is pd.Series else pd.Index
result = np.sqrt(idx)
assert result.dtype == "f8" and isinstance(result, box)
exp = pd.Float64Index(np.sqrt(np.array([1, 2, 3, 4, 5])), name="x")
exp = tm.box_expected(exp, box)
tm.assert_equal(result, exp)
result = np.divide(idx, 2.0)
assert result.dtype == "f8" and isinstance(result, box)
exp = pd.Float64Index([0.5, 1.0, 1.5, 2.0, 2.5], name="x")
exp = tm.box_expected(exp, box)
tm.assert_equal(result, exp)
# _evaluate_numeric_binop
result = idx + 2.0
assert result.dtype == "f8" and isinstance(result, box)
exp = pd.Float64Index([3.0, 4.0, 5.0, 6.0, 7.0], name="x")
exp = tm.box_expected(exp, box)
tm.assert_equal(result, exp)
result = idx - 2.0
assert result.dtype == "f8" and isinstance(result, box)
exp = pd.Float64Index([-1.0, 0.0, 1.0, 2.0, 3.0], name="x")
exp = tm.box_expected(exp, box)
tm.assert_equal(result, exp)
result = idx * 1.0
assert result.dtype == "f8" and isinstance(result, box)
exp = pd.Float64Index([1.0, 2.0, 3.0, 4.0, 5.0], name="x")
exp = tm.box_expected(exp, box)
tm.assert_equal(result, exp)
result = idx / 2.0
assert result.dtype == "f8" and isinstance(result, box)
exp = pd.Float64Index([0.5, 1.0, 1.5, 2.0, 2.5], name="x")
exp = tm.box_expected(exp, box)
tm.assert_equal(result, exp)
def test_where_inplace_casting(data):
# GH 22051
df = DataFrame({"a": data})
df_copy = df.where(pd.notnull(df), None).copy()
df.where(pd.notnull(df), None, inplace=True)
tm.assert_equal(df, df_copy)
def test_logical_operators_nans(self, left, right, op, expected, frame_or_series):
# GH#13896
result = op(frame_or_series(left), frame_or_series(right))
expected = frame_or_series(expected)
tm.assert_equal(result, expected)
def test_array_inference(data, expected):
result = pd.array(data)
tm.assert_equal(result, expected)
def test_array(data, dtype, expected):
result = pd.array(data, dtype=dtype)
tm.assert_equal(result, expected)
def test_numpy_transpose(self, index_or_series_obj):
obj = index_or_series_obj
tm.assert_equal(np.transpose(obj), obj)
with pytest.raises(ValueError, match=self.errmsg):
np.transpose(obj, axes=1)
def test_sample_none_weights(self, obj):
# Check None are also replaced by zeros.
weights_with_None = [None] * 10
weights_with_None[5] = 0.5
tm.assert_equal(obj.sample(n=1, axis=0, weights=weights_with_None),
obj.iloc[5:6])
def test_mul_int_identity(self, op, numeric_idx, box_with_array):
idx = numeric_idx
idx = tm.box_expected(idx, box_with_array)
result = op(idx, 1)
tm.assert_equal(result, idx)
def test_sample(self, test, obj):
# Fixes issue: 2419
# Check behavior of random_state argument
# Check for stability when receives seed or random state -- run 10
# times.
seed = np.random.randint(0, 100)
tm.assert_equal(obj.sample(n=4, random_state=seed),
obj.sample(n=4, random_state=seed))
tm.assert_equal(
obj.sample(frac=0.7, random_state=seed),
obj.sample(frac=0.7, random_state=seed),
)
tm.assert_equal(
obj.sample(n=4, random_state=np.random.RandomState(test)),
obj.sample(n=4, random_state=np.random.RandomState(test)),
)
tm.assert_equal(
obj.sample(frac=0.7, random_state=np.random.RandomState(test)),
obj.sample(frac=0.7, random_state=np.random.RandomState(test)),
)
tm.assert_equal(
obj.sample(frac=2,
replace=True,
random_state=np.random.RandomState(test)),
obj.sample(frac=2,
replace=True,
random_state=np.random.RandomState(test)),
)
os1, os2 = [], []
for _ in range(2):
np.random.seed(test)
os1.append(obj.sample(n=4))
os2.append(obj.sample(frac=0.7))
tm.assert_equal(*os1)
tm.assert_equal(*os2)
def test_dt_accessor_api_for_categorical(self):
# https://github.com/pandas-dev/pandas/issues/10661
s_dr = Series(date_range("1/1/2015", periods=5, tz="MET"))
c_dr = s_dr.astype("category")
s_pr = Series(period_range("1/1/2015", freq="D", periods=5))
c_pr = s_pr.astype("category")
s_tdr = Series(timedelta_range("1 days", "10 days"))
c_tdr = s_tdr.astype("category")
# only testing field (like .day)
# and bool (is_month_start)
get_ops = lambda x: x._datetimelike_ops
test_data = [
("Datetime", get_ops(DatetimeArray), s_dr, c_dr),
("Period", get_ops(PeriodArray), s_pr, c_pr),
("Timedelta", get_ops(TimedeltaArray), s_tdr, c_tdr),
]
assert isinstance(c_dr.dt, Properties)
special_func_defs = [
("strftime", ("%Y-%m-%d", ), {}),
("tz_convert", ("EST", ), {}),
("round", ("D", ), {}),
("floor", ("D", ), {}),
("ceil", ("D", ), {}),
("asfreq", ("D", ), {}),
# FIXME: don't leave commented-out
# ('tz_localize', ("UTC",), {}),
]
_special_func_names = [f[0] for f in special_func_defs]
# the series is already localized
_ignore_names = ["tz_localize", "components"]
for name, attr_names, s, c in test_data:
func_names = [
f for f in dir(s.dt)
if not (f.startswith("_") or f in attr_names
or f in _special_func_names or f in _ignore_names)
]
func_defs = [(f, (), {}) for f in func_names]
for f_def in special_func_defs:
if f_def[0] in dir(s.dt):
func_defs.append(f_def)
for func, args, kwargs in func_defs:
with warnings.catch_warnings():
if func == "to_period":
# dropping TZ
warnings.simplefilter("ignore", UserWarning)
res = getattr(c.dt, func)(*args, **kwargs)
exp = getattr(s.dt, func)(*args, **kwargs)
tm.assert_equal(res, exp)
for attr in attr_names:
if attr in ["week", "weekofyear"]:
# GH#33595 Deprecate week and weekofyear
continue
res = getattr(c.dt, attr)
exp = getattr(s.dt, attr)
if isinstance(res, DataFrame):
tm.assert_frame_equal(res, exp)
elif isinstance(res, Series):
tm.assert_series_equal(res, exp)
else:
tm.assert_almost_equal(res, exp)
invalid = Series([1, 2, 3]).astype("category")
msg = "Can only use .dt accessor with datetimelike"
with pytest.raises(AttributeError, match=msg):
invalid.dt
assert not hasattr(invalid, "str")
def test_s3_protocols(s3_resource, tips_file, protocol, s3so):
tm.assert_equal(
read_csv("%s://pandas-test/tips.csv" % protocol, storage_options=s3so),
read_csv(tips_file),
)
def test_replace_extension_other(self, frame_or_series):
# https://github.com/pandas-dev/pandas/issues/34530
obj = frame_or_series(pd.array([1, 2, 3], dtype="Int64"))
result = obj.replace("", "") # no exception
# should not have changed dtype
tm.assert_equal(obj, result)
def test_reindex_empty_series_tz_dtype():
# GH 20869
result = Series(dtype="datetime64[ns, UTC]").reindex([0, 1])
expected = Series([NaT] * 2, dtype="datetime64[ns, UTC]")
tm.assert_equal(result, expected)
def test_expanding_count_with_min_periods_exceeding_series_length(
frame_or_series):
# GH 25857
result = frame_or_series(range(5)).expanding(min_periods=6).count()
expected = frame_or_series([np.nan, np.nan, np.nan, np.nan, np.nan])
tm.assert_equal(result, expected)
def test_rolling_count_with_min_periods(constructor):
# GH 26996
result = constructor(range(5)).rolling(3, min_periods=3).count()
expected = constructor([np.nan, np.nan, 3.0, 3.0, 3.0])
tm.assert_equal(result, expected)
def test_arith_zero_dim_ndarray(other):
arr = pd.array([1, None, 2], dtype="Float64")
result = arr + np.array(other)
expected = arr + other
tm.assert_equal(result, expected)
def test_timedelta_fillna(self, frame_or_series):
# GH#3371
ser = Series([
Timestamp("20130101"),
Timestamp("20130101"),
Timestamp("20130102"),
Timestamp("20130103 9:01:01"),
])
td = ser.diff()
obj = frame_or_series(td)
# reg fillna
result = obj.fillna(Timedelta(seconds=0))
expected = Series([
timedelta(0),
timedelta(0),
timedelta(1),
timedelta(days=1, seconds=9 * 3600 + 60 + 1),
])
expected = frame_or_series(expected)
tm.assert_equal(result, expected)
# interpreted as seconds, no longer supported
msg = "value should be a 'Timedelta', 'NaT', or array of those. Got 'int'"
with pytest.raises(TypeError, match=msg):
obj.fillna(1)
result = obj.fillna(Timedelta(seconds=1))
expected = Series([
timedelta(seconds=1),
timedelta(0),
timedelta(1),
timedelta(days=1, seconds=9 * 3600 + 60 + 1),
])
expected = frame_or_series(expected)
tm.assert_equal(result, expected)
result = obj.fillna(timedelta(days=1, seconds=1))
expected = Series([
timedelta(days=1, seconds=1),
timedelta(0),
timedelta(1),
timedelta(days=1, seconds=9 * 3600 + 60 + 1),
])
expected = frame_or_series(expected)
tm.assert_equal(result, expected)
result = obj.fillna(np.timedelta64(10**9))
expected = Series([
timedelta(seconds=1),
timedelta(0),
timedelta(1),
timedelta(days=1, seconds=9 * 3600 + 60 + 1),
])
expected = frame_or_series(expected)
tm.assert_equal(result, expected)
result = obj.fillna(NaT)
expected = Series(
[
NaT,
timedelta(0),
timedelta(1),
timedelta(days=1, seconds=9 * 3600 + 60 + 1),
],
dtype="m8[ns]",
)
expected = frame_or_series(expected)
tm.assert_equal(result, expected)
# ffill
td[2] = np.nan
obj = frame_or_series(td)
result = obj.ffill()
expected = td.fillna(Timedelta(seconds=0))
expected[0] = np.nan
expected = frame_or_series(expected)
tm.assert_equal(result, expected)
# bfill
td[2] = np.nan
obj = frame_or_series(td)
result = obj.bfill()
expected = td.fillna(Timedelta(seconds=0))
expected[2] = timedelta(days=1, seconds=9 * 3600 + 60 + 1)
expected = frame_or_series(expected)
tm.assert_equal(result, expected)
def test_timedelta_fillna(self, frame_or_series):
# GH#3371
ser = Series(
[
Timestamp("20130101"),
Timestamp("20130101"),
Timestamp("20130102"),
Timestamp("20130103 9:01:01"),
]
)
td = ser.diff()
obj = frame_or_series(td)
# reg fillna
result = obj.fillna(Timedelta(seconds=0))
expected = Series(
[
timedelta(0),
timedelta(0),
timedelta(1),
timedelta(days=1, seconds=9 * 3600 + 60 + 1),
]
)
expected = frame_or_series(expected)
tm.assert_equal(result, expected)
# interpreted as seconds, deprecated
with pytest.raises(TypeError, match="Passing integers to fillna"):
obj.fillna(1)
result = obj.fillna(Timedelta(seconds=1))
expected = Series(
[
timedelta(seconds=1),
timedelta(0),
timedelta(1),
timedelta(days=1, seconds=9 * 3600 + 60 + 1),
]
)
expected = frame_or_series(expected)
tm.assert_equal(result, expected)
result = obj.fillna(timedelta(days=1, seconds=1))
expected = Series(
[
timedelta(days=1, seconds=1),
timedelta(0),
timedelta(1),
timedelta(days=1, seconds=9 * 3600 + 60 + 1),
]
)
expected = frame_or_series(expected)
tm.assert_equal(result, expected)
result = obj.fillna(np.timedelta64(10 ** 9))
expected = Series(
[
timedelta(seconds=1),
timedelta(0),
timedelta(1),
timedelta(days=1, seconds=9 * 3600 + 60 + 1),
]
)
expected = frame_or_series(expected)
tm.assert_equal(result, expected)
result = obj.fillna(NaT)
expected = Series(
[
NaT,
timedelta(0),
timedelta(1),
timedelta(days=1, seconds=9 * 3600 + 60 + 1),
],
dtype="m8[ns]",
)
expected = frame_or_series(expected)
tm.assert_equal(result, expected)
# ffill
td[2] = np.nan
obj = frame_or_series(td)
result = obj.ffill()
expected = td.fillna(Timedelta(seconds=0))
expected[0] = np.nan
expected = frame_or_series(expected)
tm.assert_equal(result, expected)
# bfill
td[2] = np.nan
obj = frame_or_series(td)
result = obj.bfill()
expected = td.fillna(Timedelta(seconds=0))
expected[2] = timedelta(days=1, seconds=9 * 3600 + 60 + 1)
expected = frame_or_series(expected)
tm.assert_equal(result, expected)
def test_rolling_count_with_min_periods(frame_or_series):
# GH 26996
result = frame_or_series(range(5)).rolling(3, min_periods=3).count()
expected = frame_or_series([np.nan, np.nan, 3.0, 3.0, 3.0])
tm.assert_equal(result, expected)
def test_between_time(self, close_open_fixture, frame_or_series):
rng = date_range("1/1/2000", "1/5/2000", freq="5min")
ts = DataFrame(np.random.randn(len(rng), 2), index=rng)
if frame_or_series is not DataFrame:
ts = ts[0]
stime = time(0, 0)
etime = time(1, 0)
inc_start, inc_end = close_open_fixture
filtered = ts.between_time(stime, etime, inc_start, inc_end)
exp_len = 13 * 4 + 1
if not inc_start:
exp_len -= 5
if not inc_end:
exp_len -= 4
assert len(filtered) == exp_len
for rs in filtered.index:
t = rs.time()
if inc_start:
assert t >= stime
else:
assert t > stime
if inc_end:
assert t <= etime
else:
assert t < etime
result = ts.between_time("00:00", "01:00")
expected = ts.between_time(stime, etime)
tm.assert_equal(result, expected)
# across midnight
rng = date_range("1/1/2000", "1/5/2000", freq="5min")
ts = DataFrame(np.random.randn(len(rng), 2), index=rng)
if frame_or_series is not DataFrame:
ts = ts[0]
stime = time(22, 0)
etime = time(9, 0)
filtered = ts.between_time(stime, etime, inc_start, inc_end)
exp_len = (12 * 11 + 1) * 4 + 1
if not inc_start:
exp_len -= 4
if not inc_end:
exp_len -= 4
assert len(filtered) == exp_len
for rs in filtered.index:
t = rs.time()
if inc_start:
assert (t >= stime) or (t <= etime)
else:
assert (t > stime) or (t <= etime)
if inc_end:
assert (t <= etime) or (t >= stime)
else:
assert (t < etime) or (t >= stime)
def test_truncate(self, datetime_frame, frame_or_series):
ts = datetime_frame[::3]
ts = tm.get_obj(ts, frame_or_series)
start, end = datetime_frame.index[3], datetime_frame.index[6]
start_missing = datetime_frame.index[2]
end_missing = datetime_frame.index[7]
# neither specified
truncated = ts.truncate()
tm.assert_equal(truncated, ts)
# both specified
expected = ts[1:3]
truncated = ts.truncate(start, end)
tm.assert_equal(truncated, expected)
truncated = ts.truncate(start_missing, end_missing)
tm.assert_equal(truncated, expected)
# start specified
expected = ts[1:]
truncated = ts.truncate(before=start)
tm.assert_equal(truncated, expected)
truncated = ts.truncate(before=start_missing)
tm.assert_equal(truncated, expected)
# end specified
expected = ts[:3]
truncated = ts.truncate(after=end)
tm.assert_equal(truncated, expected)
truncated = ts.truncate(after=end_missing)
tm.assert_equal(truncated, expected)
# corner case, empty series/frame returned
truncated = ts.truncate(after=ts.index[0] - ts.index.freq)
assert len(truncated) == 0
truncated = ts.truncate(before=ts.index[-1] + ts.index.freq)
assert len(truncated) == 0
msg = "Truncate: 2000-01-06 00:00:00 must be after 2000-02-04 00:00:00"
with pytest.raises(ValueError, match=msg):
ts.truncate(before=ts.index[-1] - ts.index.freq,
after=ts.index[0] + ts.index.freq)
def test_transpose(self):
for obj in self.objs:
tm.assert_equal(obj.transpose(), obj)
