Skip to content

TST: parametrize and de-duplicate timedelta64 arithmetic tests #32091

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 8 commits into from
Feb 23, 2020
Merged

TST: parametrize and de-duplicate timedelta64 arithmetic tests #32091

Changes from 6 commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
de24c54
TST: parametrize
jbrockmendel Feb 19, 2020
13d0381
TST: parametrize td64 arith test
jbrockmendel Feb 19, 2020
8444f9c
CLN/TST: de-duplicate tests
jbrockmendel Feb 19, 2020
9c35132
CLN/TST: de-duplicate, make sure we test reversed ops
jbrockmendel Feb 19, 2020
3d41254
de-duplicate tests
jbrockmendel Feb 19, 2020
3ce2686
Merge branch 'master' of https://github.com/pandas-dev/pandas into ts…
jbrockmendel Feb 19, 2020
d927ca9
Merge branch 'master' of https://github.com/pandas-dev/pandas into ts…
jbrockmendel Feb 22, 2020
4b6f51f
_get_dtype -> assert_dtype
jbrockmendel Feb 22, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
209 changes: 68 additions & 141 deletions pandas/tests/arithmetic/test_timedelta64.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,16 @@
get_upcast_box,
)


def _get_dtype(obj):
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

maybe better to pass a dtype and then call this assert_dtype ?

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

changed

"""
Helper to get the dtype for a Series, Index, or single-column DataFrame.
"""
if isinstance(obj, DataFrame):
return obj.dtypes.iat[0]
return obj.dtype


# ------------------------------------------------------------------
# Timedelta64[ns] dtype Comparisons

Expand Down Expand Up @@ -522,19 +532,35 @@ def test_tda_add_sub_index(self):
# -------------------------------------------------------------
# Binary operations TimedeltaIndex and timedelta-like

def test_tdi_iadd_timedeltalike(self, two_hours):
def test_tdi_iadd_timedeltalike(self, two_hours, box_with_array):
# only test adding/sub offsets as + is now numeric
rng = timedelta_range("1 days", "10 days")
expected = timedelta_range("1 days 02:00:00", "10 days 02:00:00", freq="D")

rng = tm.box_expected(rng, box_with_array)
expected = tm.box_expected(expected, box_with_array)

orig_rng = rng
rng += two_hours
tm.assert_index_equal(rng, expected)
tm.assert_equal(rng, expected)
if box_with_array is not pd.Index:
# Check that operation is actually inplace
tm.assert_equal(orig_rng, expected)

def test_tdi_isub_timedeltalike(self, two_hours):
def test_tdi_isub_timedeltalike(self, two_hours, box_with_array):
# only test adding/sub offsets as - is now numeric
rng = timedelta_range("1 days", "10 days")
expected = timedelta_range("0 days 22:00:00", "9 days 22:00:00")

rng = tm.box_expected(rng, box_with_array)
expected = tm.box_expected(expected, box_with_array)

orig_rng = rng
rng -= two_hours
tm.assert_index_equal(rng, expected)
tm.assert_equal(rng, expected)
if box_with_array is not pd.Index:
# Check that operation is actually inplace
tm.assert_equal(orig_rng, expected)

# -------------------------------------------------------------

Expand Down Expand Up @@ -1013,15 +1039,6 @@ def test_td64arr_add_datetime64_nat(self, box_with_array):
# ------------------------------------------------------------------
# Invalid __add__/__sub__ operations

# TODO: moved from frame tests; needs parametrization/de-duplication
def test_td64_df_add_int_frame(self):
# GH#22696 Check that we don't dispatch to numpy implementation,
# which treats int64 as m8[ns]
tdi = pd.timedelta_range("1", periods=3)
df = tdi.to_frame()
other = pd.DataFrame([1, 2, 3], index=tdi) # indexed like `df`
assert_invalid_addsub_type(df, other)

@pytest.mark.parametrize("pi_freq", ["D", "W", "Q", "H"])
@pytest.mark.parametrize("tdi_freq", [None, "H"])
def test_td64arr_sub_periodlike(self, box_with_array, tdi_freq, pi_freq):
Expand Down Expand Up @@ -1100,6 +1117,9 @@ def test_td64arr_add_sub_int(self, box_with_array, one):

def test_td64arr_add_sub_integer_array(self, box_with_array):
# GH#19959, deprecated GH#22535
# GH#22696 for DataFrame case, check that we don't dispatch to numpy
# implementation, which treats int64 as m8[ns]

rng = timedelta_range("1 days 09:00:00", freq="H", periods=3)
tdarr = tm.box_expected(rng, box_with_array)
other = tm.box_expected([4, 3, 2], box_with_array)
Expand All @@ -1119,60 +1139,6 @@ def test_td64arr_addsub_integer_array_no_freq(self, box_with_array):
# ------------------------------------------------------------------
# Operations with timedelta-like others

# TODO: this was taken from tests.series.test_ops; de-duplicate
def test_operators_timedelta64_with_timedelta(self, scalar_td):
# smoke tests
td1 = Series([timedelta(minutes=5, seconds=3)] * 3)
td1.iloc[2] = np.nan

td1 + scalar_td
scalar_td + td1
td1 - scalar_td
scalar_td - td1
td1 / scalar_td
scalar_td / td1

# TODO: this was taken from tests.series.test_ops; de-duplicate
def test_timedelta64_operations_with_timedeltas(self):
# td operate with td
td1 = Series([timedelta(minutes=5, seconds=3)] * 3)
td2 = timedelta(minutes=5, seconds=4)
result = td1 - td2
expected = Series([timedelta(seconds=0)] * 3) - Series(
[timedelta(seconds=1)] * 3
)
assert result.dtype == "m8[ns]"
tm.assert_series_equal(result, expected)

result2 = td2 - td1
expected = Series([timedelta(seconds=1)] * 3) - Series(
[timedelta(seconds=0)] * 3
)
tm.assert_series_equal(result2, expected)

# roundtrip
tm.assert_series_equal(result + td2, td1)

# Now again, using pd.to_timedelta, which should build
# a Series or a scalar, depending on input.
td1 = Series(pd.to_timedelta(["00:05:03"] * 3))
td2 = pd.to_timedelta("00:05:04")
result = td1 - td2
expected = Series([timedelta(seconds=0)] * 3) - Series(
[timedelta(seconds=1)] * 3
)
assert result.dtype == "m8[ns]"
tm.assert_series_equal(result, expected)

result2 = td2 - td1
expected = Series([timedelta(seconds=1)] * 3) - Series(
[timedelta(seconds=0)] * 3
)
tm.assert_series_equal(result2, expected)

# roundtrip
tm.assert_series_equal(result + td2, td1)

def test_td64arr_add_td64_array(self, box_with_array):
box = box_with_array
dti = pd.date_range("2016-01-01", periods=3)
Expand Down Expand Up @@ -1203,7 +1169,6 @@ def test_td64arr_sub_td64_array(self, box_with_array):
result = tdarr - tdi
tm.assert_equal(result, expected)

# TODO: parametrize over [add, sub, radd, rsub]?
@pytest.mark.parametrize(
"names",
[
Expand Down Expand Up @@ -1232,17 +1197,11 @@ def test_td64arr_add_sub_tdi(self, box, names):

result = tdi + ser
tm.assert_equal(result, expected)
if box is not pd.DataFrame:
assert result.dtype == "timedelta64[ns]"
else:
assert result.dtypes[0] == "timedelta64[ns]"
assert _get_dtype(result) == "timedelta64[ns]"

result = ser + tdi
tm.assert_equal(result, expected)
if box is not pd.DataFrame:
assert result.dtype == "timedelta64[ns]"
else:
assert result.dtypes[0] == "timedelta64[ns]"
assert _get_dtype(result) == "timedelta64[ns]"

expected = Series(
[Timedelta(hours=-3), Timedelta(days=1, hours=-4)], name=names[2]
Expand All @@ -1251,17 +1210,11 @@ def test_td64arr_add_sub_tdi(self, box, names):

result = tdi - ser
tm.assert_equal(result, expected)
if box is not pd.DataFrame:
assert result.dtype == "timedelta64[ns]"
else:
assert result.dtypes[0] == "timedelta64[ns]"
assert _get_dtype(result) == "timedelta64[ns]"

result = ser - tdi
tm.assert_equal(result, -expected)
if box is not pd.DataFrame:
assert result.dtype == "timedelta64[ns]"
else:
assert result.dtypes[0] == "timedelta64[ns]"
assert _get_dtype(result) == "timedelta64[ns]"

def test_td64arr_add_sub_td64_nat(self, box_with_array):
# GH#23320 special handling for timedelta64("NaT")
Expand Down Expand Up @@ -1296,6 +1249,7 @@ def test_td64arr_sub_NaT(self, box_with_array):

def test_td64arr_add_timedeltalike(self, two_hours, box_with_array):
# only test adding/sub offsets as + is now numeric
# GH#10699 for Tick cases
box = box_with_array
rng = timedelta_range("1 days", "10 days")
expected = timedelta_range("1 days 02:00:00", "10 days 02:00:00", freq="D")
Expand All @@ -1305,8 +1259,12 @@ def test_td64arr_add_timedeltalike(self, two_hours, box_with_array):
result = rng + two_hours
tm.assert_equal(result, expected)

result = two_hours + rng
tm.assert_equal(result, expected)

def test_td64arr_sub_timedeltalike(self, two_hours, box_with_array):
# only test adding/sub offsets as - is now numeric
# GH#10699 for Tick cases
box = box_with_array
rng = timedelta_range("1 days", "10 days")
expected = timedelta_range("0 days 22:00:00", "9 days 22:00:00")
Expand All @@ -1317,46 +1275,12 @@ def test_td64arr_sub_timedeltalike(self, two_hours, box_with_array):
result = rng - two_hours
tm.assert_equal(result, expected)

result = two_hours - rng
tm.assert_equal(result, -expected)

# ------------------------------------------------------------------
# __add__/__sub__ with DateOffsets and arrays of DateOffsets

# TODO: this was taken from tests.series.test_operators; de-duplicate
def test_timedelta64_operations_with_DateOffset(self):
# GH#10699
td = Series([timedelta(minutes=5, seconds=3)] * 3)
result = td + pd.offsets.Minute(1)
expected = Series([timedelta(minutes=6, seconds=3)] * 3)
tm.assert_series_equal(result, expected)

result = td - pd.offsets.Minute(1)
expected = Series([timedelta(minutes=4, seconds=3)] * 3)
tm.assert_series_equal(result, expected)

with tm.assert_produces_warning(PerformanceWarning):
result = td + Series(
[pd.offsets.Minute(1), pd.offsets.Second(3), pd.offsets.Hour(2)]
)
expected = Series(
[
timedelta(minutes=6, seconds=3),
timedelta(minutes=5, seconds=6),
timedelta(hours=2, minutes=5, seconds=3),
]
)
tm.assert_series_equal(result, expected)

result = td + pd.offsets.Minute(1) + pd.offsets.Second(12)
expected = Series([timedelta(minutes=6, seconds=15)] * 3)
tm.assert_series_equal(result, expected)

# valid DateOffsets
for do in ["Hour", "Minute", "Second", "Day", "Micro", "Milli", "Nano"]:
op = getattr(pd.offsets, do)
td + op(5)
op(5) + td
td - op(5)
op(5) - td

@pytest.mark.parametrize(
"names", [(None, None, None), ("foo", "bar", None), ("foo", "foo", "foo")]
)
Expand Down Expand Up @@ -1561,26 +1485,6 @@ class TestTimedeltaArraylikeMulDivOps:
# Tests for timedelta64[ns]
# __mul__, __rmul__, __div__, __rdiv__, __floordiv__, __rfloordiv__

# TODO: Moved from tests.series.test_operators; needs cleanup
@pytest.mark.parametrize("m", [1, 3, 10])
@pytest.mark.parametrize("unit", ["D", "h", "m", "s", "ms", "us", "ns"])
def test_timedelta64_conversions(self, m, unit):
startdate = Series(pd.date_range("2013-01-01", "2013-01-03"))
enddate = Series(pd.date_range("2013-03-01", "2013-03-03"))

ser = enddate - startdate
ser[2] = np.nan

# op
expected = Series([x / np.timedelta64(m, unit) for x in ser])
result = ser / np.timedelta64(m, unit)
tm.assert_series_equal(result, expected)

# reverse op
expected = Series([Timedelta(np.timedelta64(m, unit)) / x for x in ser])
result = np.timedelta64(m, unit) / ser
tm.assert_series_equal(result, expected)

# ------------------------------------------------------------------
# Multiplication
# organized with scalar others first, then array-like
Expand Down Expand Up @@ -1734,6 +1638,29 @@ def test_td64arr_div_tdlike_scalar(self, two_hours, box_with_array):
expected = 1 / expected
tm.assert_equal(result, expected)

@pytest.mark.parametrize("m", [1, 3, 10])
@pytest.mark.parametrize("unit", ["D", "h", "m", "s", "ms", "us", "ns"])
def test_td64arr_div_td64_scalar(self, m, unit, box_with_array):
startdate = Series(pd.date_range("2013-01-01", "2013-01-03"))
enddate = Series(pd.date_range("2013-03-01", "2013-03-03"))

ser = enddate - startdate
ser[2] = np.nan
flat = ser
ser = tm.box_expected(ser, box_with_array)

# op
expected = Series([x / np.timedelta64(m, unit) for x in flat])
expected = tm.box_expected(expected, box_with_array)
result = ser / np.timedelta64(m, unit)
tm.assert_equal(result, expected)

# reverse op
expected = Series([Timedelta(np.timedelta64(m, unit)) / x for x in flat])
expected = tm.box_expected(expected, box_with_array)
result = np.timedelta64(m, unit) / ser
tm.assert_equal(result, expected)

def test_td64arr_div_tdlike_scalar_with_nat(self, two_hours, box_with_array):
rng = TimedeltaIndex(["1 days", pd.NaT, "2 days"], name="foo")
expected = pd.Float64Index([12, np.nan, 24], name="foo")
Expand Down