def test_conv_read_write(setup_path):
with tm.ensure_clean() as path:
def roundtrip(key, obj, **kwargs):
obj.to_hdf(path, key, **kwargs)
return read_hdf(path, key)
o = tm.makeTimeSeries()
tm.assert_series_equal(o, roundtrip("series", o))
o = tm.makeStringSeries()
tm.assert_series_equal(o, roundtrip("string_series", o))
o = tm.makeDataFrame()
tm.assert_frame_equal(o, roundtrip("frame", o))
# table
df = DataFrame({"A": range(5), "B": range(5)})
df.to_hdf(path, "table", append=True)
result = read_hdf(path, "table", where=["index>2"])
tm.assert_frame_equal(df[df.index > 2], result)
def test_squeeze(self):
# noop
for s in [
tm.makeFloatSeries(),
tm.makeStringSeries(),
tm.makeObjectSeries()
]:
tm.assert_series_equal(s.squeeze(), s)
for df in [tm.makeTimeDataFrame()]:
tm.assert_frame_equal(df.squeeze(), df)
# squeezing
df = tm.makeTimeDataFrame().reindex(columns=["A"])
tm.assert_series_equal(df.squeeze(), df["A"])
# don't fail with 0 length dimensions GH11229 & GH8999
empty_series = Series([], name="five", dtype=np.float64)
empty_frame = DataFrame([empty_series])
tm.assert_series_equal(empty_series, empty_series.squeeze())
tm.assert_series_equal(empty_series, empty_frame.squeeze())
# axis argument
df = tm.makeTimeDataFrame(nper=1).iloc[:, :1]
assert df.shape == (1, 1)
tm.assert_series_equal(df.squeeze(axis=0), df.iloc[0])
tm.assert_series_equal(df.squeeze(axis="index"), df.iloc[0])
tm.assert_series_equal(df.squeeze(axis=1), df.iloc[:, 0])
tm.assert_series_equal(df.squeeze(axis="columns"), df.iloc[:, 0])
assert df.squeeze() == df.iloc[0, 0]
msg = "No axis named 2 for object type DataFrame"
with pytest.raises(ValueError, match=msg):
df.squeeze(axis=2)
msg = "No axis named x for object type DataFrame"
with pytest.raises(ValueError, match=msg):
df.squeeze(axis="x")
df = tm.makeTimeDataFrame(3)
tm.assert_frame_equal(df.squeeze(axis=0), df)
def test_invert(self):
ser = tm.makeStringSeries()
ser.name = "series"
tm.assert_series_equal(-(ser < 0), ~(ser < 0))
def test_neg(self):
ser = tm.makeStringSeries()
ser.name = "series"
tm.assert_series_equal(-ser, -1 * ser)
def test_transpose(self):
for s in [tm.makeFloatSeries(), tm.makeStringSeries(), tm.makeObjectSeries()]:
# calls implementation in pandas/core/base.py
tm.assert_series_equal(s.transpose(), s)
for df in [tm.makeTimeDataFrame()]:
tm.assert_frame_equal(df.transpose().transpose(), df)
def setup_method(self):
self.ts = tm.makeTimeSeries() # Was at top level in test_series
self.ts.name = "ts"
self.series = tm.makeStringSeries()
self.series.name = "series"
def test_max(self):
string_series = tm.makeStringSeries().rename("series")
self._check_stat_op("max", np.max, string_series, check_objects=True)
def test_prod(self):
string_series = tm.makeStringSeries().rename("series")
self._check_stat_op("prod", np.prod, string_series)
def test_mean(self):
string_series = tm.makeStringSeries().rename("series")
self._check_stat_op("mean", np.mean, string_series)
def test_sum(self):
string_series = tm.makeStringSeries().rename("series")
self._check_stat_op("sum", np.sum, string_series, check_allna=False)
class TestNDFrame:
# tests that don't fit elsewhere
@pytest.mark.parametrize(
"ser",
[tm.makeFloatSeries(),
tm.makeStringSeries(),
tm.makeObjectSeries()])
def test_squeeze_series_noop(self, ser):
# noop
tm.assert_series_equal(ser.squeeze(), ser)
def test_squeeze_frame_noop(self):
# noop
df = tm.makeTimeDataFrame()
tm.assert_frame_equal(df.squeeze(), df)
def test_squeeze_frame_reindex(self):
# squeezing
df = tm.makeTimeDataFrame().reindex(columns=["A"])
tm.assert_series_equal(df.squeeze(), df["A"])
def test_squeeze_0_len_dim(self):
# don't fail with 0 length dimensions GH11229 & GH8999
empty_series = Series([], name="five", dtype=np.float64)
empty_frame = DataFrame([empty_series])
tm.assert_series_equal(empty_series, empty_series.squeeze())
tm.assert_series_equal(empty_series, empty_frame.squeeze())
def test_squeeze_axis(self):
# axis argument
df = tm.makeTimeDataFrame(nper=1).iloc[:, :1]
assert df.shape == (1, 1)
tm.assert_series_equal(df.squeeze(axis=0), df.iloc[0])
tm.assert_series_equal(df.squeeze(axis="index"), df.iloc[0])
tm.assert_series_equal(df.squeeze(axis=1), df.iloc[:, 0])
tm.assert_series_equal(df.squeeze(axis="columns"), df.iloc[:, 0])
assert df.squeeze() == df.iloc[0, 0]
msg = "No axis named 2 for object type DataFrame"
with pytest.raises(ValueError, match=msg):
df.squeeze(axis=2)
msg = "No axis named x for object type DataFrame"
with pytest.raises(ValueError, match=msg):
df.squeeze(axis="x")
def test_squeeze_axis_len_3(self):
df = tm.makeTimeDataFrame(3)
tm.assert_frame_equal(df.squeeze(axis=0), df)
def test_numpy_squeeze(self):
s = tm.makeFloatSeries()
tm.assert_series_equal(np.squeeze(s), s)
df = tm.makeTimeDataFrame().reindex(columns=["A"])
tm.assert_series_equal(np.squeeze(df), df["A"])
@pytest.mark.parametrize(
"ser",
[tm.makeFloatSeries(),
tm.makeStringSeries(),
tm.makeObjectSeries()])
def test_transpose_series(self, ser):
# calls implementation in pandas/core/base.py
tm.assert_series_equal(ser.transpose(), ser)
def test_transpose_frame(self):
df = tm.makeTimeDataFrame()
tm.assert_frame_equal(df.transpose().transpose(), df)
def test_numpy_transpose(self, frame_or_series):
obj = tm.makeTimeDataFrame()
obj = tm.get_obj(obj, frame_or_series)
if frame_or_series is Series:
# 1D -> np.transpose is no-op
tm.assert_series_equal(np.transpose(obj), obj)
# round-trip preserved
tm.assert_equal(np.transpose(np.transpose(obj)), obj)
msg = "the 'axes' parameter is not supported"
with pytest.raises(ValueError, match=msg):
np.transpose(obj, axes=1)
@pytest.mark.parametrize(
"ser",
[tm.makeFloatSeries(),
tm.makeStringSeries(),
tm.makeObjectSeries()])
def test_take_series(self, ser):
indices = [1, 5, -2, 6, 3, -1]
out = ser.take(indices)
expected = Series(
data=ser.values.take(indices),
index=ser.index.take(indices),
dtype=ser.dtype,
)
tm.assert_series_equal(out, expected)
def test_take_frame(self):
indices = [1, 5, -2, 6, 3, -1]
df = tm.makeTimeDataFrame()
out = df.take(indices)
expected = DataFrame(
data=df.values.take(indices, axis=0),
index=df.index.take(indices),
columns=df.columns,
)
tm.assert_frame_equal(out, expected)
def test_take_invalid_kwargs(self, frame_or_series):
indices = [-3, 2, 0, 1]
obj = tm.makeTimeDataFrame()
obj = tm.get_obj(obj, frame_or_series)
msg = r"take\(\) got an unexpected keyword argument 'foo'"
with pytest.raises(TypeError, match=msg):
obj.take(indices, foo=2)
msg = "the 'out' parameter is not supported"
with pytest.raises(ValueError, match=msg):
obj.take(indices, out=indices)
msg = "the 'mode' parameter is not supported"
with pytest.raises(ValueError, match=msg):
obj.take(indices, mode="clip")
@pytest.mark.parametrize("is_copy", [True, False])
def test_depr_take_kwarg_is_copy(self, is_copy, frame_or_series):
# GH 27357
obj = DataFrame({"A": [1, 2, 3]})
obj = tm.get_obj(obj, frame_or_series)
msg = (
"is_copy is deprecated and will be removed in a future version. "
"'take' always returns a copy, so there is no need to specify this."
)
with tm.assert_produces_warning(FutureWarning) as w:
obj.take([0, 1], is_copy=is_copy)
assert w[0].message.args[0] == msg
def test_axis_classmethods(self, frame_or_series):
box = frame_or_series
obj = box(dtype=object)
values = box._AXIS_TO_AXIS_NUMBER.keys()
for v in values:
assert obj._get_axis_number(v) == box._get_axis_number(v)
assert obj._get_axis_name(v) == box._get_axis_name(v)
assert obj._get_block_manager_axis(
v) == box._get_block_manager_axis(v)
def test_axis_names_deprecated(self, frame_or_series):
# GH33637
box = frame_or_series
obj = box(dtype=object)
msg = "_AXIS_NAMES has been deprecated"
with tm.assert_produces_warning(FutureWarning, match=msg):
obj._AXIS_NAMES
def test_axis_numbers_deprecated(self, frame_or_series):
# GH33637
box = frame_or_series
obj = box(dtype=object)
msg = "_AXIS_NUMBERS has been deprecated"
with tm.assert_produces_warning(FutureWarning, match=msg):
obj._AXIS_NUMBERS
def test_flags_identity(self, frame_or_series):
obj = Series([1, 2])
if frame_or_series is DataFrame:
obj = obj.to_frame()
assert obj.flags is obj.flags
obj2 = obj.copy()
assert obj2.flags is not obj.flags
def test_slice_shift_deprecated(self, frame_or_series):
# GH 37601
obj = DataFrame({"A": [1, 2, 3, 4]})
obj = tm.get_obj(obj, frame_or_series)
with tm.assert_produces_warning(FutureWarning):
obj.slice_shift()
def series():
return tm.makeStringSeries(name="series")
with cf.option_context("mode.use_inf_as_na", True):
assert not notna_f(np.inf)
assert not notna_f(-np.inf)
arr = np.array([1.5, np.inf, 3.5, -np.inf])
result = notna_f(arr)
assert result.sum() == 2
@pytest.mark.parametrize("null_func", [notna, notnull, isna, isnull])
@pytest.mark.parametrize(
"ser",
[
tm.makeFloatSeries(),
tm.makeStringSeries(),
tm.makeObjectSeries(),
tm.makeTimeSeries(),
tm.makePeriodSeries(),
],
)
def test_null_check_is_series(null_func, ser):
with cf.option_context("mode.use_inf_as_na", False):
assert isinstance(null_func(ser), Series)
class TestIsNA:
def test_0d_array(self):
assert isna(np.array(np.nan))
assert not isna(np.array(0.0))
assert not isna(np.array(0))
