def test_super_transform_called(self, mocker):
"""Test that BaseTransformer.transform called."""
df = d.create_datediff_test_df()
x = DateDifferenceTransformer(
column_lower="a",
column_upper="b",
new_column_name="Y",
units="Y",
copy=True,
verbose=False,
)
expected_call_args = {
0: {
"args": (d.create_datediff_test_df(), ),
"kwargs": {}
}
}
with h.assert_function_call(
mocker,
tubular.base.BaseTransformer,
"transform",
expected_call_args,
return_value=d.create_datediff_test_df(),
):
x.transform(df)
def test_attributes_unchanged_by_transform(self):
"""Test that attributes set in init are unchanged by the transform method."""
df = d.create_datediff_test_df()
x = SeriesDtMethodTransformer(
new_column_name="b_new",
pd_method_name="to_period",
column="b",
pd_method_kwargs={"freq": "M"},
)
x2 = SeriesDtMethodTransformer(
new_column_name="b_new",
pd_method_name="to_period",
column="b",
pd_method_kwargs={"freq": "M"},
)
x.transform(df)
assert (
x.new_column_name == x2.new_column_name
), "new_column_name changed by SeriesDtMethodTransformer.transform"
assert (
x.pd_method_name == x2.pd_method_name
), "pd_method_name changed by SeriesDtMethodTransformer.transform"
assert (x.columns == x2.columns
), "columns changed by SeriesDtMethodTransformer.transform"
assert (
x.pd_method_kwargs == x2.pd_method_kwargs
), "pd_method_kwargs changed by SeriesDtMethodTransformer.transform"
def expected_df_3():
"""Expected output of test_expected_output_callable."""
df = d.create_datediff_test_df()
df["b_new"] = df["b"].dt.to_period("M")
return df
def expected_df_2():
"""Expected output of test_expected_output_overwrite."""
df = d.create_datediff_test_df()
df["a"] = [1993, 2000, 2018, 2018, 2018, 2018, 2018, 1985]
return df
def test_super_transform_called(self, mocker):
"""Test that BaseTransformer.transform called."""
df = d.create_datediff_test_df()
x = SeriesDtMethodTransformer(new_column_name="a2",
pd_method_name="year",
column="a")
expected_call_args = {
0: {
"args": (d.create_datediff_test_df(), ),
"kwargs": {}
}
}
with h.assert_function_call(mocker, tubular.base.BaseTransformer,
"transform", expected_call_args):
x.transform(df)
def test_super_transform_call(self, mocker):
"""Test the call to BaseTransformer.transform is as expected."""
df = d.create_datediff_test_df()
to_dt = ToDatetimeTransformer(column="a", new_column_name="Y")
expected_call_args = {
0: {
"args": (d.create_datediff_test_df(), ),
"kwargs": {}
}
}
with h.assert_function_call(
mocker,
tubular.base.BaseTransformer,
"transform",
expected_call_args,
return_value=d.create_datediff_test_df(),
):
to_dt.transform(df)
class TestTransform(object):
"""Tests for DateDifferenceTransformer.transform()."""
def expected_df_1():
"""Expected output for test_expected_output_units_Y."""
df = pd.DataFrame({
"a": [
datetime.datetime(1993, 9, 27, 11, 58, 58),
datetime.datetime(2000, 3, 19, 12, 59, 59),
datetime.datetime(2018, 11, 10, 11, 59, 59),
datetime.datetime(2018, 10, 10, 11, 59, 59),
datetime.datetime(2018, 10, 10, 11, 59, 59),
datetime.datetime(2018, 10, 10, 10, 59, 59),
datetime.datetime(2018, 12, 10, 11, 59, 59),
datetime.datetime(1985, 7, 23, 11, 59, 59),
],
"b": [
datetime.datetime(2020, 5, 1, 12, 59, 59),
datetime.datetime(2019, 12, 25, 11, 58, 58),
datetime.datetime(2018, 11, 10, 11, 59, 59),
datetime.datetime(2018, 11, 10, 11, 59, 59),
datetime.datetime(2018, 9, 10, 9, 59, 59),
datetime.datetime(2015, 11, 10, 11, 59, 59),
datetime.datetime(2015, 11, 10, 12, 59, 59),
datetime.datetime(2015, 7, 23, 11, 59, 59),
],
"Y": [
26.59340677135105,
19.76757257798535,
0.0,
0.08487511721664373,
-0.08236536912690427,
-2.915756882984136,
-3.082769210410435,
29.999247075573077,
],
})
return df
def expected_df_2():
"""Expected output for test_expected_output_units_M."""
df = pd.DataFrame({
"a": [
datetime.datetime(1993, 9, 27, 11, 58, 58),
datetime.datetime(2000, 3, 19, 12, 59, 59),
datetime.datetime(2018, 11, 10, 11, 59, 59),
datetime.datetime(2018, 10, 10, 11, 59, 59),
datetime.datetime(2018, 10, 10, 11, 59, 59),
datetime.datetime(2018, 10, 10, 10, 59, 59),
datetime.datetime(2018, 12, 10, 11, 59, 59),
datetime.datetime(1985, 7, 23, 11, 59, 59),
],
"b": [
datetime.datetime(2020, 5, 1, 12, 59, 59),
datetime.datetime(2019, 12, 25, 11, 58, 58),
datetime.datetime(2018, 11, 10, 11, 59, 59),
datetime.datetime(2018, 11, 10, 11, 59, 59),
datetime.datetime(2018, 9, 10, 9, 59, 59),
datetime.datetime(2015, 11, 10, 11, 59, 59),
datetime.datetime(2015, 11, 10, 12, 59, 59),
datetime.datetime(2015, 7, 23, 11, 59, 59),
],
"M": [
319.12088125621256,
237.21087093582423,
0.0,
1.0185014065997249,
-0.9883844295228512,
-34.989082595809634,
-36.993230524925224,
359.9909649068769,
],
})
return df
def expected_df_3():
"""Expected output for test_expected_output_units_D."""
df = pd.DataFrame({
"a": [
datetime.datetime(1993, 9, 27, 11, 58, 58),
datetime.datetime(2000, 3, 19, 12, 59, 59),
datetime.datetime(2018, 11, 10, 11, 59, 59),
datetime.datetime(2018, 10, 10, 11, 59, 59),
datetime.datetime(2018, 10, 10, 11, 59, 59),
datetime.datetime(2018, 10, 10, 10, 59, 59),
datetime.datetime(2018, 12, 10, 11, 59, 59),
datetime.datetime(1985, 7, 23, 11, 59, 59),
],
"b": [
datetime.datetime(2020, 5, 1, 12, 59, 59),
datetime.datetime(2019, 12, 25, 11, 58, 58),
datetime.datetime(2018, 11, 10, 11, 59, 59),
datetime.datetime(2018, 11, 10, 11, 59, 59),
datetime.datetime(2018, 9, 10, 9, 59, 59),
datetime.datetime(2015, 11, 10, 11, 59, 59),
datetime.datetime(2015, 11, 10, 12, 59, 59),
datetime.datetime(2015, 7, 23, 11, 59, 59),
],
"D": [
9713.042372685186,
7219.957627314815,
0.0,
31.0,
-30.083333333333332,
-1064.9583333333333,
-1125.9583333333333,
10957.0,
],
})
return df
def expected_df_4():
"""Expected output for test_expected_output_units_h."""
df = pd.DataFrame({
"a": [
datetime.datetime(1993, 9, 27, 11, 58, 58),
datetime.datetime(2000, 3, 19, 12, 59, 59),
datetime.datetime(2018, 11, 10, 11, 59, 59),
datetime.datetime(2018, 10, 10, 11, 59, 59),
datetime.datetime(2018, 10, 10, 11, 59, 59),
datetime.datetime(2018, 10, 10, 10, 59, 59),
datetime.datetime(2018, 12, 10, 11, 59, 59),
datetime.datetime(1985, 7, 23, 11, 59, 59),
],
"b": [
datetime.datetime(2020, 5, 1, 12, 59, 59),
datetime.datetime(2019, 12, 25, 11, 58, 58),
datetime.datetime(2018, 11, 10, 11, 59, 59),
datetime.datetime(2018, 11, 10, 11, 59, 59),
datetime.datetime(2018, 9, 10, 9, 59, 59),
datetime.datetime(2015, 11, 10, 11, 59, 59),
datetime.datetime(2015, 11, 10, 12, 59, 59),
datetime.datetime(2015, 7, 23, 11, 59, 59),
],
"h": [
233113.01694444445,
173278.98305555555,
0.0,
744.0,
-722.0,
-25559.0,
-27023.0,
262968.0,
],
})
return df
def expected_df_5():
"""Expected output for test_expected_output_units_m."""
df = pd.DataFrame({
"a": [
datetime.datetime(1993, 9, 27, 11, 58, 58),
datetime.datetime(2000, 3, 19, 12, 59, 59),
datetime.datetime(2018, 11, 10, 11, 59, 59),
datetime.datetime(2018, 10, 10, 11, 59, 59),
datetime.datetime(2018, 10, 10, 11, 59, 59),
datetime.datetime(2018, 10, 10, 10, 59, 59),
datetime.datetime(2018, 12, 10, 11, 59, 59),
datetime.datetime(1985, 7, 23, 11, 59, 59),
],
"b": [
datetime.datetime(2020, 5, 1, 12, 59, 59),
datetime.datetime(2019, 12, 25, 11, 58, 58),
datetime.datetime(2018, 11, 10, 11, 59, 59),
datetime.datetime(2018, 11, 10, 11, 59, 59),
datetime.datetime(2018, 9, 10, 9, 59, 59),
datetime.datetime(2015, 11, 10, 11, 59, 59),
datetime.datetime(2015, 11, 10, 12, 59, 59),
datetime.datetime(2015, 7, 23, 11, 59, 59),
],
"m": [
13986781.016666668,
10396738.983333332,
0.0,
44640.0,
-43320.0,
-1533540.0,
-1621380.0,
15778080.0,
],
})
return df
def expected_df_6():
"""Expected output for test_expected_output_units_s."""
df = pd.DataFrame({
"a": [
datetime.datetime(1993, 9, 27, 11, 58, 58),
datetime.datetime(2000, 3, 19, 12, 59, 59),
datetime.datetime(2018, 11, 10, 11, 59, 59),
datetime.datetime(2018, 10, 10, 11, 59, 59),
datetime.datetime(2018, 10, 10, 11, 59, 59),
datetime.datetime(2018, 10, 10, 10, 59, 59),
datetime.datetime(2018, 12, 10, 11, 59, 59),
datetime.datetime(1985, 7, 23, 11, 59, 59),
],
"b": [
datetime.datetime(2020, 5, 1, 12, 59, 59),
datetime.datetime(2019, 12, 25, 11, 58, 58),
datetime.datetime(2018, 11, 10, 11, 59, 59),
datetime.datetime(2018, 11, 10, 11, 59, 59),
datetime.datetime(2018, 9, 10, 9, 59, 59),
datetime.datetime(2015, 11, 10, 11, 59, 59),
datetime.datetime(2015, 11, 10, 12, 59, 59),
datetime.datetime(2015, 7, 23, 11, 59, 59),
],
"s": [
839206861.0,
623804339.0,
0.0,
2678400.0,
-2599200.0,
-92012400.0,
-97282800.0,
946684800.0,
],
})
return df
def expected_df_7():
"""Expected output for test_expected_output_nulls."""
df = pd.DataFrame(
{
"a": [
datetime.datetime(1993, 9, 27, 11, 58, 58),
np.NaN,
],
"b": [
np.NaN,
datetime.datetime(2019, 12, 25, 11, 58, 58),
],
"Y": [
np.NaN,
np.NaN,
],
},
index=[0, 1],
)
return df
def test_arguments(self):
"""Test that transform has expected arguments."""
h.test_function_arguments(func=DateDifferenceTransformer.transform,
expected_arguments=["self", "X"])
def test_super_transform_called(self, mocker):
"""Test that BaseTransformer.transform called."""
df = d.create_datediff_test_df()
x = DateDifferenceTransformer(
column_lower="a",
column_upper="b",
new_column_name="Y",
units="Y",
copy=True,
verbose=False,
)
expected_call_args = {
0: {
"args": (d.create_datediff_test_df(), ),
"kwargs": {}
}
}
with h.assert_function_call(
mocker,
tubular.base.BaseTransformer,
"transform",
expected_call_args,
return_value=d.create_datediff_test_df(),
):
x.transform(df)
@pytest.mark.parametrize(
"df, expected",
h.row_by_row_params(d.create_datediff_test_df(), expected_df_1()) +
h.index_preserved_params(d.create_datediff_test_df(), expected_df_1()),
)
def test_expected_output_units_Y(self, df, expected):
"""Test that the output is expected from transform, when units is Y.
This tests positive year gaps and negative year gaps.
"""
x = DateDifferenceTransformer(
column_lower="a",
column_upper="b",
new_column_name="Y",
units="Y",
copy=True,
verbose=False,
)
df_transformed = x.transform(df)
h.assert_equal_dispatch(
expected=expected,
actual=df_transformed,
msg="Unexpected values in DateDifferenceYearTransformer.transform",
)
@pytest.mark.parametrize(
"df, expected",
h.row_by_row_params(d.create_datediff_test_df(), expected_df_2()) +
h.index_preserved_params(d.create_datediff_test_df(), expected_df_2()),
)
def test_expected_output_units_M(self, df, expected):
"""Test that the output is expected from transform, when units is M.
This tests positive month gaps, negative month gaps, and missing values.
"""
x = DateDifferenceTransformer(
column_lower="a",
column_upper="b",
new_column_name="M",
units="M",
copy=True,
verbose=False,
)
df_transformed = x.transform(df)
h.assert_equal_dispatch(
expected=expected,
actual=df_transformed,
msg="Unexpected values in DateDifferenceYearTransformer.transform",
)
@pytest.mark.parametrize(
"df, expected",
h.row_by_row_params(d.create_datediff_test_df(), expected_df_3()) +
h.index_preserved_params(d.create_datediff_test_df(), expected_df_3()),
)
def test_expected_output_units_D(self, df, expected):
"""Test that the output is expected from transform, when units is D.
This tests positive month gaps, negative month gaps, and missing values.
"""
x = DateDifferenceTransformer(
column_lower="a",
column_upper="b",
new_column_name="D",
units="D",
copy=True,
verbose=False,
)
df_transformed = x.transform(df)
h.assert_equal_dispatch(
expected=expected,
actual=df_transformed,
msg="Unexpected values in DateDifferenceYearTransformer.transform",
)
@pytest.mark.parametrize(
"df, expected",
h.row_by_row_params(d.create_datediff_test_df(), expected_df_4()) +
h.index_preserved_params(d.create_datediff_test_df(), expected_df_4()),
)
def test_expected_output_units_h(self, df, expected):
"""Test that the output is expected from transform, when units is h.
This tests positive month gaps, negative month gaps, and missing values.
"""
x = DateDifferenceTransformer(
column_lower="a",
column_upper="b",
new_column_name="h",
units="h",
copy=True,
verbose=False,
)
df_transformed = x.transform(df)
h.assert_equal_dispatch(
expected=expected,
actual=df_transformed,
msg="Unexpected values in DateDifferenceYearTransformer.transform",
)
@pytest.mark.parametrize(
"df, expected",
h.row_by_row_params(d.create_datediff_test_df(), expected_df_5()) +
h.index_preserved_params(d.create_datediff_test_df(), expected_df_5()),
)
def test_expected_output_units_m(self, df, expected):
"""Test that the output is expected from transform, when units is m.
This tests positive month gaps, negative month gaps, and missing values.
"""
x = DateDifferenceTransformer(
column_lower="a",
column_upper="b",
new_column_name="m",
units="m",
copy=True,
verbose=False,
)
df_transformed = x.transform(df)
h.assert_equal_dispatch(
expected=expected,
actual=df_transformed,
msg="Unexpected values in DateDifferenceYearTransformer.transform",
)
@pytest.mark.parametrize(
"df, expected",
h.row_by_row_params(d.create_datediff_test_df(), expected_df_6()) +
h.index_preserved_params(d.create_datediff_test_df(), expected_df_6()),
)
def test_expected_output_units_s(self, df, expected):
"""Test that the output is expected from transform, when units is s.
This tests positive month gaps, negative month gaps, and missing values.
"""
x = DateDifferenceTransformer(
column_lower="a",
column_upper="b",
new_column_name="s",
units="s",
copy=True,
verbose=False,
)
df_transformed = x.transform(df)
h.assert_equal_dispatch(
expected=expected,
actual=df_transformed,
msg="Unexpected values in DateDifferenceYearTransformer.transform",
)
@pytest.mark.parametrize(
"df, expected",
h.row_by_row_params(d.create_datediff_test_nulls_df(), expected_df_7())
+ h.index_preserved_params(d.create_datediff_test_nulls_df(),
expected_df_7()),
)
def test_expected_output_nulls(self, df, expected):
"""Test that the output is expected from transform, when columns are nulls."""
x = DateDifferenceTransformer(
column_lower="a",
column_upper="b",
new_column_name="Y",
units="Y",
copy=True,
verbose=False,
)
df_transformed = x.transform(df)
h.assert_frame_equal_msg(
actual=df_transformed,
expected=expected,
msg_tag=
"Unexpected values in DateDifferenceTransformer.transform (nulls)",
)
class TestTransform(object):
"""Tests for SeriesDtMethodTransformer.transform()."""
def expected_df_1():
"""Expected output of test_expected_output_no_overwrite."""
df = d.create_datediff_test_df()
df["a_year"] = [1993, 2000, 2018, 2018, 2018, 2018, 2018, 1985]
return df
def expected_df_2():
"""Expected output of test_expected_output_overwrite."""
df = d.create_datediff_test_df()
df["a"] = [1993, 2000, 2018, 2018, 2018, 2018, 2018, 1985]
return df
def expected_df_3():
"""Expected output of test_expected_output_callable."""
df = d.create_datediff_test_df()
df["b_new"] = df["b"].dt.to_period("M")
return df
def test_arguments(self):
"""Test that transform has expected arguments."""
h.test_function_arguments(func=SeriesDtMethodTransformer.transform,
expected_arguments=["self", "X"])
def test_super_transform_called(self, mocker):
"""Test that BaseTransformer.transform called."""
df = d.create_datediff_test_df()
x = SeriesDtMethodTransformer(new_column_name="a2",
pd_method_name="year",
column="a")
expected_call_args = {
0: {
"args": (d.create_datediff_test_df(), ),
"kwargs": {}
}
}
with h.assert_function_call(mocker, tubular.base.BaseTransformer,
"transform", expected_call_args):
x.transform(df)
@pytest.mark.parametrize(
"df, expected",
h.row_by_row_params(d.create_datediff_test_df(), expected_df_1()) +
h.index_preserved_params(d.create_datediff_test_df(), expected_df_1()),
)
def test_expected_output_no_overwrite(self, df, expected):
"""Test a single column output from transform gives expected results, when not overwriting the original column."""
x = SeriesDtMethodTransformer(
new_column_name="a_year",
pd_method_name="year",
column="a",
pd_method_kwargs={},
)
df_transformed = x.transform(df)
h.assert_frame_equal_msg(
actual=df_transformed,
expected=expected,
msg_tag=
"Unexpected values in SeriesDtMethodTransformer.transform with find, not overwriting original column",
)
@pytest.mark.parametrize(
"df, expected",
h.row_by_row_params(d.create_datediff_test_df(), expected_df_2()) +
h.index_preserved_params(d.create_datediff_test_df(), expected_df_2()),
)
def test_expected_output_overwrite(self, df, expected):
"""Test a single column output from transform gives expected results, when overwriting the original column."""
x = SeriesDtMethodTransformer(
new_column_name="a",
pd_method_name="year",
column="a",
pd_method_kwargs={},
)
df_transformed = x.transform(df)
h.assert_frame_equal_msg(
actual=df_transformed,
expected=expected,
msg_tag=
"Unexpected values in SeriesDtMethodTransformer.transform with pad, overwriting original column",
)
@pytest.mark.parametrize(
"df, expected",
h.row_by_row_params(d.create_datediff_test_df(), expected_df_3()) +
h.index_preserved_params(d.create_datediff_test_df(), expected_df_3()),
)
def test_expected_output_callable(self, df, expected):
"""Test transform gives expected results, when pd_method_name is a callable."""
x = SeriesDtMethodTransformer(
new_column_name="b_new",
pd_method_name="to_period",
column="b",
pd_method_kwargs={"freq": "M"},
)
df_transformed = x.transform(df)
h.assert_frame_equal_msg(
actual=df_transformed,
expected=expected,
msg_tag=
"Unexpected values in SeriesDtMethodTransformer.transform with to_period",
)
def test_attributes_unchanged_by_transform(self):
"""Test that attributes set in init are unchanged by the transform method."""
df = d.create_datediff_test_df()
x = SeriesDtMethodTransformer(
new_column_name="b_new",
pd_method_name="to_period",
column="b",
pd_method_kwargs={"freq": "M"},
)
x2 = SeriesDtMethodTransformer(
new_column_name="b_new",
pd_method_name="to_period",
column="b",
pd_method_kwargs={"freq": "M"},
)
x.transform(df)
assert (
x.new_column_name == x2.new_column_name
), "new_column_name changed by SeriesDtMethodTransformer.transform"
assert (
x.pd_method_name == x2.pd_method_name
), "pd_method_name changed by SeriesDtMethodTransformer.transform"
assert (x.columns == x2.columns
), "columns changed by SeriesDtMethodTransformer.transform"
assert (
x.pd_method_kwargs == x2.pd_method_kwargs
), "pd_method_kwargs changed by SeriesDtMethodTransformer.transform"