def test_only_nan_in_group(self):
data = Table(
Domain([ContinuousVariable("A"),
ContinuousVariable("B")]),
np.array([[1, np.nan], [2, 1], [1, np.nan], [2, 1]]),
)
self.send_signal(self.widget.Inputs.data, data)
# select feature A as group-by
self._set_selection(self.widget.gb_attrs_view, [0])
# select all aggregations for feature B
self.select_table_rows(self.widget.agg_table_view, [1])
for cb in self.widget.agg_checkboxes.values():
while not cb.isChecked():
cb.click()
# unselect all aggregations for attr A
self.select_table_rows(self.widget.agg_table_view, [0])
for cb in self.widget.agg_checkboxes.values():
while cb.isChecked():
cb.click()
expected_columns = [
"B - Mean",
"B - Median",
"B - Mode",
"B - Standard deviation",
"B - Variance",
"B - Sum",
"B - Min. value",
"B - Max. value",
"B - Span",
"B - First value",
"B - Last value",
"B - Random value",
"B - Count defined",
"B - Count",
"B - Proportion defined",
"B - Concatenate",
"A",
]
n = np.nan
expected_df = pd.DataFrame(
[
[n, n, n, n, n, 0, n, n, n, n, n, n, 0, 2, 0, "", 1],
[1, 1, 1, 0, 0, 2, 1, 1, 0, 1, 1, 1, 2, 2, 1, "1.0 1.0", 2],
],
columns=expected_columns,
)
output_df = table_to_frame(self.get_output(self.widget.Outputs.data),
include_metas=True)
pd.testing.assert_frame_equal(
output_df,
expected_df,
check_dtype=False,
check_column_type=False,
check_categorical=False,
)
def test_only_nan_in_group(self):
data = Table(
Domain([ContinuousVariable("A"), ContinuousVariable("B")]),
np.array([[1, np.nan], [2, 1], [1, np.nan], [2, 1]]),
)
self.send_signal(self.widget.Inputs.data, data)
# select feature A as group-by
self._set_selection(self.widget.gb_attrs_view, [0])
# select all aggregations for feature B
self.select_table_rows(self.widget.agg_table_view, [1])
for cb in self.widget.agg_checkboxes.values():
while not cb.isChecked():
cb.click()
# unselect all aggregations for attr A
self.select_table_rows(self.widget.agg_table_view, [0])
for cb in self.widget.agg_checkboxes.values():
while cb.isChecked():
cb.click()
expected_columns = [
"B - 平均值",
"B - 中位数",
"B - 取模",
"B - 标准差",
"B - 方差",
"B - 和",
"B - 最小值",
"B - 最大值",
"B - 跨度",
"B - 首值",
"B - 末值",
"B - 随机值",
"B - 非缺失数量",
"B - 数量",
"B - 非缺失占比",
"B - 串接(Concatenate)",
"A",
]
n = np.nan
expected_df = pd.DataFrame(
[
[n, n, n, n, n, 0, n, n, n, n, n, n, 0, 2, 0, "", 1],
[1, 1, 1, 0, 0, 2, 1, 1, 0, 1, 1, 1, 2, 2, 1, "1.0 1.0", 2],
],
columns=expected_columns,
)
output_df = table_to_frame(
self.get_output(self.widget.Outputs.data), include_metas=True
)
pd.testing.assert_frame_equal(
output_df,
expected_df,
check_dtype=False,
check_column_type=False,
check_categorical=False,
)
def __init__(self, table: Table, by: List[Variable]):
self.table = table
df = table_to_frame(table, include_metas=True)
# observed=True keeps only groups with at leas one instance
self.group_by = df.groupby([a.name for a in by], observed=True)
# lru_cache that is caches on the object level
self.compute_aggregation = lru_cache()(self._compute_aggregation)
def test_aggregation(self):
d = self.data.domain
gb = self.data.groupby([self.data.domain["a"], self.data.domain["b"]])
output = gb.aggregate({
d["cvar"]: [("Mean", "mean"), ("Median", "median"),
("Mean1", np.mean)],
d["dvar"]: [("Count defined", "count"), ("Count", "size")],
d["svar"]: [("Concatenate", "".join)],
})
expected_columns = [
"cvar - Mean",
"cvar - Median",
"cvar - Mean1",
"dvar - Count defined",
"dvar - Count",
"svar - Concatenate",
"a", # groupby variables are last two in metas
"b",
]
exp_df = pd.DataFrame(
[
[0.15, 0.15, 0.15, 2, 2, "sval1sval2", 1, 1],
[0.3, 0.3, 0.3, 1, 2, "sval2", 1, 2],
[0.433, 0.4, 0.433, 3, 3, "sval1sval2sval1", 1, 3],
[1.5, 1.5, 1.5, 2, 2, "sval2sval1", 2, 1],
[-0.5, -0.5, -0.5, 2, 2, "sval2sval1", 2, 2],
[5, 5, 5, 2, 2, "sval2sval1", 2, 3],
],
columns=expected_columns,
)
out_df = table_to_frame(output, include_metas=True)
pd.testing.assert_frame_equal(
out_df,
exp_df,
check_dtype=False,
check_column_type=False,
check_categorical=False,
atol=1e-3,
)
def test_aggregation(self):
"""Test aggregation results"""
self.send_signal(self.widget.Inputs.data, self.data)
output = self.get_output(self.widget.Outputs.data)
np.testing.assert_array_almost_equal(
output.X, [[1, 2.143, 0.317, 0], [2, 2, 2, 0]], decimal=3)
np.testing.assert_array_equal(
output.metas,
np.array(
[
[
"sval1 sval2 sval2 sval1 sval2 sval1",
1.0,
],
[
"sval2 sval1 sval2 sval1 sval2 sval1",
2.0,
],
],
dtype=object,
),
)
# select all aggregations for all features except a and b
self._set_selection(self.widget.gb_attrs_view, [1, 2])
self.select_table_rows(self.widget.agg_table_view, [2, 3, 4])
# select all aggregations
for cb in self.widget.agg_checkboxes.values():
cb.click()
while not cb.isChecked():
cb.click()
self.select_table_rows(self.widget.agg_table_view, [0, 1])
# unselect all aggregations for attr a and b
for cb in self.widget.agg_checkboxes.values():
while cb.isChecked():
cb.click()
expected_columns = [
"cvar - Mean",
"cvar - Median",
"cvar - Mode",
"cvar - Standard deviation",
"cvar - Variance",
"cvar - Sum",
"cvar - Min. value",
"cvar - Max. value",
"cvar - Span",
"cvar - First value",
"cvar - Last value",
"cvar - Count defined",
"cvar - Count",
"cvar - Proportion defined",
"dvar - Mode",
"dvar - First value",
"dvar - Last value",
"dvar - Count defined",
"dvar - Count",
"dvar - Proportion defined",
"svar - First value",
"svar - Last value",
"svar - Count defined",
"svar - Count",
"svar - Proportion defined",
"cvar - Concatenate",
"dvar - Concatenate",
"svar - Concatenate",
"a", # groupby variables are last two in metas
"b",
]
# fmt: off
expected_df = pd.DataFrame(
[[
.15, .15, .1, .07, .005, .3, .1, .2, .1, 0.1, 0.2, 2, 2, 1,
"val1", "val1", "val2", 2, 2, 1, "sval1", "sval2", 2, 2, 1,
"0.1 0.2", "val1 val2", "sval1 sval2", 1, 1
],
[
.3, .3, .3, np.nan, np.nan, .3, .3, .3, 0, .3, .3, 1, 2, 0.5,
"val2", "val2", "val2", 1, 2, 0.5, "", "sval2", 2, 2, 1,
"0.3", "val2", "sval2", 1, 2
],
[
.433, .4, .3, 0.153, 0.023, 1.3, .3, .6, .3, .3, .6, 3, 3, 1,
"val1", "val1", "val1", 3, 3, 1, "sval1", "sval1", 3, 3, 1,
"0.3 0.4 0.6", "val1 val2 val1", "sval1 sval2 sval1", 1, 3
],
[
1.5, 1.5, 1, 0.707, 0.5, 3, 1, 2, 1, 1, 2, 2, 2, 1, "val1",
"val2", "val1", 2, 2, 1, "sval2", "sval1", 2, 2, 1, "1.0 2.0",
"val2 val1", "sval2 sval1", 2, 1
],
[
-0.5, -0.5, -4, 4.95, 24.5, -1, -4, 3, 7, 3, -4, 2, 2, 1,
"val1", "val2", "val1", 2, 2, 1, "sval2", "sval1", 2, 2, 1,
"3.0 -4.0", "val2 val1", "sval2 sval1", 2, 2
],
[
5, 5, 5, 0, 0, 10, 5, 5, 0, 5, 5, 2, 2, 1, "val1", "val2",
"val1", 2, 2, 1, "sval2", "sval1", 2, 2, 1, "5.0 5.0",
"val2 val1", "sval2 sval1", 2, 3
]],
columns=expected_columns)
# fmt: on
output_df = table_to_frame(self.get_output(self.widget.Outputs.data),
include_metas=True)
# remove random since it is not possible to test
output_df = output_df.loc[:, ~output_df.columns.str.
endswith("Random value")]
pd.testing.assert_frame_equal(
output_df,
expected_df,
check_dtype=False,
check_column_type=False,
check_categorical=False,
atol=1e-3,
)