def test_filter_subsets(min, max):
data = generate_samples(0, 5000, 3)
upset_data = UpSet(data, subset_size='auto')
subset_upset_data = UpSet(data,
subset_size='auto',
min_subset_size=min,
max_subset_size=max)
intersections = upset_data.intersections
df = upset_data._df
subset_intersections = intersections[np.logical_and(
intersections >= min, intersections <= max)]
subset_df = df[df.index.isin(subset_intersections.index)]
assert_series_equal(subset_upset_data.intersections, subset_intersections)
def _pack_binary(X):
X = pd.DataFrame(X)
out = 0
for i, (_, col) in enumerate(X.items()):
out *= 2
out += col
return out
subset_df_packed = _pack_binary(subset_df.index.to_frame())
subset_data_packed = _pack_binary(subset_intersections.index.to_frame())
subset_df['_bin'] = pd.Series(subset_df_packed).map(
pd.Series(np.arange(len(subset_data_packed)),
index=subset_data_packed))
assert_frame_equal(subset_upset_data._df, subset_df)
def test_not_unique(sort_by, sort_categories_by):
kw = {
'sort_by': sort_by,
'sort_categories_by': sort_categories_by,
'subset_size': 'sum',
'sum_over': None
}
Xagg = generate_counts()
df1, intersections1, totals1 = _process_data(Xagg, **kw)
Xunagg = generate_samples()['value']
Xunagg.loc[:] = 1
df2, intersections2, totals2 = _process_data(Xunagg, **kw)
assert_series_equal(intersections1, intersections2, check_dtype=False)
assert_series_equal(totals1, totals2, check_dtype=False)
assert set(df1.columns) == {'_value', '_bin'}
assert set(df2.columns) == {'_value', '_bin'}
assert len(df2) == len(Xunagg)
assert df2['_bin'].nunique() == len(intersections2)
if sort_categories_by:
assert is_ascending(totals.values[::-1])
assert np.all(totals.index.values == intersections.index.names)
assert np.all(df.index.names == intersections.index.names)
assert set(df.columns) == {'_value', '_bin'}
assert_index_equal(df['_value'].reorder_levels(x.index.names).index,
x.index)
assert_array_equal(df['_value'], x)
assert_index_equal(intersections.iloc[df['_bin']].index, df.index)
assert len(df) == len(x)
@pytest.mark.parametrize('x', [
generate_samples()['value'],
generate_counts(),
])
def test_subset_size_series(x):
kw = {
'sort_by': 'cardinality',
'sort_categories_by': 'cardinality',
'sum_over': None
}
df_sum, intersections_sum, totals_sum = _process_data(x,
subset_size='sum',
**kw)
if x.index.is_unique:
expected_warning = None
else:
