def setUp(self):
self.totals_name = config.get_value('aggregation', 'totals_name')
self.label_abs = config.get_value('aggregation', 'label_abs')
self.ndigits = config.get_value('aggregation', 'ndigits')
self.df = pd._testing.makeCustomDataframe(
nrows=5,
ncols=4,
data_gen_f=lambda r, c: randint(1, 100),
)
def setUp(self):
self.na_rep = config.get_value('aggregation', 'na_rep')
categories = {
key:[self.na_rep if val is None else val for val in values]
for key, values in test.CATEGORIES.items()
}
self.taste = [i for i in test.CATEGORIES['taste'] if i is not None]
self.touch = [i for i in test.CATEGORIES['touch'] if i is not None]
kwargs = dict(
columns = 'taste',
index = ['smell', 'touch'],
aggfunc = 'size'
)
self.df = test.dataset(
seed='squid',
categories=categories
).pivot_table(**kwargs)
self.df_cats = test.dataset(
categories=categories,
to_categories=True,
).pivot_table(**kwargs)
def test_add_rows_within(self):
left = (totals.add(self.df, level=-1).xs(config.get_value(
'aggregation', 'subtotals_name'),
level=-1).values)
right = self.df.groupby(level=-2).sum().values
comparison = (left == right).all()
self.assertTrue(comparison)
def test_add_cols_within(self):
subtotals_name = config.get_value('aggregation', 'subtotals_name')
left = (totals.add(self.df, axis=1, level=1).xs(subtotals_name,
axis=1,
level=1).values)
right = self.df.groupby(level=0, axis=1).sum().values
comparison = (left == right).all()
self.assertTrue(comparison)
def test_add_multiple_levels(self):
subtotals_name = config.get_value('aggregation', 'subtotals_name')
result = totals.add(self.df, axis=1, level=[0, 'C1'])
subtotals_result = result.xs(subtotals_name, axis=1, level=1)
calc_subtotals = self.df.groupby(level=0, axis=1).sum()
self.assertTrue(subtotals_result.eq(calc_subtotals).all().all())
totals_result = result.iloc[:, -1]
calc_totals = self.df.sum(axis=1)
self.assertTrue(totals_result.equals(calc_totals))
def setUp(self):
self.totals_name = config.get_value('aggregation', 'totals_name')
df = pd._testing.makeDataFrame().head(5)
df.columns = pd.Categorical(df.columns)
df.index = pd.Categorical(df.index)
self.df = df