def test_gb_labels_enum(self):
# make sure enum groupby keys are displayed as string, not integer code
c = Categorical([10, 10, 10, 20, 30, 20, 10, 20, 20], {
'a': 30,
'b': 20,
'c': 10
})
c_result = c.count()
c_labels = c_result[c_result.label_get_names()][0]
ds = Dataset({'catcol': c, 'data': arange(9)})
ds_result = ds.gbu('catcol').count()
ds_labels = ds_result[ds_result.label_get_names()][0]
assert c_labels.dtype.char == ds_labels.dtype.char
assert bool(np.all(c_labels == ds_labels))
def test_as_categorical(self):
ds = Dataset({
'keycol1': np.random.choice(['a', 'b', 'c'], 30),
'keycol2': np.random.choice(['a', 'b', 'c'], 30),
'data': np.random.rand(30),
})
gbu = ds.gbu('keycol1')
c = Categorical(ds.keycol1, ordered=False, sort_gb=False)
cgbu = gbu.as_categorical()
gbu_result = gbu.sum()
c_result = c.sum(ds.data)
cgbu_result = cgbu.sum(ds.data)
for name, col in gbu_result.items():
assert bool(np.all(c_result[name] == col))
assert bool(np.all(cgbu_result[name] == col))
61.68,
72.85,
91.71,
61.12,
])
tens = FastArray([10] * 30)
ds = Dataset({
'strings': str_fa.copy(),
'ints': int_fa,
'floats': flt_fa,
'tens': tens
})
gb = ds.gb('strings')
ds_nums = Dataset({'ints': int_fa, 'floats': flt_fa, 'tens': tens})
data_to_compare = ['ints', 'floats', 'tens']
gbu = ds.gbu('strings')
gb_funcs_L1 = [
'sum',
'mean',
'min',
'max',
'var',
'std',
'nansum',
'nanmean',
'nanmin',
'nanmax',
'nanvar',
'nanstd',
]