def test_fromstring_serialized(tmp_path, source, filename, includes_lattice):
if filename is None:
context = Context.fromstring(source, frmat='python-literal')
else:
target = tmp_path / filename
kwargs = {'encoding': 'utf-8'}
target.write_text(source, **kwargs)
context = Context.fromfile(str(target),
frmat='python-literal',
**kwargs)
assert context.objects == SERIALIZED['objects']
assert context.properties == SERIALIZED['properties']
assert context.bools == [
(True, False, False, True, False, True, True, False, False, True),
(True, False, False, True, False, True, False, True, True, False),
(False, True, True, False, False, True, True, False, False, True),
(False, True, True, False, False, True, False, True, True, False),
(False, True, False, True, True, False, True, False, False, True),
(False, True, False, True, True, False, False, True, True, False)
]
if includes_lattice:
assert 'lattice' in context.__dict__
else:
assert 'lattice' not in context.__dict__
def __init__(self,
dataframe,
leaves,
annotate=None,
dummy_formatter=None,
keep_names=True,
comp_prefix=None,
col_formatter=None,
na_value=None,
AOC=False,
collections=False,
verbose=True):
"""
Arguments:
dataframe (:class:`pandas:pandas.DataFrame`): A dataframe
leaves (dict): Dictionnaire de microclasses
annotate (dict): Extra annotations to add on lattice.
Of the form: {<object label>:<annotation>}
dummy_formatter (func): Function to make dummies from the table. (default to panda's)
keep_names (bool): whether to keep original column names when dropping duplicate dummy columns.
comp_prefix (str): If there are two sets of properties, the prefix used to distinguish column names.
AOC (bool): Whether to limit ourselves to Attribute or Object Concepts.
col_formatter (func): Function to format columns in the context table.
na_value : A value tu use as "Na". Defaults to `None`
collections (bool): Whether the table contains :class:`representations.patterns.PatternCollection` objects.
"""
self.comp = comp_prefix # whether there are two sets of properties.
if na_value is not None:
dataframe = dataframe.applymap(lambda x: None
if x == na_value else x)
if collections:
dummies = to_dummies(dataframe, keep_names=keep_names)
elif dummy_formatter:
dummies = dummy_formatter(dataframe)
else:
dummies = pd.get_dummies(dataframe, prefix_sep="=")
dummies = dummies.applymap(lambda x: "X" if x == 1 else "")
if col_formatter:
dummies.columns = col_formatter(dummies.columns)
if verbose:
print("Reading the context and building the lattice...")
context_str = dummies.to_csv()
c1 = Context.fromstring(context_str, frmat='csv')
self.context = c1
self.lattice = c1.lattice
if annotate:
for label in annotate:
if label in self.lattice.supremum.extent:
self.lattice[[label
]]._extra_qumin_annotation = annotate[label]
self.leaves = leaves
if verbose:
print("Converting to qumin node...")
if AOC:
self.nodes = self._lattice_to_nodeAOC()
else:
self.nodes = self._lattice_to_node()
font = {'family': 'DejaVu Sans', 'weight': 'normal', 'size': 9}
matplotlib.rc('font', **font)
