def test_json_roundtrip(context, path_or_fileobj, encoding):
context = Context(context.objects, context.properties, context.bools)
assert 'lattice' not in context.__dict__
is_fileobj = hasattr(path_or_fileobj, 'seek')
kwargs = {'encoding': encoding} if encoding is not None else {}
context.tojson(path_or_fileobj, ignore_lattice=True, **kwargs)
if is_fileobj:
path_or_fileobj.seek(0)
assert 'lattice' not in context.__dict__
deserialized = Context.fromjson(path_or_fileobj, **kwargs)
if is_fileobj:
path_or_fileobj.seek(0)
assert 'lattice' not in deserialized.__dict__
assert deserialized == context
assert isinstance(context.lattice, Lattice)
assert 'lattice' in context.__dict__
context.tojson(path_or_fileobj, ignore_lattice=None, **kwargs)
if is_fileobj:
path_or_fileobj.seek(0)
deserialized = Context.fromjson(path_or_fileobj, **kwargs)
assert 'lattice' in deserialized.__dict__
assert deserialized == context
assert deserialized.lattice._eq(context.lattice)
def local_fca(self, molecules):
props = self.get_properties(molecules)
props = list(set(props))
sub = list(molecules[0].subjects())[0]
molecule_properties = [
str(prop.encode('utf-8')) + '->' + str(value.encode('utf-8'))
for prop, value in props
]
molecule_names = [
"{}_{}".format(str(sub.encode('utf-8')), y)
for y in [2014, 2015, 2016]
]
mat = []
for molecule in molecules:
row = [False] * len(props)
for idx, (prop, val) in enumerate(props):
if (sub, prop, val) in molecule:
row[idx] = True
mat.append(row)
c = Context(molecule_names, molecule_properties, mat)
res = c.lattice
result = []
for (extent, intent) in res:
result.append((list(extent), list(intent)))
return result
def test_dict_roundtrip(context, ignore_lattice):
context = Context(context.objects, context.properties, context.bools)
assert 'lattice' not in context.__dict__
d = context.todict(ignore_lattice=ignore_lattice)
assert isinstance(d, dict) and d
assert all(d[k] for k in ('objects', 'properties', 'context'))
if ignore_lattice or ignore_lattice is None:
assert 'lattice' not in context.__dict__
assert 'lattice' not in d
else:
assert 'lattice' in context.__dict__
assert d['lattice']
result = Context.fromdict(d)
assert isinstance(result, Context)
assert result == context
if ignore_lattice or ignore_lattice is None:
assert 'lattice' not in result.__dict__
else:
assert 'lattice' in result.__dict__
assert result.lattice._eq(context.lattice)
def build_iceberg_lattice(filename, lattice, threshold):
irreducable = []
for i, (intent, extent) in enumerate(lattice):
coverage = list(intent)
if (len(intent) < threshold):
continue
is_irreducable = True
for j, (intent1, extent1) in enumerate(lattice):
if (j == i or len(intent1) < threshold
or len(intent) <= len(intent1)):
continue
is_subset = True
for obj in intent1:
if (not (obj in intent)):
is_subset = False
break
if is_subset:
for obj in intent1:
if obj in coverage:
coverage.remove(obj)
if (len(coverage) == 0):
is_irreducable = False
break
if is_irreducable:
irreducable.append((intent, extent))
#print intent, extent
#print '\n'
df = Definition()
for intent, extent in irreducable:
obj_name = ';'.join(intent)
df.add_object(obj_name, list(extent))
conc = Context(*df)
conc.tofile(filename='iceberg.' + filename, frmat='csv')
def __init__(self, csv_location):
# the Frame-capability lattice
self.context = Context.fromfile(csv_location, frmat='csv')
self.lattice = self.context.lattice
# the Frame-uncapability lattice
self.context_inv = Context(*self.context.definition().inverted())
self.lattice_inv = self.context_inv.lattice
# the list of all capabilities and frames
self.capabilities = self.context.properties
self.frames = self.context.objects
def dictToConcept(data_matrix):
""" From dictionnary to concepts """
definition = concepts.Definition()
for (current_obj, current_values) in data_matrix.items():
definition.add_object(current_obj, current_values)
context = Context(*definition)
lattice = context.lattice
return context, lattice
def nonascii_context(abba=(u'Agneta F\xe4ltskog', u'Anni-Frid Lyngstat',
u'Benny Andersson', u'Bj\xf6rn Ulvaeus')):
d = Definition()
for o in abba:
d.add_object(o, [u'human', u'singer'])
d.add_property(u'female', abba[:2])
d.add_property(u'male', abba[2:])
d.add_property(u'keyboarder', [abba[2]])
d.add_property(u'guitarrist', [abba[3]])
d.add_property(u'sch\xf6n', abba[::2])
return Context(*d)
def test_todict(context, d):
assert 'lattice' not in context.__dict__
if 'lattice' in d:
context = Context(context.objects, context.properties, context.bools)
assert 'lattice' not in context.__dict__
for ignore_lattice in (False, None):
assert context.todict(ignore_lattice=ignore_lattice) == d
assert 'lattice' in context.__dict__
else:
for ignore_lattice in (True, None):
assert context.todict(ignore_lattice=ignore_lattice) == d
assert 'lattice' not in context.__dict__
def predict_fca(s):
properties = s.index.values
objects = [str(s.name)]
bools = tuple(s.astype(bool))
s_lattice = Context(objects, properties, [bools])
s_intents = set()
for extent_s, intent_s in s_lattice.lattice:
s_intents.add(intent_s)
sets = set(list(s_intents)[1])
probs = []
for i in range(0, no_of_classes):
for intent_c in class_intents_sets[i]:
setc = set(intent_c)
if sets.issubset(setc):
probs.append(i)
if len(probs) == 0:
return -1
return max(probs, key=probs.count)
# Creating and save context for implication rules
X_train_one_hot['Class'] = y_train
X_train_Class_split = pd.concat([
X_train_one_hot,
pd.get_dummies(X_train_one_hot['Class'], prefix='Class')
],
axis=1)
X_train_Class_split = X_train_Class_split.drop(["Class"],
axis=1).drop_duplicates()
objects = X_train_Class_split.index.values
objects = [str(oi) for oi in objects]
properties = X_train_Class_split.columns.values
bools = list(
X_train_Class_split.astype(bool).itertuples(index=False, name=None))
cxt = Context(objects, properties, bools)
cxt.tofile('diabetes_context.cxt', frmat='cxt', encoding='utf-8')
## Create concepts lattices for each class
c = {}
l = {}
no_of_classes = 2
X_train_one_hot['Class'] = y_train
X_train_one_hot = X_train_one_hot.drop_duplicates()
for i in range(0, no_of_classes):
X_temp = X_train_one_hot.copy(deep=True)
X_temp = X_temp[X_temp['Class'] == i].drop(["Class"], axis=1)
objects = X_temp.index.values
objects = [str(oi) for oi in objects]
properties = X_temp.columns.values