def fit(self,X,Y):
"""Fit the model according to the given training datastructure.
Parameters
----------
df : pandas dataframe with name variables with last column as target
variable.
Returns
-------
self : object
"""
is_nominal_target = is_classifier(self)
start_time = time()
#self._rulelist = _fit_rulelist(
# X,Y, self.target_model, self.max_depth,self.beam_width,self.min_support, self.n_cutpoints,
# self.task,self.discretization,self.max_rules,self.alpha_gain)
data = Data(input_data=X, n_cutpoints=self.n_cutpoints, discretization=self.discretization,
target_data=Y, target_model=self.target_model, min_support=self.min_support)
if is_nominal_target:
self._rulelist = CategoricalRuleList(data, self.task, self.max_depth, self.beam_width, self.min_support, self.max_rules,
self.alpha_gain)
else:
self._rulelist = GaussianRuleList(data, self.task, self.max_depth, self.beam_width, self.min_support, self.max_rules,
self.alpha_gain)
self._rulelist = greedy_and_beamsearch(data, self._rulelist)
self._rulelist.add_description()
self.runtime = time() - start_time
self.number_rules = self._rulelist.number_rules
self.rule_sets = [bitset2indexes(bitset) for bitset in self._rulelist.bitset_rules]
return self
def generate_items(self, bitset_uncovered) -> Iterator[Item]:
#TODO: make dynamic generation of items based on "candidate"
if self.discretization == 'static':
for item in self.items:
yield item
elif self.discretization == 'dynamic':
indexes = np.array(bitset2indexes(bitset_uncovered))
items, cardinality_operator = self.create_items(indexes)
for item in items:
yield item
def replace_stats(self, data, bitarray_indices):
self.usage = self.update_usage(bitarray_indices)
indices_subgroup = bitset2indexes(bitarray_indices)
target_values = data.targets_info.array_data[indices_subgroup, :]
if self.usage > 2:
for index_column in range(data.number_targets):
self._compute_statistic_free(data, index_column,
target_values[:, index_column])
elif self.usage <= 2:
self._not_enough_points(data)
return self
def replace_stats(self, data, bitarray_indices):
self.usage = self.update_usage(bitarray_indices)
indices_subgroup = bitset2indexes(bitarray_indices)
if data.number_targets == 1:
column_values = data.targets_info.array_data[indices_subgroup, 0]
self.rss[0] = compute_RSS(column_values, self.mean)
#mean = compute_mean_special(datastructure.target_data_test, indices_subgroup, index_column)
#self.rss[0] = compute_RSS_special(datastructure.target_data_test[:,0], indices_subgroup, self.mean)
elif data.number_targets > 1:
target_values = data.targets_info.array_data[indices_subgroup, :]
for icol, column_values in enumerate(target_values.T):
self.rss[icol] = compute_RSS(column_values, self.mean[icol])
return self
def test_oneatend_array(self):
test_input = mpz(16)
expected_bitarray = np.array([4], dtype = np.int32)
actual_bitarray = bitset2indexes(test_input)
np.testing.assert_array_equal(expected_bitarray,actual_bitarray)
def test_oneinbeggining_array(self):
test_input = mpz(1)
expected_bitarray = np.array([0])
actual_bitarray = bitset2indexes(test_input)
np.testing.assert_array_equal(expected_bitarray,actual_bitarray)
def test_empty_array(self):
test_input = mpz(0)
expected_bitarray = np.array([], dtype = np.int32)
actual_bitarray = bitset2indexes(test_input)
np.testing.assert_array_equal(expected_bitarray,actual_bitarray)
def test_allconsecutive_array(self):
test_input = mpz(15)
expected_bitarray = np.array([0,1, 2, 3],dtype = np.int32)
actual_bitarray = bitset2indexes(test_input)
np.testing.assert_array_equal(expected_bitarray,actual_bitarray)