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_inputvalues_one_target(constant_parameters):
input_input_data, input_n_cutpoints, input_discretization, input_target_data, input_minsupp = constant_parameters
# targets
np.random.seed(seed=42)
dictoutput = {"target1": np.arange(100)}
input_output_data = pd.DataFrame(data=dictoutput)
data_class = Data(input_input_data, input_n_cutpoints,
input_discretization, input_output_data,
input_target_data, input_minsupp)
input_bitarray_for_statistic = bit_mask(data_class.number_instances)
yield data_class, input_bitarray_for_statistic
def generate_inputvalues_one_target(constant_parameters):
input_input_data, input_n_cutpoints, input_discretization, input_target_data, input_minsupp = constant_parameters
# targets
dictoutput = {
"target1":
np.array(["below50" if i < 50 else "above49" for i in range(100)])
}
input_output_data = pd.DataFrame(data=dictoutput)
data_class = Data(input_input_data, input_n_cutpoints,
input_discretization, input_output_data,
input_target_data, input_minsupp)
input_bitarray_for_statistic = bit_mask(data_class.number_instances)
yield data_class
def generate_input_dataframe_two_target_variancezero(constant_parameters):
input_n_cutpoints, input_discretization, input_target_data, input_minsupp = constant_parameters
dictinput = {
"attribute1":
np.arange(100),
"attribute2":
np.array(["below50" if i < 50 else "above49" for i in range(100)])
}
input_input_data = pd.DataFrame(data=dictinput)
dictoutput = {"target1": np.arange(100), "target2": np.ones(100)}
input_output_data = pd.DataFrame(data=dictoutput)
data = Data(input_input_data, input_n_cutpoints, input_discretization,
input_output_data, input_target_data, input_minsupp)
yield data
def generate_input_dataframe_one_target(constant_parameters):
input_n_cutpoints, input_discretization, input_target_data, input_minsupp = constant_parameters
dictinput = {
"attribute1":
np.arange(100000),
"attribute2":
np.array(
["below1000" if i < 1000 else "above999" for i in range(100000)])
}
input_input_data = pd.DataFrame(data=dictinput)
dictoutput = {"target1": np.random.normal(loc=1, scale=1, size=100000)}
input_output_data = pd.DataFrame(data=dictoutput)
data = Data(input_input_data, input_n_cutpoints, input_discretization,
input_output_data, input_target_data, input_minsupp)
yield data
def generate_inputvalues_two_targets(constant_parameters):
input_input_data, input_n_cutpoints, input_discretization, input_target_data, input_minsupp = constant_parameters
# targets
dictoutput = {
"target1":
np.array(["below50" if i < 50 else "above49" for i in range(100)]),
"target2":
np.array(["below99" if i < 99 else "above99" for i in range(100)])
}
input_output_data = pd.DataFrame(data=dictoutput)
data_class = Data(input_input_data, input_n_cutpoints,
input_discretization, input_output_data,
input_target_data, input_minsupp)
yield data_class
def generate_input_dataframe_two_target_normal(constant_parameters):
input_n_cutpoints, input_discretization, input_target_data, input_minsupp = constant_parameters
dictinput = {
"attribute1":
np.arange(100000),
"attribute2":
np.array(
["below1000" if i < 1000 else "above999" for i in range(100000)])
}
input_input_data = pd.DataFrame(data=dictinput)
dictoutput = {
"target1":
np.concatenate((np.random.normal(loc=20, scale=3, size=16666),
np.random.normal(loc=100, scale=6, size=83334)),
axis=None),
"target2":
np.concatenate((np.random.normal(loc=10, scale=2, size=16666),
np.random.normal(loc=50, scale=5, size=83334)),
axis=None)
}
input_output_data = pd.DataFrame(data=dictoutput)
data = Data(input_input_data, input_n_cutpoints, input_discretization,
input_output_data, input_target_data, input_minsupp)
yield data
def test_gaussian_twotargets(self, generate_input_dataframe_two_target,
constant_parameters):
input_input_data, input_output_data = generate_input_dataframe_two_target
input_n_cutpoints, input_discretization, input_target_data, input_minsupp = constant_parameters
expected_number_targets = 2
expected_number_attributes = 2
expected_number_instances = 100
expected_attribute_names = {"attribute1", "attribute2"}
expected_target_names = {"target1", "target2"}
output_data = Data(input_input_data, input_n_cutpoints,
input_discretization, input_output_data,
input_target_data, input_minsupp)
pd.testing.assert_frame_equal(input_input_data, output_data.input_data)
pd.testing.assert_frame_equal(input_output_data,
output_data.target_data)
assert expected_number_attributes == output_data.number_attributes
assert expected_number_attributes == len(output_data.attributes)
assert expected_number_targets == output_data.number_targets
assert expected_number_instances == output_data.number_instances
assert expected_attribute_names == output_data.attribute_names
assert expected_target_names == output_data.target_names
@pytest.mark.xfail
def test_name_not_present(self):
pass
@pytest.mark.xfail
def test_category_not_present(self):
pass
@pytest.mark.xfail
def test_receives_series(self):
pass
def test_gaussian_onetarget(self, generate_input_dataframe_one_target,
constant_parameters):
input_input_data, input_output_data = generate_input_dataframe_one_target
input_n_cutpoints, input_discretization, input_target_data, input_minsupp = constant_parameters
expected_number_targets = 1
expected_number_attributes = 2
expected_number_instances = 100
expected_attribute_names = {"attribute1", "attribute2"}
expected_target_names = {"target1"}
output_data = Data(input_input_data, input_n_cutpoints,
input_discretization, input_output_data,
input_target_data, input_minsupp)
pd.testing.assert_frame_equal(input_input_data, output_data.input_data)
pd.testing.assert_frame_equal(input_output_data,
output_data.target_data)
assert expected_number_attributes == output_data.number_attributes
assert expected_number_attributes == len(output_data.attributes)
assert expected_number_targets == output_data.number_targets
assert expected_number_instances == output_data.number_instances
assert expected_attribute_names == output_data.attribute_names
assert expected_target_names == output_data.target_names
def generate_input_dataframe_two_target(constant_parameters):
input_input_data, input_output_data, input_n_cutpoints, input_discretization, input_target_data ,input_minsupp\
= constant_parameters
data = Data(input_input_data, input_n_cutpoints, input_discretization,
input_output_data, input_target_data, input_minsupp)
yield data