def test_n_negative(self):
input_n1 = 1
input_maximum = 2
input_n2 = 2
expected_probability_total = 1
actual_probability_total = 2**-universal_code_integers_maximum(input_n1,input_maximum)+\
2**-universal_code_integers_maximum(input_n2, input_maximum)
assert expected_probability_total == pytest.approx(
actual_probability_total)
def test_numericattribute(self, auxiliar_numericattribute):
numericattribute = auxiliar_numericattribute
expected_length_item_1_operator = log2(
6) + universal_code_integers_maximum(1, 2)
expected_length_item_2_operator = log2(
3) + universal_code_integers_maximum(2, 2)
expected_output = [("column1", 1, expected_length_item_1_operator),
("column1", 2, expected_length_item_2_operator)]
output = [*compute_item_length(numericattribute)]
assert expected_output[0][0] == output[0][0]
assert expected_output[0][1] == output[0][1]
assert expected_output[0][2] == pytest.approx(output[0][2])
assert expected_output[1][0] == output[1][0]
assert expected_output[1][1] == output[1][1]
assert expected_output[1][2] == pytest.approx(output[1][2])
def test_n_one(self):
#edge case
input_n = 1
input_maximum = 1
expected_codelength = 0
codelength = universal_code_integers_maximum(input_n, input_maximum)
assert expected_codelength == pytest.approx(codelength)
def test_nominalattribute(self, auxiliar_nominalattribute):
nominalattribute = auxiliar_nominalattribute
expected_length_item_1_operator = log2(
2) + universal_code_integers_maximum(1, 1)
expected_output = [("column1", 1, expected_length_item_1_operator)]
output = [*compute_item_length(nominalattribute)]
assert expected_output[0][0] == output[0][0]
assert expected_output[0][1] == output[0][1]
assert expected_output[0][2] == pytest.approx(output[0][2])
def test_add_rule_2items(self, search_parameters,
generate_input_dataframe_two_target_normal,
generate_subgroup_2subgroups):
data = generate_input_dataframe_two_target_normal
input_target_model, input_max_depth, input_beam_width, input_minsupp, input_max_rules, input_alpha_gain = search_parameters
subgroup2add1, subgroup2add2 = generate_subgroup_2subgroups
input_task = "discovery"
output_ruleset = GaussianRuleList(data, input_task, input_max_depth,
input_beam_width, input_minsupp,
input_max_rules, input_alpha_gain)
output_ruleset.add_rule(subgroup2add1, data)
output_ruleset.add_rule(subgroup2add2, data)
expected_number_instances = data.number_instances
expected_bitset_uncovered = mpz()
expected_bitset_covered = bit_mask(100000)
expected_number_rules = 2
expected_length_model = universal_code_integers(2) + \
universal_code_integers(1) +uniform_combination_code(1, 2) +\
universal_code_integers_maximum(1, 2) + uniform_code(10)+ \
universal_code_integers(1) + uniform_combination_code(1, 2) + \
universal_code_integers_maximum(1, 1) + uniform_code(2)
actual_numberinstances1 = popcount(output_ruleset.subgroups[0].bitarray) + \
popcount(output_ruleset.subgroups[1].bitarray &~ output_ruleset.subgroups[0].bitarray) + \
popcount(output_ruleset.bitset_uncovered)
actual_numberinstances2 = output_ruleset.support_covered + output_ruleset.support_uncovered
actual_numberinstances3 = popcount(output_ruleset.bitset_covered) + \
popcount(output_ruleset.bitset_uncovered)
actual_numberinstances4 = output_ruleset.subgroups[0].usage + output_ruleset.subgroups[1].usage +\
output_ruleset.default_rule_statistics.usage
assert expected_number_instances == actual_numberinstances1
assert expected_number_instances == actual_numberinstances2
assert expected_number_instances == actual_numberinstances3
assert expected_number_instances == actual_numberinstances4
assert expected_bitset_uncovered == output_ruleset.bitset_uncovered
assert expected_bitset_covered == output_ruleset.bitset_covered
assert expected_number_rules == output_ruleset.number_rules
assert expected_length_model == pytest.approx(
output_ruleset.length_model)
def compute_item_length(attribute: Attribute) -> float:
""" Computes the code of an attribute based on its cardinality
"""
for n_operators in range(1, attribute.max_operators + 1):
l_number_operators = universal_code_integers_maximum(
n_operators, attribute.max_operators)
l_code = uniform_code(attribute.cardinality_operator[n_operators])
l_item = l_number_operators + l_code
yield attribute.name, n_operators, l_item
#def compute_item_length_uniformforall(attribute: Attribute) -> float:
# cardinality = sum([attribute.cardinality_operator[n_operators] for n_operators in range(1,attribute.max_operators+1)])
# l_item = uniform_code(cardinality)
# for n_operators in range(1,attribute.max_operators+1):
# yield attribute.name, n_operators, l_item
def test_add_rule_itemnumeric(self, search_parameters,
generate_input_dataframe_two_target_normal,
generate_subgroup_oneitem_numeric):
data = generate_input_dataframe_two_target_normal
input_target_model, input_max_depth, input_beam_width, input_minsupp, input_max_rules, input_alpha_gain = search_parameters
subgroup2add = generate_subgroup_oneitem_numeric
input_task = "discovery"
output_ruleset = GaussianRuleList(data, input_task, input_max_depth,
input_beam_width, input_minsupp,
input_max_rules, input_alpha_gain)
output_ruleset.add_rule(subgroup2add, data)
expected_number_instances = data.number_instances
expected_bitset_uncovered = indexes2bitset(
[i for i in range(expected_number_instances) if i > 16666])
expected_bitset_covered = indexes2bitset(
[i for i in range(expected_number_instances) if i < 16666 + 1])
expected_number_rules = 1
expected_length_model = universal_code_integers(1) + universal_code_integers(1)+\
uniform_combination_code(1, 2) + universal_code_integers_maximum(1,2)+ \
uniform_code(10)
actual_numberinstances1 = popcount(output_ruleset.subgroups[0].bitarray) +\
popcount(output_ruleset.bitset_uncovered)
actual_numberinstances2 = output_ruleset.support_covered + output_ruleset.support_uncovered
actual_numberinstances3 = popcount(output_ruleset.bitset_covered) +\
popcount(output_ruleset.bitset_uncovered)
actual_numberinstances4 = output_ruleset.subgroups[
0].usage + output_ruleset.default_rule_statistics.usage
assert expected_number_instances == actual_numberinstances1
assert expected_number_instances == actual_numberinstances2
assert expected_number_instances == actual_numberinstances3
assert expected_number_instances == actual_numberinstances4
assert expected_bitset_uncovered == output_ruleset.bitset_uncovered
assert expected_bitset_covered == output_ruleset.bitset_covered
assert expected_number_rules == output_ruleset.number_rules
assert expected_length_model == pytest.approx(
output_ruleset.length_model)