def test_evidenced_outside_on_path_graph(get_complex_graph_and_configurations):
test_data = get_complex_graph_and_configurations
hypothgraph = test_data['hypothgraph']
partial_within = test_data['partial_within']
source = partial_within.source
target = partial_within.target
before_confidence = compute_confidence.confidence(hypothgraph, partial_within)
before_max_confidence = compute_confidence.max_confidence(hypothgraph, source, target)
before_norm_confidence = compute_confidence.normalized_confidence(hypothgraph, partial_within)
# Evidence nodes which will not contribute to the causation confidence
on_boundary_nodes = boundary.on_boundary(hypothgraph, source, target)
outside_evidence_nodes = partial_within.evidenced_nodes + list(on_boundary_nodes)
# create new hypothesis configuration
new_conf = Hypoth_Conf(source=source,
target=target,
evidenced_nodes=outside_evidence_nodes)
after_confidence = compute_confidence.confidence(hypothgraph, new_conf)
after_max_confidence = compute_confidence.max_confidence(hypothgraph, source, target)
after_norm_confidence = compute_confidence.normalized_confidence(hypothgraph, new_conf)
assert before_confidence == after_confidence
assert before_max_confidence == after_max_confidence
assert before_norm_confidence == after_norm_confidence
def test_nothing_evidenced_on_path_graph(get_complex_graph_and_configurations):
test_data = get_complex_graph_and_configurations
hypothgraph = test_data['hypothgraph']
nothing = test_data['nothing']
# confidence with nothing evidenced should be 0
confidence = compute_confidence.confidence(hypothgraph, nothing)
assert confidence == 0
# max confidence for the same boundary should be bigger than confidence
max_confidence = compute_confidence.max_confidence(hypothgraph, nothing.source, nothing.target)
assert max_confidence > confidence
# normalized confidence should also be zero since we have nothing evidenced
normalized_confidence = compute_confidence.normalized_confidence(hypothgraph, nothing)
assert normalized_confidence == 0
def test_partial_evidenced_within_on_path_graph(get_complex_graph_and_configurations):
test_data = get_complex_graph_and_configurations
hypothgraph = test_data['hypothgraph']
partial_within = test_data['partial_within']
# confidence with nothing evidenced should be 0
confidence = compute_confidence.confidence(hypothgraph, partial_within)
assert confidence > 0
# max confidence for the same boundary should be bigger than confidence
max_confidence = compute_confidence.max_confidence(
hypothgraph, partial_within.source, partial_within.target)
assert max_confidence > confidence
# normalized confidence should be in (0..1)
normalized_confidence = compute_confidence.normalized_confidence(
hypothgraph, partial_within)
assert normalized_confidence > 0 and normalized_confidence < 1
def test_full_evidenced_within_on_path_graph(get_complex_graph_and_configurations):
test_data = get_complex_graph_and_configurations
hypothgraph = test_data['hypothgraph']
full_within = test_data['full_within']
# confidence with nothing evidenced should be 0
confidence = compute_confidence.confidence(hypothgraph, full_within)
assert confidence > 0
# max confidence for the same boundary should be equal to confidence
max_confidence = compute_confidence.max_confidence(
hypothgraph, full_within.source, full_within.target)
assert max_confidence == confidence
# normalized confidence should be 1
normalized_confidence = compute_confidence.normalized_confidence(
hypothgraph, full_within)
assert normalized_confidence == 1
def test_relative_confidence_richer(get_sample_configuration):
big, small, source, target = get_sample_configuration
# generate hypothesis configurations according to the small hypothesis
nothing_small = Hypoth_Conf(source, target, [])
partial_small = Hypoth_Conf(
source, target,
list(boundary.partial_nodes_boundary_interior(small, source, target)))
full_small = Hypoth_Conf(
source, target,
list(boundary.in_boundary_interior(small, source, target)))
# relative confidence is the normalized confidence in the small
# hypothegraph to the bigger hypothgraph
nothing_conf_big = compute_confidence.normalized_confidence(
big, nothing_small)
nothing_conf_small = compute_confidence.normalized_confidence(
small, nothing_small)
relative_nothing = abs(nothing_conf_small - nothing_conf_big)
partial_conf_big = compute_confidence.normalized_confidence(
big, partial_small)
partial_conf_small = compute_confidence.normalized_confidence(
small, partial_small)
relative_partial = abs(partial_conf_small - partial_conf_big)
full_conf_big = compute_confidence.normalized_confidence(big, full_small)
full_conf_small = compute_confidence.normalized_confidence(
small, full_small)
relative_full = abs(full_conf_small - full_conf_big)
# with nothing evidenced our confidence should be 0 regardless of the size
# of the hypothesis
assert nothing_conf_big == nothing_conf_small == 0
# with partial nodes smaller hypothesis confidence is at least as big as
# the confidence in the bigger hypothesis, but usually is bigger
assert partial_conf_small >= partial_conf_big
# with full nodes evidenced in the smaller hypothesis, the same
# configuration in the bigger hypothesis can only give a smaller confidence
assert full_conf_small >= full_conf_big