def test_learn_example_dataset_1(test_input):
"""Learn from the example database."""
_bk = Background(modes=example_data.train.modes,
use_std_logic_variables=True)
_dn = RDN(background=_bk, target="cancer", n_estimators=test_input)
_dn.fit(example_data.train)
assert len(_dn.estimators_) == test_input
def test_initialize_bad_n_estimators(test_input):
"""Test bad values for n_estimators"""
_dn = RDN(target="cancer",
background=Background(),
n_estimators=test_input)
with pytest.raises(ValueError):
_dn.fit(example_data.train)
def test_predict_example_data(test_input):
"""Test learn and predict."""
_bk = Background(modes=example_data.train.modes,
use_std_logic_variables=True)
_dn = RDN(background=_bk, target="cancer", n_estimators=test_input)
_dn.fit(example_data.train)
assert_array_equal(_dn.predict(example_data.test),
np.array([1.0, 1.0, 1.0, 0.0, 0.0]))
def test_predict_proba_test_data():
"""Assert arrays are almost equal on output of predict_proba()"""
_bk = Background(modes=example_data.train.modes,
use_std_logic_variables=True)
_dn = RDN(background=_bk, target="cancer", n_estimators=5)
_dn.fit(example_data.train)
assert_array_almost_equal(
_dn.predict_proba(example_data.test),
np.array([0.74, 0.74, 0.74, 0.25, 0.25]),
decimal=2,
)
def test_initialize_bad_background(test_input):
"""Test bad input for background"""
_dn = RDN(target="cancer", background=test_input)
with pytest.raises(ValueError):
_dn.fit(example_data.train)
def test_initialize_bad_target(test_input):
"""Initialize an RDN with incorrect target values."""
_dn = RDN(target=test_input)
with pytest.raises(ValueError):
_dn.fit(example_data.train)
import matplotlib.pyplot as plt
bk = Background(
modes=example_data.train.modes,
use_std_logic_variables=True,
)
clf = RDN(
background=bk,
target='cancer',
max_tree_depth=2,
node_size=2,
n_estimators=20,
)
clf.fit(example_data.train)
x = np.arange(1, 21)
y_pos = []
y_neg = []
thresholds = []
for n_trees in x:
clf.set_params(n_estimators=n_trees)
probs = clf.predict_proba(example_data.test)
thresholds.append(clf.threshold_)
y_pos.append(np.mean(probs[np.nonzero(clf.classes_)]))
y_neg.append(np.mean(probs[clf.classes_ == 0]))
thresholds = np.array(thresholds)
bk = Background(
modes=[
"male(+name).", "father(+name,+name).", "childof(+name,+name).",
"siblingof(+name,+name)."
],
number_of_clauses=8,
use_prolog_variables=True,
)
clf = RDN(
background=bk,
target="father",
n_estimators=5,
)
clf.fit(train_db)
test_db = Database()
test_db.pos = [
"father(elizabeth,mrbennet).",
"father(jane,mrbennet).",
"father(charlotte,mrlucas).",
]
test_db.neg = [
"father(charlotte,mrsbennet).",
"father(jane,mrlucas).",
"father(mrsbennet,mrbennet).",
"father(jane,elizabeth).",
]