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,
)
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)
y_pos = np.array(y_pos)
y_neg = np.array(y_neg)
plt.plot(x, y_pos, "b-", label="Mean Probability of positive examples")
plt.plot(x, y_neg, "r-", label="Mean Probability of negative examples")
plt.plot(x, thresholds, "k--", label="Margin")
plt.title("Class Probability vs. Number Trees")
plt.xlabel("Number of Trees")
plt.ylabel("Probability of belonging to Positive Class")
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).",
]
test_db.facts = [
"male(mrbennet).",
"male(mrlucas).",
"male(darcy).",
"childof(mrbennet,elizabeth).",
"childof(mrsbennet,elizabeth).",
"childof(mrbennet,jane).",
"childof(mrsbennet,jane).",
"childof(mrlucas,charlotte).",
"childof(mrslucas,charlotte).",
"siblingof(jane,elizabeth).",
"siblingof(elizabeth,jane).",
]
print(clf.predict_proba(test_db))