def test_predict_fixed(self, iris_test_data, iris_edge_list):
df = iris_test_data.copy()
ground_truth = np.array([
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[2, 2, 2, 1, 1, 1, 2, 0, 1, 1],
[0, 2, 1, 1, 0, 2, 2, 1, 1, 1],
[2, 1, 1, 1, 1, 2, 1, 2, 1, 0],
[1, 1, 1, 1, 2, 2, 2, 1, 2, 1],
[1, 2, 1, 0, 1, 2, 1, 1, 0, 1],
[2, 1, 2, 1, 2, 2, 1, 1, 1, 2],
[2, 1, 2, 1, 1, 2, 2, 2, 1, 1],
[2, 1, 1, 1, 2, 2, 1, 2, 1, 2],
[1, 2, 1, 1, 1, 2, 2, 2, 2, 2],
[2, 2, 1, 2, 2, 2, 1, 2, 2, 2],
])
discretiser_params = {
"sepal width (cm)": {
"method": "fixed",
"numeric_split_points": [3]
},
"petal length (cm)": {
"method": "fixed",
"numeric_split_points": [3.7]
},
"petal width (cm)": {
"method": "fixed",
"numeric_split_points": [1.2]
},
}
label = df["sepal length (cm)"]
df.drop(["sepal length (cm)"], axis=1, inplace=True)
clf = BayesianNetworkClassifier(
iris_edge_list,
discretiser_kwargs=discretiser_params,
discretiser_alg={
"sepal width (cm)": "unsupervised",
"petal length (cm)": "unsupervised",
"petal width (cm)": "unsupervised",
},
)
clf.fit(df, label)
output = clf.predict(df)
assert np.array_equal(output.reshape(15, -1), ground_truth)
def test_dt_discretiser(self, iris_test_data, iris_edge_list):
df = iris_test_data.copy()
ground_truth = np.array([
[0, 0, 0, 0, 0, 1, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 1, 0],
[1, 0, 0, 0, 1, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 1, 0, 0, 0, 0, 0],
[2, 2, 2, 1, 1, 1, 2, 0, 1, 1],
[0, 1, 1, 1, 1, 2, 1, 1, 1, 1],
[2, 1, 1, 1, 1, 1, 1, 1, 1, 0],
[1, 1, 1, 1, 1, 1, 2, 1, 1, 1],
[1, 1, 1, 0, 1, 1, 1, 1, 0, 1],
[2, 1, 2, 2, 2, 2, 1, 2, 2, 2],
[2, 2, 2, 1, 1, 2, 2, 2, 2, 1],
[2, 1, 2, 1, 2, 2, 1, 1, 2, 2],
[2, 2, 2, 1, 2, 2, 2, 2, 1, 2],
[2, 2, 1, 2, 2, 2, 1, 2, 2, 1],
])
supervised_param = {
"sepal width (cm)": {
"max_depth": 2,
"random_state": 2020
},
"petal length (cm)": {
"max_depth": 2,
"random_state": 2020
},
"petal width (cm)": {
"max_depth": 2,
"random_state": 2020
},
}
label = df["sepal length (cm)"]
df.drop(["sepal length (cm)"], axis=1, inplace=True)
clf = BayesianNetworkClassifier(
iris_edge_list,
discretiser_kwargs=supervised_param,
discretiser_alg={
"sepal width (cm)": "tree",
"petal length (cm)": "tree",
"petal width (cm)": "tree",
},
)
clf.fit(df, label)
output = clf.predict(df)
assert np.array_equal(output.reshape(15, -1), ground_truth)
def test_shuffled_data(self, iris_test_data, iris_edge_list):
df = iris_test_data.copy()
df = df.sample(frac=0.5, random_state=2020)
ground_truth = np.array([
[2, 0, 1, 2, 2, 1, 2, 0, 0, 0, 2, 1, 0, 2, 2],
[0, 1, 2, 2, 0, 0, 1, 2, 0, 2, 1, 1, 2, 0, 0],
[2, 0, 0, 0, 2, 0, 0, 1, 0, 1, 0, 2, 1, 0, 2],
[2, 1, 2, 2, 0, 0, 1, 1, 0, 2, 1, 2, 2, 1, 1],
[0, 0, 0, 0, 1, 2, 0, 0, 1, 2, 2, 0, 0, 2, 0],
])
supervised_param = {
"sepal width (cm)": {
"max_depth": 2,
"random_state": 2020
},
"petal length (cm)": {
"max_depth": 2,
"random_state": 2020
},
"petal width (cm)": {
"max_depth": 2,
"random_state": 2020
},
}
label = df["sepal length (cm)"]
df.drop(["sepal length (cm)"], axis=1, inplace=True)
clf = BayesianNetworkClassifier(
iris_edge_list,
discretiser_kwargs=supervised_param,
discretiser_alg={
"sepal width (cm)": "tree",
"petal length (cm)": "tree",
"petal width (cm)": "tree",
},
)
clf.fit(df, label)
output = clf.predict(df)
assert np.isnan(output).sum() == 0
assert (ground_truth == output.reshape(5, 15)).all()
def test_return_probability(self, iris_test_data, iris_edge_list):
df = iris_test_data.copy()
discretiser_params = {
"sepal width (cm)": {
"method": "fixed",
"numeric_split_points": [3]
},
"petal length (cm)": {
"method": "fixed",
"numeric_split_points": [3.7]
},
"petal width (cm)": {
"method": "fixed",
"numeric_split_points": [1.2]
},
}
label = df["sepal length (cm)"]
df.drop(["sepal length (cm)"], axis=1, inplace=True)
clf = BayesianNetworkClassifier(
iris_edge_list,
discretiser_kwargs=discretiser_params,
discretiser_alg={
"sepal width (cm)": "unsupervised",
"petal length (cm)": "unsupervised",
"petal width (cm)": "unsupervised",
},
return_prob=True,
)
clf.fit(df, label)
output = clf.predict(df.iloc[0:1])
assert len(list(output)) == 3
assert math.isclose(output["sepal length (cm)_0"].values,
0.764706,
abs_tol=1e-3)
assert math.isclose(output["sepal length (cm)_1"].values,
0.215686,
abs_tol=1e-3)