def test_determine_pairs_to_do():
X, y = load_iris()
# Train a model and make predictions
X_train, X_test, y_train, y_test = model_selection.train_test_split(
X, y, shuffle=True
)
model = pipeline.make_pipeline(
preprocessing.StandardScaler(),
linear_model.LogisticRegression(solver="lbfgs", multi_class="auto"),
)
model.fit(X_train, y_train)
y_pred = model.predict_proba(X_test)
y_pred = pd.DataFrame(y_pred, columns=model.classes_)
# With memoization
explainer = ethik.ClassificationExplainer(memoize=True, n_jobs=1)
to_do = explainer._determine_pairs_to_do(["sepal length (cm)"], ["setosa"])
assert to_do == {"sepal length (cm)": ["setosa"]}
explainer.explain_bias(X_test["sepal length (cm)"], y_pred["setosa"])
to_do = explainer._determine_pairs_to_do(["sepal length (cm)"], ["setosa"])
assert to_do == {}
to_do = explainer._determine_pairs_to_do(
["sepal length (cm)", "petal width (cm)"], ["setosa", "virginica"]
)
assert to_do == {
"petal width (cm)": ["setosa", "virginica"],
"sepal length (cm)": ["virginica"],
}
def test_target_identity():
X, y = load_iris()
X_train, X_test, y_train, y_test = model_selection.train_test_split(
X, y, shuffle=True, random_state=42)
model = pipeline.make_pipeline(preprocessing.StandardScaler(),
neighbors.KNeighborsClassifier())
model.fit(X_train, y_train)
y_pred = model.predict_proba(X_test)
y_pred = pd.DataFrame(y_pred, columns=model.classes_)
explainer = ethik.ClassificationExplainer(memoize=True)
label = y_pred.columns[0]
explainer.explain_influence(X_test=X_test, y_pred=y_pred[label])
explainer.explain_influence(X_test=X_test["petal width (cm)"],
y_pred=y_pred[label])
rows = explainer.info.query(
f"label == '{label}' and feature == 'petal width (cm)' and tau == -0.85"
)
assert len(rows) == 1
def setup_adult():
url = "https://archive.ics.uci.edu/ml/machine-learning-databases/adult/adult.data"
names = [
"age",
"workclass",
"fnlwgt",
"education",
"education-num",
"marital-status",
"occupation",
"relationship",
"race",
"gender",
"capital-gain",
"capital-loss",
"hours-per-week",
"native-country",
"salary",
]
dtypes = {
"workclass": "category",
"education": "category",
"marital-status": "category",
"occupation": "category",
"relationship": "category",
"race": "category",
"gender": "category",
"native-country": "category",
}
X = pd.read_csv(url, names=names, header=None, dtype=dtypes)
X["gender"] = (X["gender"].str.strip().astype("category")
) # Remove leading whitespace
y = X.pop("salary").map({" <=50K": False, " >50K": True})
X_train, X_test, y_train, y_test = model_selection.train_test_split(
X, y, shuffle=True, random_state=42)
model = lgb.LGBMClassifier(random_state=42).fit(X_train, y_train)
y_pred = model.predict_proba(X_test)[:, 1]
y_pred = pd.Series(y_pred, name=">$50k")
explainer = ethik.ClassificationExplainer()
return explainer, X_test, y_pred, y_test
#print(X_test['averageAll']) classifier = svm.SVC(kernel='linear', gamma='auto', C=2, probability=True) classifier.fit(X_train, y_train) y_predict = classifier.predict(X_test) y_pred = classifier.predict_proba(X_test)[:, 1] y_pred = pd.Series(y_pred, name='averageAll') import ethik explainer = ethik.ClassificationExplainer() print(y_pred) #print(X_test['averageAll']) #explainer.plot_influence(X_test=X_test, y_pred=y_predict).show() #classifier.predict_proba #evaluation from sklearn.metrics import classification_report
def test_check_tol():
for tol in (-1, 0):
with pytest.raises(ValueError):
ethik.ClassificationExplainer(tol=tol)
def test_check_max_iterations():
for max_iterations in (-1, 0):
with pytest.raises(ValueError):
ethik.ClassificationExplainer(max_iterations=max_iterations)
def test_check_conf_level():
for conf_level in (-1, 0, 0.5):
with pytest.raises(ValueError):
ethik.ClassificationExplainer(conf_level=conf_level)
def test_check_sample_frac():
for sample_frac in (-1, 0, 1):
with pytest.raises(ValueError):
ethik.ClassificationExplainer(sample_frac=sample_frac)
def test_check_n_samples():
for n_samples in (-1, 0):
with pytest.raises(ValueError):
ethik.ClassificationExplainer(n_samples=n_samples)
def test_check_alpha():
for alpha in (-1, -0.1, 0.5, 1):
with pytest.raises(ValueError):
ethik.ClassificationExplainer(alpha=alpha)