def test_friedman_mse_in_graphviz():
clf = DecisionTreeRegressor(criterion="friedman_mse", random_state=0)
clf.fit(X, y)
dot_data = StringIO()
export_graphviz(clf, out_file=dot_data)
clf = GradientBoostingClassifier(n_estimators=2, random_state=0)
clf.fit(X, y)
for estimator in clf.estimators_:
export_graphviz(estimator[0], out_file=dot_data)
for finding in finditer(r"\[.*?samples.*?\]", dot_data.getvalue()):
assert "friedman_mse" in finding.group()
def test_thresholded_scorers():
# Test scorers that take thresholds.
X, y = make_blobs(random_state=0, centers=2)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
clf = LogisticRegression(random_state=0)
clf.fit(X_train, y_train)
score1 = get_scorer('roc_auc')(clf, X_test, y_test)
score2 = roc_auc_score(y_test, clf.decision_function(X_test))
score3 = roc_auc_score(y_test, clf.predict_proba(X_test)[:, 1])
assert_almost_equal(score1, score2)
assert_almost_equal(score1, score3)
logscore = get_scorer('neg_log_loss')(clf, X_test, y_test)
logloss = log_loss(y_test, clf.predict_proba(X_test))
assert_almost_equal(-logscore, logloss)
# same for an estimator without decision_function
clf = DecisionTreeClassifier()
clf.fit(X_train, y_train)
score1 = get_scorer('roc_auc')(clf, X_test, y_test)
score2 = roc_auc_score(y_test, clf.predict_proba(X_test)[:, 1])
assert_almost_equal(score1, score2)
# test with a regressor (no decision_function)
reg = DecisionTreeRegressor()
reg.fit(X_train, y_train)
score1 = get_scorer('roc_auc')(reg, X_test, y_test)
score2 = roc_auc_score(y_test, reg.predict(X_test))
assert_almost_equal(score1, score2)
# Test that an exception is raised on more than two classes
X, y = make_blobs(random_state=0, centers=3)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
clf.fit(X_train, y_train)
with pytest.raises(ValueError, match="multiclass format is not supported"):
get_scorer('roc_auc')(clf, X_test, y_test)
# test error is raised with a single class present in model
# (predict_proba shape is not suitable for binary auc)
X, y = make_blobs(random_state=0, centers=2)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
clf = DecisionTreeClassifier()
clf.fit(X_train, np.zeros_like(y_train))
with pytest.raises(ValueError, match="need classifier with two classes"):
get_scorer('roc_auc')(clf, X_test, y_test)
# for proba scorers
with pytest.raises(ValueError, match="need classifier with two classes"):
get_scorer('neg_log_loss')(clf, X_test, y_test)
def _make_estimators(X_train, y_train, y_ml_train):
# Make estimators that make sense to test various scoring methods
sensible_regr = DecisionTreeRegressor(random_state=0)
# some of the regressions scorers require strictly positive input.
sensible_regr.fit(X_train, y_train + 1)
sensible_clf = DecisionTreeClassifier(random_state=0)
sensible_clf.fit(X_train, y_train)
sensible_ml_clf = DecisionTreeClassifier(random_state=0)
sensible_ml_clf.fit(X_train, y_ml_train)
return dict(
[(name, sensible_regr) for name in REGRESSION_SCORERS] +
[(name, sensible_clf) for name in CLF_SCORERS] +
[(name, sensible_clf) for name in CLUSTER_SCORERS] +
[(name, sensible_ml_clf) for name in MULTILABEL_ONLY_SCORERS]
)
def test_export_text():
clf = DecisionTreeClassifier(max_depth=2, random_state=0)
clf.fit(X, y)
expected_report = dedent("""
|--- feature_1 <= 0.00
| |--- class: -1
|--- feature_1 > 0.00
| |--- class: 1
""").lstrip()
assert export_text(clf) == expected_report
# testing that leaves at level 1 are not truncated
assert export_text(clf, max_depth=0) == expected_report
# testing that the rest of the tree is truncated
assert export_text(clf, max_depth=10) == expected_report
expected_report = dedent("""
|--- b <= 0.00
| |--- class: -1
|--- b > 0.00
| |--- class: 1
""").lstrip()
assert export_text(clf, feature_names=['a', 'b']) == expected_report
expected_report = dedent("""
|--- feature_1 <= 0.00
| |--- weights: [3.00, 0.00] class: -1
|--- feature_1 > 0.00
| |--- weights: [0.00, 3.00] class: 1
""").lstrip()
assert export_text(clf, show_weights=True) == expected_report
expected_report = dedent("""
|- feature_1 <= 0.00
| |- class: -1
|- feature_1 > 0.00
| |- class: 1
""").lstrip()
assert export_text(clf, spacing=1) == expected_report
X_l = [[-2, -1], [-1, -1], [-1, -2], [1, 1], [1, 2], [2, 1], [-1, 1]]
y_l = [-1, -1, -1, 1, 1, 1, 2]
clf = DecisionTreeClassifier(max_depth=4, random_state=0)
clf.fit(X_l, y_l)
expected_report = dedent("""
|--- feature_1 <= 0.00
| |--- class: -1
|--- feature_1 > 0.00
| |--- truncated branch of depth 2
""").lstrip()
assert export_text(clf, max_depth=0) == expected_report
X_mo = [[-2, -1], [-1, -1], [-1, -2], [1, 1], [1, 2], [2, 1]]
y_mo = [[-1, -1], [-1, -1], [-1, -1], [1, 1], [1, 1], [1, 1]]
reg = DecisionTreeRegressor(max_depth=2, random_state=0)
reg.fit(X_mo, y_mo)
expected_report = dedent("""
|--- feature_1 <= 0.0
| |--- value: [-1.0, -1.0]
|--- feature_1 > 0.0
| |--- value: [1.0, 1.0]
""").lstrip()
assert export_text(reg, decimals=1) == expected_report
assert export_text(reg, decimals=1, show_weights=True) == expected_report
X_single = [[-2], [-1], [-1], [1], [1], [2]]
reg = DecisionTreeRegressor(max_depth=2, random_state=0)
reg.fit(X_single, y_mo)
expected_report = dedent("""
|--- first <= 0.0
| |--- value: [-1.0, -1.0]
|--- first > 0.0
| |--- value: [1.0, 1.0]
""").lstrip()
assert export_text(reg, decimals=1,
feature_names=['first']) == expected_report
assert export_text(reg, decimals=1, show_weights=True,
feature_names=['first']) == expected_report