def test_importances():
"""Check variable importances."""
X, y = datasets.make_classification(n_samples=2000,
n_features=10,
n_informative=3,
n_redundant=0,
n_repeated=0,
shuffle=False,
random_state=0)
for name, Tree in CLF_TREES.items():
clf = Tree(random_state=0)
clf.fit(X, y)
importances = clf.feature_importances_
n_important = np.sum(importances > 0.1)
assert_equal(importances.shape[0], 10, "Failed with {0}".format(name))
assert_equal(n_important, 3, "Failed with {0}".format(name))
X_new = clf.transform(X, threshold="mean")
assert_less(0, X_new.shape[1], "Failed with {0}".format(name))
assert_less(X_new.shape[1], X.shape[1], "Failed with {0}".format(name))
# Check on iris that importances are the same for all builders
clf = DecisionTreeClassifier(random_state=0)
clf.fit(iris.data, iris.target)
clf2 = DecisionTreeClassifier(random_state=0,
max_leaf_nodes=len(iris.data))
clf2.fit(iris.data, iris.target)
assert_array_equal(clf.feature_importances_,
clf2.feature_importances_)
def test_importances():
"""Check variable importances."""
X, y = datasets.make_classification(n_samples=2000,
n_features=10,
n_informative=3,
n_redundant=0,
n_repeated=0,
shuffle=False,
random_state=0)
for name, Tree in CLF_TREES.items():
clf = Tree(random_state=0)
clf.fit(X, y)
importances = clf.feature_importances_
n_important = np.sum(importances > 0.1)
assert_equal(importances.shape[0], 10, "Failed with {0}".format(name))
assert_equal(n_important, 3, "Failed with {0}".format(name))
X_new = clf.transform(X, threshold="mean")
assert_less(0, X_new.shape[1], "Failed with {0}".format(name))
assert_less(X_new.shape[1], X.shape[1], "Failed with {0}".format(name))
# Check on iris that importances are the same for all builders
clf = DecisionTreeClassifier(random_state=0)
clf.fit(iris.data, iris.target)
clf2 = DecisionTreeClassifier(random_state=0,
max_leaf_nodes=len(iris.data))
clf2.fit(iris.data, iris.target)
assert_array_equal(clf.feature_importances_, clf2.feature_importances_)
def test_big_input():
"""Test if the warning for too large inputs is appropriate."""
X = np.repeat(10 ** 40., 4).astype(np.float64).reshape(-1, 1)
clf = DecisionTreeClassifier()
try:
clf.fit(X, [0, 1, 0, 1])
except ValueError as e:
assert_in("float32", str(e))
def test_big_input():
"""Test if the warning for too large inputs is appropriate."""
X = np.repeat(10**40., 4).astype(np.float64).reshape(-1, 1)
clf = DecisionTreeClassifier()
try:
clf.fit(X, [0, 1, 0, 1])
except ValueError as e:
assert_in("float32", str(e))
def test_sample_weight():
"""Check sample weighting."""
# Test that zero-weighted samples are not taken into account
X = np.arange(100)[:, np.newaxis]
y = np.ones(100)
y[:50] = 0.0
sample_weight = np.ones(100)
sample_weight[y == 0] = 0.0
clf = DecisionTreeClassifier(random_state=0)
clf.fit(X, y, sample_weight=sample_weight)
assert_array_equal(clf.predict(X), np.ones(100))
# Test that low weighted samples are not taken into account at low depth
X = np.arange(200)[:, np.newaxis]
y = np.zeros(200)
y[50:100] = 1
y[100:200] = 2
X[100:200, 0] = 200
sample_weight = np.ones(200)
sample_weight[y == 2] = .51 # Samples of class '2' are still weightier
clf = DecisionTreeClassifier(max_depth=1, random_state=0)
clf.fit(X, y, sample_weight=sample_weight)
assert_equal(clf.tree_.threshold[0], 149.5)
sample_weight[y == 2] = .5 # Samples of class '2' are no longer weightier
clf = DecisionTreeClassifier(max_depth=1, random_state=0)
clf.fit(X, y, sample_weight=sample_weight)
assert_equal(clf.tree_.threshold[0], 49.5) # Threshold should have moved
# Test that sample weighting is the same as having duplicates
X = iris.data
y = iris.target
duplicates = rng.randint(0, X.shape[0], 200)
clf = DecisionTreeClassifier(random_state=1)
clf.fit(X[duplicates], y[duplicates])
sample_weight = np.bincount(duplicates, minlength=X.shape[0])
clf2 = DecisionTreeClassifier(random_state=1)
clf2.fit(X, y, sample_weight=sample_weight)
internal = clf.tree_.children_left != tree._tree.TREE_LEAF
assert_array_almost_equal(clf.tree_.threshold[internal],
clf2.tree_.threshold[internal])
def test_sample_weight():
"""Check sample weighting."""
# Test that zero-weighted samples are not taken into account
X = np.arange(100)[:, np.newaxis]
y = np.ones(100)
y[:50] = 0.0
sample_weight = np.ones(100)
sample_weight[y == 0] = 0.0
clf = DecisionTreeClassifier(random_state=0)
clf.fit(X, y, sample_weight=sample_weight)
assert_array_equal(clf.predict(X), np.ones(100))
# Test that low weighted samples are not taken into account at low depth
X = np.arange(200)[:, np.newaxis]
y = np.zeros(200)
y[50:100] = 1
y[100:200] = 2
X[100:200, 0] = 200
sample_weight = np.ones(200)
sample_weight[y == 2] = .51 # Samples of class '2' are still weightier
clf = DecisionTreeClassifier(max_depth=1, random_state=0)
clf.fit(X, y, sample_weight=sample_weight)
assert_equal(clf.tree_.threshold[0], 149.5)
sample_weight[y == 2] = .5 # Samples of class '2' are no longer weightier
clf = DecisionTreeClassifier(max_depth=1, random_state=0)
clf.fit(X, y, sample_weight=sample_weight)
assert_equal(clf.tree_.threshold[0], 49.5) # Threshold should have moved
# Test that sample weighting is the same as having duplicates
X = iris.data
y = iris.target
duplicates = rng.randint(0, X.shape[0], 200)
clf = DecisionTreeClassifier(random_state=1)
clf.fit(X[duplicates], y[duplicates])
sample_weight = np.bincount(duplicates, minlength=X.shape[0])
clf2 = DecisionTreeClassifier(random_state=1)
clf2.fit(X, y, sample_weight=sample_weight)
internal = clf.tree_.children_left != tree._tree.TREE_LEAF
assert_array_almost_equal(clf.tree_.threshold[internal],
clf2.tree_.threshold[internal])
