def test_dtype_of_classifier_probas(strategy):
y = [0, 2, 1, 1]
X = np.zeros(4)
model = DummyClassifier(strategy=strategy, random_state=0, constant=0)
probas = model.fit(X, y).predict_proba(X)
assert probas.dtype == np.float64
def test_constant_strategy_exceptions():
X = [[0], [0], [0], [0]] # ignored
y = [2, 1, 2, 2]
clf = DummyClassifier(strategy="constant", random_state=0)
assert_raises(ValueError, clf.fit, X, y)
clf = DummyClassifier(strategy="constant", random_state=0,
constant=[2, 0])
assert_raises(ValueError, clf.fit, X, y)
def test_uniform_strategy():
X = [[0]] * 4 # ignored
y = [1, 2, 1, 1]
clf = DummyClassifier(strategy="uniform", random_state=0)
clf.fit(X, y)
X = [[0]] * 500
y_pred = clf.predict(X)
p = np.bincount(y_pred) / float(len(X))
assert_almost_equal(p[1], 0.5, decimal=1)
assert_almost_equal(p[2], 0.5, decimal=1)
_check_predict_proba(clf, X, y)
def test_classifier_prediction_independent_of_X(strategy):
y = [0, 2, 1, 1]
X1 = [[0]] * 4
clf1 = DummyClassifier(strategy=strategy, random_state=0, constant=0)
clf1.fit(X1, y)
predictions1 = clf1.predict(X1)
X2 = [[1]] * 4
clf2 = DummyClassifier(strategy=strategy, random_state=0, constant=0)
clf2.fit(X2, y)
predictions2 = clf2.predict(X2)
assert_array_equal(predictions1, predictions2)
def test_most_frequent_and_prior_strategy_with_2d_column_y():
# non-regression test added in
# https://github.com/scikit-learn/scikit-learn/pull/13545
X = [[0], [0], [0], [0]]
y_1d = [1, 2, 1, 1]
y_2d = [[1], [2], [1], [1]]
for strategy in ("most_frequent", "prior"):
clf_1d = DummyClassifier(strategy=strategy, random_state=0)
clf_2d = DummyClassifier(strategy=strategy, random_state=0)
clf_1d.fit(X, y_1d)
clf_2d.fit(X, y_2d)
assert_array_equal(clf_1d.predict(X), clf_2d.predict(X))
def test_constant_strategy():
X = [[0], [0], [0], [0]] # ignored
y = [2, 1, 2, 2]
clf = DummyClassifier(strategy="constant", random_state=0, constant=1)
clf.fit(X, y)
assert_array_equal(clf.predict(X), np.ones(len(X)))
_check_predict_proba(clf, X, y)
X = [[0], [0], [0], [0]] # ignored
y = ['two', 'one', 'two', 'two']
clf = DummyClassifier(strategy="constant", random_state=0, constant='one')
clf.fit(X, y)
assert_array_equal(clf.predict(X), np.array(['one'] * 4))
_check_predict_proba(clf, X, y)
def test_classification_sample_weight():
X = [[0], [0], [1]]
y = [0, 1, 0]
sample_weight = [0.1, 1., 0.1]
clf = DummyClassifier().fit(X, y, sample_weight)
assert_array_almost_equal(clf.class_prior_, [0.2 / 1.2, 1. / 1.2])
def test_constant_strategy_multioutput():
X = [[0], [0], [0], [0]] # ignored
y = np.array([[2, 3],
[1, 3],
[2, 3],
[2, 0]])
n_samples = len(X)
clf = DummyClassifier(strategy="constant", random_state=0,
constant=[1, 0])
clf.fit(X, y)
assert_array_equal(clf.predict(X),
np.hstack([np.ones((n_samples, 1)),
np.zeros((n_samples, 1))]))
_check_predict_proba(clf, X, y)
def test_constant_strategy_sparse_target():
X = [[0]] * 5 # ignored
y = sp.csc_matrix(np.array([[0, 1],
[4, 0],
[1, 1],
[1, 4],
[1, 1]]))
n_samples = len(X)
clf = DummyClassifier(strategy="constant", random_state=0, constant=[1, 0])
clf.fit(X, y)
y_pred = clf.predict(X)
assert sp.issparse(y_pred)
assert_array_equal(y_pred.toarray(), np.hstack([np.ones((n_samples, 1)),
np.zeros((n_samples, 1))]))
def test_most_frequent_and_prior_strategy_sparse_target():
X = [[0]] * 5 # ignored
y = sp.csc_matrix(np.array([[1, 0],
[1, 3],
[4, 0],
[0, 1],
[1, 0]]))
n_samples = len(X)
y_expected = np.hstack([np.ones((n_samples, 1)), np.zeros((n_samples, 1))])
for strategy in ("most_frequent", "prior"):
clf = DummyClassifier(strategy=strategy, random_state=0)
clf.fit(X, y)
y_pred = clf.predict(X)
assert sp.issparse(y_pred)
assert_array_equal(y_pred.toarray(), y_expected)
def test_most_frequent_and_prior_strategy_multioutput():
X = [[0], [0], [0], [0]] # ignored
y = np.array([[1, 0],
[2, 0],
[1, 0],
[1, 3]])
n_samples = len(X)
for strategy in ("prior", "most_frequent"):
clf = DummyClassifier(strategy=strategy, random_state=0)
clf.fit(X, y)
assert_array_equal(clf.predict(X),
np.hstack([np.ones((n_samples, 1)),
np.zeros((n_samples, 1))]))
_check_predict_proba(clf, X, y)
_check_behavior_2d(clf)
def test_uniform_strategy_multioutput():
X = [[0]] * 4 # ignored
y = np.array([[2, 1],
[2, 2],
[1, 2],
[1, 1]])
clf = DummyClassifier(strategy="uniform", random_state=0)
clf.fit(X, y)
X = [[0]] * 500
y_pred = clf.predict(X)
for k in range(y.shape[1]):
p = np.bincount(y_pred[:, k]) / float(len(X))
assert_almost_equal(p[1], 0.5, decimal=1)
assert_almost_equal(p[2], 0.5, decimal=1)
_check_predict_proba(clf, X, y)
_check_behavior_2d(clf)
def test_uniform_strategy_sparse_target_warning():
X = [[0]] * 5 # ignored
y = sp.csc_matrix(np.array([[2, 1],
[2, 2],
[1, 4],
[4, 2],
[1, 1]]))
clf = DummyClassifier(strategy="uniform", random_state=0)
assert_warns_message(UserWarning,
"the uniform strategy would not save memory",
clf.fit, X, y)
X = [[0]] * 500
y_pred = clf.predict(X)
for k in range(y.shape[1]):
p = np.bincount(y_pred[:, k]) / float(len(X))
assert_almost_equal(p[1], 1 / 3, decimal=1)
assert_almost_equal(p[2], 1 / 3, decimal=1)
assert_almost_equal(p[4], 1 / 3, decimal=1)
def test_stratified_strategy_sparse_target():
X = [[0]] * 5 # ignored
y = sp.csc_matrix(np.array([[4, 1],
[0, 0],
[1, 1],
[1, 4],
[1, 1]]))
clf = DummyClassifier(strategy="stratified", random_state=0)
clf.fit(X, y)
X = [[0]] * 500
y_pred = clf.predict(X)
assert sp.issparse(y_pred)
y_pred = y_pred.toarray()
for k in range(y.shape[1]):
p = np.bincount(y_pred[:, k]) / float(len(X))
assert_almost_equal(p[1], 3. / 5, decimal=1)
assert_almost_equal(p[0], 1. / 5, decimal=1)
assert_almost_equal(p[4], 1. / 5, decimal=1)
def test_partial_dependence_pipeline():
# check that the partial dependence support pipeline
iris = load_iris()
scaler = StandardScaler()
clf = DummyClassifier(random_state=42)
pipe = make_pipeline(scaler, clf)
clf.fit(scaler.fit_transform(iris.data), iris.target)
pipe.fit(iris.data, iris.target)
features = 0
pdp_pipe, values_pipe = partial_dependence(pipe,
iris.data,
features=[features])
pdp_clf, values_clf = partial_dependence(clf,
scaler.transform(iris.data),
features=[features])
assert_allclose(pdp_pipe, pdp_clf)
assert_allclose(
values_pipe[0],
values_clf[0] * scaler.scale_[features] + scaler.mean_[features])
def test_warning_recursion_non_constant_init():
# make sure that passing a non-constant init parameter to a GBDT and using
# recursion method yields a warning.
gbc = GradientBoostingClassifier(init=DummyClassifier(), random_state=0)
gbc.fit(X, y)
with pytest.warns(
UserWarning,
match='Using recursion method with a non-constant init predictor'):
partial_dependence(gbc, X, [0], method='recursion')
with pytest.warns(
UserWarning,
match='Using recursion method with a non-constant init predictor'):
partial_dependence(gbc, X, [0], method='recursion')
def test_dummy_classifier_on_3D_array():
X = np.array([[['foo']], [['bar']], [['baz']]])
y = [2, 2, 2]
y_expected = [2, 2, 2]
y_proba_expected = [[1], [1], [1]]
cls = DummyClassifier()
cls.fit(X, y)
y_pred = cls.predict(X)
y_pred_proba = cls.predict_proba(X)
assert_array_equal(y_pred, y_expected)
assert_array_equal(y_pred_proba, y_proba_expected)
def test_most_frequent_and_prior_strategy():
X = [[0], [0], [0], [0]] # ignored
y = [1, 2, 1, 1]
for strategy in ("most_frequent", "prior"):
clf = DummyClassifier(strategy=strategy, random_state=0)
clf.fit(X, y)
assert_array_equal(clf.predict(X), np.ones(len(X)))
_check_predict_proba(clf, X, y)
if strategy == "prior":
assert_array_almost_equal(clf.predict_proba([X[0]]),
clf.class_prior_.reshape((1, -1)))
else:
assert_array_almost_equal(clf.predict_proba([X[0]]),
clf.class_prior_.reshape((1, -1)) > 0.5)
def test_multidimensional_X():
"""
Check that the AdaBoost estimators can work with n-dimensional
data matrix
"""
from mrex.dummy import DummyClassifier, DummyRegressor
rng = np.random.RandomState(0)
X = rng.randn(50, 3, 3)
yc = rng.choice([0, 1], 50)
yr = rng.randn(50)
boost = AdaBoostClassifier(DummyClassifier(strategy='most_frequent'))
boost.fit(X, yc)
boost.predict(X)
boost.predict_proba(X)
boost = AdaBoostRegressor(DummyRegressor())
boost.fit(X, yr)
boost.predict(X)
from mrex.dummy import DummyClassifier
from mrex.datasets import fetch_20newsgroups_vectorized
from mrex.metrics import accuracy_score
from mrex.utils.validation import check_array
from mrex.ensemble import RandomForestClassifier
from mrex.ensemble import ExtraTreesClassifier
from mrex.ensemble import AdaBoostClassifier
from mrex.linear_model import LogisticRegression
from mrex.naive_bayes import MultinomialNB
ESTIMATORS = {
"dummy":
DummyClassifier(),
"random_forest":
RandomForestClassifier(max_features="sqrt", min_samples_split=10),
"extra_trees":
ExtraTreesClassifier(max_features="sqrt", min_samples_split=10),
"logistic_regression":
LogisticRegression(),
"naive_bayes":
MultinomialNB(),
"adaboost":
AdaBoostClassifier(n_estimators=10),
}
###############################################################################
# Data
# Normalize features
X = X / 255
# Create train-test split (as [Joachims, 2006])
print("Creating train-test split...")
n_train = 60000
X_train = X[:n_train]
y_train = y[:n_train]
X_test = X[n_train:]
y_test = y[n_train:]
return X_train, X_test, y_train, y_test
ESTIMATORS = {
"dummy": DummyClassifier(),
'CART': DecisionTreeClassifier(),
'ExtraTrees': ExtraTreesClassifier(),
'RandomForest': RandomForestClassifier(),
'Nystroem-SVM': make_pipeline(
Nystroem(gamma=0.015, n_components=1000), LinearSVC(C=100)),
'SampledRBF-SVM': make_pipeline(
RBFSampler(gamma=0.015, n_components=1000), LinearSVC(C=100)),
'LogisticRegression-SAG': LogisticRegression(solver='sag', tol=1e-1,
C=1e4),
'LogisticRegression-SAGA': LogisticRegression(solver='saga', tol=1e-1,
C=1e4),
'MultilayerPerceptron': MLPClassifier(
hidden_layer_sizes=(100, 100), max_iter=400, alpha=1e-4,
solver='sgd', learning_rate_init=0.2, momentum=0.9, verbose=1,
tol=1e-4, random_state=1),
def test_string_labels():
X = [[0]] * 5
y = ["paris", "paris", "tokyo", "amsterdam", "berlin"]
clf = DummyClassifier(strategy="most_frequent")
clf.fit(X, y)
assert_array_equal(clf.predict(X), ["paris"] * 5)
def test_classifier_score_with_None(y, y_test):
clf = DummyClassifier(strategy="most_frequent")
clf.fit(None, y)
assert clf.score(None, y_test) == 0.5
def test_classifier_exceptions():
clf = DummyClassifier(strategy="unknown")
assert_raises(ValueError, clf.fit, [], [])
assert_raises(NotFittedError, clf.predict, [])
assert_raises(NotFittedError, clf.predict_proba, [])