def __init__(self,
n_estimators=100,
max_features="auto",
max_depth=6,
min_samples_split=2,
min_weight_fraction_leaf=0.0,
n_jobs=-1,
random_state=None,
random_seed=0,
**kwargs):
parameters = {
"n_estimators": n_estimators,
"max_features": max_features,
"max_depth": max_depth,
"min_samples_split": min_samples_split,
"min_weight_fraction_leaf": min_weight_fraction_leaf,
"n_jobs": n_jobs
}
parameters.update(kwargs)
random_seed = deprecate_arg("random_state", "random_seed",
random_state, random_seed)
et_classifier = SKExtraTreesClassifier(random_state=random_seed,
**parameters)
super().__init__(parameters=parameters,
component_obj=et_classifier,
random_seed=random_seed)
def test_feature_importance(X_y_binary):
X, y = X_y_binary
clf = ExtraTreesClassifier(n_jobs=1)
sk_clf = SKExtraTreesClassifier(max_depth=6, random_state=0, n_jobs=1)
sk_clf.fit(X, y)
sk_feature_importance = sk_clf.feature_importances_
clf.fit(X, y)
feature_importance = clf.feature_importance
np.testing.assert_almost_equal(sk_feature_importance,
feature_importance,
decimal=5)
def test_fit_predict_binary(X_y_binary):
X, y = X_y_binary
sk_clf = SKExtraTreesClassifier(max_depth=6, random_state=0)
sk_clf.fit(X, y)
y_pred_sk = sk_clf.predict(X)
y_pred_proba_sk = sk_clf.predict_proba(X)
clf = ExtraTreesClassifier()
clf.fit(X, y)
y_pred = clf.predict(X)
y_pred_proba = clf.predict_proba(X)
np.testing.assert_almost_equal(y_pred, y_pred_sk, decimal=5)
np.testing.assert_almost_equal(y_pred_proba, y_pred_proba_sk, decimal=5)
def test_fit_predict_multi(X_y_multi):
X, y = X_y_multi
sk_clf = SKExtraTreesClassifier(max_depth=6, random_state=0)
sk_clf.fit(X, y)
y_pred_sk = sk_clf.predict(X)
y_pred_proba_sk = sk_clf.predict_proba(X)
clf = ExtraTreesClassifier()
fitted = clf.fit(X, y)
assert isinstance(fitted, ExtraTreesClassifier)
y_pred = clf.predict(X)
y_pred_proba = clf.predict_proba(X)
np.testing.assert_almost_equal(y_pred, y_pred_sk, decimal=5)
np.testing.assert_almost_equal(y_pred_proba, y_pred_proba_sk, decimal=5)
from sklearn.linear_model import LogisticRegression
from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC
from sklearn.tree import DecisionTreeClassifier
from sklearn.datasets import load_breast_cancer, load_iris, load_wine
from extra_trees.ensemble.forest import ExtraTreesClassifier
# prepare models
classification_models = [
('Logistic', LogisticRegression()),
('Nearest Neighbors', KNeighborsClassifier()),
('SVM', SVC()),
('DecisionTree', DecisionTreeClassifier()),
('RandomForest', RandomForestClassifier()),
('ExtraTrees (SciKit)', SKExtraTreesClassifier()),
('ExtraTrees', ExtraTreesClassifier()),
]
seed = 7
print("breast_cancer")
breast_cancer = load_breast_cancer()
X, y = breast_cancer.data, breast_cancer.target
# evaluate each model in turn
results = []
names = []
scoring = 'accuracy'
for name, model in classification_models:
kfold = model_selection.KFold(n_splits=10, random_state=seed)
cv_results = model_selection.cross_val_score(model, X, y, cv=kfold, scoring=scoring)
results.append(cv_results)
"ExtraTrees (SciKit)",
"ExtraTrees",
]
classifiers = [
KNeighborsClassifier(3),
SVC(kernel="linear", C=0.025),
SVC(gamma=2, C=1),
GaussianProcessClassifier(1.0 * RBF(1.0), warm_start=True),
MLPClassifier(alpha=1),
GaussianNB(),
QuadraticDiscriminantAnalysis(),
AdaBoostClassifier(),
DecisionTreeClassifier(max_depth=5),
RandomForestClassifier(max_depth=5, n_estimators=10, max_features=2),
SKExtraTreesClassifier(n_estimators=10, max_features=2),
ExtraTreesClassifier(n_estimators=10, max_features=2),
]
X, y = make_classification(n_features=2,
n_redundant=0,
n_informative=2,
random_state=1,
n_clusters_per_class=1)
rng = np.random.RandomState(2)
X += 2 * rng.uniform(size=X.shape)
linearly_separable = (X, y)
datasets = [
make_moons(noise=0.3, random_state=0),
make_circles(noise=0.2, factor=0.5, random_state=1), linearly_separable
n_redundant=2)
train_samples = 100 # Samples used for training the models
X_train = X[:train_samples]
X_test = X[train_samples:]
y_train = y[:train_samples]
y_test = y[train_samples:]
# Create classifiers
lr = LogisticRegression()
gnb = GaussianNB()
svc = LinearSVC(C=1.0)
dtc = DecisionTreeClassifier(min_samples_split=2)
rfc = RandomForestClassifier(n_estimators=100)
sk_etc = SKExtraTreesClassifier(n_estimators=100)
etc = ExtraTreesClassifier(n_estimators=100)
# #############################################################################
# Plot calibration plots
plt.figure(figsize=(10, 10))
ax1 = plt.subplot2grid((3, 1), (0, 0), rowspan=2)
ax2 = plt.subplot2grid((3, 1), (2, 0))
ax1.plot([0, 1], [0, 1], "k:", label="Perfectly calibrated")
for clf, name in [
(lr, 'Logistic'),
(gnb, 'Naive Bayes'),
(svc, 'Support Vector Classification'),
(dtc, 'Decision Tree'),