def test_plot_roc_curve_error_non_binary(pyplot, data):
X, y = data
clf = DecisionTreeClassifier()
clf.fit(X, y)
msg = "Estimator should solve a binary classification problem"
with pytest.raises(ValueError, match=msg):
plot_roc_curve(clf, X, y)
def test_ovr_pipeline():
# Test with pipeline of length one
# This test is needed because the multiclass estimators may fail to detect
# the presence of predict_proba or decision_function.
clf = Pipeline([("tree", DecisionTreeClassifier())])
ovr_pipe = OneVsRestClassifier(clf)
ovr_pipe.fit(iris.data, iris.target)
ovr = OneVsRestClassifier(DecisionTreeClassifier())
ovr.fit(iris.data, iris.target)
assert_array_equal(ovr.predict(iris.data), ovr_pipe.predict(iris.data))
def test_pickle_version_warning_is_not_raised_with_matching_version():
iris = datasets.load_iris()
tree = DecisionTreeClassifier().fit(iris.data, iris.target)
tree_pickle = pickle.dumps(tree)
assert b"version" in tree_pickle
tree_restored = assert_no_warnings(pickle.loads, tree_pickle)
# test that we can predict with the restored decision tree classifier
score_of_original = tree.score(iris.data, iris.target)
score_of_restored = tree_restored.score(iris.data, iris.target)
assert score_of_original == score_of_restored
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 test_set_random_state():
lda = LinearDiscriminantAnalysis()
tree = DecisionTreeClassifier()
# Linear Discriminant Analysis doesn't have random state: smoke test
set_random_state(lda, 3)
set_random_state(tree, 3)
assert tree.random_state == 3
def test_export_text_errors():
clf = DecisionTreeClassifier(max_depth=2, random_state=0)
clf.fit(X, y)
err_msg = "max_depth bust be >= 0, given -1"
with pytest.raises(ValueError, match=err_msg):
export_text(clf, max_depth=-1)
err_msg = "feature_names must contain 2 elements, got 1"
with pytest.raises(ValueError, match=err_msg):
export_text(clf, feature_names=['a'])
err_msg = "decimals must be >= 0, given -1"
with pytest.raises(ValueError, match=err_msg):
export_text(clf, decimals=-1)
err_msg = "spacing must be > 0, given 0"
with pytest.raises(ValueError, match=err_msg):
export_text(clf, spacing=0)
def bench_scikit_tree_classifier(X, Y):
"""Benchmark with scikit-learn decision tree classifier"""
from mrex.tree import DecisionTreeClassifier
gc.collect()
# start time
tstart = datetime.now()
clf = DecisionTreeClassifier()
clf.fit(X, Y).predict(X)
delta = (datetime.now() - tstart)
# stop time
scikit_classifier_results.append(delta.seconds +
delta.microseconds / mu_second)
def test_plot_tree_gini(pyplot):
# mostly smoke tests
# Check correctness of export_graphviz for criterion = gini
clf = DecisionTreeClassifier(max_depth=3,
min_samples_split=2,
criterion="gini",
random_state=2)
clf.fit(X, y)
# Test export code
feature_names = ['first feat', 'sepal_width']
nodes = plot_tree(clf, feature_names=feature_names)
assert len(nodes) == 3
assert nodes[0].get_text() == ("first feat <= 0.0\ngini = 0.5\n"
"samples = 6\nvalue = [3, 3]")
assert nodes[1].get_text() == "gini = 0.0\nsamples = 3\nvalue = [3, 0]"
assert nodes[2].get_text() == "gini = 0.0\nsamples = 3\nvalue = [0, 3]"
def test_ovr_coef_exceptions():
# Not fitted exception!
ovr = OneVsRestClassifier(LinearSVC(random_state=0))
# lambda is needed because we don't want coef_ to be evaluated right away
assert_raises(ValueError, lambda x: ovr.coef_, None)
# Doesn't have coef_ exception!
ovr = OneVsRestClassifier(DecisionTreeClassifier())
ovr.fit(iris.data, iris.target)
assert_raises(AttributeError, lambda x: ovr.coef_, None)
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_graphviz_errors():
# Check for errors of export_graphviz
clf = DecisionTreeClassifier(max_depth=3, min_samples_split=2)
# Check not-fitted decision tree error
out = StringIO()
with pytest.raises(NotFittedError):
export_graphviz(clf, out)
clf.fit(X, y)
# Check if it errors when length of feature_names
# mismatches with number of features
message = ("Length of feature_names, "
"1 does not match number of features, 2")
with pytest.raises(ValueError, match=message):
export_graphviz(clf, None, feature_names=["a"])
message = ("Length of feature_names, "
"3 does not match number of features, 2")
with pytest.raises(ValueError, match=message):
export_graphviz(clf, None, feature_names=["a", "b", "c"])
# Check error when argument is not an estimator
message = "is not an estimator instance"
with pytest.raises(TypeError, match=message):
export_graphviz(clf.fit(X, y).tree_)
# Check class_names error
out = StringIO()
with pytest.raises(IndexError):
export_graphviz(clf, out, class_names=[])
# Check precision error
out = StringIO()
with pytest.raises(ValueError, match="should be greater or equal"):
export_graphviz(clf, out, precision=-1)
with pytest.raises(ValueError, match="should be an integer"):
export_graphviz(clf, out, precision="1")
def test_raises_on_score_list():
# Test that when a list of scores is returned, we raise proper errors.
X, y = make_blobs(random_state=0)
f1_scorer_no_average = make_scorer(f1_score, average=None)
clf = DecisionTreeClassifier()
assert_raises(ValueError,
cross_val_score,
clf,
X,
y,
scoring=f1_scorer_no_average)
grid_search = GridSearchCV(clf,
scoring=f1_scorer_no_average,
param_grid={'max_depth': [1, 2]})
assert_raises(ValueError, grid_search.fit, X, y)
def test_gridsearch():
# Check that base trees can be grid-searched.
# AdaBoost classification
boost = AdaBoostClassifier(base_estimator=DecisionTreeClassifier())
parameters = {
'n_estimators': (1, 2),
'base_estimator__max_depth': (1, 2),
'algorithm': ('SAMME', 'SAMME.R')
}
clf = GridSearchCV(boost, parameters)
clf.fit(iris.data, iris.target)
# AdaBoost regression
boost = AdaBoostRegressor(base_estimator=DecisionTreeRegressor(),
random_state=0)
parameters = {'n_estimators': (1, 2), 'base_estimator__max_depth': (1, 2)}
clf = GridSearchCV(boost, parameters)
clf.fit(boston.data, boston.target)
def test_precision():
rng_reg = RandomState(2)
rng_clf = RandomState(8)
for X, y, clf in zip(
(rng_reg.random_sample((5, 2)),
rng_clf.random_sample((1000, 4))),
(rng_reg.random_sample((5, )),
rng_clf.randint(2, size=(1000, ))),
(DecisionTreeRegressor(criterion="friedman_mse", random_state=0,
max_depth=1),
DecisionTreeClassifier(max_depth=1, random_state=0))):
clf.fit(X, y)
for precision in (4, 3):
dot_data = export_graphviz(clf, out_file=None, precision=precision,
proportion=True)
# With the current random state, the impurity and the threshold
# will have the number of precision set in the export_graphviz
# function. We will check the number of precision with a strict
# equality. The value reported will have only 2 precision and
# therefore, only a less equal comparison will be done.
# check value
for finding in finditer(r"value = \d+\.\d+", dot_data):
assert (
len(search(r"\.\d+", finding.group()).group()) <=
precision + 1)
# check impurity
if is_classifier(clf):
pattern = r"gini = \d+\.\d+"
else:
pattern = r"friedman_mse = \d+\.\d+"
# check impurity
for finding in finditer(pattern, dot_data):
assert (len(search(r"\.\d+", finding.group()).group()) ==
precision + 1)
# check threshold
for finding in finditer(r"<= \d+\.\d+", dot_data):
assert (len(search(r"\.\d+", finding.group()).group()) ==
precision + 1)
def test_score_sample_weight():
rng = np.random.RandomState(0)
# test both ClassifierMixin and RegressorMixin
estimators = [
DecisionTreeClassifier(max_depth=2),
DecisionTreeRegressor(max_depth=2)
]
sets = [datasets.load_iris(), datasets.load_boston()]
for est, ds in zip(estimators, sets):
est.fit(ds.data, ds.target)
# generate random sample weights
sample_weight = rng.randint(1, 10, size=len(ds.target))
# check that the score with and without sample weights are different
assert (est.score(ds.data, ds.target) != est.score(
ds.data, ds.target,
sample_weight=sample_weight)), ("Unweighted and weighted scores "
"are unexpectedly equal")
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),
'MLP-adam': MLPClassifier(
# Parameters
n_classes = 3
plot_colors = "ryb"
plot_step = 0.02
# Load data
iris = load_iris()
for pairidx, pair in enumerate([[0, 1], [0, 2], [0, 3], [1, 2], [1, 3], [2,
3]]):
# We only take the two corresponding features
X = iris.data[:, pair]
y = iris.target
# Train
clf = DecisionTreeClassifier().fit(X, y)
# Plot the decision boundary
plt.subplot(2, 3, pairidx + 1)
x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
xx, yy = np.meshgrid(np.arange(x_min, x_max, plot_step),
np.arange(y_min, y_max, plot_step))
plt.tight_layout(h_pad=0.5, w_pad=0.5, pad=2.5)
Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])
Z = Z.reshape(xx.shape)
cs = plt.contourf(xx, yy, Z, cmap=plt.cm.RdYlBu)
plt.xlabel(iris.feature_names[pair[0]])
# Standardize first 10 features (the numerical ones)
mean = X_train.mean(axis=0)
std = X_train.std(axis=0)
mean[10:] = 0.0
std[10:] = 1.0
X_train = (X_train - mean) / std
X_test = (X_test - mean) / std
return X_train, X_test, y_train, y_test
ESTIMATORS = {
'GBRT': GradientBoostingClassifier(n_estimators=250),
'ExtraTrees': ExtraTreesClassifier(n_estimators=20),
'RandomForest': RandomForestClassifier(n_estimators=20),
'CART': DecisionTreeClassifier(min_samples_split=5),
'SGD': SGDClassifier(alpha=0.001),
'GaussianNB': GaussianNB(),
'liblinear': LinearSVC(loss="l2",
penalty="l2",
C=1000,
dual=False,
tol=1e-3),
'SAG': LogisticRegression(solver='sag', max_iter=2, C=1000)
}
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument('--classifiers',
nargs="+",
choices=ESTIMATORS,
from mrex.discriminant_analysis import QuadraticDiscriminantAnalysis
h = .02 # step size in the mesh
names = [
"Nearest Neighbors", "Linear SVM", "RBF SVM", "Gaussian Process",
"Decision Tree", "Random Forest", "Neural Net", "AdaBoost", "Naive Bayes",
"QDA"
]
classifiers = [
KNeighborsClassifier(3),
SVC(kernel="linear", C=0.025),
SVC(gamma=2, C=1),
GaussianProcessClassifier(1.0 * RBF(1.0)),
DecisionTreeClassifier(max_depth=5),
RandomForestClassifier(max_depth=5, n_estimators=10, max_features=1),
MLPClassifier(alpha=1, max_iter=1000),
AdaBoostClassifier(),
GaussianNB(),
QuadraticDiscriminantAnalysis()
]
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)
###############################################################################
# Total impurity of leaves vs effective alphas of pruned tree
# ---------------------------------------------------------------
# Minimal cost complexity pruning recursively finds the node with the "weakest
# link". The weakest link is characterized by an effective alpha, where the
# nodes with the smallest effective alpha are pruned first. To get an idea of
# what values of ``ccp_alpha`` could be appropriate, scikit-learn provides
# :func:`DecisionTreeClassifier.cost_complexity_pruning_path` that returns the
# effective alphas and the corresponding total leaf impurities at each step of
# the pruning process. As alpha increases, more of the tree is pruned, which
# increases the total impurity of its leaves.
X, y = load_breast_cancer(return_X_y=True)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
clf = DecisionTreeClassifier(random_state=0)
path = clf.cost_complexity_pruning_path(X_train, y_train)
ccp_alphas, impurities = path.ccp_alphas, path.impurities
###############################################################################
# In the following plot, the maximum effective alpha value is removed, because
# it is the trivial tree with only one node.
fig, ax = plt.subplots()
ax.plot(ccp_alphas[:-1], impurities[:-1], marker='o', drawstyle="steps-post")
ax.set_xlabel("effective alpha")
ax.set_ylabel("total impurity of leaves")
ax.set_title("Total Impurity vs effective alpha for training set")
###############################################################################
# Next, we train a decision tree using the effective alphas. The last value
# in ``ccp_alphas`` is the alpha value that prunes the whole tree,
import numpy as np
import matplotlib.pyplot as plt
from mrex import datasets
from mrex.tree import DecisionTreeClassifier
from mrex.neighbors import KNeighborsClassifier
from mrex.svm import SVC
from mrex.ensemble import VotingClassifier
# Loading some example data
iris = datasets.load_iris()
X = iris.data[:, [0, 2]]
y = iris.target
# Training classifiers
clf1 = DecisionTreeClassifier(max_depth=4)
clf2 = KNeighborsClassifier(n_neighbors=7)
clf3 = SVC(gamma=.1, kernel='rbf', probability=True)
eclf = VotingClassifier(estimators=[('dt', clf1), ('knn', clf2),
('svc', clf3)],
voting='soft',
weights=[2, 1, 2])
clf1.fit(X, y)
clf2.fit(X, y)
clf3.fit(X, y)
eclf.fit(X, y)
# Plotting decision regions
x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
def test_thresholded_scorers_multilabel_indicator_data():
# Test that the scorer work with multilabel-indicator format
# for multilabel and multi-output multi-class classifier
X, y = make_multilabel_classification(allow_unlabeled=False,
random_state=0)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
# Multi-output multi-class predict_proba
clf = DecisionTreeClassifier()
clf.fit(X_train, y_train)
y_proba = clf.predict_proba(X_test)
score1 = get_scorer('roc_auc')(clf, X_test, y_test)
score2 = roc_auc_score(y_test, np.vstack([p[:, -1] for p in y_proba]).T)
assert_almost_equal(score1, score2)
# Multi-output multi-class decision_function
# TODO Is there any yet?
clf = DecisionTreeClassifier()
clf.fit(X_train, y_train)
clf._predict_proba = clf.predict_proba
clf.predict_proba = None
clf.decision_function = lambda X: [p[:, 1] for p in clf._predict_proba(X)]
y_proba = clf.decision_function(X_test)
score1 = get_scorer('roc_auc')(clf, X_test, y_test)
score2 = roc_auc_score(y_test, np.vstack([p for p in y_proba]).T)
assert_almost_equal(score1, score2)
# Multilabel predict_proba
clf = OneVsRestClassifier(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))
assert_almost_equal(score1, score2)
# Multilabel decision function
clf = OneVsRestClassifier(LinearSVC(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))
assert_almost_equal(score1, score2)
# Running ``GridSearchCV`` using multiple evaluation metrics
# ----------------------------------------------------------
#
X, y = make_hastie_10_2(n_samples=8000, random_state=42)
# The scorers can be either be one of the predefined metric strings or a scorer
# callable, like the one returned by make_scorer
scoring = {'AUC': 'roc_auc', 'Accuracy': make_scorer(accuracy_score)}
# Setting refit='AUC', refits an estimator on the whole dataset with the
# parameter setting that has the best cross-validated AUC score.
# That estimator is made available at ``gs.best_estimator_`` along with
# parameters like ``gs.best_score_``, ``gs.best_params_`` and
# ``gs.best_index_``
gs = GridSearchCV(DecisionTreeClassifier(random_state=42),
param_grid={'min_samples_split': range(2, 403, 10)},
scoring=scoring,
refit='AUC',
return_train_score=True)
gs.fit(X, y)
results = gs.cv_results_
###############################################################################
# Plotting the result
# -------------------
plt.figure(figsize=(13, 13))
plt.title("GridSearchCV evaluating using multiple scorers simultaneously",
fontsize=16)
X1, y1 = make_gaussian_quantiles(cov=2.,
n_samples=200,
n_features=2,
n_classes=2,
random_state=1)
X2, y2 = make_gaussian_quantiles(mean=(3, 3),
cov=1.5,
n_samples=300,
n_features=2,
n_classes=2,
random_state=1)
X = np.concatenate((X1, X2))
y = np.concatenate((y1, -y2 + 1))
# Create and fit an AdaBoosted decision tree
bdt = AdaBoostClassifier(DecisionTreeClassifier(max_depth=1),
algorithm="SAMME",
n_estimators=200)
bdt.fit(X, y)
plot_colors = "br"
plot_step = 0.02
class_names = "AB"
plt.figure(figsize=(10, 5))
# Plot the decision boundaries
plt.subplot(121)
x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
from mrex.tree import DecisionTreeClassifier
# Parameters
n_classes = 3
n_estimators = 30
cmap = plt.cm.RdYlBu
plot_step = 0.02 # fine step width for decision surface contours
plot_step_coarser = 0.5 # step widths for coarse classifier guesses
RANDOM_SEED = 13 # fix the seed on each iteration
# Load data
iris = load_iris()
plot_idx = 1
models = [DecisionTreeClassifier(max_depth=None),
RandomForestClassifier(n_estimators=n_estimators),
ExtraTreesClassifier(n_estimators=n_estimators),
AdaBoostClassifier(DecisionTreeClassifier(max_depth=3),
n_estimators=n_estimators)]
for pair in ([0, 1], [0, 2], [2, 3]):
for model in models:
# We only take the two corresponding features
X = iris.data[:, pair]
y = iris.target
# Shuffle
idx = np.arange(X.shape[0])
np.random.seed(RANDOM_SEED)
np.random.shuffle(idx)
def test_set_params_updates_valid_params():
# Check that set_params tries to set SVC().C, not
# DecisionTreeClassifier().C
gscv = GridSearchCV(DecisionTreeClassifier(), {})
gscv.set_params(estimator=SVC(), estimator__C=42.0)
assert gscv.estimator.C == 42.0
from mrex import datasets
from mrex.tree import DecisionTreeClassifier
from mrex.metrics import zero_one_loss
from mrex.ensemble import AdaBoostClassifier
n_estimators = 400
# A learning rate of 1. may not be optimal for both SAMME and SAMME.R
learning_rate = 1.
X, y = datasets.make_hastie_10_2(n_samples=12000, random_state=1)
X_test, y_test = X[2000:], y[2000:]
X_train, y_train = X[:2000], y[:2000]
dt_stump = DecisionTreeClassifier(max_depth=1, min_samples_leaf=1)
dt_stump.fit(X_train, y_train)
dt_stump_err = 1.0 - dt_stump.score(X_test, y_test)
dt = DecisionTreeClassifier(max_depth=9, min_samples_leaf=1)
dt.fit(X_train, y_train)
dt_err = 1.0 - dt.score(X_test, y_test)
ada_discrete = AdaBoostClassifier(base_estimator=dt_stump,
learning_rate=learning_rate,
n_estimators=n_estimators,
algorithm="SAMME")
ada_discrete.fit(X_train, y_train)
ada_real = AdaBoostClassifier(base_estimator=dt_stump,
learning_rate=learning_rate,
[('lr', LinearRegression()),
('rf', RandomForestRegressor(n_estimators=5))]))]
)
@pytest.mark.parametrize("drop", [None, 'drop'])
def test_none_estimator_with_weights(X, y, voter, drop):
# check that an estimator can be set to None and passing some weight
# regression test for
# https://github.com/scikit-learn/scikit-learn/issues/13777
voter.fit(X, y, sample_weight=np.ones(y.shape))
voter.set_params(lr=drop)
voter.fit(X, y, sample_weight=np.ones(y.shape))
y_pred = voter.predict(X)
assert y_pred.shape == y.shape
@pytest.mark.parametrize(
"estimator",
[VotingRegressor(
estimators=[('lr', LinearRegression()),
('tree', DecisionTreeRegressor(random_state=0))]),
VotingClassifier(
estimators=[('lr', LogisticRegression(random_state=0)),
('tree', DecisionTreeClassifier(random_state=0))])],
ids=['VotingRegressor', 'VotingClassifier']
)
def test_check_estimators_voting_estimator(estimator):
# FIXME: to be removed when meta-estimators can be specified themselves
# their testing parameters (for required parameters).
check_estimator(estimator)
check_no_attributes_set_in_init(estimator.__class__.__name__, estimator)
from mrex.datasets import make_gaussian_quantiles
from mrex.ensemble import AdaBoostClassifier
from mrex.metrics import accuracy_score
from mrex.tree import DecisionTreeClassifier
X, y = make_gaussian_quantiles(n_samples=13000,
n_features=10,
n_classes=3,
random_state=1)
n_split = 3000
X_train, X_test = X[:n_split], X[n_split:]
y_train, y_test = y[:n_split], y[n_split:]
bdt_real = AdaBoostClassifier(DecisionTreeClassifier(max_depth=2),
n_estimators=600,
learning_rate=1)
bdt_discrete = AdaBoostClassifier(DecisionTreeClassifier(max_depth=2),
n_estimators=600,
learning_rate=1.5,
algorithm="SAMME")
bdt_real.fit(X_train, y_train)
bdt_discrete.fit(X_train, y_train)
real_test_errors = []
discrete_test_errors = []
for real_test_predict, discrete_train_predict in zip(
- the rules that were used to predict a sample; - the decision path shared by a group of samples. """ import numpy as np from mrex.model_selection import train_test_split from mrex.datasets import load_iris from mrex.tree import DecisionTreeClassifier iris = load_iris() X = iris.data y = iris.target X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0) estimator = DecisionTreeClassifier(max_leaf_nodes=3, random_state=0) estimator.fit(X_train, y_train) # The decision estimator has an attribute called tree_ which stores the entire # tree structure and allows access to low level attributes. The binary tree # tree_ is represented as a number of parallel arrays. The i-th element of each # array holds information about the node `i`. Node 0 is the tree's root. NOTE: # Some of the arrays only apply to either leaves or split nodes, resp. In this # case the values of nodes of the other type are arbitrary! # # Among those arrays, we have: # - left_child, id of the left child of the node # - right_child, id of the right child of the node # - feature, feature used for splitting the node # - threshold, threshold value at the node #
