def test_min_impurity_decrease():
X, y = datasets.make_hastie_10_2(n_samples=100, random_state=1)
all_estimators = [RandomForestClassifier, RandomForestRegressor,
ExtraTreesClassifier, ExtraTreesRegressor]
for Estimator in all_estimators:
est = Estimator(min_impurity_decrease=0.1)
est.fit(X, y)
for tree in est.estimators_:
# Simply check if the parameter is passed on correctly. Tree tests
# will suffice for the actual working of this param
assert tree.min_impurity_decrease == 0.1
def test_min_impurity_split():
# Test if min_impurity_split of base estimators is set
# Regression test for #8006
X, y = datasets.make_hastie_10_2(n_samples=100, random_state=1)
all_estimators = [RandomForestClassifier, RandomForestRegressor,
ExtraTreesClassifier, ExtraTreesRegressor]
for Estimator in all_estimators:
est = Estimator(min_impurity_split=0.1)
est = assert_warns_message(DeprecationWarning, "min_impurity_decrease",
est.fit, X, y)
for tree in est.estimators_:
assert tree.min_impurity_split == 0.1
.. [1] T. Hastie, R. Tibshirani and J. Friedman, "Elements of Statistical
Learning Ed. 2", Springer, 2009.
"""
print(__doc__)
# Author: Peter Prettenhofer <*****@*****.**>
#
# License: BSD 3 clause
import numpy as np
import matplotlib.pyplot as plt
from mrex import ensemble
from mrex import datasets
X, y = datasets.make_hastie_10_2(n_samples=12000, random_state=1)
X = X.astype(np.float32)
# map labels from {-1, 1} to {0, 1}
labels, y = np.unique(y, return_inverse=True)
X_train, X_test = X[:2000], X[2000:]
y_train, y_test = y[:2000], y[2000:]
original_params = {
'n_estimators': 1000,
'max_leaf_nodes': 4,
'max_depth': None,
'random_state': 2,
'min_samples_split': 5
}
# and randomly permute it
iris = datasets.load_iris()
rng = check_random_state(0)
perm = rng.permutation(iris.target.size)
iris.data = iris.data[perm]
iris.target = iris.target[perm]
# also load the boston dataset
# and randomly permute it
boston = datasets.load_boston()
perm = rng.permutation(boston.target.size)
boston.data = boston.data[perm]
boston.target = boston.target[perm]
# also make a hastie_10_2 dataset
hastie_X, hastie_y = datasets.make_hastie_10_2(n_samples=20, random_state=1)
hastie_X = hastie_X.astype(np.float32)
# Get the default backend in joblib to test parallelism and interaction with
# different backends
DEFAULT_JOBLIB_BACKEND = joblib.parallel.get_active_backend()[0].__class__
FOREST_CLASSIFIERS = {
"ExtraTreesClassifier": ExtraTreesClassifier,
"RandomForestClassifier": RandomForestClassifier,
}
FOREST_REGRESSORS = {
"ExtraTreesRegressor": ExtraTreesRegressor,
"RandomForestRegressor": RandomForestRegressor,
}
# License: BSD 3 clause
import time
import numpy as np
import matplotlib.pyplot as plt
from mrex import ensemble
from mrex import datasets
from mrex.model_selection import train_test_split
print(__doc__)
data_list = [datasets.load_iris(), datasets.load_digits()]
data_list = [(d.data, d.target) for d in data_list]
data_list += [datasets.make_hastie_10_2()]
names = ['Iris Data', 'Digits Data', 'Hastie Data']
n_gb = []
score_gb = []
time_gb = []
n_gbes = []
score_gbes = []
time_gbes = []
n_estimators = 500
for X, y in data_list:
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.2,
from matplotlib import pyplot as plt
from mrex.datasets import make_hastie_10_2
from mrex.model_selection import GridSearchCV
from mrex.metrics import make_scorer
from mrex.metrics import accuracy_score
from mrex.tree import DecisionTreeClassifier
print(__doc__)
###############################################################################
# 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)
def test_make_hastie_10_2():
X, y = make_hastie_10_2(n_samples=100, random_state=0)
assert X.shape == (100, 10), "X shape mismatch"
assert y.shape == (100, ), "y shape mismatch"
assert np.unique(y).shape == (2, ), "Unexpected number of classes"