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
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,
n_estimators=n_estimators,
algorithm="SAMME.R")
ax[0].set_title("Number of nodes vs alpha")
ax[1].plot(ccp_alphas, depth, marker='o', drawstyle="steps-post")
ax[1].set_xlabel("alpha")
ax[1].set_ylabel("depth of tree")
ax[1].set_title("Depth vs alpha")
fig.tight_layout()
###############################################################################
# Accuracy vs alpha for training and testing sets
# ----------------------------------------------------
# When ``ccp_alpha`` is set to zero and keeping the other default parameters
# of :class:`DecisionTreeClassifier`, the tree overfits, leading to
# a 100% training accuracy and 88% testing accuracy. As alpha increases, more
# of the tree is pruned, thus creating a decision tree that generalizes better.
# In this example, setting ``ccp_alpha=0.015`` maximizes the testing accuracy.
train_scores = [clf.score(X_train, y_train) for clf in clfs]
test_scores = [clf.score(X_test, y_test) for clf in clfs]
fig, ax = plt.subplots()
ax.set_xlabel("alpha")
ax.set_ylabel("accuracy")
ax.set_title("Accuracy vs alpha for training and testing sets")
ax.plot(ccp_alphas,
train_scores,
marker='o',
label="train",
drawstyle="steps-post")
ax.plot(ccp_alphas,
test_scores,
marker='o',
label="test",