report_train = classification_report(y_train, y_pred_train)
report_test = classification_report(y_test, y_pred_test)
print("Training\n%s" % report_train)
print("Testing\n%s" % report_test)
iterations = np.arange(1, lboost.n_estimators + 1)
staged_accuracy_train = list(lboost.staged_score(X_train, y_train))
staged_accuracy_test = list(lboost.staged_score(X_test, y_test))
plt.figure(figsize=(10, 8))
plt.plot(iterations, staged_accuracy_train, label="Training", marker=".")
plt.plot(iterations, staged_accuracy_test, label="Test", marker=".")
plt.xlabel("Iteration")
plt.ylabel("Accuracy")
plt.title("Ensemble accuracy during each boosting iteration")
plt.legend(loc="best", shadow=True, frameon=True)
plt.tight_layout()
plt.show()
plt.close()
contrib_train = lboost.contributions(X_train)
plt.figure(figsize=(10, 8))
plt.plot(iterations, contrib_train, lw=2)
plt.xlabel("Estimator Number")
plt.ylabel("Average Absolute Contribution")
plt.title("Average absolute contribution of the estimators in the ensemble")
plt.show()
plt.close()
def _toy_dataset_test(load_func,
test_size=(1. / 3),
random_state=0,
min_score_train=0.9,
min_score_test=0.9):
"""Create a classification unit test from a scikit-learn toy dataset."""
# Fetch the dataset
data = load_func()
X = data.data
y = data.target_names[data.target]
# Distinct classes
classes = data.target_names
n_classes = len(classes)
# Binary/multiclass classification indicator
is_binary = (n_classes == 2)
# Shuffle data and split it into training/testing samples
X_train, X_test, y_train, y_test = \
train_test_split(X, y, test_size=test_size, shuffle=True, stratify=y,
random_state=random_state)
for bootstrap in (True, False):
# Fit a LogitBoost model
logitboost = LogitBoost(bootstrap=bootstrap, random_state=random_state)
logitboost.fit(X_train, y_train)
# Compute accuracy scores and assert minimum accuracy
score_train = logitboost.score(X_train, y_train)
score_test = logitboost.score(X_test, y_test)
assert score_train >= min_score_train, \
("Failed with bootstrap=%s: training score %.3f less than %.3f"
% (bootstrap, score_train, min_score_train))
assert score_test >= min_score_test, \
("Failed with bootstrap=%s: testing score %.3f less than %.3f"
% (bootstrap, score_test, min_score_test))
# Get probabilities and the decision function
predict_proba = logitboost.predict_proba(X_test)
decision_function = logitboost.decision_function(X_test)
# predict_proba() should always return (n_samples, n_classes)
assert predict_proba.shape == (X_test.shape[0], n_classes)
# decision_function() shape depends on the classification task
if is_binary:
assert decision_function.shape == (X_test.shape[0], )
else:
assert decision_function.shape == (X_test.shape[0], n_classes)
# Check that the last item of a staged method is the same as a regular
# method
staged_predict = np.asarray(list(logitboost.staged_predict(X_test)))
staged_predict_proba = \
np.asarray(list(logitboost.staged_predict_proba(X_test)))
staged_decision_function = \
np.asarray(list(logitboost.staged_decision_function(X_test)))
staged_score = \
np.asarray(list(logitboost.staged_score(X_test, y_test)))
np.testing.assert_equal(staged_predict[-1], logitboost.predict(X_test))
np.testing.assert_almost_equal(staged_predict_proba[-1],
logitboost.predict_proba(X_test))
np.testing.assert_almost_equal(staged_decision_function[-1],
logitboost.decision_function(X_test))
np.testing.assert_almost_equal(staged_score[-1],
logitboost.score(X_test, y_test))
# contributions() should return one non-negative number for each
# estimator in the ensemble
contrib = logitboost.contributions(X_train)
assert contrib.shape == (logitboost.n_estimators, )
assert np.all(contrib >= 0)