def test_classification_report_imbalanced_multiclass_with_digits():
iris = datasets.load_iris()
y_true, y_pred, _ = make_prediction(dataset=iris, binary=False)
# print classification report with class names
expected_report = ("pre rec spe f1 geo iba sup setosa 0.82609 0.79167 "
"0.92157 0.80851 0.85415 0.72010 24 versicolor "
"0.33333 0.09677 0.86364 0.15000 0.28910 0.07717 "
"31 virginica 0.41860 0.90000 0.54545 0.57143 0.70065 "
"0.50831 20 avg / total 0.51375 0.53333 0.79733 "
"0.47310 0.57966 0.39788 75")
report = classification_report_imbalanced(
y_true,
y_pred,
labels=np.arange(len(iris.target_names)),
target_names=iris.target_names,
digits=5,
)
assert _format_report(report) == expected_report
# print classification report with label detection
expected_report = ("pre rec spe f1 geo iba sup 0 0.83 0.79 0.92 0.81 "
"0.85 0.72 24 1 0.33 0.10 0.86 0.15 0.29 0.08 31 "
"2 0.42 0.90 0.55 0.57 0.70 0.51 20 avg / total 0.51 "
"0.53 0.80 0.47 0.58 0.40 75")
report = classification_report_imbalanced(y_true, y_pred)
assert _format_report(report) == expected_report
def test_classification_report_imbalanced_multiclass():
iris = datasets.load_iris()
y_true, y_pred, _ = make_prediction(dataset=iris, binary=False)
# print classification report with class names
expected_report = ("pre rec spe f1 geo iba sup setosa 0.83 0.79 0.92 "
"0.81 0.85 0.72 24 versicolor 0.33 0.10 0.86 0.15 "
"0.29 0.08 31 virginica 0.42 0.90 0.55 0.57 0.70 "
"0.51 20 avg / total 0.51 0.53 0.80 0.47 0.58 0.40 75")
report = classification_report_imbalanced(
y_true,
y_pred,
labels=np.arange(len(iris.target_names)),
target_names=iris.target_names,
)
assert _format_report(report) == expected_report
# print classification report with label detection
expected_report = ("pre rec spe f1 geo iba sup 0 0.83 0.79 0.92 0.81 "
"0.85 0.72 24 1 0.33 0.10 0.86 0.15 0.29 0.08 31 "
"2 0.42 0.90 0.55 0.57 0.70 0.51 20 avg / total "
"0.51 0.53 0.80 0.47 0.58 0.40 75")
report = classification_report_imbalanced(y_true, y_pred)
assert _format_report(report) == expected_report
def test_classification_report_imbalanced_dict():
iris = datasets.load_iris()
y_true, y_pred, _ = make_prediction(dataset=iris, binary=False)
report = classification_report_imbalanced(
y_true,
y_pred,
labels=np.arange(len(iris.target_names)),
target_names=iris.target_names,
output_dict=True,
)
outer_keys = set(report.keys())
inner_keys = set(report[0].keys())
expected_outer_keys = {
0,
1,
2,
"avg_pre",
"avg_rec",
"avg_spe",
"avg_f1",
"avg_geo",
"avg_iba",
"total_support",
}
expected_inner_keys = {'spe', 'f1', 'sup', 'rec', 'geo', 'iba', 'pre'}
assert outer_keys == expected_outer_keys
assert inner_keys == expected_inner_keys
def test_classification_report_imbalanced_multiclass_with_string_label():
y_true, y_pred, _ = make_prediction(binary=False)
y_true = np.array(["blue", "green", "red"])[y_true]
y_pred = np.array(["blue", "green", "red"])[y_pred]
expected_report = ("pre rec spe f1 geo iba sup blue 0.83 0.79 0.92 0.81 "
"0.85 0.72 24 green 0.33 0.10 0.86 0.15 0.29 0.08 31 "
"red 0.42 0.90 0.55 0.57 0.70 0.51 20 avg / total "
"0.51 0.53 0.80 0.47 0.58 0.40 75")
report = classification_report_imbalanced(y_true, y_pred)
assert _format_report(report) == expected_report
expected_report = ("pre rec spe f1 geo iba sup a 0.83 0.79 0.92 0.81 0.85 "
"0.72 24 b 0.33 0.10 0.86 0.15 0.29 0.08 31 c 0.42 "
"0.90 0.55 0.57 0.70 0.51 20 avg / total 0.51 0.53 "
"0.80 0.47 0.58 0.40 75")
report = classification_report_imbalanced(y_true,
y_pred,
target_names=["a", "b", "c"])
assert _format_report(report) == expected_report
def test_classification_report_imbalanced_multiclass_with_unicode_label():
y_true, y_pred, _ = make_prediction(binary=False)
labels = np.array(["blue\xa2", "green\xa2", "red\xa2"])
y_true = labels[y_true]
y_pred = labels[y_pred]
expected_report = ("pre rec spe f1 geo iba sup blue¢ 0.83 0.79 0.92 0.81 "
"0.85 0.72 24 green¢ 0.33 0.10 0.86 0.15 0.29 0.08 31 "
"red¢ 0.42 0.90 0.55 0.57 0.70 0.51 20 avg / total "
"0.51 0.53 0.80 0.47 0.58 0.40 75")
report = classification_report_imbalanced(y_true, y_pred)
assert _format_report(report) == expected_report
# Generate a dataset
X, y = datasets.make_classification(
n_classes=2,
class_sep=2,
weights=[0.1, 0.9],
n_informative=10,
n_redundant=1,
flip_y=0,
n_features=20,
n_clusters_per_class=4,
n_samples=5000,
random_state=RANDOM_STATE,
)
pipeline = pl.make_pipeline(os.SMOTE(random_state=RANDOM_STATE),
LinearSVC(random_state=RANDOM_STATE))
# Split the data
X_train, X_test, y_train, y_test = train_test_split(X,
y,
random_state=RANDOM_STATE)
# Train the classifier with balancing
pipeline.fit(X_train, y_train)
# Test the classifier and get the prediction
y_pred_bal = pipeline.predict(X_test)
# Show the classification report
print(classification_report_imbalanced(y_test, y_pred_bal))
