from sklearn import preprocessing
labels = ['setosa', 'versicolor', 'virginica']
encoder = preprocessing.LabelEncoder()
encoder.fit(labels)
for i, item in enumerate(encoder.classes_):
print(item, '=>', i)
setosa => 0 versicolor => 1 virginica => 2
more_labels = ['versicolor', 'versicolor', 'virginica', 'setosa', 'versicolor']
more_labels_encoded = encoder.transform(more_labels)
print('More labels =', more_labels)
print('More labels encoded =', list(more_labels_encoded))
More labels = ['versicolor', 'versicolor', 'virginica', 'setosa', 'versicolor'] More labels encoded = [1, 1, 2, 0, 1]
X, y