Pandas 3.0 will significantly boost performance by replacing NumPy with PyArrow as its default engine, enabling faster loading and reading of columnar data.
>>> from sklearn.neighbors import NearestCentroid
>>> import numpy as np
>>> X = np.array( [-1, -1 » , -2, -1 » , -3, -2 » , 1, 1 » , 2, 1 » , 3, 2 » ])
>>> y = np.array( 1, 1, 1, 2, 2, 2 » )
>>> clf = NearestCentroid()
>>> clf.fit(X, y)
NearestCentroid()
>>> print(clf.predict( [-0.8, -1 » ]))
1 »
>>> import numpy as np
>>> X = np.array( [-1, -1 » , -2, -1 » , -3, -2 » , 1, 1 » , 2, 1 » , 3, 2 » ])
>>> y = np.array( 1, 1, 1, 2, 2, 2 » )
>>> clf = NearestCentroid()
>>> clf.fit(X, y)
NearestCentroid()
>>> print(clf.predict( [-0.8, -1 » ]))
1 »
