import unittest
import importlib
import numpy as np
import scipy.spatial.distance as dist
import scipy.cluster.hierarchy as sch


def _dynamic_test(test_case, condition, success_message, failure_message):
    if condition:
        test_case._testMethodName = success_message
        test_case.assertTrue(True, success_message)
    else:
        test_case._testMethodName = failure_message
        test_case.fail(failure_message)


def get_first_differing_index(expected_array, actual_array):
    for i, (val_1, val_2) in enumerate(zip(expected_array, actual_array)):
        if not np.array_equal(val_1, val_2):
            return i, expected_array[i], actual_array[i]

    if len(expected_array) > len(actual_array):
        return len(actual_array), expected_array[len(actual_array)], None
    else:
        return len(expected_array), None, actual_array[len(expected_array)]


class TestUserCode(unittest.TestCase):

    def test_distance_matrix_is_declared(self):
        import user_code
        _dynamic_test(
            self,
            hasattr(user_code, 'distance_matrix'),
            "The `distance_matrix` variable is declared.",
            "Expected `distance_matrix` to be declared."
        )

    def test_linkage_matrix_is_declared(self):
        import user_code
        _dynamic_test(
            self,
            hasattr(user_code, 'linkage_matrix'),
            "The `linkage_matrix` variable is declared.",
            "Expected `linkage_matrix` to be declared."
        )

    def test_distance_matrix_is_correct(self):
        import user_code
        from sklearn.datasets import make_blobs

        data, _ = make_blobs(n_samples=10, centers=3, cluster_std=1.0, random_state=42)
        expected_value = dist.pdist(data, metric='euclidean')

        variable = 'distance_matrix'
        actual_value = getattr(user_code, variable, None)
        condition = False
        if actual_value is None:
            failure_message = f"The `{variable}` variable is not declared."
        elif not isinstance(actual_value, np.ndarray):
            failure_message = f"`{variable}` is not a `numpy.ndarray`."
        elif actual_value.size == 0:
            failure_message = f"`{variable}` is empty."
        elif np.array_equal(actual_value, expected_value):
            condition = True
            failure_message = None
        else:
            idx, expected_element, actual_element = get_first_differing_index(expected_value, actual_value)
            failure_message = f"Expected `{variable}` to contain `{expected_element}` at index {idx}, but got `{actual_element}`."

        _dynamic_test(
            self,
            condition,
            f"`{variable}` contains the correct data.",
            failure_message
        )

    def test_linkage_matrix_is_correct(self):
        import user_code
        from sklearn.datasets import make_blobs

        data, _ = make_blobs(n_samples=10, centers=3, cluster_std=1.0, random_state=42)
        expected_distance = dist.pdist(data, metric='euclidean')
        expected_value = sch.linkage(expected_distance, method='single')

        variable = 'linkage_matrix'
        actual_value = getattr(user_code, variable, None)
        condition = False
        if actual_value is None:
            failure_message = f"The `{variable}` variable is not declared."
        elif not isinstance(actual_value, np.ndarray):
            failure_message = f"`{variable}` is not a `numpy.ndarray`."
        elif actual_value.size == 0:
            failure_message = f"`{variable}` is empty."
        elif np.array_equal(actual_value, expected_value):
            condition = True
            failure_message = None
        else:
            idx, expected_element, actual_element = get_first_differing_index(expected_value, actual_value)
            failure_message = f"Expected `{variable}` to contain `{expected_element}` at index {idx}, but got `{actual_element}`."

        _dynamic_test(
            self,
            condition,
            f"`{variable}` contains the correct data.",
            failure_message
        )


if __name__ == '__main__':
    unittest.main()

test_main.py

Tutustu piilevien rakenteiden tunnistamiseen ohjaamattoman oppimisen avulla. Hallitse keskeisimmät klusterointialgoritmit, kuten K-Means, hierarkkinen klusterointi, DBSCAN ja Gaussin seosmallit. Opettele arvioimaan klusteroinnin laatua WSS- ja Silhouette-mittareilla, käsittelemään erilaisia etäisyysmittareita sekä toteuttamaan kestäviä ratkaisuja aidoilla aineistoilla. Kehitä osaamista asiakassegmentoinnissa ja rakenteiden löytämisessä merkitsemättömästä datasta Scikit-learnin avulla.

Haaste: Hierarkkisen Klusteroinnin Toteuttaminen

Ratkaisu