Python源码示例:sklearn.metrics.homogeneity_score()

示例1
def bench_k_means(estimator, name, data):
    estimator.fit(data)
    # A short explanation for every score:
    # homogeneity:          each cluster contains only members of a single class (range 0 - 1)
    # completeness:         all members of a given class are assigned to the same cluster (range 0 - 1)
    # v_measure:            harmonic mean of homogeneity and completeness
    # adjusted_rand:        similarity of the actual values and their predictions,
    #                       ignoring permutations and with chance normalization
    #                       (range -1 to 1, -1 being bad, 1 being perfect and 0 being random)
    # adjusted_mutual_info: agreement of the actual values and predictions, ignoring permutations
    #                       (range 0 - 1, with 0 being random agreement and 1 being perfect agreement)
    # silhouette:           uses the mean distance between a sample and all other points in the same class,
    #                       as well as the mean distance between a sample and all other points in the nearest cluster
    #                       to calculate a score (range: -1 to 1, with the former being incorrect,
    #                       and the latter standing for highly dense clustering.
    #                       0 indicates overlapping clusters.
    print('%-9s \t%i \thomogeneity: %.3f \tcompleteness: %.3f \tv-measure: %.3f \tadjusted-rand: %.3f \t'
          'adjusted-mutual-info: %.3f \tsilhouette: %.3f'
          % (name, estimator.inertia_,
             metrics.homogeneity_score(y, estimator.labels_),
             metrics.completeness_score(y, estimator.labels_),
             metrics.v_measure_score(y, estimator.labels_),
             metrics.adjusted_rand_score(y, estimator.labels_),
             metrics.adjusted_mutual_info_score(y,  estimator.labels_),
             metrics.silhouette_score(data, estimator.labels_,
                                      metric='euclidean'))) 
示例2
def homogeneity_kmeans_scorer(self, min_similarity):
        return self.kmeans_scorer(
            metrics.homogeneity_score,
            min_similarity
        ) 
示例3
def homogeneity_dbscan_scorer(self, min_similarity):
        return self.dbscan_scorer(
            metrics.homogeneity_score,
            min_similarity
        ) 
示例4
def evaluate_on_digits():
    digits = datasets.load_digits()
    data = digits.data
    target = digits.target
    gng = GrowingNeuralGas(data)
    gng.fit_network(e_b=0.05, e_n=0.006, a_max=8, l=100, a=0.5, d=0.995, passes=5, plot_evolution=False)
    clustered_data = gng.cluster_data()
    print('Found %d clusters.' % nx.number_connected_components(gng.network))
    target_infered = []
    for observation, cluster in clustered_data:
        target_infered.append(cluster)
    homogeneity = metrics.homogeneity_score(target, target_infered)
    print(homogeneity)
    gng.plot_clusters(gng.reduce_dimension(gng.cluster_data())) 
示例5
def bench_k_means(estimator, name, data):
    t0 = time()
    estimator.fit(data)
    print('% 9s   %.2fs    %i   %.3f   %.3f   %.3f   %.3f   %.3f    %.3f'
          % (name, (time() - t0), estimator.inertia_,
             metrics.homogeneity_score(labels, estimator.labels_),
             metrics.completeness_score(labels, estimator.labels_),
             metrics.v_measure_score(labels, estimator.labels_),
             metrics.adjusted_rand_score(labels, estimator.labels_),
             metrics.adjusted_mutual_info_score(labels,  estimator.labels_),
             metrics.silhouette_score(data, estimator.labels_,
                                      metric='euclidean',
                                      sample_size=sample_size))) 
示例6
def test_homogeneity_score(self):
        result = self.df.metrics.homogeneity_score()
        expected = metrics.homogeneity_score(self.target, self.pred)
        self.assertEqual(result, expected) 
示例7
def test_KMeans_scores(self):
        digits = datasets.load_digits()
        df = pdml.ModelFrame(digits)

        scaled = pp.scale(digits.data)
        df.data = df.data.pp.scale()
        self.assert_numpy_array_almost_equal(df.data.values, scaled)

        clf1 = cluster.KMeans(init='k-means++', n_clusters=10,
                              n_init=10, random_state=self.random_state)
        clf2 = df.cluster.KMeans(init='k-means++', n_clusters=10,
                                 n_init=10, random_state=self.random_state)
        clf1.fit(scaled)
        df.fit_predict(clf2)

        expected = m.homogeneity_score(digits.target, clf1.labels_)
        self.assertEqual(df.metrics.homogeneity_score(), expected)

        expected = m.completeness_score(digits.target, clf1.labels_)
        self.assertEqual(df.metrics.completeness_score(), expected)

        expected = m.v_measure_score(digits.target, clf1.labels_)
        self.assertEqual(df.metrics.v_measure_score(), expected)

        expected = m.adjusted_rand_score(digits.target, clf1.labels_)
        self.assertEqual(df.metrics.adjusted_rand_score(), expected)

        expected = m.homogeneity_score(digits.target, clf1.labels_)
        self.assertEqual(df.metrics.homogeneity_score(), expected)

        expected = m.silhouette_score(scaled, clf1.labels_, metric='euclidean',
                                      sample_size=300, random_state=self.random_state)
        result = df.metrics.silhouette_score(metric='euclidean', sample_size=300,
                                             random_state=self.random_state)
        self.assertAlmostEqual(result, expected) 
示例8
def bench_k_means(estimator, name, data):
    t0 = time()
    estimator.fit(data)
    print('% 9s   %.2fs    %i   %.3f   %.3f   %.3f   %.3f   %.3f    %.3f'
          % (name, (time() - t0), estimator.inertia_,
             metrics.homogeneity_score(labels, estimator.labels_),
             metrics.completeness_score(labels, estimator.labels_),
             metrics.v_measure_score(labels, estimator.labels_),
             metrics.adjusted_rand_score(labels, estimator.labels_),
             metrics.adjusted_mutual_info_score(labels,  estimator.labels_),
             metrics.silhouette_score(data, estimator.labels_,
                                      metric='euclidean',
                                      sample_size=sample_size)))