• Search by Module
• Search by Words
• Search Projects

• Java
• Python
• JavaScript
• TypeScript
• C++
• Scala
• Blog

• discomll-master
  • discomll
    • ensemble
      • distributed_weighted_forest_rand.py
      • distributed_random_forest.py
      • distributed_weighted_forest.py
      • __init__.py
      • core
        • __init__.py
        • k_medoids.py
        • decision_tree.py
        • measures.py
      • forest_distributed_decision_trees.py
    • datasets
      • regression_data_test1.txt
      • iris_meta.csv
      • breast_cancer_wisconsin_cont.txt
      • iris.txt
      • regression_data_test2.txt
      • chunk_testdata.sh
      • ex3_test.txt
      • regression_data2.txt
      • breast_cancer_wisconsin_cont_test.txt
      • iris_test.txt
      • breastcancer_meta.csv
      • breast_cancer_wisconsin.names.txt
      • ex4.txt
      • ex3.txt
      • breast_cancer_wisconsin_disc.txt
      • breast_cancer_wisconsin_disc_test.txt
      • __init__.py
      • iris.names.txt
      • regression_data1.txt
    • utils
      • model_view.py
      • accuracy.py
      • distribution.py
      • __init__.py
    • examples
      • ensemble
        • dwf_rand_breastcancer_url.py
        • dwf_breastcancer_url.py
        • __init__.py
        • drf_breastcancer_url.py
        • fddt_breastcancer_url.py
      • big_data
        • logreg_sonar.py
        • nb_lymphography.py
        • kmeans_segmentation.py
        • fddt_segmentation.py
        • lwlr_fraction.py
        • linreg_fraction.py
        • lwlr_linear.py
        • drf_segmentation.py
        • drf_lymphography.py
        • linreg_linear.py
        • svm_ionosphere.py
        • svm_sonar.py
        • fddt_lymphography.py
        • dwfr_lymphography.py
        • logreg_ionosphere.py
        • __init__.py
        • kmeans_linear.py
        • nb_segmentation.py
        • dwfr_segmentation.py
      • classification
        • logistic_regression_ddfs.py
        • linear_svm_ddfs.py
        • naivebayes_ddfs.py
        • __init__.py
      • chunk_testdata.sh
      • clustering
        • __init__.py
        • kmeans_ddfs.py
      • regression
        • linear_regression_ddfs.py
        • __init__.py
        • locally_weighted_linear_regression_ddfs.py
      • __init__.py
    • classification
      • linear_svm.py
      • naivebayes.py
      • __init__.py
      • logistic_regression.py
    • clustering
      • __init__.py
      • kmeans.py
    • regression
      • linear_regression.py
      • locally_weighted_linear_regression.py
      • __init__.py
    • __init__.py
    • tests
      • chunk_testdata.py
      • tests_clustering.py
      • tests_regression.py
      • locally_weighted_linear_regression.py
      • datasets.py
      • __init__.py
      • tests_classification.py
    • dataset.py
  • setup.py
  • LICENSE.md
  • setup.cfg
  • README.md
  • requirements.txt
  • .gitignore

import unittest

import numpy as np
from disco.core import result_iterator

import datasets


class Tests_Clustering(unittest.TestCase):
    @classmethod
    def setUpClass(self):
        import chunk_testdata
        from disco import ddfs
        ddfs = ddfs.DDFS()

        if not ddfs.exists("test:ex3"):
            print "Chunking test datasets to DDFS..."
            chunk_testdata.chunk_testdata()

    def test_kmeans_iris(self):
        # python -m unittest tests_clustering.Tests_Clustering.test_kmeans_iris
        from discomll.clustering import kmeans
        from sklearn.cluster import KMeans

        max_iter = 10
        clusters = 3
        random_seed = 0

        x_train, y_train, x_test, y_test = datasets.iris()
        train_data, test_data = datasets.iris_discomll()

        sk_kmeans = KMeans(n_clusters=clusters, max_iter=max_iter, n_init=1, random_state=random_seed).fit(x_train)
        centroids1 = sk_kmeans.cluster_centers_
        # predictions1 = sk_kmeans.predict(x_test)

        centroids_url = kmeans.fit(train_data,
                                   n_clusters=clusters,
                                   max_iterations=max_iter,
                                   random_state=random_seed)

        predictions_url = kmeans.predict(test_data, centroids_url)
        # predictions2 = [v[1] for k,v in result_iterator(predictions_url)]

        centroids2 = [v["x"] for k, v in result_iterator(centroids_url["kmeans_fitmodel"])]
        centroids2[0], centroids2[2] = centroids2[2], centroids2[0]
        self.assertTrue(np.allclose(centroids1, centroids2))

    def test_kmeans_breastcancer(self):
        # python -m unittest tests_clustering.Tests_Clustering.test_kmeans_breastcancer
        from discomll.clustering import kmeans
        from sklearn.cluster import KMeans

        max_iter = 10
        clusters = 2
        random_seed = 2

        x_train, _, x_test, _ = datasets.breastcancer_disc()
        train_data, test_data = datasets.breastcancer_disc_discomll()

        kmeans2 = KMeans(n_clusters=clusters, max_iter=max_iter, n_init=1, random_state=random_seed).fit(x_train)
        centroids1 = kmeans2.cluster_centers_
        predictions1 = kmeans2.predict(x_test)

        centroids_url = kmeans.fit(train_data,
                                   n_clusters=clusters,
                                   max_iterations=max_iter,
                                   random_state=random_seed)

        predictions_url = kmeans.predict(test_data, centroids_url)
        predictions2 = [v[0] for k, v in result_iterator(predictions_url)]
        centroids2 = [v["x"] for k, v in result_iterator(centroids_url["kmeans_fitmodel"])]

        centroids2[0], centroids2[1] = centroids2[1], centroids2[0]

        self.assertTrue(np.allclose(centroids1, centroids2))


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