def test_adagrad_mse_batch(self): testdata = np_read_csv( os.path.join(unittest_data_path, "adagrad_mse_batch.csv"), range(1)) import adagrad_mse_batch as ex ex.read_csv = self.read_csv result = ex.main() self.assertTrue(np.allclose(result.minimum, testdata))
def test_svm_multiclass_batch(self): testdata = np_read_csv( os.path.join(unittest_data_path, "svm_multiclass_batch.csv"), range(1)) import svm_multiclass_batch as ex ex.read_csv = self.read_csv (predict_result, _) = ex.main() self.assertTrue(np.allclose(predict_result.prediction, testdata))
def test_univariate_outlier_batch(self): testdata = np_read_csv( os.path.join(unittest_data_path, "univariate_outlier_batch.csv"), range(1)) import univariate_outlier_batch as ex ex.read_csv = self.read_csv (_, result) = ex.main() self.assertTrue(np.allclose(result.weights, testdata))
def test_pca_transform_batch(self): testdata = np_read_csv( os.path.join(unittest_data_path, "pca_transform_batch.csv"), range(2)) import pca_transform_batch as ex ex.read_csv = self.read_csv _, result = ex.main() self.assertTrue(np.allclose(result.transformedData, testdata))
def test_log_reg_dense_batch(self): testdata = np_read_csv( os.path.join(unittest_data_path, "log_reg_dense_batch.csv"), range(1)) import log_reg_dense_batch as ex ex.read_csv = self.read_csv (_, predict_result, _) = ex.main() self.assertTrue(np.allclose(predict_result.prediction, testdata))
def test_naive_bayes_stream(self): testdata = np_read_csv( os.path.join(unittest_data_path, "naive_bayes_batch.csv"), range(1)) import naive_bayes_streaming as ex ex.read_csv = self.read_csv (predict_result, _) = ex.main() self.assertTrue(np.allclose(predict_result.prediction, testdata))
def test_ridge_regression_stream(self): testdata = np_read_csv( os.path.join(unittest_data_path, "ridge_regression_batch.csv"), range(2)) import ridge_regression_streaming as ex ex.read_csv = self.read_csv (predict_result, _) = ex.main() self.assertTrue(np.allclose(predict_result.prediction, testdata))
def test_lbfgs_cr_entr_loss_batch(self): testdata = np_read_csv( os.path.join(unittest_data_path, "lbfgs_cr_entr_loss_batch.csv"), range(1)) import lbfgs_cr_entr_loss_batch as ex ex.read_csv = self.read_csv result = ex.main() self.assertTrue(np.allclose(result.minimum, testdata))
def test_decision_tree_classification_batch(self): testdata = np_read_csv( os.path.join(unittest_data_path, "decision_tree_classification_batch.csv"), range(1)) import decision_tree_classification_batch as ex ex.read_csv = self.read_csv (_, predict_result, _) = ex.main() self.assertTrue(np.allclose(predict_result.prediction, testdata))
def test_svm_batch(self): testdata = np_read_csv( os.path.join(unittest_data_path, "svm_batch.csv"), range(1)) import svm_batch as ex ex.read_csv = self.read_csv (predict_result, _) = ex.main() self.assertTrue( np.absolute(predict_result.prediction - testdata).max() < np.absolute(predict_result.prediction.max() - predict_result.prediction.min()) * 0.05)
def test_gradient_boosted_regression_batch(self): testdata = np_read_csv( os.path.join(unittest_data_path, "gradient_boosted_regression_batch.csv"), range(1)) import gradient_boosted_regression_batch as ex ex.read_csv = self.read_csv (_, predict_result, _) = ex.main() #MSE self.assertTrue( np.square(predict_result.prediction - testdata).mean() < 1e-2)
def test_svd_batch(self): import svd_batch as ex ex.read_csv = self.read_csv (data, result) = ex.main() self.assertTrue( np.allclose( data, np.matmul( np.matmul(result.leftSingularMatrix, np.diag(result.singularValues[0])), result.rightSingularMatrix)))
def test_low_order_moms_dense_stream(self): testdata = np_read_csv( os.path.join(unittest_data_path, "low_order_moms_dense_batch.csv"), range(10)) import low_order_moms_streaming as ex ex.read_csv = self.read_csv res = ex.main() r = np.vstack( (res.minimum, res.maximum, res.sum, res.sumSquares, res.sumSquaresCentered, res.mean, res.secondOrderRawMoment, res.variance, res.standardDeviation, res.variation)) self.assertTrue(np.allclose(r, testdata))
def test_cosine_distance_batch(self): testdata = np_read_csv( os.path.join(unittest_data_path, "cosine_distance_batch.csv"), range(1)) import cosine_distance_batch as ex ex.read_csv = self.read_csv result = ex.main() r = result.cosineDistance self.assertTrue( np.allclose( np.array([[np.amin(r)], [np.amax(r)], [np.mean(r)], [np.average(r)]]), testdata))
def test_svd_stream(self): import svd_streaming as ex ex.read_csv = self.read_csv result = ex.main() data = np.loadtxt("./data/distributed/svd_1.csv", delimiter=',') for f in [ "./data/distributed/svd_{}.csv".format(i) for i in range(2, 5) ]: data = np.append(data, np.loadtxt(f, delimiter=','), axis=0) self.assertTrue( np.allclose( data, np.matmul( np.matmul(result.leftSingularMatrix, np.diag(result.singularValues[0])), result.rightSingularMatrix)))
def call(self, ex): return ex.main(readcsv=pd_read_csv)
def call(self, ex): method = 'singlePassCSR' if any(x in ex.__name__ for x in ['low_order_moms', 'covariance']) else 'fastCSR' if hasattr(ex, 'dflt_method'): low_order_moms method = ex.dflt_method.replace('defaultDense', 'fastCSR').replace('Dense', 'CSR') return ex.main(readcsv=csr_read_csv, method=method)
def test_kdtree_knn_classification_batch(self): import kdtree_knn_classification_batch as ex ex.read_csv = self.read_csv (_, predict_result, test_labels) = ex.main() self.assertTrue( np.count_nonzero(test_labels != predict_result.prediction) < 170)