diff --git a/solventmapcreator/clusteringanalysis/clusteranalysis.py b/solventmapcreator/clusteringanalysis/clusteranalysis.py
index 587e3ea5f4278bdf1f08bc508a23932586f3338a..b2078845cd59d85212aabce3f2e2a19371f37802 100644
--- a/solventmapcreator/clusteringanalysis/clusteranalysis.py
+++ b/solventmapcreator/clusteringanalysis/clusteranalysis.py
@@ -22,7 +22,7 @@ def create_dend_and_stats_all_methods(condensed_matrix, labels, filename_stem, *
"""This generates the linkage matrices for each method, and returns the
dendrogram and linkage file and statistics for each method.
"""
- linkage_matrix_dict = clustering_by_all_methods(condensed_distance_matrix)
+ linkage_matrix_dict = clustering_by_all_methods(condensed_matrix)
output_dict= {}
for method_label, linkage_matrix in linkage_matrix_dict.keys():
method_filename_stem= filename_stem + '_' + method_label
@@ -79,7 +79,7 @@ def generate_cophenetic_filename(filename_stem):
"""This generates the cophenetic and inconsistency filenamefrom the given
stem.
"""
- return filename_stem + '_coph_inconst.csv
+ return filename_stem + '_coph_inconst.csv'
def generate_linkage_filename(filename_stem):
"""This generates the filename for the linkage file.
diff --git a/solventmapcreator/test/clusteringanalysistest/clusteranalysistest.py b/solventmapcreator/test/clusteringanalysistest/clusteranalysistest.py
new file mode 100644
index 0000000000000000000000000000000000000000..9e2e3d0af7b0ce84e5e42a7d0c15359c50a66ff1
--- /dev/null
+++ b/solventmapcreator/test/clusteringanalysistest/clusteranalysistest.py
@@ -0,0 +1,183 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Script containing tests for methods in the clusteranalysis script that do not plot.
+
+@author: mark
+"""
+
+import logging
+import numpy as np
+import os
+import unittest
+import solventmapcreator.clusteringanalysis.clusteranalysis as clusteranalysis
+
+
+logging.basicConfig()
+LOGGER = logging.getLogger(__name__)
+LOGGER.setLevel(logging.WARN)
+
+class ClusterAnalysisTestCase(unittest.TestCase):
+ """Test Case for clusteranlysis script.
+ """
+ def setUp(self):
+ """Set up before tests.
+ """
+ self.example_distance_matrix = np.array([17, 21, 31, 23, 30, 34, 21, 28, 39, 43])
+ self.expected_linkage_matrix_dict = {"ward_clustering":np.array([[0., 1., 17., 2.],
+ [4., 5., 23.459184, 3.],
+ [2., 3., 28., 2.],
+ [6., 7., 43.875582, 5.]]),
+ "wpgmc_clustering":np.array([[0., 1., 17., 2.],
+ [4., 5., 20.31625, 3.],
+ [2., 3., 28., 2.],
+ [6., 7., 30.650245, 5.]]),
+ "upgmc_clustering":np.array([[0., 1., 17., 2.],
+ [4., 5., 20.31625, 3.],
+ [2., 3., 28., 2.],
+ [6., 7., 28.321566, 5.]]),
+ "wpgma_clustering":np.array([[0., 1., 17., 2.],
+ [4., 5., 22., 3.],
+ [2., 3., 28., 2.],
+ [6., 7., 35., 5.]]),
+ "upgma_clustering":np.array([[0., 1., 17., 2.],
+ [4., 5., 22., 3.],
+ [2., 3., 28., 2.],
+ [6., 7., 33., 5.]]),
+ "max_clustering": np.array([[0., 1., 17., 2.],
+ [4., 5., 23., 3.],
+ [2., 3., 28., 2.],
+ [6., 7., 43., 5.]]),
+ "min_clustering":np.array([[0., 1., 17., 2.],
+ [2., 5., 21., 3.],
+ [4., 6., 21., 4.],
+ [3., 7., 28., 5.]])}
+ self.expected_filename = "resources/expectedlinkagematrix.csv"
+ self.inconsistency_matrix = np.array([[17., 0., 1., 0.],
+ [19.5, 3.535534, 2., 0.707107],
+ [28., 0., 1., 0.],
+ [27.666667,5.507571, 3., 0.968364]])
+ self.cophenetic_coefficient = 0.73020316123580109
+ self.cophenetic_distance_matrix = np.array([17., 33., 33., 22., 33.,
+ 33., 22., 28., 33., 33.])
+ self.expected_cop_filename = "resources/expectedcopfile.csv"
+ def tearDown(self):
+ """Clean up after tests.
+ """
+ del self.example_distance_matrix
+ del self.expected_linkage_matrix_dict
+ del self.expected_filename
+ del self.inconsistency_matrix
+ del self.cophenetic_coefficient
+ del self.cophenetic_distance_matrix
+ del self.expected_cop_filename
+ if os.path.isfile("linkagematrix.csv"):
+ os.remove("linkagematrix.csv")
+ if os.path.isfile("coph_incons.csv"):
+ os.remove("coph_incons.csv")
+ if os.path.isfile("coph_incons2.csv"):
+ os.remove("coph_incons2.csv")
+ def test_generate_cophenetic_and_inconsistency_file(self):
+ """Test to see if expected file is produced.
+ """
+ actual_filename = "coph_incons2.csv"
+ coph_out = clusteranalysis.generate_cophenetic_and_inconsistency_file(self.expected_linkage_matrix_dict["upgma_clustering"],
+ self.example_distance_matrix,
+ actual_filename)
+ with open("resources/expectedcopfile2.csv", 'r') as exp_file:
+ exp_file_lines = exp_file.readlines()
+ with open(actual_filename, 'r') as act_file:
+ act_file_lines = act_file.readlines()
+ self.assertListEqual(act_file_lines, exp_file_lines)
+ def test_generate_cophenetic_filename(self):
+ """Test to see if expected filename is produced
+ """
+ expected_filename = "example_coph_inconst.csv"
+ actual_filename = clusteranalysis.generate_cophenetic_filename("example")
+ self.assertEqual(expected_filename, actual_filename)
+ def test_generate_linkage_filename(self):
+ """Test to see if expected filename is produced
+ """
+ expected_filename = "example.csv"
+ actual_filename = clusteranalysis.generate_linkage_filename("example")
+ self.assertEqual(expected_filename, actual_filename)
+ def test_write_linkage_matrix(self):
+ """Test to see if expected file is produced.
+ """
+ actual_filename = "linkagematrix.csv"
+ link_mat_out = clusteranalysis.write_linkage_matrix(self.expected_linkage_matrix_dict["upgma_clustering"],
+ actual_filename)
+ self.assertEqual(0, link_mat_out)
+ with open(self.expected_filename, 'r') as exp_file:
+ exp_file_lines = exp_file.readlines()
+ with open(actual_filename, 'r') as act_file:
+ act_file_lines = act_file.readlines()
+ self.assertListEqual(act_file_lines, exp_file_lines)
+ def test_write_cophenetic_and_inconsistency(self):
+ """Test to see if expected file is produced.
+ """
+ actual_filename = "coph_incons.csv"
+ coph_out = clusteranalysis.write_cophenetic_and_inconsistency(self.cophenetic_coefficient,
+ self.cophenetic_distance_matrix,
+ self.inconsistency_matrix,
+ actual_filename)
+ with open(self.expected_cop_filename, 'r') as exp_file:
+ exp_file_lines = exp_file.readlines()
+ with open(actual_filename, 'r') as act_file:
+ act_file_lines = act_file.readlines()
+ self.assertListEqual(act_file_lines, exp_file_lines)
+ def test_calculate_cophenetic_and_inconsistency(self):
+ """Test to see if expected dictionary is produced.
+ """
+ expected_dict = {"cophenetic_coeff":0.73020316123580109,
+ "cophenetic_distances":np.array([17., 33., 33., 22.,
+ 33., 33.,
+ 22., 28., 33., 33.]),
+ "inconsistency_matrix":np.array([[17., 0., 1., 0.],
+ [19.5, 3.535534,
+ 2., 0.707107],
+ [28., 0., 1., 0.],
+ [27.666667,5.507571,
+ 3., 0.968364]])}
+ actual_dict = clusteranalysis.calculate_cophenetic_and_inconsistency(self.expected_linkage_matrix_dict["upgma_clustering"],
+ self.example_distance_matrix)
+ self.assertListEqual(sorted(expected_dict.keys()), sorted(actual_dict.keys()))
+ for key in expected_dict.keys():
+ if key == "cophenetic_coeff":
+ self.assertAlmostEqual(expected_dict[key], actual_dict[key])
+ else:
+ np.testing.assert_array_almost_equal(expected_dict[key], actual_dict[key])
+ def test_calculate_inconsistency(self):
+ """Test to see if expected inconsistency matrix is produced.
+ """
+ expected_matrix = np.array([[17., 0., 1., 0.],
+ [19.5, 3.535534, 2., 0.707107],
+ [28., 0., 1., 0.],
+ [27.666667,5.507571, 3., 0.968364]])
+ actual_matrix = clusteranalysis.calculate_inconsistency(self.expected_linkage_matrix_dict["upgma_clustering"])
+ np.testing.assert_array_almost_equal(expected_matrix, actual_matrix)
+ def test_calculate_cophenetic_distance(self):
+ """Test to see if expected cophenetic coefficientand distances are produced.
+ """
+ expected_distance = 0.73020316123580109
+ expected_matrix = np.array([17., 33., 33., 22., 33., 33., 22., 28.,
+ 33., 33.])
+ actual_distance, actual_matrix = clusteranalysis.calculate_cophenetic_distance(self.expected_linkage_matrix_dict["upgma_clustering"],
+ self.example_distance_matrix)
+ self.assertAlmostEqual(expected_distance, actual_distance)
+ np.testing.assert_array_almost_equal(expected_matrix, actual_matrix)
+ def test_clustering_given_method(self):
+ """Test to see if expected matrix is produced.
+ """
+ actual_matrix = clusteranalysis.clustering_given_method(self.example_distance_matrix,"average")
+ np.testing.assert_array_almost_equal(self.expected_linkage_matrix_dict["upgma_clustering"],
+ actual_matrix)
+ def test_clustering_by_all_methods(self):
+ """Test to see if expected dict is produced.
+ """
+ actual_dict = clusteranalysis.clustering_by_all_methods(self.example_distance_matrix)
+ self.assertListEqual(sorted(self.expected_linkage_matrix_dict.keys()),
+ sorted(actual_dict.keys()))
+ for key in self.expected_linkage_matrix_dict.keys():
+ np.testing.assert_array_almost_equal(self.expected_linkage_matrix_dict[key],
+ actual_dict[key])
diff --git a/solventmapcreator/test/resources/expectedcopfile2.csv b/solventmapcreator/test/resources/expectedcopfile2.csv
new file mode 100644
index 0000000000000000000000000000000000000000..5184b87b2ad7dab69790c26919bd51f79195725d
--- /dev/null
+++ b/solventmapcreator/test/resources/expectedcopfile2.csv
@@ -0,0 +1,12 @@
+Cophenetic coefficient 0.7302032
+Cophenetic Distance Matrix
+0.0000000 17.0000000 33.0000000 33.0000000 22.0000000
+17.0000000 0.0000000 33.0000000 33.0000000 22.0000000
+33.0000000 33.0000000 0.0000000 28.0000000 33.0000000
+33.0000000 33.0000000 28.0000000 0.0000000 33.0000000
+22.0000000 22.0000000 33.0000000 33.0000000 0.0000000
+Mean Heights of links SD for links Number of links Inconsistency coefficient
+17.0000000 0.0000000 1.0 0.0000000
+19.5000000 3.5355339 2.0 0.7071068
+28.0000000 0.0000000 1.0 0.0000000
+27.6666667 5.5075705 3.0 0.9683641
diff --git a/solventmapcreator/test/solvationmapcreatortests.py b/solventmapcreator/test/solvationmapcreatortests.py
index b6b59921a8bb6153a44ac74a076fbf0d1200acb8..8f0c8a91a0389ef343d8fb6e4d2396090f3b6df3 100644
--- a/solventmapcreator/test/solvationmapcreatortests.py
+++ b/solventmapcreator/test/solvationmapcreatortests.py
@@ -25,7 +25,7 @@ from solventmapcreator.test.polynomialanalysistest.polynomialplottingtest import
from solventmapcreator.test.clusteringanalysistest.matrixinputtest import MatrixInputTestCase
from solventmapcreator.test.clusteringanalysistest.clustercalculationtest import ClusterCalculationTestCase
from solventmapcreator.test.clusteringanalysistest.clusterstatisticstest import ClusterStatisticsTestCase
-
+from solventmapcreator.test.clusteringanalysistest.clusteranalysistest import ClusterAnalysisTestCase
logging.basicConfig()
LOGGER = logging.getLogger(__name__)
LOGGER.setLevel(logging.WARN)
@@ -45,7 +45,7 @@ POLYNOMIAL_ANALYSIS_TEST_CASES = [PolynomialDataAnalysisTestCase,
PolynomialPlottingTestCase]
CLUSTERING_ANALYSIS_TEST_CASES = [MatrixInputTestCase, ClusterCalculationTestCase,
- ClusterStatisticsTestCase]
+ ClusterStatisticsTestCase, ClusterAnalysisTestCase]
def test_suite():
"""Function creates a test suite and then loads all the tests from the