implement tests and fix methods to give expected behaviour.

phasecalculator/analysis/similarityanalysis.py

@@ -53,7 +53,7 @@ def read_polynomial_files(poly_filename_list, **kwargs):
     """
     return polyio.read_poly_data_to_dict(poly_filename_list, **kwargs)
 
-PURE_SOLVENT_INFO = read_polynomial_files(pureinf.get_polynomial_filenames(), suffix="free_poly_split_fit.csv")
+PURE_SOLVENT_INFO = read_polynomial_files(pureinf.get_polynomial_filenames(), suffix="free_poly_fit_split.csv")
 
 def compare_all_solvents(poly_filename_list, output_dir, output_filename):
     """
@@ -163,7 +163,7 @@ def write_frame_to_file(dframe, output_filename):
     None.
 
     """
-    dframe.to_csv(output_filename, sep="\t")
+    dframe.to_csv(output_filename, sep="\t", header=True)
 
 def extract_comparison_to_pure_solvents(similarity_dframe, solv_id):
     """
@@ -181,7 +181,7 @@ def extract_comparison_to_pure_solvents(similarity_dframe, solv_id):
         DESCRIPTION.
 
     """
-    return similarity_dframe.loc[solv_id, PURE_SOLVENT_INFO.keys()].sort()
+    return similarity_dframe.loc[solv_id, PURE_SOLVENT_INFO.keys()].sort_values()
     
 def calculate_similarity_matrix(poly_data_by_id):
     """

phasecalculator/test/analysistest/similarityanalysistest.py

@@ -34,6 +34,7 @@ LOGGER.setLevel(logging.WARN)
 
 class SimilarityAnalysisTestCase(unittest.TestCase):
     """Test case for similarity analysis."""
+
     def setUp(self):
         """Set up before tests.
 
@@ -42,6 +43,16 @@ class SimilarityAnalysisTestCase(unittest.TestCase):
         None.
 
         """
+        parent_directory = pathlib.Path(__file__).parents[1]
+        self.expected_free_poly = (parent_directory /"resources" / "expected_parsedfreepoly.csv").absolute().as_posix()
+        self.expected_matrix_file = (parent_directory/ "resources"/ "expectd_matrix.csv").absolute().as_posix()
+        self.example_poly_data = simanalysis.read_polynomial_files([self.expected_free_poly], suffix="freepoly.csv",
+                                                    temperature_dir=True)
+        self.example_with_pure_data = {**simanalysis.PURE_SOLVENT_INFO,
+                                       **self.example_poly_data}
+        self.example_matrix = simanalysis.calculate_similarity_matrix(self.example_with_pure_data)
+        self.actual_matrix_file = "actual_matrix.csv"
+        self.actual_series_file = "resourcesexpected_parsedfreepoly.csv.csv"
     def tearDown(self):
         """Clean up after tests.
 
@@ -58,7 +69,26 @@ class SimilarityAnalysisTestCase(unittest.TestCase):
         None.
 
         """
-        self.fail("not implemented")
+        expected_dict = {'resourcesexpected,parsed':{8: {'negative': {'RMSE': 0.0137444779,
+                                               'coefficients': np.array([-2.60836624e-01,  4.65295250e-01,  2.57637417e-01,  2.19491128e-01,
+        4.20087475e-02,  4.02289353e-03,  2.12247938e-04,  5.89243946e-06,
+        6.73443996e-08]),
+                                               'covar': 0.0379710451935,
+                                               'order': 8},
+                                  'positive': {'RMSE': 0.008907316,
+                                               'coefficients': np.array([-2.52075337e-01, -7.07009850e-01,  9.86359325e-01, -1.40859321e+00,
+        5.04060101e-01, -9.17970326e-02,  9.28812463e-03, -4.97458825e-04,
+        1.10198937e-05]),
+                                               'covar': 0.008013368123414,
+                                               'order': 8}}}}
+        actual_dict = self.example_poly_data
+        self.assertListEqual(list(expected_dict.keys()), list(actual_dict.keys()))
+        for region, info_dict in actual_dict['resourcesexpected,parsed'][8].items():
+            for key, value in info_dict.items():
+                if key == "coefficients":
+                    np.testing.assert_allclose(value, expected_dict['resourcesexpected,parsed'][8][region][key])
+                else:
+                    self.assertEqual(value, expected_dict['resourcesexpected,parsed'][8][region][key])
     def test_compare_all_solvents(self):
         """Test
 
@@ -67,7 +97,10 @@ class SimilarityAnalysisTestCase(unittest.TestCase):
         None.
 
         """
-        self.fail("not implemented")
+        simanalysis.compare_all_solvents([self.expected_free_poly], "", self.actual_matrix_file)
+        self.assertTrue(pathlib.Path(self.actual_matrix_file).is_file())
+        actual_dataframe = pandas.read_csv(self.actual_matrix_file, sep="\t",header=0,index_col=0)
+        self.assertEqual((262,262), actual_dataframe.shape)
     def test_compare_with_pure_solvents(self):
         """Test
 
@@ -76,7 +109,11 @@ class SimilarityAnalysisTestCase(unittest.TestCase):
         None.
 
         """
-        self.fail("not implemented")
+        simanalysis.compare_with_pure_solvents([self.expected_free_poly], "")
+        self.assertTrue(pathlib.Path(self.actual_series_file).is_file())
+        self.assertTrue(pathlib.Path(self.actual_matrix_file).is_file())
+        actual_dataframe = pandas.read_csv(self.actual_series_file, sep="\t",header=0,index_col=0)
+        self.assertEqual((261,1), actual_dataframe.shape)
     def test_compare_solvent_list(self):
         """Test
 
@@ -85,7 +122,10 @@ class SimilarityAnalysisTestCase(unittest.TestCase):
         None.
 
         """
-        self.fail("not implemented")
+        simanalysis.compare_solvent_list([self.expected_free_poly], "", self.actual_matrix_file)
+        self.assertTrue(pathlib.Path(self.actual_matrix_file).is_file())
+        actual_dataframe = pandas.read_csv(self.actual_matrix_file, sep="\t",header=0,index_col=0)
+        self.assertEqual((1,1), actual_dataframe.shape)
     def test_write_frame_to_file(self):
         """Test
 
@@ -94,7 +134,8 @@ class SimilarityAnalysisTestCase(unittest.TestCase):
         None.
 
         """
-        self.fail("not implemented")
+        simanalysis.write_frame_to_file(self.example_matrix, self.actual_matrix_file)
+        self.assertTrue(pathlib.Path(self.actual_matrix_file).is_file())
     def test_extract_comparison_to_pure_solvents(self):
         """Test
 
@@ -103,13 +144,22 @@ class SimilarityAnalysisTestCase(unittest.TestCase):
         None.
 
         """
-        self.fail("not implemented")
+        extracted_data = simanalysis.extract_comparison_to_pure_solvents(self.example_matrix, "resourcesexpected,parsed")
+        expected_top5 = pandas.Series(data={"formamide":0.07340402,
+"hydrogen peroxide": 0.12358179,
+"methanesulfonic acid": 0.12495022,
+"ethylene glycol": 0.13908444,
+"1,2-butanediol": 0.14388483}, name="resourcesexpected,parsed")
+        np.testing.assert_allclose(expected_top5.values, extracted_data[:5].values)
+        self.assertListEqual(expected_top5.index.to_list(), extracted_data[:5].index.to_list())
     def test_calculate_similarity_matrix(self):
-        """Test
+        """Test expected dataframe produced.
 
         Returns
         -------
         None.
 
         """
-        self.fail("not implemented")
\ No newline at end of file
+        actual_dataframe = self.example_matrix
+        self.assertEqual((262,262), actual_dataframe.shape)
+        
\ No newline at end of file