Merge pull request #53 from BAMresearch/unittest-mixture-metadata-ext…

…raction

Unittest mixture metadata extraction

tests/mapping/test_mapping_script.py

@@ -0,0 +1,121 @@
+import unittest
+import rdflib
+import datetime
+import os
+import yaml
+from pathlib import Path
+
+from lebedigital.mapping.emodul_mapping import generate_knowledge_graph, get_date_time_value
+
+class TestMappingScript(unittest.TestCase):
+
+    def query_and_test_result(self, typeOfQuery, predicate, prop, g):
+        print(f"""Query for {typeOfQuery}:""")
+        q = f"""
+                SELECT ?o WHERE {{
+                        {predicate} {prop} ?o .
+                }}
+                """
+        print(q)
+        result = g.query(q)
+        return result
+
+
+    def print_next(self):
+        print("Pass")
+        print("###################Next Query#####################################")
+
+
+    def print_first(self):
+        print("###################First Query####################################")
+
+
+    def test_generate_knowledge_graph(self):
+        metadataPath = 'testMetaData.yaml'
+        filename = "knowledgeGraph.ttl"
+        print("Start testing:")
+        # Generate a testMetadata file
+        print("Generate metadata file for test:")
+        target_data = {'experimentName': 'BA-Losert MI E-Modul 28d v. 04.08.14 Probe 4',
+                       'software_specification': 'MTS793|MPT|DEU|1|2|,|.|:|49|1|1|A',
+                       'operator_timestamp': '13:25:39',
+                       'operator_date': '01.09.2014',
+                       'tester_name': 'Kh',
+                       'specimen_name': 'BA-Losert E-Modul 28d v. 04.08.14 Probe 4',
+                       'remark': 'Kraftgeregelt 3,9 kN/s',
+                       'weight': 5342.0,
+                       'weight_unit': 'g',
+                       'diameter': 98.6,
+                       'length': 300.3,
+                       'length_unit': 'mm',
+                       'mix_file': '2014_08_05 Rezeptur_MI.xlsx'}
+
+        with open(metadataPath, 'w') as yamlFile:
+            yaml.dump(target_data, yamlFile)
+        print("Generate knowledgeGraph:")
+        generate_knowledge_graph(metadataPath, filename)
+
+        g = rdflib.Graph()
+        result = g.parse(filename, format='ttl')
+        print("Query knowledgeGraph:")
+
+        self.print_first()
+
+        result = self.query_and_test_result('diameter', 'ns1:informationbearingentity1',
+                                       'ns7:has_decimal_value', g)
+        for row in result:
+            self.assertEqual(target_data['diameter'], float(row.o))
+
+        self.print_next()
+
+        result = self.query_and_test_result('length', 'ns1:informationbearingentity2',
+                                       'ns7:has_decimal_value', g)
+        for row in result:
+            self.assertEqual(target_data['length'], float(row.o))
+
+        self.print_next()
+
+        result = self.query_and_test_result('weight', 'ns1:informationbearingentity3',
+                                       'ns7:has_decimal_value', g)
+        for row in result:
+            self.assertEqual(target_data['weight'], float(row.o))
+
+        self.print_next()
+
+        time = get_date_time_value(target_data)
+        result = self.query_and_test_result('operator_time', 'ns1:informationbearingentity6',
+                                       'ns1:has_datetime_value', g)
+        for row in result:
+            self.assertEqual(time, datetime.datetime.strptime(str(row.o).replace('T', ' '), "%Y-%m-%d %H:%M:%S"))
+
+        self.print_next()
+
+        result = self.query_and_test_result('operatorName', 'ns1:informationbearingentity7',
+                                       'ns7:has_text_value', g)
+        for row in result:
+            self.assertEqual(target_data['tester_name'], str(row.o))
+
+        self.print_next()
+        result = self.query_and_test_result('rawFileName', 'ns1:informationbearingentity4',
+                                       'ns7:has_text_value', g)
+        for row in result:
+            self.assertEqual(target_data['experimentName'], str(row.o))
+
+        self.print_next()
+        result = self.query_and_test_result('rawFileName', 'ns1:informationbearingentity5',
+                                       'ns7:has_text_value', g)
+        rawPath = os.path.join(Path(__file__).parents[2], 'usecases',
+                               'MinimumWorkingExample', 'Data', 'E-modul', target_data['experimentName'])
+
+        for row in result:
+            self.assertEqual(rawPath, str(row.o))
+
+        print('Pass all tests')
+
+        print("Deleting test files:")
+        os.remove(filename)
+        os.remove(metadataPath)
+
+        print("End testing")
+
+    # test_generate_knowledge_graph()

tests/raw_data_processing/mixture/test_mixture_metadata_extraction.py

@@ -0,0 +1,49 @@
+import os
+from lebedigital.raw_data_processing.mixture.mixture_metadata_extraction import extract_metadata_mixture
+
+
+def test_mixture_metadata_extraction():
+    """Testing the mixture metadata extraction on a single example"""
+
+    # setting up the test example input
+    input_path = '../usecases/MinimumWorkingExample/Data/Mischungen/2014_08_05 Rezeptur_MI.xlsx'
+
+    # make sure that the path exists
+    assert(os.path.exists(input_path))
+
+    target_data = {'operator_date': '2014-06-30',
+                   'tester_name': 'Werner',
+                   'specimen_name': 'BA-Losert MI',
+                   'cement--QuantityInMix': 330.0,
+                   'cement--BulkDensity': 3.123,
+                   'cement--Volume': 105.7,
+                   'cement--Annotation': 'CEM I 42.5 R',
+                   'water_total--QuantityInMix': 175.0,
+                   'water_total--BulkDensity': 1.0,
+                   'water_total--Volume': 175.0,
+                   'water_cement_ratio': 0.5303030303030303,
+                   'water_effective--QuantityInMix': float('nan'),
+                   'water_effective--BulkDensity': float('nan'),
+                   'water_effective--Volume': float('nan'),
+                   'air_content--QuantityInMix': 0.0,
+                   'air_content--BulkDensity': 0.0,
+                   'air_content--Volume': 20.0,
+                   'addition1--QuantityInMix': 273.0,
+                   'addition1--BulkDensity': 2.74,
+                   'addition1--Volume': 99.6,
+                   'addition1--Annotation': 'Medenbach - Kalksteinmehl',
+                   'admixture--QuantityInMix': 5.61,
+                   'admixture--BulkDensity': 1.05,
+                   'admixture--Volume': 5.3,
+                   'admixture--Annotation': 'FM 595 BASF',
+                   'aggregate--QuantityInMix': 1564.0,
+                   'aggregate--BulkDensity': float('nan'),
+                   'aggregate--Volume': 594.4000000000001}
+
+    # run extraction and getting a dictionary with metadata
+    test_data = extract_metadata_mixture(input_path, None)
+
+    # test each value
+    # conversion to string is required as float.nan != float.nan
+    for key in target_data.keys():
+        assert(str(test_data[key]) == str(target_data[key]))

tests/raw_data_processing/youngs_modulus_data/test_metadata_extraction_emodul.py

@@ -0,0 +1,32 @@
+import unittest
+
+from lebedigital.raw_data_processing.youngs_modulus_data \
+    .emodul_metadata_extraction import extract_metadata_emodulus
+class TestMetaDataExtractionEmodul(unittest.TestCase):
+    def test_metadata_extraction_emodul(self):
+        """Tesing the metadata extraction on a single example"""
+
+        # setting up the test example
+        input = '../usecases/MinimumWorkingExample/Data/E-modul/BA-Losert MI E-Modul 28d v. 04.08.14 Probe 4'
+        mix_file = 'mix.dat'
+        specimen_file = 'specimen.dat'
+
+        target_data = {'experimentName': 'BA-Losert MI E-Modul 28d v. 04.08.14 Probe 4',
+                                               'software_specification': 'MTS793|MPT|DEU|1|2|,|.|:|49|1|1|A',
+                                               'operator_timestamp': '13:25:39',
+                                               'operator_date': '01.09.2014',
+                                               'tester_name': 'Kh',
+                                               'specimen_name': 'BA-Losert E-Modul 28d v. 04.08.14 Probe 4',
+                                               'remark': 'Kraftgeregelt 3,9 kN/s',
+                                               'weight': 5342.0,
+                                               'weight_unit': 'g',
+                                               'diameter': 98.6,
+                                               'length': 300.3,
+                                               'length_unit': 'mm',
+                                               'mix_file': '2014_08_05 Rezeptur_MI.xlsx'}
+
+        # run extraction and getting a dictionary with metadata
+        test_data = extract_metadata_emodulus(input, specimen_file, mix_file)
+
+        # checking if result is correct
+        self.assertEqual(test_data, target_data)

tests/raw_data_processing/youngs_modulus_data/test_processed_data_from_rawdata.py

@@ -0,0 +1,20 @@
+import unittest
+import os
+
+from lebedigital.raw_data_processing.youngs_modulus_data.emodul_generate_processed_data import \
+    processed_data_from_rawdata
+
+class TestProcessedDataFromRawData(unittest.TestCase):
+
+    def test_emodul_generate_processed_data(self):
+        """
+        Testing the processed data generation on a single experiment
+        """
+
+        rawdata_location = '../usecases/MinimumWorkingExample/Data/E-modul/BA-Losert MI E-Modul 28d v. 04.08.14 Probe 4'
+        processeddat_location = './BA-Losert MI E-Modul 28d v. 04.08.14 Probe 4' + '.csv'
+
+        processed_data_from_rawdata(locationOfRawData=rawdata_location, locationOfProcessedData=processeddat_location)
+
+        self.assertTrue(os.path.exists('./BA-Losert MI E-Modul 28d v. 04.08.14 Probe 4.csv'))
+