updated unit tests to reflect recent code changes

Tests/test_msdataset.py

@@ -15,6 +15,7 @@
 from nPYc.enumerations import VariableType
 from generateTestDataset import generateTestDataset
 import tempfile
+from nPYc.utilities._errorHandling import npycToolboxError
 
 
 
@@ -1352,8 +1353,9 @@ def test_inferbatches_warns(self):
 		msData = copy.deepcopy(self.msData)
 		msData.sampleMetadata.drop('Run Order', axis=1, inplace=True)
 		msData.sampleMetadata.drop('Acquired Time', axis=1, inplace=True)
-		self.assertWarnsRegex(UserWarning, 'Unable to infer batches without complete run order or acquired time info, skipping.',
-							msData._inferBatches)
+		#self.assertWarnsRegex(UserWarning, 'Unable to infer batches without `Run Order` or `Acquired Time` columns in dataset.sampleMetadata',
+		#					msData._inferBatches)
+		self.assertRaises(npycToolboxError, msData._inferBatches)
 
 	def test_amendbatches(self):
 
@@ -1535,6 +1537,7 @@ def test_dilutionlevels(self):
 	def test_feature_correlation(self):
 
 		self.msData.addSampleInfo(descriptionFormat='Raw Data', filePath=os.path.join('..','..','npc-standard-project','Raw_Data'))
+		self.msData.addSampleInfo(descriptionFormat='Infer Batches')
 
 		with self.subTest(msg='Testing Pearson correlations'):
 			correlations = numpy.array([0.99999997, 0.32017508, 1., -0.0693418])
@@ -1700,10 +1703,10 @@ def test_dilutionlevels(self):
 	def test_feature_correlation(self):
 
 		self.msData.addSampleInfo(descriptionFormat='Raw Data', filePath=os.path.join('..','..','npc-standard-project','Raw_Data'))
-		# self.msData.addSampleInfo(descriptionFormat='Batches')
+		self.msData.addSampleInfo(descriptionFormat='Infer Batches')
 
 		self.msData_PeakTable.addSampleInfo(descriptionFormat='Raw Data', filePath=os.path.join('..','..','npc-standard-project','Raw_Data'))
-		# self.msData_PeakTable.addSampleInfo(descriptionFormat='Batches')
+		self.msData_PeakTable.addSampleInfo(descriptionFormat='Infer Batches')
 
 		with self.subTest(msg='Testing Pearson correlations'):
 			correlations = numpy.array([0.99999997, 0.32017508, 1., -0.0693418])
@@ -1841,7 +1844,7 @@ def test_dilutionlevels(self):
 	def test_feature_correlation(self):
 
 		self.msData.addSampleInfo(descriptionFormat='Raw Data', filePath=os.path.join('..','..','npc-standard-project','Raw_Data'))
-		# self.msData.addSampleInfo(descriptionFormat='Batches')
+		self.msData.addSampleInfo(descriptionFormat='Infer Batches')
 
 		with self.subTest(msg='Testing Pearson correlations'):
 			correlations = numpy.array([0.99999997, 0.32017508, 1., -0.0693418])
@@ -2030,7 +2033,7 @@ def test_dilutionlevels(self):
 	def test_feature_correlation(self):
 
 		self.lcData.addSampleInfo(descriptionFormat='Raw Data', filePath=os.path.join('..','..','npc-standard-project','Raw_Data'))
-		# self.lcData.addSampleInfo(descriptionFormat='Batches')
+		self.lcData.addSampleInfo(descriptionFormat='Infer Batches')
 
 		with self.subTest(msg='Testing Pearson correlations'):
 			correlations = numpy.array([0.99999997, 0.32017508, 1., -0.0693418])

Tests/test_regression.py

@@ -1,9 +1,11 @@
 import os
 import sys
 import unittest
+import copy
 
 sys.path.append("..")
 import nPYc
+from nPYc.utilities._errorHandling import npycToolboxError
 
 """
 Tests for checking specific data values remain the same after report functionality changes
@@ -25,25 +27,45 @@ def setUp(self):
                                    sop="GenericMS",
                                    noFeatureParams=9)
 
-        self.data.addSampleInfo(descriptionFormat="Basic CSV",
-                                filePath=os.path.join("..", "..",
-                                                      "npc-standard-project",
-                                                      "Regression_Testing_Data",
-                                                      "DEVSET U RPOS Basic CSV_regressionTesting.csv"))
-
-
     def test_setup(self):
         self.assertIsNotNone(self.data)
 
-    def test_XCMS_metadata_report_correct(self):
+    def test_error_correct(self):
+        """
+        Check error is thrown when sample metadata is missing from basic CSV
+        """
+        msData = copy.deepcopy(self.data)
 
-        sample_summary = nPYc.reports._generateSampleReport(self.data, returnOutput=True)
+        # This is designed to succeed if the npycToolboxError is caught, otherwise to fail
+        try:
+            self.assertRaises(npycToolboxError, msData.addSampleInfo(descriptionFormat="Basic CSV",
+                                                                 filePath=os.path.join("..", "..",
+                                                                                          "npc-standard-project",
+                                                                                          "Regression_Testing_Data",
+                                                                                          "DEVSET U RPOS Basic CSV_regressionTesting_sampleMissing.csv")))
+        except npycToolboxError:# as e:
+            #print(e)
+            return
+
+        self.fail()
+
+    def test_XCMS_metadata_report_correct(self):
         """
         Check returns against expected. sample_summary is a dictionary of dataframes with keys:
         for key in sample_summary.keys():
             print(key)
             print(sample_summary[key])
         """
+
+        # Add basic CSV info
+        self.data.addSampleInfo(descriptionFormat="Basic CSV",
+                                filePath=os.path.join("..", "..",
+                                                      "npc-standard-project",
+                                                      "Regression_Testing_Data",
+                                                      "DEVSET U RPOS Basic CSV_regressionTesting.csv"))
+
+        sample_summary = nPYc.reports._generateSampleReport(self.data, returnOutput=True)
+
         # Acquired - Totals
         self.assertEqual(sample_summary["Acquired"].loc["All", "Total"], 214)
         self.assertEqual(sample_summary["Acquired"].loc["Study Sample", "Total"], 78)
@@ -71,7 +93,7 @@ def test_XCMS_metadata_report_correct(self):
         self.assertEqual(sample_summary["Acquired"].loc["Blank", "Missing/Excluded"], 0)
         self.assertEqual(sample_summary["Acquired"].loc["Unknown", "Missing/Excluded"], 0)
 
-        self.assertEqual(sample_summary["NoMetadata Details"].loc[0, "Sample File Name"], "PipelineTesting_RPOS_ToF10_U1W98")
+        #self.assertEqual(sample_summary["NoMetadata Details"].loc[0, "Sample File Name"], "PipelineTesting_RPOS_ToF10_U1W98")
         self.assertEqual(sample_summary["UnknownType Details"].loc[0, "Sample File Name"], "PipelineTesting_RPOS_ToF10_U1W98")
         self.assertEqual(sample_summary["NotAcquired"].loc[0, "Sample File Name"], "PipelineTesting_RPOS_ToF10_U1W97")
         self.assertEqual(sample_summary["Excluded Details"].loc[0, "Sample File Name"], "PipelineTesting_RPOS_ToF10_U1W97")

Tests/test_reports.py

@@ -268,6 +268,7 @@ def test_reports_ms_correlationtodilution(self):
         data.addSampleInfo(descriptionFormat='Raw Data',
                            filePath=os.path.join('..', '..', 'npc-standard-project', 'Raw_Data', 'ms',
                                                  'parameters_data'))
+        data.addSampleInfo(descriptionFormat='Infer Batches')
         # data.sampleMetadata['Correction Batch'] = data.sampleMetadata['Batch']
         data.corrExclusions = data.sampleMask
 

nPYc/reports/_generateReportMS.py

@@ -650,7 +650,7 @@ def _featureReport(dataset, destinationPath=None):
                 print('Figure 5: TIC of serial dilution (SRD) samples coloured by sample dilution.')
 
             plotLRTIC(dataset,
-                      sampleMask=LRmask,
+                      sampleMask=acquiredMasks['SRDmask'],
                       savePath=saveAs,
                       figureFormat=dataset.Attributes['figureFormat'],
                       dpi=dataset.Attributes['dpi'],

nPYc/reports/_generateSampleReport.py

@@ -107,17 +107,16 @@ def _generateSampleReport(dataTrue, withExclusions=False, destinationPath=None,
 
 	# Determine if samples have been excluded
 	if hasattr(data, 'excludedFlag') and (len(data.excludedFlag) > 0):
-		excludedIX = [i for i, x in enumerate(data.excludedFlag) if x == 'Samples']
-		sampleMetadataExcluded = pandas.DataFrame(
-			columns=['Sample File Name', 'Sample ID', 'SampleType', 'AssayRole', 'Exclusion Details'])
 
-		# Stick info of all previously excluded samples together
-		for i in excludedIX:
-			temp = copy.deepcopy(data.sampleMetadataExcluded[i])
+		# Create dataframe with columns required
+		cols = ['Sample File Name', 'Sample ID', 'SampleType', 'AssayRole', 'Exclusion Details']
+		sampleMetadataExcluded = pandas.DataFrame(columns=cols)
 
-			sampleMetadataExcluded = sampleMetadataExcluded.append(temp[['Sample File Name', 'Sample ID',
-																		 'SampleType', 'AssayRole',
-																		 'Exclusion Details']], ignore_index=True)
+		# Add info of all previously excluded samples (keep only columns required)
+		excludedIX = [i for i, x in enumerate(data.excludedFlag) if x == 'Samples']
+		for i in excludedIX:
+			sampleMetadataExcluded = pandas.concat([sampleMetadataExcluded, data.sampleMetadataExcluded[i]], ignore_index=True)
+			sampleMetadataExcluded = sampleMetadataExcluded[sampleMetadataExcluded.columns.intersection(cols)]
 
 		# Sample type masks, and only those marked as 'sample' or 'unknown' flagged
 		excludedMasks = generateTypeRoleMasks(sampleMetadataExcluded)