Migrate to pytest and implement code coverage.

.coveragerc

@@ -1,2 +1,3 @@
 [run]
-source=OrthoEvol
+source=OrthoEvol
+disable_warnings = couldnt-parse

.travis.yml

@@ -1,21 +1,45 @@
 language: python
-dist: xenial
 os: linux
 cache: pip
-python:
-  - "3.5"
-  - "3.6"
-  - "3.7"
-  - "3.8"
 notifications:
   email: [email protected]
-# command to install dependencies
-install:
-  - "pip install --upgrade pip setuptools wheel"
-  - "pip install --only-binary=numpy,scipy numpy scipy"
-  - "pip install matplotlib ipython jupyter sympy pytest"
-  - "pip install -r requirements.txt"
-  - "pip install ."
-# command to run unittests via pytest
+jobs:
+  include:
+    - python: 3.5
+      dist: trusty
+      install:
+        - pip install --upgrade pip setuptools wheel
+        - pip install --only-binary=numpy,scipy numpy scipy
+        - pip install matplotlib ipython jupyter sympy pytest codecov "pytest-cov<=2.6.0"
+        - pip install -r requirements.txt
+        - pip install .
+    - python: 3.6
+      dist: xenial
+      install:
+        - pip install --upgrade pip setuptools wheel
+        - pip install --only-binary=numpy,scipy numpy scipy
+        - pip install matplotlib ipython jupyter sympy pytest codecov pytest-cov
+        - pip install -r requirements.txt
+        - pip install .
+    - python: 3.7
+      dist: xenial
+      install:
+        - pip install --upgrade pip setuptools wheel
+        - pip install --only-binary=numpy,scipy numpy scipy
+        - pip install matplotlib ipython jupyter sympy pytest codecov pytest-cov
+        - pip install -r requirements.txt
+        - pip install .
+    - python: 3.8
+      dist: xenial
+      install:
+        - pip install --upgrade pip setuptools wheel
+        - pip install --only-binary=numpy,scipy numpy scipy
+        - pip install matplotlib ipython jupyter sympy pytest codecov pytest-cov
+        - pip install -r requirements.txt
+        - pip install .
+# command to run unittests
 script:
-  - pytest tests/
+  - pytest --cov-report=xml --cov=OrthoEvol tests/
+# upload code coverage
+after_success:
+  - codecov

OrthoEvol/Orthologs/Align/msa.py

@@ -108,14 +108,14 @@ def guidance2(self, seqFile, msaProgram, seqType, dataset='MSA', seqFilter=None,
         gene = Path(seqFile).stem
         geneDir = self.raw_data / Path(gene)
         self.guidancelog.info(geneDir)
-        if seqType is 'nuc':
+        if seqType == 'nuc':
             g2_seqFile = str(geneDir / Path(gene + '_G2.ffn'))  # Need for all iterations
             rem_file = str(geneDir / Path(gene + '_G2_removed.ffn'))   # Need for all iterations
             g2_alnFile = str(geneDir / Path(gene + '_G2_na.aln'))
             g2_seqcolFilter = str(geneDir / Path(gene + 'G2sfcf_na.aln'))
             g2_colFilter = str(geneDir / Path(gene + '_G2cf_na.aln'))
             g2_maskedFile = str(geneDir / Path(gene + '_G2mf_na.aln'))
-        elif seqType is 'aa':
+        elif seqType == 'aa':
             g2_seqFile = str(geneDir / Path(gene + '_G2.faa'))  # Need for all iterations
             rem_file = str(geneDir / Path(gene + '_G2_removed.faa'))   # Need for all iterations
             g2_alnFile = str(geneDir / Path(gene + '_G2_aa.aln'))
@@ -176,9 +176,9 @@ def guidance2(self, seqFile, msaProgram, seqType, dataset='MSA', seqFilter=None,
                 elif set_iter >= iteration > 1:
 
                     # Depending on the filter strategy increment the seqCutoff
-                    if seqFilter is "inclusive":
+                    if seqFilter == "inclusive":
                         kwargs['seqCutoff'] -= kwargs['increment']
-                    elif seqFilter is "exclusive":
+                    elif seqFilter == "exclusive":
                         kwargs['seqCutoff'] += kwargs['increment']
                     # seqFile changes to g2_seqFile and the cutoffs change
                     G2Cmd = Guidance2Commandline(seqFile=g2_seqFile, msaProgram=msaProgram, seqType=seqType,

OrthoEvol/Orthologs/GenBank/genbank.py

@@ -94,7 +94,7 @@ def name_fasta_file(self, path, gene, org, feat_type,
         # Create path variables.  (typically raw_data/<gene>/GENBANK
         feat_path = path
         # Create a format-able string for file names
-        if feat_type_rank is "CDS":
+        if feat_type_rank == "CDS":
             single = '%s_%s%s%s'
             multi = '%s%s%s'
         else:
@@ -406,7 +406,7 @@ def get_fasta_files(self, acc_dict, db=True):
             for _, _, gbk_files in os.walk(str(self.target_gbk_files_path)):
                 # For each genbank record write a set of FASTA files.
                 for gbk_file in gbk_files:
-                    if Path(gbk_file).suffix is '.gbk':
+                    if Path(gbk_file).suffix == '.gbk':
                         record = SeqIO.read(gbk_file, 'genbank')
                         self.write_fasta_files(record, acc_dict)
                         self.genbanklog.info("FASTA files for %s created." % gbk_file)

OrthoEvol/Tools/logit/logit.py

@@ -53,12 +53,12 @@ def custom(cls, logname, logfile, level, fmt='default'):
         :return: A custom_log object is returned.
         """
 
-        if fmt is 'default':
+        if fmt == 'default':
             fmt = '[%(levelname)-2s - %(name)s]: %(message)s'
-        elif fmt is 'custom':
+        elif fmt == 'custom':
             # TODO Allow customization
             raise NotImplementedError('Feature not integrated yet!')
-        elif fmt is not 'default' or 'custom':
+        elif fmt != 'default' or 'custom':
             raise Exception('User did not provide a format for the logger.')
 
         custom_log = setup_logger(name=logname, logfile=logfile,

OrthoEvol/Tools/slackify/notify.py

@@ -19,7 +19,7 @@ def __init__(self, slackconfig='slackconfig.cfg', cfg=True):
         # Use False if you did not create a config file
         if not cfg:
             apikey = input('Insert your slack apikey here: ')
-            if len(apikey) is not 42:  # Standard length of slack apikey
+            if len(apikey) != 42:  # Standard length of slack apikey
                 raise ValueError('Your slack APIKEY is incorrect.')
 
             slack = Slacker(apikey)

OrthoEvol/utilities.py

@@ -28,6 +28,7 @@
 # Set up logging
 blastutils_log = LogIt().default(logname="blast-utils", logfile=None)
 seqidlist_log = LogIt().default(logname="gi-lists", logfile=None)
+utils_log = LogIt().default(logname="utils", logfile=None)
 _datefmt = '%I:%M:%S %p on %m-%d-%Y'
 _date = str(datetime.now().strftime(_datefmt))
 
@@ -445,17 +446,17 @@ def multi_fasta_manipulator(self, target_file, man_file, output_file,
         # Create a new multi-fasta record object using the target_file,
         # reference, and output
         # Remove specific sequences from a fasta file
-        if manipulation is 'remove':
+        if manipulation == 'remove':
             self.multi_fasta_remove(target_file, man_file, new_file)
         # Combine all the FASTA sequence in one record object
-        elif manipulation is 'add':
+        elif manipulation == 'add':
             self.muli_fasta_add(target_file, man_file, new_file)
         # Sort one fasta file based on the order of another
         # Works for alignments
-        elif manipulation is 'sort':
+        elif manipulation == 'sort':
             self.multi_fasta_sort(target_file, man_file, new_file)
 
-        print('A new fasta file has been created.')
+        utils_log.info('A new fasta file has been created.')
         return new_file
 
     # def dir_config(path, tier_frame_dict):
@@ -505,7 +506,7 @@ def multi_fasta_remove(self, target_file, man_file, output_file):
                 target_file,
                 'fasta') if record.id in ids)
 
-        print('Sequences have been filtered.')
+        utils_log.info('Sequences have been filtered.')
         SeqIO.write(new_records, str(output_file), 'fasta')
         SeqIO.write(old_records, str(rem_file), 'fasta')
 
@@ -532,11 +533,11 @@ def muli_fasta_add(self, target_file, man_file, output_file):
                     target_file, 'fasta', ), SeqIO.parse(man_file, 'fasta'))
                 count = SeqIO.write(new_records, tmp_file, 'fasta')
                 tmp_file.seek(0)
-                print('temp file count: ' + str(count))
+                utils_log.info('temp file count: ' + str(count))
                 SeqIO.write(SeqIO.parse(tmp_file, 'fasta'), str(output_file), 'fasta')
-            print('Sequences have been added.')
+            utils_log.info('Sequences have been added.')
         else:
-            print('You can only add files together.  Not python objects.')
+            utils_log.warning('You can only add files together.  Not python objects.')
 
     def multi_fasta_sort(self, target_file, man_file, output_file):
         """Sorts selected reference sequences in a multi-FASTA files.
@@ -569,15 +570,15 @@ def multi_fasta_sort(self, target_file, man_file, output_file):
             for unsorted_aln_record in SeqIO.parse(target_file, 'fasta'):
                 # If an appropriate id is found, then append to the MSA object.
                 if unsorted_aln_record.id == sorted_seq_record.id:
-                    print(unsorted_aln_record.id)
-                    print(sorted_seq_record.id)
+                    utils_log.info(unsorted_aln_record.id)
+                    utils_log.info(sorted_seq_record.id)
                     aln.append(unsorted_aln_record)  # MSA object
                     break
         count = AlignIO.write(aln, tmp_file, 'fasta')
         tmp_file.seek(0)
-        print('temp file count: ' + str(count))
+        utils_log.info('temp file count: ' + str(count))
         AlignIO.write(AlignIO.read(tmp_file, 'fasta'), str(output_file), 'fasta')
-        print('Alignment has been sorted.')
+        utils_log.info('Alignment has been sorted.')
 
 
 class OrthologUtils(BlastUtils, GenbankUtils):
@@ -877,7 +878,7 @@ def __init__(self, packagename):
     def _getversion(self):
         import_module(self.packagename)
         version = pkg_resources.get_distribution(self.packagename).version
-        print('Version %s of %s is installed.' % (version, self.packagename))
+        utils_log.info('Version %s of %s is installed.' % (version, self.packagename))
 
 
 class FunctionRepeater(object):
@@ -933,7 +934,7 @@ def system_cmd(self, cmd, timeout=None, print_flag=True,
         for line in iter(proc.stdout.readline, ""):
             stdout_list.append(line.rstrip())
             if print_flag:
-                print(line, end="")
+                utils_log.info(line, end="")
             sys.stdout.flush()
             if write_flag:
                 with open(file_name, 'a') as output_file:

pytest.ini

@@ -0,0 +1,4 @@
+[pytest]
+addopts = -ra -q
+testpaths =
+    tests