Fix loading_bar in tests

tests/godagtimed_old.py

@@ -3,20 +3,23 @@
 
 import os
 import timeit
+
 from goatools.test_data.godag_timed import GoDagTimed
 from goatools.test_data.godag_timed import prt_hms
 from goatools.base import download_go_basic_obo
 
 REPO = os.path.join(os.path.dirname(os.path.abspath(__file__)), "..")
 
+
 def test_deprecatedloc_godagtimed():
     """Test deprecated location of GoDagTimed"""
     tic = timeit.default_timer()
-    prt_hms(tic, 'prt_hms TESTED')
+    prt_hms(tic, "prt_hms TESTED")
 
     fin_go_obo = os.path.join(REPO, "go-basic.obo")
-    download_go_basic_obo(fin_go_obo, loading_bar=None)
+    download_go_basic_obo(fin_go_obo)
     GoDagTimed(fin_go_obo)
 
-if __name__ == '__main__':
+
+if __name__ == "__main__":
     test_deprecatedloc_godagtimed()

tests/i148_semsim_lin.py

@@ -4,57 +4,59 @@
 
 import os
 import sys
+
 from itertools import combinations_with_replacement as combo_w_rplc
-from goatools.base import get_godag
-from goatools.associations import dnld_annofile
+
 from goatools.anno.gpad_reader import GpadReader
-#### from goatools.semantic import semantic_similarity
-from goatools.semantic import TermCounts
-#### from goatools.semantic import get_info_content
-#### from goatools.semantic import deepest_common_ancestor
-from goatools.semantic import resnik_sim
+from goatools.associations import dnld_annofile
+from goatools.base import get_godag
 from goatools.semantic import lin_sim
-#### from goatools.godag.consts import NS2GO
+from goatools.semantic import TermCounts
 
 REPO = os.path.join(os.path.dirname(os.path.abspath(__file__)), "..")
 
-def test_i148_semsim_lin(prt=sys.stdout):
+
+def test_i148_semsim_lin():
     """Test for issue 148, Lin Similarity if a term has no annotations"""
-    fin_gpad = os.path.join(REPO, 'goa_human.gpad')
-    dnld_annofile(fin_gpad, 'gpad')
+    fin_gpad = os.path.join(REPO, "goa_human.gpad")
+    dnld_annofile(fin_gpad, "gpad")
 
-    godag = get_godag(os.path.join(REPO, "go-basic.obo"), loading_bar=None)
+    godag = get_godag(os.path.join(REPO, "go-basic.obo"))
     annoobj = GpadReader(fin_gpad, godag=godag)
 
     goids = [
-        'GO:0042581',
-        'GO:0101002',
-        'GO:0042582',
-        'GO:0070820',
-        'GO:0008021',
-        'GO:0005766',
-        'GO:0016591']
-
-    associations = annoobj.get_id2gos('CC')
+        "GO:0042581",
+        "GO:0101002",
+        "GO:0042582",
+        "GO:0070820",
+        "GO:0008021",
+        "GO:0005766",
+        "GO:0016591",
+    ]
+
+    associations = annoobj.get_id2gos("CC")
     termcounts = TermCounts(godag, associations)
 
     # Calculate Lin values
-    p2v = {frozenset([a, b]): lin_sim(a, b, godag, termcounts) for a, b in combo_w_rplc(goids, 2)}
+    p2v = {
+        frozenset([a, b]): lin_sim(a, b, godag, termcounts)
+        for a, b in combo_w_rplc(goids, 2)
+    }
     _prt_values(goids, p2v, prt=sys.stdout)
 
 
 def _prt_values(goids, p2v, prt=sys.stdout):
     """Print values"""
-    prt.write('           {HDR}\n'.format(HDR=' '.join(goids)))
-    none = 'None     '
+    prt.write("           {HDR}\n".format(HDR=" ".join(goids)))
+    none = "None     "
     for go_row in goids:
-        prt.write('{GO} '.format(GO=go_row))
+        prt.write("{GO} ".format(GO=go_row))
         for go_col in goids:
             val = p2v[frozenset([go_row, go_col])]
-            txt = '{L:<9.6} '.format(L=val) if val is not None else none
-            prt.write('{T:10} '.format(T=txt))
-        prt.write('\n')
+            txt = "{L:<9.6} ".format(L=val) if val is not None else none
+            prt.write("{T:10} ".format(T=txt))
+        prt.write("\n")
 
 
-if __name__ == '__main__':
+if __name__ == "__main__":
     test_i148_semsim_lin()

tests/test_altid_godag.py

@@ -2,14 +2,16 @@
 
 from goatools.base import get_godag
 
+
 def test_alt_id():
     """Ensure that alternate GO IDs."""
-    obo_dag = get_godag("go-basic.obo", loading_bar=None)
+    obo_dag = get_godag("go-basic.obo")
     alt_ids = get_altids(obo_dag)
     obo_goids = obo_dag.keys()
     obo_goids_set = set(obo_goids)
     assert len(alt_ids.intersection(obo_goids_set)) == len(alt_ids)
 
+
 def get_altids(obo_dag):
     """Get all alternate GO ids for entire go-basic.obo DAG."""
     alt_ids_all = set()
@@ -19,5 +21,6 @@ def get_altids(obo_dag):
             alt_ids_all |= set(alt_ids_cur)
     return alt_ids_all
 
-if __name__ == '__main__':
+
+if __name__ == "__main__":
     test_alt_id()

tests/test_anno_rd_gene2go.py

@@ -1,64 +1,69 @@
 #!/usr/bin/env python
 """Ensure NEW results are equal to OLD results: read_ncbi_gene2go."""
 
-from __future__ import print_function
-
 import os
 import sys
+
 from collections import defaultdict
+
 from goatools.associations import dnld_ncbi_gene_file
 from goatools.anno.genetogo_reader import Gene2GoReader
 
 
 REPO = os.path.join(os.path.dirname(os.path.abspath(__file__)), "..")
 
+
 def test_anno_read():
     """Test reading an NCBI gene2go annotation file."""
-    fin_anno = os.path.join(REPO, 'gene2go')
+    fin_anno = os.path.join(REPO, "gene2go")
     _dnld_anno(fin_anno)
-    #godag = get_godag(os.path.join(REPO, 'go-basic.obo'), loading_bar=None)
 
-    print('\nTEST STORING ONLY ONE SPECIES')
+    print("\nTEST STORING ONLY ONE SPECIES")
     obj = Gene2GoReader(fin_anno)
     assert len(obj.taxid2asscs) == 1
     obj.prt_summary_anno2ev()
 
-    print('\nTEST STORING ALL SPECIES')
+    print("\nTEST STORING ALL SPECIES")
     obj = Gene2GoReader(fin_anno, taxids=True)
-    assert len(obj.taxid2asscs) > 1, '**EXPECTED MORE: len(taxid2asscs) == {N}'.format(
-        N=len(obj.taxid2asscs))
+    assert len(obj.taxid2asscs) > 1, "**EXPECTED MORE: len(taxid2asscs) == {N}".format(
+        N=len(obj.taxid2asscs)
+    )
     obj.prt_summary_anno2ev()
 
-    print('\nTEST GETTING ASSOCIATIONS FOR ONE SPECIES')
+    print("\nTEST GETTING ASSOCIATIONS FOR ONE SPECIES")
     print("\nTEST read_ncbi_gene2go_old: [9606]")
     old_g2go_hsa = read_ncbi_gene2go_old(fin_anno, [9606])
     ## new_g2go_hsa = read_ncbi_gene2go(fin_anno, [9606])
     new_g2go_hsa = obj.get_id2gos_nss(taxids=[9606])
-    assert old_g2go_hsa == new_g2go_hsa, \
-      'OLD({O}) != NEW({N})'.format(O=len(old_g2go_hsa), N=len(new_g2go_hsa))
+    assert old_g2go_hsa == new_g2go_hsa, "OLD({O}) != NEW({N})".format(
+        O=len(old_g2go_hsa), N=len(new_g2go_hsa)
+    )
     print("\nTEST read_ncbi_gene2go_old: 9606")
     ## assert old_g2go_hsa == read_ncbi_gene2go(fin_anno, 9606)
     assert old_g2go_hsa == obj.get_id2gos_nss(taxid=9606)
 
-    print('\nTEST GETTING REVERSE ASSOCIATIONS: GO2GENES')
+    print("\nTEST GETTING REVERSE ASSOCIATIONS: GO2GENES")
     go2geneids = True
     print("\nTEST read_ncbi_gene2go_old: 9606 go2geneids=True")
     old_go2gs_hsa = read_ncbi_gene2go_old(fin_anno, [9606], go2geneids=go2geneids)
     ## new_go2gs_hsa = read_ncbi_gene2go(fin_anno, 9606, go2geneids=go2geneids)
     new_go2gs_hsa = obj.get_id2gos_nss(taxid=9606, go2geneids=go2geneids)
-    print('OLD:', next(iter(old_go2gs_hsa.items())))
-    print('NEW:', next(iter(new_go2gs_hsa.items())))
-    assert old_go2gs_hsa == new_go2gs_hsa, \
-       'OLD({O}) != NEW({N})'.format(O=len(old_go2gs_hsa), N=len(new_go2gs_hsa))
+    print("OLD:", next(iter(old_go2gs_hsa.items())))
+    print("NEW:", next(iter(new_go2gs_hsa.items())))
+    assert old_go2gs_hsa == new_go2gs_hsa, "OLD({O}) != NEW({N})".format(
+        O=len(old_go2gs_hsa), N=len(new_go2gs_hsa)
+    )
 
-    print('\nTEST RETURNING ASSOCIATIONS FOR SELECTED EVIDENCE CODES')
-    evcodes = set(['ISO', 'IKR'])
+    print("\nTEST RETURNING ASSOCIATIONS FOR SELECTED EVIDENCE CODES")
+    evcodes = set(["ISO", "IKR"])
     print("\nTEST read_ncbi_gene2go_old: 9606 evcodes=True")
-    old_gene2gos_evc = read_ncbi_gene2go_old(fin_anno, taxids=[9606], ev_include=evcodes)
+    old_gene2gos_evc = read_ncbi_gene2go_old(
+        fin_anno, taxids=[9606], ev_include=evcodes
+    )
     ## new_gene2gos_evc = read_ncbi_gene2go(fin_anno, 9606, ev_include=evcodes)
     new_gene2gos_evc = obj.get_id2gos_nss(taxid=9606, ev_include=evcodes)
-    print('OLD:', next(iter(old_gene2gos_evc.items())))
-    print('NEW:', next(iter(new_gene2gos_evc.items())))
+    print("OLD:", next(iter(old_gene2gos_evc.items())))
+    print("NEW:", next(iter(new_gene2gos_evc.items())))
     assert old_gene2gos_evc == new_gene2gos_evc
 
 
@@ -67,10 +72,11 @@ def _dnld_anno(file_anno):
     if os.path.exists(file_anno):
         assert os.path.getsize(file_anno) > 1000000, "BAD ANNO({F})".format(F=file_anno)
         return
-    dnld_ncbi_gene_file(file_anno, loading_bar=None)
+    dnld_ncbi_gene_file(file_anno)
     assert os.path.isfile(file_anno), "MISSING ANNO({F})".format(F=file_anno)
     assert os.path.getsize(file_anno) > 1000000, "BAD ANNO({F})".format(F=file_anno)
 
+
 # Fomerly in goatools/associations.py file
 def read_ncbi_gene2go_old(fin_gene2go, taxids=None, **kws):
     """Read NCBI's gene2go. Return gene2go data for user-specified taxids."""
@@ -79,26 +85,30 @@ def read_ncbi_gene2go_old(fin_gene2go, taxids=None, **kws):
     id2gos = defaultdict(set)
     # Optional detailed associations split by taxid and having both ID2GOs & GO2IDs
     # e.g., taxid2asscs = defaultdict(lambda: defaultdict(lambda: defaultdict(set))
-    taxid2asscs = kws.get('taxid2asscs', None)
-    evs = kws.get('ev_include', None)
+    taxid2asscs = kws.get("taxid2asscs", None)
+    evs = kws.get("ev_include", None)
     # By default, return id2gos. User can cause go2geneids to be returned by:
     #   >>> read_ncbi_gene2go(..., go2geneids=True
-    b_geneid2gos = not kws.get('go2geneids', False)
-    if taxids is None: # Default taxid is Human
+    b_geneid2gos = not kws.get("go2geneids", False)
+    if taxids is None:  # Default taxid is Human
         taxids = [9606]
-    with open(fin_gene2go) as ifstrm:
+    with open(fin_gene2go, encoding="utf-8") as ifstrm:
         # pylint: disable=too-many-nested-blocks
         for line in ifstrm:
-            if line[0] != '#': # Line contains data. Not a comment
-                line = line.rstrip() # chomp
-                flds = line.split('\t')
+            if line[0] != "#":  # Line contains data. Not a comment
+                line = line.rstrip()  # chomp
+                flds = line.split("\t")
                 if len(flds) >= 5:
                     taxid_curr, geneid, go_id, evidence, qualifier = flds[:5]
                     taxid_curr = int(taxid_curr)
                     # NOT: Used when gene is expected to have function F, but does NOT.
                     # ND : GO function not seen after exhaustive annotation attempts to the gene.
                     ## if taxid_curr in taxids and qualifier != 'NOT' and evidence != 'ND':
-                    if taxid_curr in taxids and 'NOT' not in qualifier and evidence != 'ND':
+                    if (
+                        taxid_curr in taxids
+                        and "NOT" not in qualifier
+                        and evidence != "ND"
+                    ):
                         # Optionally specify a subset of GOs based on their evidence.
                         if evs is None or evidence in evs:
                             geneid = int(geneid)
@@ -107,11 +117,13 @@ def read_ncbi_gene2go_old(fin_gene2go, taxids=None, **kws):
                             else:
                                 id2gos[go_id].add(geneid)
                             if taxid2asscs is not None:
-                                taxid2asscs[taxid_curr]['ID2GOs'][geneid].add(go_id)
-                                taxid2asscs[taxid_curr]['GO2IDs'][go_id].add(geneid)
-        sys.stdout.write("  {N:,} items READ: {ASSC}\n".format(N=len(id2gos), ASSC=fin_gene2go))
-    return id2gos # return simple associations
+                                taxid2asscs[taxid_curr]["ID2GOs"][geneid].add(go_id)
+                                taxid2asscs[taxid_curr]["GO2IDs"][go_id].add(geneid)
+        sys.stdout.write(
+            "  {N:,} items READ: {ASSC}\n".format(N=len(id2gos), ASSC=fin_gene2go)
+        )
+    return id2gos  # return simple associations
 
 
-if __name__ == '__main__':
+if __name__ == "__main__":
     test_anno_read()