add YAPF to GH Actions -- fix remaining lint errors in tdc/

.github/workflows/conda-tests.yml

@@ -36,10 +36,11 @@ jobs:
           auto-update-conda: true
           auto-activate-base: true
 
-      - name: Create and start Conda environment. Run tests.
+      - name: Create and start Conda environment. Run tests. Run YAPF
         run: |
           echo "Creating Conda Environment from environment.yml"
           conda env create -f environment.yml
           conda activate tdc-conda-env
           python run_tests.py
+          yapf --style=google -r -d tdc
           conda deactivate

tdc/multi_pred/__init__.py

@@ -10,4 +10,4 @@
 from .ppi import PPI
 from .test_multi_pred import TestMultiPred
 from .tcr_epi import TCREpitopeBinding
-from .trialoutcome import TrialOutcome 
+from .trialoutcome import TrialOutcome

tdc/test/dev_tests/chem_utils_test/test_molconverter.py

@@ -21,7 +21,6 @@ def setUp(self):
         print(os.getcwd())
         pass
 
-
     def test_MolConvert(self):
         from tdc.chem_utils import MolConvert
 
@@ -35,7 +34,7 @@ def test_MolConvert(self):
 
         MolConvert.eligible_format()
 
-    # 
+    #
     def tearDown(self):
         print(os.getcwd())
 

tdc/test/dev_tests/chem_utils_test/test_molfilter.py

@@ -21,14 +21,13 @@ def setUp(self):
         print(os.getcwd())
         pass
 
-
     def test_MolConvert(self):
         from tdc.chem_utils import MolFilter
 
         filters = MolFilter(filters=["PAINS"], HBD=[0, 6])
         filters(["CCSc1ccccc1C(=O)Nc1onc2c1CCC2"])
 
-    # 
+    #
     def tearDown(self):
         print(os.getcwd())
 

tdc/test/dev_tests/chem_utils_test/test_oracles.py

@@ -21,7 +21,6 @@ def setUp(self):
         print(os.getcwd())
         pass
 
-
     def test_Oracle(self):
         from tdc import Oracle
 
@@ -35,7 +34,6 @@ def test_Oracle(self):
         oracle = Oracle(name="Hop")
         x = oracle(["CC(=O)OC1=CC=CC=C1C(=O)O", "C1=CC=C(C=C1)C=O"])
 
-
     def test_distribution(self):
         from tdc import Evaluator
 

tdc/test/dev_tests/utils_tests/test_misc_utils.py

@@ -33,7 +33,6 @@ def test_neg_sample(self):
     #    data = ADME(name='Caco2_Wang')
     #    x = data.label_distribution()
 
-
     def test_get_label_map(self):
         from tdc.multi_pred import DDI
         from tdc.utils import get_label_map
@@ -42,26 +41,22 @@ def test_get_label_map(self):
         split = data.get_split()
         get_label_map(name="DrugBank", task="DDI")
 
-
     def test_balanced(self):
         from tdc.single_pred import HTS
 
         data = HTS(name="SARSCoV2_3CLPro_Diamond")
         data.balanced(oversample=True, seed=42)
 
-
     def test_cid2smiles(self):
         from tdc.utils import cid2smiles
 
         smiles = cid2smiles(2248631)
 
-
     def test_uniprot2seq(self):
         from tdc.utils import uniprot2seq
 
         seq = uniprot2seq("P49122")
 
-
     def test_to_graph(self):
         from tdc.multi_pred import DTI
 
@@ -95,7 +90,7 @@ def test_to_graph(self):
         )
         # output: {'pyg_graph': the PyG graph object, 'index_to_entities': a dict map from ID in the data to node ID in the PyG object, 'split': {'train': df, 'valid': df, 'test': df}}
 
-    # 
+    #
     def tearDown(self):
         print(os.getcwd())
 

tdc/test/dev_tests/utils_tests/test_splits.py

@@ -21,22 +21,19 @@ def setUp(self):
         print(os.getcwd())
         pass
 
-
     def test_random_split(self):
         from tdc.single_pred import ADME
 
         data = ADME(name="Caco2_Wang")
         split = data.get_split(method="random")
 
-
     def test_scaffold_split(self):
         ## requires RDKit
         from tdc.single_pred import ADME
 
         data = ADME(name="Caco2_Wang")
         split = data.get_split(method="scaffold")
 
-
     def test_cold_start_split(self):
         from tdc.multi_pred import DTI
 
@@ -70,21 +67,18 @@ def test_cold_start_split(self):
             self.assertEqual(0, len(train_entity.intersection(test_entity)))
             self.assertEqual(0, len(valid_entity.intersection(test_entity)))
 
-
     def test_combination_split(self):
         from tdc.multi_pred import DrugSyn
 
         data = DrugSyn(name="DrugComb")
         split = data.get_split(method="combination")
 
-
     def test_time_split(self):
         from tdc.multi_pred import DTI
 
         data = DTI(name="BindingDB_Patent")
         split = data.get_split(method="time", time_column="Year")
 
-
     def test_tearDown(self):
         print(os.getcwd())
 

tdc/utils/label.py

@@ -222,7 +222,8 @@ def NegSample(df, column_names, frac, two_types):
                     4: "Y"
                 })
             ],
-                           ignore_index=True, sort=False)
+                           ignore_index=True,
+                           sort=False)
         return df
     else:
         df_unique_id1 = np.unique(df[id1].values.reshape(-1))
@@ -267,5 +268,6 @@ def NegSample(df, column_names, frac, two_types):
                 4: "Y"
             })
         ],
-                       ignore_index=True, sort=False)
+                       ignore_index=True,
+                       sort=False)
         return df