Merge pull request #98 from monarch-initiative/develop

Further minor QoL updates

.github/workflows/build.yml

@@ -24,10 +24,10 @@ jobs:
       OS: ubuntu
 
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
 
       - name: set up python
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v3
         with:
           python-version: ${{ matrix.python-version }}
 

examples/data/string.tsv

@@ -2,9 +2,4 @@ protein1 protein2 neighborhood fusion cooccurence coexpression experimental data
 10090.ENSMUSP00000000001 10090.ENSMUSP00000020316 0 0 0 116 90 0 67 183
 10090.ENSMUSP00000000001 10090.ENSMUSP00000022816 0 0 0 62 0 0 137 155
 10090.ENSMUSP00000000001 10090.ENSMUSP00000048234 0 0 0 0 147 0 166 258
-10090.ENSMUSP00000000001 10090.ENSMUSP00000017365 0 0 0 0 165 0 0 165
-10090.ENSMUSP00000000001 10090.ENSMUSP00000033545 0 0 0 0 179 0 57 192
-10090.ENSMUSP00000000001 10090.ENSMUSP00000113105 0 0 0 0 179 0 417 500
-10090.ENSMUSP00000000001 10090.ENSMUSP00000036031 0 0 0 58 181 0 85 232
-10090.ENSMUSP00000000001 10090.ENSMUSP00000039580 0 0 0 60 158 0 81 209
-10090.ENSMUSP00000000001 10090.ENSMUSP00000040516 0 0 0 0 196 0 0 196
+10090.ENSMUSP00000000001 10090.ENSMUSP00000012345 0 0 0 0 117 0 0 765

examples/data/string2.tsv

@@ -4,7 +4,12 @@ protein1 protein2 neighborhood fusion cooccurence coexpression experimental data
 10090.ENSMUSP00000000001 10090.ENSMUSP00000061493 0 0 0 156 45 0 0 159
 10090.ENSMUSP00000000001 10090.ENSMUSP00000090329 0 0 0 0 196 0 0 196
 10090.ENSMUSP00000000001 10090.ENSMUSP00000026270 0 0 0 187 0 0 49 193
-10090.ENSMUSP00000000001 10090.ENSMUSP00000001115 0 0 0 0 119 0 148 218
+10090.ENSMUSP00000000001 10090.ENSMUSP00000001115 0 0 0 0 119 0 148 918
 10090.ENSMUSP00000000001 10090.ENSMUSP00000020101 0 0 0 0 181 0 85 218
 10090.ENSMUSP00000000001 10090.ENSMUSP00000063804 0 0 0 0 179 0 57 192
 10090.ENSMUSP00000000001 10090.ENSMUSP00000018012 0 0 0 65 220 0 100 286
+10090.ENSMUSP00000000001 10090.ENSMUSP00000033545 0 0 0 0 179 0 57 192
+10090.ENSMUSP00000000001 10090.ENSMUSP00000113105 0 0 0 0 179 0 417 500
+10090.ENSMUSP00000000001 10090.ENSMUSP00000036031 0 0 0 58 181 0 85 232
+10090.ENSMUSP00000000001 10090.ENSMUSP00000039580 0 0 0 60 158 0 81 209
+10090.ENSMUSP00000000001 10090.ENSMUSP00000040516 0 0 0 0 196 0 0 196

koza/cli_runner.py

@@ -64,23 +64,24 @@ def transform_source(
 
     with open(source, 'r') as source_fh:
         source_config = PrimaryFileConfig(**yaml.load(source_fh, Loader=UniqueIncludeLoader))
-        if not source_config.name:
-            source_config.name = Path(source).stem
+
+    if not source_config.name:
+        source_config.name = Path(source).stem
 
-        if not source_config.transform_code:
-            # look for it alongside the source conf as a .py file
-            source_config.transform_code = str(Path(source).parent / Path(source).stem) + '.py'
+    if not source_config.transform_code:
+        # look for it alongside the source conf as a .py file
+        source_config.transform_code = str(Path(source).parent / Path(source).stem) + '.py'
 
-        koza_source = Source(source_config, row_limit)
+    koza_source = Source(source_config, row_limit)
 
-        translation_table = get_translation_table(
-            global_table if global_table else source_config.global_table,
-            local_table if local_table else source_config.local_table,
-        )
+    translation_table = get_translation_table(
+        global_table if global_table else source_config.global_table,
+        local_table if local_table else source_config.local_table,
+    )
 
-        source_koza = set_koza_app(koza_source, translation_table, output_dir, output_format, schema)
-        source_koza.process_maps()
-        source_koza.process_sources()
+    source_koza = set_koza_app(koza_source, translation_table, output_dir, output_format, schema)
+    source_koza.process_maps()
+    source_koza.process_sources()
 
 
 def validate_file(

koza/io/reader/csv_reader.py

@@ -4,9 +4,9 @@
 from koza.model.config.source_config import FieldType, HeaderMode
 from koza.utils.log_utils import get_logger
 
-LOG = get_logger(__name__)
-# import logging
-# LOG = logging.getLogger(__name__)
+# LOG = get_logger(__name__)
+import logging
+LOG = logging.getLogger(__name__)
 
 
 FIELDTYPE_CLASS = {
@@ -112,6 +112,7 @@ def __next__(self) -> Dict[str, Any]:
 
         try:
             if self.line_count == self.row_limit:
+                LOG.debug("Row limit reached")
                 raise StopIteration
             else:
                 row = next(self.reader)

koza/main.py

@@ -37,9 +37,8 @@ def transform(
     # os.path.splitext(os.path.basename(source))[0] # name of the yaml file without the yaml
 
     set_log_config(logging.INFO if (verbose is None) else logging.DEBUG if (verbose == True) else logging.WARNING)
-    logfile = Path(f"logs/{source.split('/')[1]}_{source.split('/')[2][:-5]}.log")
     logger = get_logger(__name__, verbose) if not logging.getLogger().hasHandlers() else logging.getLogger()
-    if log: fh = add_log_fh(logger, logfile)
+    if log: fh = add_log_fh(logger, f"logs/{Path(source).name}.log")
 
     output_path = Path(output_dir)
 

koza/utils/log_utils.py

@@ -36,7 +36,7 @@ def get_logger(name: str, verbose: bool = None) -> logging.Logger:
 
     logger = logging.getLogger(name)
     logger.setLevel(log_level)
-    # logger.propagate = False
+    logger.propagate = False
 
     if not logger.hasHandlers():
         stream_handler = logging.StreamHandler(sys.stdout)