eliminate subparser in dropseq_aggregation clp (#474)

* rename package stuff I missed

* Eliminate subparser stuff

src/python/dropseq_aggregation/README.md

@@ -1,13 +1,13 @@
-# Simple python tools for managing tabular cell metadata text files..
+# Simple python tools for managing tabular cell metadata text files.
 
 ## Installation
 
 Requires python >= 3.8
 ```
-pip install 'git+https://github.com/broadinstitute/Drop-seq.git#egg=dropseq_metadata&subdirectory=src/python/dropseq_metadata'
+pip install 'git+https://github.com/broadinstitute/Drop-seq.git#egg=dropseq_aggregation&subdirectory=src/python/dropseq_aggregation'
 ```
 
 ## Usage
 
-Run `dropseq_metadata -h` for usage information.
+Run `join_and_filter_tsv -h` for usage information.
 

src/python/dropseq_aggregation/pyproject.toml

@@ -2,7 +2,7 @@
 requires = ["hatchling"]
 build-backend = "hatchling.build"
 [project]
-name = "dropseq_metadata"
+name = "dropseq_aggregation"
 version = "3.0.2"
 dependencies = [
     "pandas==2.2.3"
@@ -24,4 +24,5 @@ Homepage = "https://github.com/broadinstitute/Drop-seq/"
 Issues = "https://github.com/broadinstitute/Drop-seq/issues"
 
 [project.scripts]
-dropseq_metadata = "dropseq_metadata.cli:main"
+join_and_filter_tsv = "dropseq_aggregation.join_and_filter_tsv:main"
+

src/python/dropseq_aggregation/src/dropseq_aggregation/__init__.py

@@ -20,3 +20,25 @@
 # LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 # SOFTWARE.
+
+import logging
+
+# I cannot believe I need to do this to cause logger to write to stderr.
+logging.basicConfig(
+    level=logging.INFO,               # Set the logging level (DEBUG, INFO, WARNING, ERROR, CRITICAL)
+    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
+    handlers=[logging.StreamHandler()] # StreamHandler writes to sys.stderr by default
+)
+logger = logging.getLogger(__name__)
+
+dctLogLevel = {
+    "DEBUG": logging.DEBUG,
+    "INFO": logging.INFO,
+    "WARNING": logging.WARNING,
+    "ERROR": logging.ERROR,
+    "CRITICAL": logging.CRITICAL
+}
+
+def add_log_argument(parser):
+    parser.add_argument("--log-level", "-l", default="INFO", choices=dctLogLevel.keys(),
+                        help="Set the logging level.  (default: %(default)s)")

src/python/dropseq_aggregation/src/dropseq_aggregation/join_and_filter_tsv.py

@@ -39,12 +39,10 @@
 
 import argparse
 import sys
+
 import pandas as pd
 from pandas.errors import MergeError
-try:
-    from . import cli
-except ImportError:
-    import cli
+from . import logger, add_log_argument
 
 DELETEME_COLUMN_SUFFIX = '_deleteme'
 
@@ -77,8 +75,9 @@ def try_convert_string(s):
 def load_values_file(file):
     return pd.read_csv(file, sep='\t', header=None).iloc[0]
 
-def add_subparser(subparsers):
-    parser = subparsers.add_parser("join_and_filter_tsv", description=__doc__)
+def parse_args(args):
+    parser = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
+    add_log_argument(parser)
     parser.add_argument("--input", "-i", type=argparse.FileType('r'),
                         help="Primary tab-separated file to join.  Default: %(default)s", default=sys.stdin)
     parser.add_argument("--output", "-o", type=argparse.FileType('w'),
@@ -101,8 +100,12 @@ def add_subparser(subparsers):
                         help="Filter out rows where COLUMN is not one of the given VALUEs.  May be specified multiple times.")
     parser.add_argument("--exclude", nargs='+', action='append', default=[], metavar=('COLUMN', 'VALUE'),
                         help="Filter out rows where COLUMN is one of the given VALUEs.  May be specified multiple times.")
+    return parser.parse_args(args)
+
+def main(args=None):
+    run(parse_args(args))
 
-def main(options):
+def run(options):
     # load the primary file
     primary = pd.read_csv(options.input, sep='\t')
     options.input.close()
@@ -115,7 +118,7 @@ def main(options):
             primary = primary.merge(secondary, how='left', left_on=input_col, right_on=join_col, validate="many_to_one",
                                     suffixes=(None, DELETEME_COLUMN_SUFFIX))
         except MergeError    as e:
-            cli.logger.error(f"Error joining {join_file} on {input_col} and {join_col}: {e}")
+            logger.error(f"Error joining {join_file} on {input_col} and {join_col}: {e}")
             return 1
         if not join_col_in_left:
             # drop the join column from the merged data frame
@@ -153,4 +156,5 @@ def main(options):
     options.output.close()
     return 0
 
-
+if __name__ == "__main__":
+    sys.exit(main())

src/python/dropseq_aggregation/tests/test_join_and_filter_tsv.py

@@ -53,7 +53,7 @@ def test_basic(self):
         secondary = os.path.join(self.testDataDir, "sample1.100.scPred.txt")
         options = self.options._replace(input=open(primary),
                                         join=[(secondary, "CELL_BARCODE", "CELL_BARCODE")])
-        self.assertEqual(dropseq_aggregation.join_and_filter_tsv.main(options), 0)
+        self.assertEqual(dropseq_aggregation.join_and_filter_tsv.run(options), 0)
         self.assertSharedColumnsEqual(self.outputFile, primary)
         self.assertSharedColumnsEqual(self.outputFile, secondary)
 
@@ -62,7 +62,7 @@ def test_fewer_secondary(self):
         secondary = os.path.join(self.testDataDir, "sample1.50.scPred.txt")
         options = self.options._replace(input=open(primary),
                                         join=[(secondary, "CELL_BARCODE", "CELL_BARCODE")])
-        self.assertEqual(dropseq_aggregation.join_and_filter_tsv.main(options), 0)
+        self.assertEqual(dropseq_aggregation.join_and_filter_tsv.run(options), 0)
         self.assertSharedColumnsEqual(self.outputFile, primary)
         self.assertSharedColumnsEqual(self.outputFile, secondary, wideRows=49)
 
@@ -71,7 +71,7 @@ def test_fewer_primary(self):
         secondary = os.path.join(self.testDataDir, "sample1.100.scPred.txt")
         options = self.options._replace(input=open(primary),
                                         join=[(secondary, "CELL_BARCODE", "CELL_BARCODE")])
-        self.assertEqual(dropseq_aggregation.join_and_filter_tsv.main(options), 0)
+        self.assertEqual(dropseq_aggregation.join_and_filter_tsv.run(options), 0)
         self.assertSharedColumnsEqual(self.outputFile, primary)
         self.assertSharedColumnsEqual(self.outputFile, secondary, narrowRows=49)
 
@@ -82,7 +82,7 @@ def test_additional_join(self):
         options = self.options._replace(input=open(primary),
                                         join=[(secondary1, "CELL_BARCODE", "CELL_BARCODE"),
                                               (secondary2, "DONOR", "DONOR")])
-        self.assertEqual(dropseq_aggregation.join_and_filter_tsv.main(options), 0)
+        self.assertEqual(dropseq_aggregation.join_and_filter_tsv.run(options), 0)
         self.assertSharedColumnsEqual(self.outputFile, primary)
         self.assertSharedColumnsEqual(self.outputFile, secondary1)
         self.assertMultiJoin(self.outputFile, secondary2, "DONOR", "DONOR")
@@ -94,7 +94,7 @@ def test_set(self):
         options = self.options._replace(input=open(primary),
                                         join=[(secondary, "CELL_BARCODE", "CELL_BARCODE")],
                                         set=setTuples)
-        self.assertEqual(dropseq_aggregation.join_and_filter_tsv.main(options), 0)
+        self.assertEqual(dropseq_aggregation.join_and_filter_tsv.run(options), 0)
         outputDf = pd.read_csv(self.outputFile, sep='\t')
         for column, value in setTuples:
             self.assertTrue((outputDf[column] == value).all())
@@ -107,7 +107,7 @@ def test_min(self):
         options = self.options._replace(input=open(primary),
                                         join=[(secondary, "CELL_BARCODE", "CELL_BARCODE")],
                                         min=[("max.prob", "0.8")])
-        self.assertEqual(dropseq_aggregation.join_and_filter_tsv.main(options), 0)
+        self.assertEqual(dropseq_aggregation.join_and_filter_tsv.run(options), 0)
         outputDf = pd.read_csv(self.outputFile, sep='\t')
         self.assertTrue((outputDf["max.prob"] >= 0.8).all())
         primaryDf = pd.read_csv(primary, sep='\t')
@@ -119,7 +119,7 @@ def test_max(self):
         options = self.options._replace(input=open(primary),
                                         join=[(secondary, "CELL_BARCODE", "CELL_BARCODE")],
                                         max=[("max.prob", "0.8")])
-        self.assertEqual(dropseq_aggregation.join_and_filter_tsv.main(options), 0)
+        self.assertEqual(dropseq_aggregation.join_and_filter_tsv.run(options), 0)
         outputDf = pd.read_csv(self.outputFile, sep='\t')
         self.assertTrue((outputDf["max.prob"] <= 0.8).all())
         primaryDf = pd.read_csv(primary, sep='\t')
@@ -130,7 +130,7 @@ def test_include_file(self):
         includeFile = os.path.join(self.testDataDir, "donor_subset.txt")
         options = self.options._replace(input=open(primary),
                                         include_file=[("DONOR", includeFile)])
-        self.assertEqual(dropseq_aggregation.join_and_filter_tsv.main(options), 0)
+        self.assertEqual(dropseq_aggregation.join_and_filter_tsv.run(options), 0)
         outputDf = pd.read_csv(self.outputFile, sep='\t')
         includeValues = pd.read_csv(includeFile, sep='\t', header=None).iloc[0]
         self.assertTrue((outputDf["DONOR"].isin(includeValues)).all())
@@ -140,7 +140,7 @@ def test_exclude_file(self):
         excludeFile = os.path.join(self.testDataDir, "donor_subset.txt")
         options = self.options._replace(input=open(primary),
                                         exclude_file=[("DONOR", excludeFile)])
-        self.assertEqual(dropseq_aggregation.join_and_filter_tsv.main(options), 0)
+        self.assertEqual(dropseq_aggregation.join_and_filter_tsv.run(options), 0)
         outputDf = pd.read_csv(self.outputFile, sep='\t')
         excludeValues = pd.read_csv(excludeFile, sep='\t', header=None).iloc[0]
         self.assertFalse((outputDf["DONOR"].isin(excludeValues)).any())
@@ -152,7 +152,7 @@ def test_include_exclude(self):
         options = self.options._replace(input=open(primary),
                                         include=[["DONOR"] + donorsToInclude],
                                         exclude=[["predClass"] + predClassesToExclude])
-        self.assertEqual(dropseq_aggregation.join_and_filter_tsv.main(options), 0)
+        self.assertEqual(dropseq_aggregation.join_and_filter_tsv.run(options), 0)
         outputDf = pd.read_csv(self.outputFile, sep='\t')
         self.assertTrue((outputDf["DONOR"].isin(donorsToInclude)).all())
         self.assertFalse((outputDf["predClass"].isin(predClassesToExclude)).any())
@@ -162,13 +162,13 @@ def test_negative_non_unique_join(self):
         secondary = os.path.join(self.testDataDir, "sample1.nonunique.scPred.txt")
         options = self.options._replace(input=open(primary),
                                         join=[(secondary, "CELL_BARCODE", "CELL_BARCODE")])
-        self.assertEqual(dropseq_aggregation.join_and_filter_tsv.main(options), 1)
+        self.assertEqual(dropseq_aggregation.join_and_filter_tsv.run(options), 1)
 
     def test_boolean(self):
         primary = os.path.join(self.testDataDir, "sample1.100.cell_metadata.txt")
         options = self.options._replace(input=open(primary),
                                         exclude=[["doublet", "true"]])
-        self.assertEqual(dropseq_aggregation.join_and_filter_tsv.main(options), 0)
+        self.assertEqual(dropseq_aggregation.join_and_filter_tsv.run(options), 0)
         outputDf = pd.read_csv(self.outputFile, sep='\t')
         self.assertFalse(outputDf["doublet"].any())