A few changes:

- adding a RELEASING.md
- adding a logging.conf for use by scripts
- changing scripts to use logger instead of printing
- upping dependent package versions, upping isovar version

RELEASING.md

@@ -0,0 +1,8 @@
+# Releasing Isovar
+
+This document explains what do once your [Pull Request](https://www.atlassian.com/git/tutorials/making-a-pull-request/) has been reviewed and all final changes applied. Now you're ready merge your branch into master and release it to the world:
+
+0. Make sure that you have `pandoc` and `pypandoc` installed: this is needed for readme markdown on PyPI. (See [here](http://pandoc.org/installing.html) and [here](https://pypi.python.org/pypi/pypandoc), respectively, for instructions.)
+1. Bump the [version](http://semver.org/) in `__init__.py`, as part of the PR you want to release.
+2. Merge your branch into master.
+3. Run `python setup.py sdist upload`, which pushes the newest release to PyPI.

isovar/__init__.py

@@ -14,4 +14,4 @@
 
 from __future__ import print_function, division, absolute_import
 
-__version__ = "0.2.2"
+__version__ = "0.2.3"

isovar/cli/logging.conf

@@ -0,0 +1,56 @@
+[loggers]
+keys=root,isovar,varcode,pyensembl,datacache
+
+[formatters]
+keys=simpleFormatter
+
+[handlers]
+keys=consoleHandler,consoleHandlerCritical
+
+[logger_root]
+level=INFO
+handlers=consoleHandlerCritical
+
+[handler_consoleHandler]
+class=StreamHandler
+level=INFO
+formatter=simpleFormatter
+args=(sys.stdout,)
+
+[handler_consoleHandlerCritical]  # only for root logger: essentially silent
+class=StreamHandler
+level=CRITICAL
+formatter=simpleFormatter
+args=(sys.stdout,)
+
+[formatter_simpleFormatter]
+format=%(asctime)s - %(name)s - %(levelname)s - %(message)s
+datefmt=
+
+# isovar
+
+[logger_isovar]
+level=DEBUG
+qualname=isovar
+handlers=consoleHandler
+
+# varcode
+
+[logger_varcode]
+level=DEBUG
+qualname=varcode
+handlers=consoleHandler
+
+# pyensembl
+
+[logger_pyensembl]
+level=DEBUG
+qualname=pyensembl
+handlers=consoleHandler
+
+# datacache
+
+[logger_datacache]
+level=DEBUG
+qualname=datacache
+handlers=consoleHandler

requirements.txt

@@ -1,7 +1,7 @@
 numpy>=1.7
 pandas>=0.13.1
-pyensembl>=1.0.0
-varcode>=0.5.0
+pyensembl>=1.0.3
+varcode>=0.5.9
 pysam>=0.9.0
 scikit-bio==0.4.2
 nose>=1.3.3

script/isovar-allele-counts.py

@@ -18,25 +18,31 @@
 Prints number of reads supporting ref, alt, and other alleles at variant loci.
 """
 
-from __future__ import print_function, division, absolute_import
+from __future__ import division, absolute_import
+import logging
+import logging.config
+import pkg_resources
 
 from isovar.cli.rna_reads import (
     make_rna_reads_arg_parser,
     allele_reads_generator_from_args
 )
 from isovar.allele_counts import allele_counts_dataframe
 
-parser = make_rna_reads_arg_parser()
 
+logging.config.fileConfig(pkg_resources.resource_filename('isovar.cli', 'logging.conf'))
+logger = logging.getLogger(__name__)
+
+parser = make_rna_reads_arg_parser()
 parser.add_argument(
     "--output",
     default="isovar-allele-counts-result.csv",
     help="Name of CSV file which contains read sequences")
 
 if __name__ == "__main__":
     args = parser.parse_args()
-    print(args)
+    logger.info(args)
     variants_and_allele_reads_generator = allele_reads_generator_from_args(args)
     allele_counts_df = allele_counts_dataframe(variants_and_allele_reads_generator)
-    print(allele_counts_df)
+    logger.info(allele_counts_df)
     allele_counts_df.to_csv(args.output)

script/isovar-allele-reads.py

@@ -18,13 +18,19 @@
 Prints names and sequences of reads overlapping a given set of variants.
 """
 
-from __future__ import print_function, division, absolute_import
+from __future__ import division, absolute_import
+import logging
+import logging.config
+import pkg_resources
 
 from isovar.cli.rna_reads import (
     make_rna_reads_arg_parser,
     allele_reads_dataframe_from_args
 )
 
+logging.config.fileConfig(pkg_resources.resource_filename('isovar.cli', 'logging.conf'))
+logger = logging.getLogger(__name__)
+
 parser = make_rna_reads_arg_parser()
 parser.add_argument(
     "--output",
@@ -33,7 +39,7 @@
 
 if __name__ == "__main__":
     args = parser.parse_args()
-    print(args)
+    logger.info(args)
     df = allele_reads_dataframe_from_args(args)
-    print(df)
+    logger.info(df)
     df.to_csv(args.output)

script/isovar-protein-sequences.py

@@ -22,18 +22,19 @@
 
 from __future__ import print_function, division, absolute_import
 import logging
+import logging.config
+import pkg_resources
 
 from isovar.cli.protein_sequences import (
     make_protein_sequences_arg_parser,
     protein_sequences_dataframe_from_args
 )
 
 
+logging.config.fileConfig(pkg_resources.resource_filename('isovar.cli', 'logging.conf'))
 logger = logging.getLogger(__name__)
 
-
 parser = make_protein_sequences_arg_parser()
-
 parser.add_argument(
     "--output",
     default="isovar-translate-variants-results.csv",

script/isovar-reference-contexts.py

@@ -15,14 +15,19 @@
 # limitations under the License.
 
 from __future__ import print_function, division, absolute_import
+import logging
+import logging.config
+import pkg_resources
 
 from isovar.cli.reference_context import (
     make_reference_context_arg_parser,
     reference_contexts_dataframe_from_args
 )
 
-parser = make_reference_context_arg_parser()
+logging.config.fileConfig(pkg_resources.resource_filename('isovar.cli', 'logging.conf'))
+logger = logging.getLogger(__name__)
 
+parser = make_reference_context_arg_parser()
 parser.add_argument(
     "--output",
     default="isovar-reference-contexts-result.csv",
@@ -31,5 +36,5 @@
 if __name__ == "__main__":
     args = parser.parse_args()
     reference_contexts_df = reference_contexts_dataframe_from_args(args)
-    print(reference_contexts_df)
+    logger.info(reference_contexts_df)
     reference_contexts_df.to_csv(args.output)

script/isovar-translations.py

@@ -20,12 +20,18 @@
 """
 
 from __future__ import print_function, division, absolute_import
+import logging
+import logging.config
+import pkg_resources
 
 from isovar.cli.translation import (
     make_translation_arg_parser,
     translations_dataframe_from_args,
 )
 
+logging.config.fileConfig(pkg_resources.resource_filename('isovar.cli', 'logging.conf'))
+logger = logging.getLogger(__name__)
+
 parser = make_translation_arg_parser()
 parser.add_argument(
     "--output",
@@ -34,7 +40,7 @@
 
 if __name__ == "__main__":
     args = parser.parse_args()
-    print(args)
+    logger.info(args)
     df = translations_dataframe_from_args(args)
-    print(df)
+    logger.info(df)
     df.to_csv(args.output)

script/isovar-variant-reads.py

@@ -19,22 +19,27 @@
 """
 
 from __future__ import print_function, division, absolute_import
+import logging
+import logging.config
+import pkg_resources
 
 from isovar.cli.rna_reads import (
     variant_reads_dataframe_from_args,
     make_rna_reads_arg_parser,
 )
 
-parser = make_rna_reads_arg_parser()
+logging.config.fileConfig(pkg_resources.resource_filename('isovar.cli', 'logging.conf'))
+logger = logging.getLogger(__name__)
 
+parser = make_rna_reads_arg_parser()
 parser.add_argument(
     "--output",
     default="isovar-variant-reads-result.csv",
     help="Name of CSV file which contains variant read sequences")
 
 if __name__ == "__main__":
     args = parser.parse_args()
-    print(args)
+    logger.info(args)
     df = variant_reads_dataframe_from_args(args)
-    print(df)
+    logger.info(df)
     df.to_csv(args.output)

script/isovar-variant-sequences.py

@@ -15,22 +15,28 @@
 # limitations under the License.
 
 from __future__ import print_function, division, absolute_import
+import logging
+import logging.config
+import pkg_resources
 
 from isovar.cli.variant_sequences import (
     make_variant_sequences_arg_parser,
     variant_sequences_dataframe_from_args
 )
 
-parser = make_variant_sequences_arg_parser(add_sequence_length_arg=True)
 
+logging.config.fileConfig(pkg_resources.resource_filename(__name__, 'logging.conf'))
+logger = logging.getLogger(__name__)
+
+parser = make_variant_sequences_arg_parser(add_sequence_length_arg=True)
 parser.add_argument(
     "--output",
     default="isovar-variant-sequences-results.csv",
     help="Name of CSV file which contains predicted sequences")
 
 if __name__ == "__main__":
     args = parser.parse_args()
-    print(args)
+    logger.info(args)
     df = variant_sequences_dataframe_from_args(args)
-    print(df)
+    logger.info(df)
     df.to_csv(args.output)

setup.py

@@ -68,11 +68,12 @@
             'pysam >= 0.9.0',
             'pandas',
             'scikit-bio==0.4.2',
-            'varcode>=0.5.0',
-            'pyensembl>=1.0.0'
+            'varcode>=0.5.9',
+            'pyensembl>=1.0.3'
         ],
         long_description=readme,
         packages=find_packages(),
+        package_data={'isovar.cli': ['logging.conf']},
         scripts=[
             "script/isovar-protein-sequences.py",
             "script/isovar-translations.py",