Resolve "Formatting and logging"

README.md

@@ -32,10 +32,10 @@ To generate the sampled transcripts, open a new shell, activate your environment
 ```
 conda activate transcript-structure-generator
 
-transcript-generator --transcripts <transcripts_file> --annotation <annotations_file> --prob_inclusion=<probability_inclusion>
+transcript-generator --transcripts <transcripts_file> --annotation <annotations_file> --prob_inclusion=<probability_inclusion> [--log "INFO"]
 ```
 
-where the transcripts file should be csv-formatted, the annotation file gtf-formatted and the inclusion probability for introns a float in the range [0,1].
+where the transcripts file should be csv-formatted, the annotation file gtf-formatted and the inclusion probability for introns a float in the range [0,1]. The log parameter is optional and can be one of `["CRITICAL", "ERROR", "WARNING", "INFO", "DEBUG"]`. The default is `INFO`.
 
 
 # Development

pyproject.toml

@@ -15,6 +15,9 @@ dependencies = [
     "tqdm",
 ]
 
+[tool.setuptools]
+packages = ["tsg"]
+
 [project.urls]
 "Homepage" = "https://git.scicore.unibas.ch/zavolan_group/tools/transcript-structure-generator"
 

tsg/cli.py

@@ -5,13 +5,19 @@ from pathlib import Path
 from tsg.main import sample_transcripts
 
 
-def setup_logging(loglevel: str=None) -> None:
+def setup_logging(loglevel: str = None) -> None:
     # Set up logging
     if loglevel:
         numeric_level = getattr(logging, loglevel.upper())
         if not isinstance(numeric_level, int):
             raise ValueError("Invalid log level: %s" % loglevel)
-        logging.basicConfig(level=numeric_level)
+    else:
+        numeric_level = getattr(logging, "INFO")
+
+    logging.basicConfig(
+        format='[%(asctime)s: %(levelname)s] %(message)s (module "%(module)s")',
+        level=numeric_level,
+    )
 
 
 def build_arg_parser():
@@ -42,6 +48,7 @@ def output_filename(filename: str) -> str:
         raise NotImplementedError()
     return outfile
 
+
 def app():
     args = get_args()
 

tsg/main.py

@@ -229,12 +229,16 @@ class TranscriptGenerator:
         if self.strand == "+":
             origninal_end = df_generated["end"]
             df_generated["end"] = np.where(
-                inclusions, df_generated["start"].shift(periods=-1, fill_value=-1) - 1, origninal_end
+                inclusions,
+                df_generated["start"].shift(periods=-1, fill_value=-1) - 1,
+                origninal_end,
             )
         if self.strand == "-":
             origninal_start = df_generated["start"]
             df_generated["start"] = np.where(
-                inclusions, df_generated["end"].shift(periods=-1, fill_value=-1) + 1, origninal_start
+                inclusions,
+                df_generated["end"].shift(periods=-1, fill_value=-1) + 1,
+                origninal_start,
             )
 
         original_id = df_generated["exon_id"]
@@ -269,7 +273,7 @@ class TranscriptGenerator:
             df = reverse_parse_free_text(df)
 
             write_gtf(df, filename)
-            LOG.info(f"Transcript {self.id} sampled")
+            LOG.debug(f"Transcript {self.id} sampled")
         except ValueError:
             LOG.error(f"Transcript {self.id} could not be sampled.")
 
@@ -283,10 +287,13 @@ def sample_transcripts(
 ):
     transcripts = read_abundances(input_transcripts_file)
 
+    LOG.info("Parsing annotations...")
     annotations = Gtf()
     annotations.read_file(input_annotations_file)
     annotations.parse_free_text()
+    LOG.info("Done parsing...")
 
+    LOG.info("Start sampling transcripts...")
     # Set up output file, write header once and append data in loop
     write_header(output_annotations_file)
 
@@ -303,3 +310,4 @@ def sample_transcripts(
         )
         transcripts.generate_annotations(output_annotations_file)
         transcripts.generate_transcripts(output_transcripts_file)
+    LOG.info("Done.")