feat: add stats to CLI

hicstuff/commands.py

@@ -14,9 +14,10 @@
     -view (map visualization)
     -pipeline (whole contact map generation)
     -distancelaw (Analysis tool and plot for the distance law)
+    -stats (Extract stats from log)
 
 Running 'pipeline' implies running 'digest', but not
-iteralign or filter unless specified, because they can
+'iteralign' or 'filter' unless specified, because they can
 take up a lot of time for dimnishing returns.
 
 Note
@@ -38,7 +39,7 @@
 import re
 import sys, os, shutil
 import tempfile
-from os.path import join, dirname
+from os.path import join, dirname, basename
 from matplotlib import pyplot as plt
 from matplotlib import cm
 from docopt import docopt
@@ -54,6 +55,7 @@
 import hicstuff.digest as hcd
 import hicstuff.iteralign as hci
 import hicstuff.filter as hcf
+import hicstuff.stats as hcs
 from hicstuff.version import __version__
 import hicstuff.io as hio
 from hicstuff.log import logger
@@ -1656,6 +1658,25 @@ def execute(self):
         )
         logger.info("Output image saved at %s.", out)
 
+class Stats(AbstractCommand):
+    """Extract stats from a hicstuff log file.
+
+    usage:
+        stats <log>
+
+    arguments:
+        log               Path to a hicstuff log file.
+    """
+
+    def execute(self):
+        log_file = self.args["<log>"]
+        hcs.get_pipeline_stats(log_file)
+        prefix = re.sub(".hicstuff.*", "", basename(log_file))
+        out_dir = dirname(log_file)
+        stats_file_path = join(out_dir, prefix + ".stats.txt")
+        with open(stats_file_path, 'r') as file: 
+            lines = [line for line in file]
+            print(''.join(lines))
 
 def parse_bin_str(bin_str):
     """Bin string parsing
@@ -1696,7 +1717,6 @@ def parse_bin_str(bin_str):
 
     return binning
 
-
 def parse_ucsc(ucsc_str, bins):
     """
     Take a UCSC region in UCSC notation and a list of bin chromosomes and

hicstuff/main.py

@@ -21,6 +21,7 @@
     iteralign       Iteratively aligns reads to a reference genome.
     missview        Preview missing Hi-C bins in based on the genome and read length.
     pipeline        Hi-C pipeline to generate contact matrix from fastq files.
+    stats           Extract mapping statistics from a hicstuff pipeline log file.
     rebin           Bin the matrix and regenerate files accordingly.
     subsample       Bootstrap subsampling of contacts from a Hi-C map.
     view            Visualize a Hi-C matrix.    

hicstuff/pipeline.py

@@ -1140,7 +1140,7 @@ def _out_file(fname):
     # Get stats on the pipeline
     try:
         logger.info("Fetching mapping and pairing stats")
-        stats = hcs.get_pipeline_stats(prefix, out_dir, log_file)
+        stats = hcs.get_pipeline_stats(log_file)
         logger.info(stats)
     except IndexError: 
         logger.warning("IndexError. Stats not compiled.")

hicstuff/stats.py

@@ -3,17 +3,15 @@
 
 import re 
 from os.path import join
+from os.path import dirname
+from os.path import basename
 import json
 
-def get_pipeline_stats(prefix, out_dir, log_file):
+def get_pipeline_stats(log_file):
     """Get stats after pipeline execution.
 
     Parameters
     ----------
-    prefix : str
-        The prefix used to create output files by the pipeline.
-    out_dir : str
-        The prefix used to create output files by the pipeline.
     log_file : str
         Path to hicstuff log file.
 
@@ -36,6 +34,8 @@ def get_pipeline_stats(prefix, out_dir, log_file):
             - Trans ratio
     """
 
+    prefix = re.sub(".hicstuff.*", "", basename(log_file))
+    out_dir = dirname(log_file)
     with open(log_file) as file:
         log_lines = [line.rstrip() for line in file]