enabling stats as properly formatted TSV

as requested by wdecoster/nanostat#29
wdecoster · Aug 19, 2020 · b5f8898 · b5f8898
1 parent bb7aaa3
commit b5f8898
Show file tree

Hide file tree

Showing 4 changed files with 15 additions and 7 deletions.
diff --git a/nanocomp/NanoComp.py b/nanocomp/NanoComp.py
@@ -65,13 +65,14 @@ def main():
         if args.barcoded:
             datadf["dataset"] = datadf["barcode"]
         identifiers = list(datadf["dataset"].unique())
-        write_stats(
+        stats_df = write_stats(
             datadfs=[datadf[datadf["dataset"] == i] for i in identifiers],
             outputfile=settings["path"] + "NanoStats.txt",
-            names=identifiers)
+            names=identifiers,
+            as_tsv=args.tsv_stats)
         if args.plot != 'false':
             plots = make_plots(datadf, settings)
-            make_report(plots, settings["path"])
+            make_report(plots, settings["path"], stats_df=stats_df)
         logging.info("Succesfully processed all input.")
     except Exception as e:
         logging.error(e, exc_info=True)
@@ -181,7 +182,7 @@ def make_plots(df, settings):
     return plots
 
 
-def make_report(plots, path):
+def make_report(plots, path, stats_df):
     '''
     Creates a fat html report based on the previously created files
     plots is a list of Plot objects defined by a path and title
@@ -208,7 +209,10 @@ def make_report(plots, path):
         </head>"""
     html_content = ["\n<body>\n<h1>NanoComp report</h1>"]
     html_content.append("<h2>Summary statistics</h2>")
-    html_content.append(utils.stats2html(path + "NanoStats.txt"))
+    if stats_df is not None:
+        html_content.append(stats_df.to_html())
+    else:
+        html_content.append(utils.stats2html(path + "NanoStats.txt"))
     html_content.append('\n<br>\n<br>\n<br>\n<br>')
     html_content.append("<h2>Plots</h2>")
     for plot in plots:

diff --git a/nanocomp/utils.py b/nanocomp/utils.py
@@ -31,6 +31,7 @@ def chunks(values, chunks):
 
 
 def stats2html(statsf):
+    '''for legacy stats output files'''
     df = pd.read_csv(statsf, sep=':', header=None, names=['feature', 'value'])
     values = df["value"].str.strip().str.replace('\t', ' ').str.split().replace(np.nan, '')
     num = len(values[0]) or 1
@@ -154,6 +155,9 @@ def get_args():
     general.add_argument("--store",
                          help="Store the extracted data in a pickle file for future plotting.",
                          action="store_true")
+    general.add_argument("--tsv_stats",
+                         help="Output the stats file as a properly formatted TSV.",
+                         action='store_true')
     filtering = parser.add_argument_group(
         title='Options for filtering or transforming input prior to plotting')
     filtering.add_argument("--readtype",

diff --git a/nanocomp/version.py b/nanocomp/version.py
@@ -1 +1 @@
-__version__ = "1.11.3"
+__version__ = "1.12.0"
diff --git a/setup.py b/setup.py
@@ -33,7 +33,7 @@
     install_requires=['pandas',
                       'numpy',
                       'nanoget>=1.4.0',
-                      'nanomath>=0.23.1',
+                      'nanomath>=1.0.0',
                       'NanoPlot>=1.21.0',
                       'psutil',
                       'plotly>=3.4.2',