[MRG] update mapping notebook to include SNP graph, and etc. (#168)

* fix gz problem with test-private

* copy_local_genomes now gzips files

* fix mapping notebook fig #s, include SNP figure

Makefile

@@ -38,17 +38,18 @@ databases/podar-ref/:
 	mkdir -p databases/podar-ref
 	curl -L https://osf.io/vbhy5/download -o databases/podar-ref.tar.gz
 	cd databases/podar-ref/ && tar xzf ../podar-ref.tar.gz
+	parallel -j 4 gzip {} ::: $$(ls databases/podar-ref/*.fa)
 
 # sketch the ref genomes
 databases/podar-ref.zip: databases/podar-ref/
 	sourmash sketch dna -p k=31,scaled=1000 --name-from-first \
-	    databases/podar-ref/*.fa -o databases/podar-ref.zip
+	    databases/podar-ref/*.fa.gz -o databases/podar-ref.zip
 
 # download taxonomy
 databases/podar-ref.tax.csv:
 	curl -L https://osf.io/4yhjw/download -o databases/podar-ref.tax.csv
 
 # create info file and genomes directory:
 databases/podar-ref.info.csv:
-	python -m genome_grist.copy_local_genomes databases/podar-ref/*.fa -o databases/podar-ref.info.csv -d databases/podar-ref.d
+	python -m genome_grist.copy_local_genomes databases/podar-ref/*.fa.gz -o databases/podar-ref.info.csv -d databases/podar-ref.d
 	python -m genome_grist.make_info_file databases/podar-ref.info.csv

genome_grist/copy_local_genomes.py

@@ -9,7 +9,8 @@
 import csv
 import os
 import shutil
-
+import gzip
+import contextlib
 
 def main():
     p = argparse.ArgumentParser()
@@ -50,8 +51,21 @@ def main():
         print(f"read identifer '{ident}' and name '{remainder}'")
 
         destfile = os.path.join(args.output_directory, f"{ident}_genomic.fna.gz")
-        print(f"copying '{filename}' to '{destfile}'")
-        shutil.copyfile(filename, destfile)
+
+        is_gzipped = False
+        with contextlib.suppress(OSError):
+            with gzip.open(filename) as fp:
+                fp.read(1)
+                is_gzipped = True
+
+        if is_gzipped:
+            print(f"copying '{filename}' to '{destfile}'")
+            shutil.copyfile(filename, destfile)
+        else:
+            print(f"compressing '{filename}' into '{destfile}'")
+            with open(filename, 'rb') as fp:
+                with gzip.open(destfile, 'w') as outfp:
+                    outfp.write(fp.read())
 
         w.writerow(dict(ident=ident, display_name=remainder,
                         genome_filename=destfile))