brain: add python and R code to local repository.

1 files changed, 43 insertions, 0 deletions

diff --git a/Code/delete_not_used_fastq.py b/Code/delete_not_used_fastq.py
new file mode 100644
index 0000000..67d368b
--- /dev/null
+++ b/Code/delete_not_used_fastq.py
@@ -0,0 +1,43 @@
+# Usage: python delete_not_used_fastq.py
+#        Edit DIR, the directory containing all fastq.gz files.
+#        Also generate USED_IDS.
+# Purpose: list fastq.gz files that are not used. Move them to to.be.deleted folder.
+#
+# 20 Apr 2017, slcu, hui
+
+import glob, os
+
+def read_ids(fname):
+    f = open(fname)
+    d = {}
+    for line in f:
+        line = line.strip()
+        d[line] = 1
+    f.close()
+    return d
+
+DIR = '/home/hui/network/R/Raw'
+destDIR = os.path.join(DIR, 'to.be.deleted')
+USED_IDS = '/home/hui/network/v03/Data/temp/used.sra.ids.txt' # generated by grep @ /home/hui/network/v03/Data/parameter/parameter_for_buildRmatrix.txt | grep 'SRR\|ERR\|DRR' | perl -pe 'substr($_, 0, 3) = ""; s/X+$//'
+
+
+if not os.path.isdir(destDIR):
+    os.makedirs(destDIR)
+    
+ids = read_ids(USED_IDS)
+flst = glob.glob(os.path.join(DIR, '*.gz'))
+
+print('file\tsize.in.G')
+sum = 0
+for path in flst:
+    fname = os.path.basename(path)
+    if '_' in fname:
+        i = fname[0:fname.find('_')]
+    else:
+        i = fname[0:fname.find('.')]
+    if not i in ids:
+        print('%s\t%4.2f' % (path, 1.0*os.path.getsize(path)/(1024*1024*1024)))
+        sum += 1.0*os.path.getsize(path)/(1024*1024*1024)
+        cmd = 'mv %s %s' % (path, destDIR)
+        os.system(cmd)
+print('Total %4.2f G moved to %s' % (sum, destDIR))