From e8dfa85cd7e0428e53aac532c31f1ac1cc3cf1c1 Mon Sep 17 00:00:00 2001
From: Calvin <calvin@EESI>
Date: Thu, 7 Mar 2013 17:17:20 -0500
Subject: starting to modularize

---
 quikr_train.py | 74 ----------------------------------------------------------
 1 file changed, 74 deletions(-)
 delete mode 100755 quikr_train.py

(limited to 'quikr_train.py')

diff --git a/quikr_train.py b/quikr_train.py
deleted file mode 100755
index a427436..0000000
--- a/quikr_train.py
+++ /dev/null
@@ -1,74 +0,0 @@
-#!/usr/bin/python
-import numpy as np
-import os
-import sys
-import gzip
-from subprocess import *
-import platform
-import argparse
-
-def main():
-  """
-  You can call this script independently, and will save the 
-  trained matrix as a numpy file.
-  example: python quikr-train.py -i input.fasta -k 6 -o trained_matrix.npy
- 
-  """
-  parser = argparse.ArgumentParser(description=
-  " quikr_train returns a custom trained matrix that can be used with \
-    the quikr function. \n You must supply a kmer. \n ")
-
-  parser.add_argument("-i", "--input", help="training database of sequences (fasta format)", required=True)
-  parser.add_argument("-o", "--output", help="sensing matrix (text file)", required=True)
-  parser.add_argument("-k", "--kmer", help="kmer size (integer)", 
-                      type=int, required=False )
-  parser.add_argument("-z", "--compress", help="compress output (integer)", 
-                      action='store_true', required=False)
-
-  args = parser.parse_args()
-
-  if not os.path.isfile(args.input):
-    parser.error( "Input database not found")
-
-  # call the quikr train function, save the output with np.save
-  matrix = quikr_train(args.input, args.kmer)
-
-  if args.compress: 
-    output_file = gzip.open(args.output, "wb")
-  else:
-    output_file = open(args.output, "wb")
-
-  np.save(output_file, matrix)
-
-  return 0
-
-def quikr_train(input_file_location, kmer):
-  """
-  Takes a input fasta file, and kmer, returns a custom trained matrix
-  """
-
-  kmer_file_name = str(kmer) + "mers.txt"
-
-  if not os.path.isfile(kmer_file_name):
-    print "could not find kmer file"
-    exit()
-
-  
-  uname = platform.uname()[0]
-
-  if uname == "Linux": 
-    input_file = Popen(["./probabilities-by-read-linux", str(kmer), input_file_location, kmer_file_name], stdout=PIPE) 
-  elif uname == "Darwin":
-    input_file = Popen(["./probabilities-by-read-osx", str(kmer), input_file_location, kmer_file_name]) 
-
-  # load and  normalize the matrix by dividing each element by the sum of it's column.
-  # also do some fancy rotations so that it works properly with quikr
-  matrix  = np.loadtxt(input_file.stdout)
-  
-  matrix = np.rot90(matrix)
-  matrix = matrix / matrix.sum(0)
-  matrix = np.flipud(matrix);
-  return matrix
-  
-if __name__ == "__main__":
-    sys.exit(main())
-- 
cgit v1.2.3