ls-bsr_convert.py

#imports numpy as needed by pandas module
import numpy as np

#imports pandas module to read through excell sheet
import pandas as pd

#imports arg parse
import argparse


parser = argparse.ArgumentParser()

#argument requires user to input the name of a textfile containing the xl data matrix
parser.add_argument('--input', help='Enter the name of the xl file .')
#argument requires user for an output file
parser.add_argument('--output', help= 'Enter the name of the text file you want to output your aprroximate patterns found in the sequence.')
arguments=parser.parse_args()

#if the user doesnt put in an input file its prompts them to do so
if arguments.input == None:
    input_xl = raw_input('Please enter the name of a xl file : ')
    
else:
    input_xl = arguments.input
    
#if the user doesnt put in an input file its prompts them to do so
if arguments.output == None:
    output = raw_input('Please enter the name of a output file : ')
    
else:
    output = arguments.output

#USing the pandas module it reads in the excell file into a data structure that can be read/modified in python
data_file =pd.read_excel(input_xl)

# Creates a list of all the headers at the top of the excel file
headers = data_file.columns

#Creates a dictionary. The dictionary will have the genome id's as the keys and a select data set as its value.
g_dict= {}
values= data_file.index

#iterates through all of the genome id's in the excell file
#Uses the pandas function .loc to select a specific data set. In this case it is saying to set the variable clms to a data set to all the rows under the specific column containing the header we are iterating through. i.e)      A B C
    #                                                                                 I  4 3 2
    #                                                                                II  5 2 4
    #                                                                               III  3 4 5
    #  clms = data_file.loc[:(or all rows),h(the firs iteration h=A)]
    #print clms
    #     A 
    #  I  4 
    # II  5 
    #III  3 
#Then if the header is not a key in the dicitonary G dict it will set put the header in the dict with the sub data set coresponding to the 6 fingerprints 
for h in headers:
    
    clms = data_file.loc[:,h]
    if h not in g_dict:
        g_dict[h]= clms
#Next it goes through each of the keys in the dictionary looking at the percent values for each likeliness
#If the likeliness factor is less than 90% it sets the value to 0 if it is greater than 90% it sets it equal to 1
for keys in g_dict:
    
    pb = g_dict[keys]

    for x in range(len(pb)):
        if pb.ix[x] >= .90:
            pb.ix[x]= 1
        
        else:
            pb.ix[x] = 0

# Creates a new dictionary with the key as the genome ID and the value a list of the binary numbers
binary= {}
for keys in g_dict:
    p = g_dict[keys]
    if keys not in binary:
        binary[keys]= []
    
    
    for x in range(len(pb)):
        binary[keys].append(p.ix[x])
        
        
       
outputfile = open(output,'w')

# iterates through all the keys in the dictionary and writes the binary fingerprint to an output file.
for keys in g_dict:
    outputfile.write('GENOME ID: %s\n%s\n\n' %(keys,g_dict[keys]))
out=open('o.txt','w')