The following Python script was created to count keyword occurrences in a string. It expects a tab delimited text file with the first column being the ID, second column being the text (status), and third column is the date. It outputs a tab delimited file with the ID, date and for each of the term - 0 if not in string, 1 if term is found in the string.

Usage

Arguments

Argument 1 - input file
Argument 2 - output file
Argument 3 - terms file

Command line

python scriptfile.py inputfile.txt outputfile.txt terms.txt

The code

import string, os, sys
import operator, math

if __name__ == '__main__':

    TermDict={}
    TermTup=[]
    TermFile=open(sys.argv[3], "r")
    line = TermFile.readline()
    while line:
        term=line.strip().lower()
        TermDict[term]="0"
        TermTup.append(term)
        line = TermFile.readline()
    #endwhile
    TermFile.close()

    outFile=open(sys.argv[2], "w")
    outLine='mpid\tdate\t'
    for i in range(0, len(TermTup)):
        outLine=outLine+TermTup[i]+'\t'
    #end
    outLine=outLine+'\n'
    outFile.write(outLine)


    inFile=open(sys.argv[1], "r")
    line = inFile.readline()
    while line:

        mpid=line[:line.find("\t")]
        print "mpid: "+mpid
        line=line[line.find("\t")+1 : ]
        status=line[:line.find("\t")]
        line=line[line.find("\t")+1 : ]
        date=line.strip()

        status=status.lower()
        for term in TermDict:
            if string.find(status, term)>-1:
                TermDict[term]="1"
            #endif
        #endfor
        
        outLine=mpid+'\t'+date+'\t'
        for i in range(0, len(TermTup)):
            outLine=outLine+TermDict[TermTup[i]]+'\t'
            if TermDict[TermTup[i]]=="1":
                TermDict[TermTup[i]]="0"
            #endif
        #endfor
        outLine=outLine+'\n'
        outFile.write(outLine)

        line = inFile.readline()
    #endwhile
    inFile.close()
    outFile.close()

Credits

Big thanks to Yaron Charka for help with this script.