Parse feature names in Fragile Families Challenge

gistfile1.py

def parse_codebook_data(fname):
    fNames = dict()
    with open(fname, 'r') as fl:
        lstate = False
        for line in fl:
            if line.startswith('-----'):
                lstate = True
            else:
                if lstate:
                    while '  ' in line:
                        line = line.replace('  ', ' ')
                    #print line
                    temp = line.strip().split(' ')
                    fNames[temp[0]] = ' '.join(temp[1:])
                lstate = False
    return fNames
                
    
featureNames = dict()
# Looking for a path that has all feature description files
for fname in glob.glob('data/codebooks/ff*.txt'):
    featureNames.update(parse_codebook_data(fname))
for f in featureNames:
    if 'education' in featureNames[f]:
        print '[{}]: {}'.format(f, featureNames[f])