argument analysis added as command line

# process command line arguments

parser = ArgumentParser()

parser.add_argument("-c", "--combine", action="store_true", default=False, help="whether to combine or not")

parser.add_argument("-a", "--arg", default='ARG0', help="focus on an arg")

parser.add_argument("-a", "--arg", default=None, help="analyze args or not")

parser.add_argument("-n", "--n", type=int, default=50, help="nr of top verbs to show")

parser.add_argument("-mf", "--min_freq", type=int, default=5, help="min verb frequency to eliminate rarest verbs")

args = parser.parse_args()

MIN_FREQ = args.min_freq

N = args.n

ARG = args.arg

# load files

sent = pd.read_csv('data/sent_df.csv', names=['sent_id','bias','doc_id','s'])

#df.verb = df.verb.apply(lemmatizer.lemmatize)

# arg

df = df[df.arg.str.endswith('0')]

if ARG:

    #df = df[df.arg.str.endswith(ARG)]

    df.verb += ' (' + df.arg.str[2:] + ')'

# compute overall counts

    counts['normalized'] = counts.within / counts.across #gr.verb.value_counts(normalize=True)

    #counts.normalized = counts.normalized.apply(round)

    sorted_verbs = counts.sort_values(by="normalized", ascending=False).head(N)

    sorted_verbs.to_csv("frequent_verbs/{}.csv".format(n_edit), sep="\t")

    sorted_verbs.to_csv("frequent_verbs/{}{}.csv".format(n_edit, '_arg' if ARG else ''), sep="\t")

    binned[n] = sorted_verbs.index

print(binned.head(N))

binned.to_csv('frequent_verbs/most_freq_verbs.csv')

binned.to_csv('frequent_verbs/most_freq_verbs{}.csv'.format('_arg' if ARG else ''))

exit(0)