Commit 39cf08a6 authored by vdberg's avatar vdberg
Browse files

to file

parent 2908c030

process_srl.py

+3 −1
Original line number Diff line number Diff line
@@ -44,6 +44,7 @@ def load_nameslab(): 
parser = ArgumentParser()

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

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

parser.add_argument("-n", "--n", type=int, default=100, help="nr of top verbs to show")

args = parser.parse_args()

df = load_output(dir='outputs', combine=args.combine)
@@ -88,9 +89,10 @@ for n, gr in df.groupby(['bias', 'name_bias']): 
    counts = gr.verb.value_counts()

    counts = counts / overall_counts.loc[counts.index]

    counts.index += counts.apply(cust)

    sorted_verbs = counts.sort_values(ascending=False).head(10)

    sorted_verbs = counts.sort_values(ascending=False).head(N)

    grs[n] = sorted_verbs.index

print(grs)

grs.to_csv('most_freq_verbs.csv')



exit(0)