Loading process_srl.py +2 −0 Original line number Diff line number Diff line Loading @@ -61,6 +61,7 @@ parser.add_argument("-max", "--max_freq", type=int, default=2000, help="min verb parser.add_argument("-l", "--lemmatize", action="store_true", default=False, help="whether to (re)do lemmatization") args = parser.parse_args() MIN_FREQ = args.min_freq MAX_FREQ = args.max_freq N = args.n ARG = args.arg LEMMATIZE = args.lemmatize Loading Loading @@ -119,6 +120,7 @@ print(overall_freq.head(3)) print(overall_freq.tail(3)) df["across"] = overall_freq.loc[df.verb].values df = df[df.across > MIN_FREQ] df = df[df.across < MAX_FREQ] binned = pd.DataFrame() for n, gr in df.groupby(['bias', 'name_bias']): n_edit = '{}_coverage_of_{}_person'.format(n[0], n[1]) Loading Loading
process_srl.py +2 −0 Original line number Diff line number Diff line Loading @@ -61,6 +61,7 @@ parser.add_argument("-max", "--max_freq", type=int, default=2000, help="min verb parser.add_argument("-l", "--lemmatize", action="store_true", default=False, help="whether to (re)do lemmatization") args = parser.parse_args() MIN_FREQ = args.min_freq MAX_FREQ = args.max_freq N = args.n ARG = args.arg LEMMATIZE = args.lemmatize Loading Loading @@ -119,6 +120,7 @@ print(overall_freq.head(3)) print(overall_freq.tail(3)) df["across"] = overall_freq.loc[df.verb].values df = df[df.across > MIN_FREQ] df = df[df.across < MAX_FREQ] binned = pd.DataFrame() for n, gr in df.groupby(['bias', 'name_bias']): n_edit = '{}_coverage_of_{}_person'.format(n[0], n[1]) Loading