Commit e64f0072 authored by EstherMaria's avatar EstherMaria
Browse files
parents 924c1853 20844bd4
Loading
Loading
Loading
Loading
+6 −3
Original line number Diff line number Diff line
@@ -2,7 +2,7 @@ from allennlp.predictors.predictor import Predictor
import pandas as pd
import logging, re
import time

from argparse import ArgumentParser

def load_nameslab():
    namfn = 'data/names_labeled.csv'
@@ -50,14 +50,17 @@ def hardcoded_clean(names):
    names.w = names.w.str.replace('2.', '')
    return names

parser = ArgumentParser()
parser.add_argument("-s", "--start_i", help="which i to start from")
args = parser.parse_args()

sent = pd.read_csv('data/sent_df.csv')
sent = sent[sent.s.apply(crude_ner) == True]
#print(max(sent.index))
#vdberg_output_11315.csv.csv.csv.csv 64210
over = [i for i in sent.index if i > 115503] #99.000
over = [i for i in sent.index if i > args.start_i] #99.000 #130562
start_i = over[0]
data = sent.loc[start_i:]

srl_pred = Predictor.from_path("https://s3-us-west-2.amazonaws.com/allennlp/models/srl-model-2018.05.25.tar.gz")
allen_ner = Predictor.from_path("https://s3-us-west-2.amazonaws.com/allennlp/models/ner-model-2018.12.18.tar.gz")