Commit c2bc3b61 authored by vdberg's avatar vdberg
Browse files

fix and shift

parent 9eea7955
Loading
Loading
Loading
Loading
+5 −2
Original line number Diff line number Diff line
@@ -44,8 +44,10 @@ def ner(t):
sent = pd.read_csv('data/sent_df.csv')
sent = sent[sent.s.apply(crude_ner) == True]
#print(max(sent.index))
#exit(0) #vdberg_output_11315.csv.csv.csv.csv
data = sent.loc[11315:]
#vdberg_output_11315.csv.csv.csv.csv 64210
#print([i for i in sent.index if i > 64202])
#exit(0)
data = sent.loc[64202:]

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")
@@ -70,6 +72,7 @@ for i, r in data.iterrows():
    tagged = pd.DataFrame(zip(*tagged), columns=['w', 'n'] + verbs)
    persons = tagged[tagged.n.str.endswith('PER')]
    names = persons[persons.w.apply(crude_ner) == True].copy()
    names = names.w.apply.str.strip('-')
    #print('names', names)

    verbs = names.set_index(['w']).iloc[:,1:]