Commit b6e7b7f2 authored by vdberg's avatar vdberg
Browse files

Fix and print

parent 1d72fe76

srl.py

+13 −9
Original line number Diff line number Diff line
@@ -43,7 +43,8 @@ def ner(t): 


sent = pd.read_csv('data/sent_df.csv')

sent = sent[sent.s.apply(crude_ner) == True]

data = sent[:]

#print([i for i in sent.index if i > 1400])

data = sent.iloc[1449:]



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")
@@ -67,7 +68,9 @@ for i,r in data.iterrows(): 
    names = persons[persons.w.apply(crude_ner) == True].copy()

    #print('names', names)



    verbs = names.set_index(['w']).iloc[:,1:].copy().stack().reset_index(level=1, name='arg').rename(columns={'level_1':'verb'})

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

    if not verbs.empty:

        verbs = verbs.copy().stack().reset_index(level=1, name='arg').rename(columns={'level_1':'verb'})

        #print('verbs', verbs)

        verbs = verbs.replace({'O':None}).dropna()

        #print('verbs', verbs)
@@ -75,6 +78,7 @@ for i,r in data.iterrows(): 
        verbs['same'] = namlabs_df.loc[verbs.index].bias.values == r.bias

        #print('verbs', verbs)

        verb_df = verb_df.append(verbs)

    print('Found {} verbs'.format(len(verbs)))



verb_df.arg = verb_df.arg.str[2:]

verb_df.to_csv('vdberg_output.csv')

vdberg_output.csv

+2 −1
Original line number Diff line number Diff line 
,arg,same,verb

Clinton,ARG1,True,excoriated
 
Obama,ARG1,False,freaking

Obama,ARGM-DIR,False,move