Commit 53b9781e authored by vdberg's avatar vdberg
Browse files

final version - 3 sentences

parent 2bb97eea

srl.py

+1 −8
Original line number Diff line number Diff line
@@ -43,21 +43,17 @@ def ner(t): 


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

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

data = sent[:50]

data = sent[:3]



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")



logging.basicConfig(filename='vdberg_log.log',level=logging.DEBUG)



verb_df = pd.DataFrame(columns=['arg', 'verb', 'same'])

for i,r in data.iterrows():

    names = ner(r.s)

    #print('Predicting NER for {}: {}'.format(i, r.s))

    logging.info('Predicting NER for {}: {}'.format(i, r.s))



    roles = srl_pred.predict(sentence=r.s)['verbs']

    logging.info('Predicted roles for {}'.format(i))

    #print('roles', roles)



    # extract info
@@ -67,9 +63,7 @@ for i,r in data.iterrows(): 
    #print('verbs', verbs)



    tagged = pd.DataFrame(zip(*tagged), columns=['w', 'n'] + verbs)

    #print('tagged', tagged)

    persons = tagged[tagged.n.str.endswith('PER')]

    #print('persons', persons)

    names = persons[persons.w.apply(crude_ner) == True].copy()

    #print('names', names)
@@ -78,7 +72,6 @@ for i,r in data.iterrows(): 
    verbs = verbs.replace({'O':None}).dropna()

    #print('verbs', verbs)

    #names['nambias'] = namlabs_df.loc[verbs.index].bias.values

    logging.info('Extracted verbs with politicians as args for {}'.format(i))

    verbs['same'] = namlabs_df.loc[verbs.index].bias.values == r.bias

    #print('verbs', verbs)

    verb_df = verb_df.append(verbs)

vdberg_output.csv

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

Clinton,ARG1,True,excoriated

vdberg_output_local.csv

0 → 100644
+2 −0
Original line number Diff line number Diff line 
,arg,same,verb

Clinton,ARG1,True,excoriated