Loading srl.py +8 −4 Original line number Diff line number Diff line Loading @@ -43,6 +43,13 @@ def ner(t): ### load sent_df def hardcoded_clean(names): names.w = names.w.str.replace('\ufeff', '') names.w = names.w.str.replace('—', '') names.w = names.w.str.replace('‘s', '') names.w = names.w.str.replace('2.', '') return names sent = pd.read_csv('data/sent_df.csv') sent = sent[sent.s.apply(crude_ner) == True] #print(max(sent.index)) Loading Loading @@ -75,11 +82,8 @@ for i, r in data.iterrows(): persons = tagged[tagged.n.str.endswith('PER')] names = persons[persons.w.apply(crude_ner) == True].copy() #names.w = names.w.str.strip('—') names.w = names.w.str.replace('—', '') names.w = names.w.str.replace('\ufeff', '') names.w = names.w.str.replace('‘s', '') #print('names', names) names = hardcoded_clean(names) 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'}) Loading Loading
srl.py +8 −4 Original line number Diff line number Diff line Loading @@ -43,6 +43,13 @@ def ner(t): ### load sent_df def hardcoded_clean(names): names.w = names.w.str.replace('\ufeff', '') names.w = names.w.str.replace('—', '') names.w = names.w.str.replace('‘s', '') names.w = names.w.str.replace('2.', '') return names sent = pd.read_csv('data/sent_df.csv') sent = sent[sent.s.apply(crude_ner) == True] #print(max(sent.index)) Loading Loading @@ -75,11 +82,8 @@ for i, r in data.iterrows(): persons = tagged[tagged.n.str.endswith('PER')] names = persons[persons.w.apply(crude_ner) == True].copy() #names.w = names.w.str.strip('—') names.w = names.w.str.replace('—', '') names.w = names.w.str.replace('\ufeff', '') names.w = names.w.str.replace('‘s', '') #print('names', names) names = hardcoded_clean(names) 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'}) Loading