Commit 9eea7955 authored by vdberg's avatar vdberg
Browse files

processÄ

parent 6b623faf

process_srl.py

+2 −1
Original line number Diff line number Diff line
@@ -31,6 +31,7 @@ print(df.shape) 
nltk.download('wordnet')

lemmatizer = WordNetLemmatizer()

df['lemma'] = df.verb.apply(lemmatizer.lemmatize)

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



vad = pd.read_csv('data/NRC-VAD-Lexicon.txt', delimiter='\t', index_col=0)

df['dom'] = df.lemma.apply(get_dom)
@@ -42,7 +43,7 @@ arg_agr = pd.DataFrame(columns=['']) 
dom_agr = pd.DataFrame(columns=[''])

for n, gr in grs:

    print(n, gr.dom.mean())

    arg_agr[n] = gr['arg'].value_counts()

    arg_agr[n] = gr['arg'].value_counts(normalize=True)

    #dom_agr[n] = gr.nlargest(n=10, columns=['dom'])



print(arg_agr.head(n=10))