top_ner.py

named_entities = []
for sentence in corpus:
    temp_entity_name = ''
    temp_named_entity = None
    sentence = nlp(sentence)
    for word in sentence:
        term = word.text 
        tag = word.ent_type_
        if tag:
            temp_entity_name = ' '.join([temp_entity_name, term]).strip()
            temp_named_entity = (temp_entity_name, tag)
        else:
            if temp_named_entity:
                named_entities.append(temp_named_entity)
                temp_entity_name = ''
                temp_named_entity = None

entity_frame = pd.DataFrame(named_entities, 
                            columns=['Entity Name', 'Entity Type'])

# get the top named entities
top_entities = (entity_frame.groupby(by=['Entity Name', 'Entity Type'])
                           .size()
                           .sort_values(ascending=False)
                           .reset_index().rename(columns={0 : 'Frequency'}))
top_entities.T.iloc[:,:15]