# Extracting definition from different words in each sentence
# Extractinf from ecah row the, NOUN, VERBS, NOUN Plural
text = data['Omschrijving_Skill_without_stopwords'].tolist()
tagged_texts = pos_tag_sents(map(word_tokenize, text))
data['pos'] = pos_tag_sents( data['Omschrijving_Skill_without_stopwords'].apply(word_tokenize).tolist() )
data['Nouns'] = data['pos'].apply(lambda row: [i[0] for i in row if i[1] == 'NN'])
data['Verbs'] = data['pos'].apply(lambda row: [i[0] for i in row if i[1] == 'VB'])
data['Adj'] = data['pos'].apply(lambda row: [i[0] for i in row if i[1] == 'JJ'])
data['NOUN Pltagged_textsural'] = data['pos'].apply(lambda row: [i[0] for i in row if i[1] == 'NNS'])
data['Omschrijving_Skill_without_stopwords'] = data['Omschrijving_Skill_without_stopwords'].astype(str)
data['Omschrijving_Skill_without_stopwords'] = data['Omschrijving_Skill_without_stopwords'].str.split("t", n =1, expand=True)
the output is
0 [(beschikbaarheid, NN), (mili, NN)]
1 [(par, NN)]
2 [(opera, NN)]
3 [(mili, NN)]
4 [(opera, NN)]
...
4696 [(on, IN)]
4697 [(veiligheidssys, NN)]
4698 []
4699 [(a, DT)]
4700 [(a, DT)]
Name: pos, Length: 4701, dtype: object
I want to count from data['pos'] how many nouns, verbs etc I have so I want to have an output:
('NN':3, 'DT':2 )
I tried the following code:
Counter([j for i, j in pos_tag(word_tokenize(tagged_text))])
but I got an error:
TypeError: 'function' object is not iterable
I have the idea that because I have an list, I can't use counter. I tried to convert the data['Omschrijving_skill_without_stopwords'] to a dictionary But that does not work, can any one help me to count my tags so that I know many tags I have?
Thank you