In [1]:
import codecs
import nltk

CORPUS_FOLDER = '/home/spenteco/0/corpora/muncie_public_library_corpus/PG_no_backmatter_fiction/'

texts = [
    {'file_name': 'Bront_Charlotte_Jane_Eyre_An_Autobiography_PG_1260.txt', 
         'raw_text': '', 'tokens': [], 'text_obj': None},
    {'file_name': 'Dickens_Charles_David_Copperfield_PG_766.txt', 
         'raw_text': '', 'tokens': [], 'text_obj': None},
    {'file_name': 'Thackeray_William_Makepeace_Vanity_Fair_PG_599.txt', 
         'raw_text': '', 'tokens': [], 'text_obj': None},
]

for t in texts:
    t['raw_text'] = codecs.open(CORPUS_FOLDER + t['file_name'], 'r', encoding='utf-8').read()
    t['tokens'] = nltk.word_tokenize(t['raw_text'])
    t['text_obj'] = nltk.Text(t['tokens'])
    
print 'Done!'

Done!
In [2]:
import spacy
from textblob import TextBlob
nlp = spacy.load('en')
print spacy.__version__

1.9.0
In [3]:
import re
from collections import defaultdict, Counter
from textblob.wordnet import VERB
from textblob import Word

hyper = lambda s: s.hypernyms()

for text in texts:
    
    print
    print text['file_name'], '\t', 'len(text[\'tokens\'])', len(text['tokens'])
    print
    
    cleaned_text = re.sub('\s+', ' ', text['raw_text'])
    
    doc = nlp(cleaned_text)
    
    synset_counts = defaultdict(int)
    
    for t in doc:
        if t.pos_ == 'VERB':

            word_synsets =  Word(t.lemma_).get_synsets(pos=VERB)
            for w in word_synsets:
                synset_counts[w.name()] += 1
                h = list(w.closure(hyper, depth=10))
                for s in h:
                    synset_counts[s.name()] += 1
                
    for w in Counter(synset_counts).most_common(20):
        print w[0], w[1], (float(w[1]) / float(len(text['tokens'])))
    
                    
                    
        

Bront_Charlotte_Jane_Eyre_An_Autobiography_PG_1260.txt 	len(text['tokens']) 228761

be.v.01 39035 0.170636603267
act.v.01 33043 0.144443327315
change.v.02 32449 0.141846730868
interact.v.01 26097 0.114079760099
communicate.v.02 21261 0.0929397930591
make.v.03 20810 0.0909683031636
change.v.01 18366 0.0802846639069
move.v.02 16116 0.0704490713015
think.v.03 15545 0.067953016467
inform.v.01 14981 0.0654875612539
be.v.03 11990 0.0524127801505
tell.v.02 11646 0.0509090273255
travel.v.01 11406 0.0498598974476
get.v.01 11197 0.0489462801789
impart.v.01 10479 0.0458076332941
undergo.v.01 10149 0.044365079712
convey.v.01 9925 0.043385891826
equal.v.01 9925 0.043385891826
evaluate.v.02 8224 0.0359501838163
constitute.v.01 7889 0.0344857733617

Dickens_Charles_David_Copperfield_PG_766.txt 	len(text['tokens']) 432229

be.v.01 81511 0.18858290397
act.v.01 67002 0.155015049893
change.v.02 64924 0.1502074132
interact.v.01 54624 0.126377452693
make.v.03 45462 0.105180355784
communicate.v.02 44804 0.103658014617
think.v.03 34984 0.0809385765416
change.v.01 34039 0.0787522355048
inform.v.01 33387 0.0772437758688
move.v.02 31114 0.0719849894385
be.v.03 25793 0.0596743855688
tell.v.02 25280 0.0584875147202
get.v.01 24277 0.0561669855563
impart.v.01 23405 0.0541495364726
convey.v.01 22552 0.0521760455684
travel.v.01 22124 0.0511858297338
undergo.v.01 21950 0.0507832653524
equal.v.01 20397 0.0471902625691
evaluate.v.02 17189 0.039768270986
constitute.v.01 17004 0.0393402571322

Thackeray_William_Makepeace_Vanity_Fair_PG_599.txt 	len(text['tokens']) 359731

be.v.01 58238 0.161893192413
act.v.01 51177 0.142264636631
change.v.02 46589 0.129510662134
interact.v.01 40652 0.113006663312
make.v.03 33199 0.0922884043911
communicate.v.02 33109 0.0920382174458
move.v.02 23526 0.0653988674871
change.v.01 23510 0.0653543898079
inform.v.01 23364 0.0649485309857
think.v.03 22084 0.0613903166533
be.v.03 18383 0.0511020734938
get.v.01 18275 0.0508018491595
tell.v.02 17920 0.0498150006533
travel.v.01 16625 0.0462150884967
impart.v.01 16272 0.0452337997003
undergo.v.01 15693 0.0436242636859
convey.v.01 15408 0.042832005026
equal.v.01 14415 0.0400716090634
constitute.v.01 12463 0.0346453322066
transfer.v.05 12129 0.0337168606542
In [ ]: