>>> from nltk.book import *
>>> text1.concordance('monstrous')
Displaying 11 of 11 matches:
ong the former , one was of a most monstrous size . ... This came towards us ,
ON OF THE PSALMS . " Touching that monstrous bulk of the whale or ork we have r
ll over with a heathenish array of monstrous clubs and spears . Some were thick
d as you gazed , and wondered what monstrous cannibal and savage could ever hav
that has survived the flood ; most monstrous and most mountainous ! That Himmal
they might scout at Moby Dick as a monstrous fable , or still worse and more de
th of Radney .'" CHAPTER 55 Of the Monstrous Pictures of Whales . I shall ere l
ing Scenes . In connexion with the monstrous pictures of whales , I am strongly
ere to enter upon those still more monstrous stories of them which are to be fo
ght have been rummaged out of this monstrous cabinet there is no telling . But
of Whale - Bones ; for Whales of a monstrous size are oftentimes cast up dead u

>>> from nltk.book import *
>>> text1.similar('monstrous')
imperial subtly impalpable pitiable curious abundant peril
trustworthy untoward singular lamentable few determined ma
horrible tyrannical lazy mystifying christian exasperate

>>> from nltk.book import *
>>> text2.common_contexts(['monstrous','very']
a_pretty is_pretty a_lucky am_glad be_glad

>>> ds
['you', 'i', 'love', 'meet', 'solve', 'drink']
>>> len(ds)
6
>>> set(ds)
set(['love', 'i', 'drink', 'solve', 'meet', 'you'])
>>> sorted(ds)
['drink', 'i', 'love', 'meet', 'solve', 'you']

>>> ds.count('love')
1
>>> from nltk.book import *
>>> text1.count('you')
841

>>> from nltk.book import *
>>> fdist=FreqDist(text1)
>>> type(fdist)
<class 'nltk.probability.FreqDist'>
>>> fdist.hapaxes()[:10]
[u'funereal', u'unscientific', u'prefix', u'plaudits', u'woody', u'disobeying', u'Westers', u'DRYDEN', u'Untried', u'superficially']
>>> fdist.items()[:10]
[(u'funereal', 1), (u'unscientific', 1), (u'divinely', 2), (u'foul', 11), (u'four', 74), (u'gag', 2), (u'prefix', 1), (u'woods', 9), (u'clotted', 2), (u'Du
>>> fdist.max
<bound method FreqDist.max of FreqDist({u',': 18713, u'the': 13721, u'.': 6862, u'of': 6536, u'and': 6024, u'a': 4569, u'to': 4542, u';': 4072, u'in': 3916
>>> fdist.max()
u','
>>> fdist.freq('employment')
3.834076505162584e-06

>>> from nltk.book import *
>>> text1.dispersion_plot(['monition', 'furrowed', 'tauntings', 'foul'])
>>> text1.dispersion_plot(['monitions', 'furrowed', 'tauntings', 'foul'])

>>> import nltk
>>> from nltk.corpus import brown
>>> cfd=nltk.ConditionalFreqDist(
... (genre, word)
... for genre in brown.categories()
... for word in brown.words(categories=genre))
>>> genres=['news', 'religion', 'hobbies', 'romance']
>>> modals=['can', 'could', 'may', 'might', 'must', 'will']
>>> cfd.tabulate(conditions=genres, samples=modals)can could   may might  must  willnews    93    86    66    38    50   389
religion    82    59    78    12    54    71hobbies   268    58   131    22    83   264romance    74   193    11    51    45    43

>>> from nltk.book import FreqDist
>>> from nltk.book import text1
>>> fdist=FreqDist(text1)
>>> fdist.plot(50)

>>> text1.collocations()
Sperm Whale; Moby Dick; White Whale; old man; Captain Ahab; sperm
whale; Right Whale; Captain Peleg; New Bedford; Cape Horn; cried Ahab;
years ago; lower jaw; never mind; Father Mapple; cried Stubb; chief
mate; white whale; ivory leg; one hand
>>>

>>> ds
['you', 'can', 'understand', 'me', 'than', 'done']
>>> import nltk
>>> fd=nltk.Text(ds)
>>> fd
<Text: you can understand me than done...>

 1 >>> from nltk.corpus import brown
 2 >>> import nltk
 3 >>> cfdist=nltk.ConditionalFreqDist(
 4 ... (genre, word)
 5 ... for genre in brown.categories()
 6 ... for word in brown.words(categories=genre))
 7 >>>
 8 >>> cfdist.conditions()
 9 [u'mystery', u'belles_lettres', u'humor', u'government', u'fiction', u'reviews', u'religion', u'romance', u'science_fiction', u'adventure'
10 >>> cfdist['mystery']
11 FreqDist({u'.': 3326, u',': 2805, u'the': 2573, u'to': 1284, u'and': 1215, u'a': 1136, u'of': 903, u'was': 820, u'``': 740, u"''": 738, ..
12 >>> cfdist['mystery']['and']
13 1215
14 >>> genres=['news', 'religion', 'hobbies', 'science_fiction', 'romance']
15 >>> modals=['can', 'could', 'may', 'might', 'must', 'will']
16 >>> cfdist.tabulate(conditions=genres, samples=modals)
17                   can could   may might  must  will
18            news    93    86    66    38    50   389
19        religion    82    59    78    12    54    71
20         hobbies   268    58   131    22    83   264
21 science_fiction    16    49     4    12     8    16
22         romance    74   193    11    51    45    43
23 >>> cfdist.plot()

View Code

>>> cfdist.plot(samples=modals, conditions=genres)