Last login: Wed Jul 16 10:35:54 on ttyp1
Welcome to Darwin!
DB029Podium:~ buckeye$ python

Python 2.5.2 (r252:60911, Feb 22 2008, 07:57:53) 
[GCC 4.0.1 (Apple Computer, Inc. build 5363)] on darwin
Type "help", "copyright", "credits" or "license" for more information.
>>> 
>>> import nltk
>>> import nltk.corpus
>>> nltk.corpus.brown.tagged_words()[17]
('evidence', 'NN')
>>> 
DB029Podium:~ buckeye$ python
Python 2.5.2 (r252:60911, Feb 22 2008, 07:57:53) 
[GCC 4.0.1 (Apple Computer, Inc. build 5363)] on darwin
Type "help", "copyright", "credits" or "license" for more information.
>>> import nltk
>>> import nltk.corpus
>>> brown = nltk.corpus.brown.words()
>>> brown[17]
'evidence'
>>> brown[16:19]
['no', 'evidence', "''"]
>>> brown[:19]
['The', 'Fulton', 'County', 'Grand', 'Jury', 'said', 'Friday', 'an', 'investigation', 'of', "Atlanta's", 'recent', 'primary', 'election', 'produced', '``', 'no', 'evidence', "''"]
>>> brown[-1]
'.'
>>> brown[-10]
'the'
>>> brown[-10:-1]
['the', 'figure', 'inside', 'the', 'coral-colored', 'boucle', 'dress', 'was', 'stupefying']
>>> brown[-10:]
['the', 'figure', 'inside', 'the', 'coral-colored', 'boucle', 'dress', 'was', 'stupefying', '.']
>>> brown[-10:0]
[]
>>> brown[:10]
['The', 'Fulton', 'County', 'Grand', 'Jury', 'said', 'Friday', 'an', 'investigation', 'of']
>>> brown[0:10]
['The', 'Fulton', 'County', 'Grand', 'Jury', 'said', 'Friday', 'an', 'investigation', 'of']
>>> inaugural = nltk.corpus.inaugural.words()
>>> inaugural[0:10]
['Fellow', '-', 'Citizens', 'of', 'the', 'Senate', 'and', 'of', 'the', 'House']
>>> print nltk.corpus.inaugural.words  
<bound method PlaintextCorpusReader.words of <PlaintextCorpusReader in '/usr/share/nltk/data/corpora/inaugural'>>
>>> brown = nltk.corpus.brown.tagged_words()
>>> brown[:20]
[('The', 'AT'), ('Fulton', 'NP-TL'), ('County', 'NN-TL'), ('Grand', 'JJ-TL'), ('Jury', 'NN-TL'), ('said', 'VBD'), ('Friday', 'NR'), ('an', 'AT'), ('investigation', 'NN'), ('of', 'IN'), ("Atlanta's", 'NP$'), ('recent', 'JJ'), ('primary', 'NN'), ('election', 'NN'), ('produced', 'VBD'), ('``', '``'), ('no', 'AT'), ('evidence', 'NN'), ("''", "''"), ('that', 'CS')]
>>> inaugural = nltk.corpus.inaugural.tagged_words()
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
AttributeError: 'PlaintextCorpusReader' object has no attribute 'tagged_words'
>>> print nltk.corpus.inaugural.items()       
__main__:1: DeprecationWarning: 
  Function _get_items() has been deprecated.  Use corpus.files()
  instead
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
TypeError: 'tuple' object is not callable
>>> print nltk.corpus.inaugural.items  
('1789-Washington.txt', '1793-Washington.txt', '1797-Adams.txt', '1801-Jefferson.txt', '1805-Jefferson.txt', '1809-Madison.txt', '1813-Madison.txt', '1817-Monroe.txt', '1821-Monroe.txt', '1825-Adams.txt', '1829-Jackson.txt', '1833-Jackson.txt', '1837-VanBuren.txt', '1841-Harrison.txt', '1845-Polk.txt', '1849-Taylor.txt', '1853-Pierce.txt', '1857-Buchanan.txt', '1861-Lincoln.txt', '1865-Lincoln.txt', '1869-Grant.txt', '1873-Grant.txt', '1877-Hayes.txt', '1881-Garfield.txt', '1885-Cleveland.txt', '1889-Harrison.txt', '1893-Cleveland.txt', '1897-McKinley.txt', '1901-McKinley.txt', '1905-Roosevelt.txt', '1909-Taft.txt', '1913-Wilson.txt', '1917-Wilson.txt', '1921-Harding.txt', '1925-Coolidge.txt', '1929-Hoover.txt', '1933-Roosevelt.txt', '1937-Roosevelt.txt', '1941-Roosevelt.txt', '1945-Roosevelt.txt', '1949-Truman.txt', '1953-Eisenhower.txt', '1957-Eisenhower.txt', '1961-Kennedy.txt', '1965-Johnson.txt', '1969-Nixon.txt', '1973-Nixon.txt', '1977-Carter.txt', '1981-Reagan.txt', '1985-Reagan.txt', '1989-Bush.txt', '1993-Clinton.txt', '1997-Clinton.txt', '2001-Bush.txt', '2005-Bush.txt')
>>> poppy = nltk.corpus.inaugural.words('1989-Bush.txt')
>>> poppy[:10]
['Mr', '.', 'Chief', 'Justice', ',', 'Mr', '.', 'President', ',', 'Vice']
>>> shrub = nltk.corpus.inaugural.words('2005-Bush.txt')
>>> shrub[:10]                                          
['Inaugural', 'Addresses', 'of', 'the', 'Presidents', 'of', 'the', 'United', 'States', '.']
>>> for language in nltk.corpus.udhr.items:
...  print language
... 
/Library/Frameworks/Python.framework/Versions/2.5/lib/python2.5/site-packages/nltk/corpus/util.py:53: DeprecationWarning: 
  Function _get_items() has been deprecated.  Use corpus.files()
  instead
  return getattr(self, attr)
Abkhaz-Cyrillic+Abkh
Abkhaz-UTF8
Achehnese-Latin1
Achuar-Shiwiar-Latin1
Adja-UTF8
Afaan_Oromo_Oromiffa-Latin1
Afrikaans-Latin1
Aguaruna-Latin1
Akuapem_Twi-UTF8
Albanian_Shqip-Latin1
Amahuaca
Amahuaca-Latin1
Amarakaeri-Latin1
Amharic-Afenegus6..60375
Amuesha-Yanesha-UTF8
Arabela-Latin1
Arabic_Alarabia-Arabic
Armenian-DallakHelv
Asante-UTF8
Ashaninca-Latin1
Asheninca-Latin1
Asturian_Bable-Latin1
Aymara-Latin1
Azeri_Azerbaijani_Cyrillic-Az.Times.Cyr.Normal0117
Azeri_Azerbaijani_Latin-Az.Times.Lat0117
Balinese-Latin1
Bambara-UTF8
Baoule-UTF8
Basque_Euskara-Latin1
Batonu_Bariba-UTF8
Belorus_Belaruski-Cyrillic
Belorus_Belaruski-UTF8
Bemba-Latin1
Bengali-UTF8
Beti-UTF8
Bhojpuri-Agra
Bichelamar-Latin1
Bikol_Bicolano-Latin1
Bora-Latin1
Bosnian_Bosanski-Cyrillic
Bosnian_Bosanski-Latin2
Bosnian_Bosanski-UTF8
Breton-Latin1
Bugisnese-Latin1
Bulgarian_Balgarski-Cyrillic
Bulgarian_Balgarski-UTF8
Burmese_Myanmar-UTF8
Burmese_Myanmar-WinResearcher
Cakchiquel-Latin1
Campa_Pajonalino-Latin1
Candoshi-Shapra-Latin1
Caquinte-Latin1
Cashibo-Cacataibo-Latin1
Cashinahua-Latin1
Catalan-Latin1
Catalan_Catala-Latin1
Cebuano-Latin1
Chamorro-Latin1
Chayahuita-Latin1
Chechewa_Nyanja-Latin1
Chickasaw-Latin1
Chinanteco-Ajitlan-Latin1
Chinanteco-UTF8
Chinese_Mandarin-GB2312
Chinese_Mandarin-HZ
Chinese_Mandarin-UTF8
Chuuk_Trukese-Latin1
Cokwe-Latin1
Corsican-Latin1
Croatian_Hrvatski-Latin2
Czech-Latin2
Czech-Latin2-err
Czech-UTF8
Czech_Cesky-Latin2
Czech_Cesky-UTF8
Dagaare-UTF8
Dagbani-UTF8
Dangme-UTF8
Danish_Dansk-Latin1
Dendi-UTF8
Ditammari-UTF8
Dutch_Nederlands-Latin1
Edo-Latin1
English-Latin1
Esperanto-T61
Esperanto-UTF8
Estonian_Eesti-Latin1
Ewe_Eve-UTF8
Fante-UTF8
Faroese-Latin1
Farsi_Persian-UTF8
Farsi_Persian-v2-UTF8
Fijian-Latin1
Filipino_Tagalog-Latin1
Finnish_Suomi-Latin1
Fon-UTF8
French_Francais-Latin1
Frisian-Latin1
Friulian_Friulano-Latin1
Ga-UTF8
Gagauz_Gagauzi-UTF8
Galician_Galego-Latin1
Garifuna_Garifuna-Latin1
German_Deutsch-Latin1
Gonja-UTF8
Greek_Ellinika-Greek
Greek_Ellinika-UTF8
Greenlandic_Inuktikut-Latin1
Guarani-Latin1
Guen_Mina-UTF8
Gujarati-UTF8
HaitianCreole_Kreyol-Latin1
HaitianCreole_Popular-Latin1
Hani-Latin1
Hausa_Haoussa-Latin1
Hawaiian-UTF8
Hebrew_Ivrit-Hebrew
Hebrew_Ivrit-UTF8
Hiligaynon-Latin1
Hindi-UTF8
Hindi_web-UTF8
Hmong_Miao-Sichuan-Guizhou-Yunnan-Latin1
Hmong_Miao-SouthernEast-Guizhou-Latin1
Hmong_Miao_Northern-East-Guizhou-Latin1
Hrvatski_Croatian-Latin2
Huasteco-Latin1
Huitoto_Murui-Latin1
Hungarian_Magyar-Latin1
Hungarian_Magyar-Latin2
Hungarian_Magyar-UTF8
Hungarian_Magyar-Unicode
Ibibio_Efik-Latin1
Icelandic_Yslenska-Latin1
Ido-Latin1
Igbo-UTF8
Iloko_Ilocano-Latin1
Indonesian-Latin1
Interlingua-Latin1
Inuktikut_Greenlandic-Latin1
IrishGaelic_Gaeilge-Latin1
Italian-Latin1
Italian_Italiano-Latin1
Japanese_Nihongo-EUC
Japanese_Nihongo-JIS
Japanese_Nihongo-SJIS
Japanese_Nihongo-UTF8
Javanese-Latin1
Jola-Fogny_Diola-UTF8
Kabye-UTF8
Kannada-UTF8
Kaonde-Latin1
Kapampangan-Latin1
Kasem-UTF8
Kazakh-Cyrillic
Kazakh-UTF8
Kiche_Quiche-Latin1
Kicongo-Latin1
Kimbundu_Mbundu-Latin1
Kinyamwezi_Nyamwezi-Latin1
Kinyarwanda-Latin1
Kituba-Latin1
Korean_Hankuko-UTF8
Kpelewo-UTF8
Krio-UTF8
Kurdish-UTF8
Lamnso_Lam-nso-UTF8
Lao-UTF8
Latin_Latina-Latin1
Latin_Latina-v2-Latin1
Latvian-Latin1
Limba-UTF8
Lingala-Latin1
Lithuanian_Lietuviskai-Baltic
Lozi-Latin1
Luba-Kasai_Tshiluba-Latin1
Luganda_Ganda-Latin1
Lunda_Chokwe-lunda-Latin1
Luvale-Latin1
Luxembourgish_Letzebuergeusch-Latin1
Macedonian-UTF8
Madurese-Latin1
Magahi-Agra
Magahi-UTF8
Makonde-Latin1
Malagasy-Latin1
Malay_BahasaMelayu-Latin1
Maltese-UTF8
Mam-Latin1
Maninka-UTF8
Maori-Latin1
Mapudungun_Mapuzgun-Latin1
Mapudungun_Mapuzgun-UTF8
Marathi-UTF8
Marshallese-Latin1
Matses-Latin1
Mayan_Yucateco-Latin1
Mazahua_Jnatrjo-UTF8
Mazateco-Latin1
Mende-UTF8
Mikmaq_Micmac-Mikmaq-Latin1
Minangkabau-Latin1
Miskito_Miskito-Latin1
Mixteco-Latin1
Mongolian_Khalkha-Cyrillic
Mongolian_Khalkha-UTF8
Moore_More-UTF8
Nahuatl-Latin1
Navaho_Dine-Navajo-Navaho-font
Ndebele-Latin1
Nepali-UTF8
Ngangela_Nyemba-Latin1
NigerianPidginEnglish-Latin1
Nomatsiguenga-Latin1
NorthernSotho_Pedi-Sepedi-Latin1
Norwegian-Latin1
Norwegian_Norsk-Bokmal-Latin1
Norwegian_Norsk-Nynorsk-Latin1
Nyanja_Chechewa-Latin1
Nyanja_Chinyanja-Latin1
Nzema-UTF8
OccitanAuvergnat-Latin1
OccitanLanguedocien-Latin1
Oromiffa_AfaanOromo-Latin1
Osetin_Ossetian-UTF8
Oshiwambo_Ndonga-Latin1
Otomi_Nahnu-Latin1
Paez-Latin1
Palauan-Latin1
Peuhl-UTF8
Picard-Latin1
Pipil-Latin1
Polish-Latin2
Polish_Polski-Latin2
Ponapean-Latin1
Portuguese_Portugues-Latin1
Pulaar-UTF8
Punjabi_Panjabi-UTF8
Purhepecha-UTF8
Qechi_Kekchi-Latin1
Quechua-Latin1
Quichua-Latin1
Rarotongan_MaoriCookIslands-Latin1
Rhaeto-Romance_Rumantsch-Latin1
Romani-Latin1
Romani-UTF8
Romanian-Latin2
Romanian_Romana-Latin2
Rukonzo_Konjo-Latin1
Rundi_Kirundi-Latin1
Runyankore-rukiga_Nkore-kiga-Latin1
Russian-Cyrillic
Russian-UTF8
Russian_Russky-Cyrillic
Russian_Russky-UTF8
Sami_Lappish-UTF8
Sammarinese-Latin1
Samoan-Latin1
Sango_Sangho-Latin1
Sanskrit-UTF8
Saraiki-UTF8
Sardinian-Latin1
ScottishGaelic_GaidhligAlbanach-Latin1
Seereer-UTF8
Serbian_Srpski-Cyrillic
Serbian_Srpski-Latin2
Serbian_Srpski-UTF8
Sharanahua-Latin1
Shipibo-Conibo-Latin1
Shona-Latin1
Sinhala-UTF8
Siswati-Latin1
Slovak-Latin2
Slovak_Slovencina-Latin2
Slovenian_Slovenscina-Latin2
SolomonsPidgin_Pijin-Latin1
Somali-Latin1
Soninke_Soninkanxaane-UTF8
Sorbian-Latin2
SouthernSotho_Sotho-Sesotho-Sutu-Sesutu-Latin1
Spanish-Latin1
Spanish_Espanol-Latin1
Sukuma-Latin1
Sundanese-Latin1
Sussu_Soussou-Sosso-Soso-Susu-UTF8
Swaheli-Latin1
Swahili_Kiswahili-Latin1
Swedish_Svenska-Latin1
Tahitian-UTF8
Tamil-UTF8
Tenek_Huasteco-Latin1
Tetum-Latin1
Themne_Temne-UTF8
Tigrinya_Tigrigna-VG2Main
Tiv-Latin1
Toba-UTF8
Tojol-abal-Latin1
TokPisin-Latin1
Tonga-Latin1
Tongan_Tonga-Latin1
Totonaco-Latin1
Trukese_Chuuk-Latin1
Turkish_Turkce-Turkish
Turkish_Turkce-UTF8
Tzeltal-Latin1
Tzotzil-Latin1
Uighur_Uyghur-Latin1
Uighur_Uyghur-UTF8
Ukrainian-Cyrillic
Ukrainian-UTF8
Umbundu-Latin1
Urarina-Latin1
Uzbek-Latin1
Vietnamese-ALRN-UTF8
Vietnamese-TCVN
Vietnamese-UTF8
Vietnamese-VIQR
Vietnamese-VPS
Vlach-Latin1
Walloon_Wallon-Latin1
Wama-UTF8
Waray-Latin1
Wayuu-Latin1
Welsh_Cymraeg-Latin1
WesternSotho_Tswana-Setswana-Latin1
Wolof-Latin1
Xhosa-Latin1
Yagua-Latin1
Yao-Latin1
Yapese-Latin1
Yoruba-UTF8
Zapoteco-Latin1
Zapoteco-SanLucasQuiavini-Latin1
Zhuang-Latin1
Zulu-Latin1
>>> from nltk.corpus import treebank
>>> print treebank.items
('wsj_0001.mrg', 'wsj_0002.mrg', 'wsj_0003.mrg', 'wsj_0004.mrg', 'wsj_0005.mrg', 'wsj_0006.mrg', 'wsj_0007.mrg', 'wsj_0008.mrg', 'wsj_0009.mrg', 'wsj_0010.mrg', 'wsj_0011.mrg', 'wsj_0012.mrg', 'wsj_0013.mrg', 'wsj_0014.mrg', 'wsj_0015.mrg', 'wsj_0016.mrg', 'wsj_0017.mrg', 'wsj_0018.mrg', 'wsj_0019.mrg', 'wsj_0020.mrg', 'wsj_0021.mrg', 'wsj_0022.mrg', 'wsj_0023.mrg', 'wsj_0024.mrg', 'wsj_0025.mrg', 'wsj_0026.mrg', 'wsj_0027.mrg', 'wsj_0028.mrg', 'wsj_0029.mrg', 'wsj_0030.mrg', 'wsj_0031.mrg', 'wsj_0032.mrg', 'wsj_0033.mrg', 'wsj_0034.mrg', 'wsj_0035.mrg', 'wsj_0036.mrg', 'wsj_0037.mrg', 'wsj_0038.mrg', 'wsj_0039.mrg', 'wsj_0040.mrg', 'wsj_0041.mrg', 'wsj_0042.mrg', 'wsj_0043.mrg', 'wsj_0044.mrg', 'wsj_0045.mrg', 'wsj_0046.mrg', 'wsj_0047.mrg', 'wsj_0048.mrg', 'wsj_0049.mrg', 'wsj_0050.mrg', 'wsj_0051.mrg', 'wsj_0052.mrg', 'wsj_0053.mrg', 'wsj_0054.mrg', 'wsj_0055.mrg', 'wsj_0056.mrg', 'wsj_0057.mrg', 'wsj_0058.mrg', 'wsj_0059.mrg', 'wsj_0060.mrg', 'wsj_0061.mrg', 'wsj_0062.mrg', 'wsj_0063.mrg', 'wsj_0064.mrg', 'wsj_0065.mrg', 'wsj_0066.mrg', 'wsj_0067.mrg', 'wsj_0068.mrg', 'wsj_0069.mrg', 'wsj_0070.mrg', 'wsj_0071.mrg', 'wsj_0072.mrg', 'wsj_0073.mrg', 'wsj_0074.mrg', 'wsj_0075.mrg', 'wsj_0076.mrg', 'wsj_0077.mrg', 'wsj_0078.mrg', 'wsj_0079.mrg', 'wsj_0080.mrg', 'wsj_0081.mrg', 'wsj_0082.mrg', 'wsj_0083.mrg', 'wsj_0084.mrg', 'wsj_0085.mrg', 'wsj_0086.mrg', 'wsj_0087.mrg', 'wsj_0088.mrg', 'wsj_0089.mrg', 'wsj_0090.mrg', 'wsj_0091.mrg', 'wsj_0092.mrg', 'wsj_0093.mrg', 'wsj_0094.mrg', 'wsj_0095.mrg', 'wsj_0096.mrg', 'wsj_0097.mrg', 'wsj_0098.mrg', 'wsj_0099.mrg', 'wsj_0100.mrg', 'wsj_0101.mrg', 'wsj_0102.mrg', 'wsj_0103.mrg', 'wsj_0104.mrg', 'wsj_0105.mrg', 'wsj_0106.mrg', 'wsj_0107.mrg', 'wsj_0108.mrg', 'wsj_0109.mrg', 'wsj_0110.mrg', 'wsj_0111.mrg', 'wsj_0112.mrg', 'wsj_0113.mrg', 'wsj_0114.mrg', 'wsj_0115.mrg', 'wsj_0116.mrg', 'wsj_0117.mrg', 'wsj_0118.mrg', 'wsj_0119.mrg', 'wsj_0120.mrg', 'wsj_0121.mrg', 'wsj_0122.mrg', 'wsj_0123.mrg', 'wsj_0124.mrg', 'wsj_0125.mrg', 'wsj_0126.mrg', 'wsj_0127.mrg', 'wsj_0128.mrg', 'wsj_0129.mrg', 'wsj_0130.mrg', 'wsj_0131.mrg', 'wsj_0132.mrg', 'wsj_0133.mrg', 'wsj_0134.mrg', 'wsj_0135.mrg', 'wsj_0136.mrg', 'wsj_0137.mrg', 'wsj_0138.mrg', 'wsj_0139.mrg', 'wsj_0140.mrg', 'wsj_0141.mrg', 'wsj_0142.mrg', 'wsj_0143.mrg', 'wsj_0144.mrg', 'wsj_0145.mrg', 'wsj_0146.mrg', 'wsj_0147.mrg', 'wsj_0148.mrg', 'wsj_0149.mrg', 'wsj_0150.mrg', 'wsj_0151.mrg', 'wsj_0152.mrg', 'wsj_0153.mrg', 'wsj_0154.mrg', 'wsj_0155.mrg', 'wsj_0156.mrg', 'wsj_0157.mrg', 'wsj_0158.mrg', 'wsj_0159.mrg', 'wsj_0160.mrg', 'wsj_0161.mrg', 'wsj_0162.mrg', 'wsj_0163.mrg', 'wsj_0164.mrg', 'wsj_0165.mrg', 'wsj_0166.mrg', 'wsj_0167.mrg', 'wsj_0168.mrg', 'wsj_0169.mrg', 'wsj_0170.mrg', 'wsj_0171.mrg', 'wsj_0172.mrg', 'wsj_0173.mrg', 'wsj_0174.mrg', 'wsj_0175.mrg', 'wsj_0176.mrg', 'wsj_0177.mrg', 'wsj_0178.mrg', 'wsj_0179.mrg', 'wsj_0180.mrg', 'wsj_0181.mrg', 'wsj_0182.mrg', 'wsj_0183.mrg', 'wsj_0184.mrg', 'wsj_0185.mrg', 'wsj_0186.mrg', 'wsj_0187.mrg', 'wsj_0188.mrg', 'wsj_0189.mrg', 'wsj_0190.mrg', 'wsj_0191.mrg', 'wsj_0192.mrg', 'wsj_0193.mrg', 'wsj_0194.mrg', 'wsj_0195.mrg', 'wsj_0196.mrg', 'wsj_0197.mrg', 'wsj_0198.mrg', 'wsj_0199.mrg')
>>> print treebank.parsed_sents('wsj_0003.mrg')[0] 
(S
  (S-TPC-1
    (NP-SBJ
      (NP (NP (DT A) (NN form)) (PP (IN of) (NP (NN asbestos))))
      (RRC
        (ADVP-TMP (RB once))
        (VP
          (VBN used)
          (NP (-NONE- *))
          (S-CLR
            (NP-SBJ (-NONE- *))
            (VP
              (TO to)
              (VP
                (VB make)
                (NP (NNP Kent) (NN cigarette) (NNS filters))))))))
    (VP
      (VBZ has)
      (VP
        (VBN caused)
        (NP
          (NP (DT a) (JJ high) (NN percentage))
          (PP (IN of) (NP (NN cancer) (NNS deaths)))
          (PP-LOC
            (IN among)
            (NP
              (NP (DT a) (NN group))
              (PP
                (IN of)
                (NP
                  (NP (NNS workers))
                  (RRC
                    (VP
                      (VBN exposed)
                      (NP (-NONE- *))
                      (PP-CLR (TO to) (NP (PRP it)))
                      (ADVP-TMP
                        (NP
                          (QP (RBR more) (IN than) (CD 30))
                          (NNS years))
                        (IN ago))))))))))))
  (, ,)
  (NP-SBJ (NNS researchers))
  (VP (VBD reported) (SBAR (-NONE- 0) (S (-NONE- *T*-1))))
  (. .))
>>> sent = "Buckeye corpora are available at zero cost"
>>> sent.split()
['Buckeye', 'corpora', 'are', 'available', 'at', 'zero', 'cost']
>>> mytagger = nltk.DefaultTagger("NN")
>>> mytagger.tag(sent.split())
[('Buckeye', 'NN'), ('corpora', 'NN'), ('are', 'NN'), ('available', 'NN'), ('at', 'NN'), ('zero', 'NN'), ('cost', 'NN')]
>>> mytagger = nltk.DefaultTagger("bozo")
>>> mytagger.tag(sent.split())
[('Buckeye', 'bozo'), ('corpora', 'bozo'), ('are', 'bozo'), ('available', 'bozo'), ('at', 'bozo'), ('zero', 'bozo'), ('cost', 'bozo')]
>>> train_sents = nltk.corpus.treebank.tagged_sents()[:3000]
>>> test_sents = nltk.corpus.treebank.tagged_sents()[3000:]
>>> len(test_sents)
914
>>> len(train_sents)
3000
>>> unigram_tagger = nltk.UnigramTagger(train_sents)
>>> unigram_tagger.tag(sent.split())
[('Buckeye', None), ('corpora', None), ('are', 'VBP'), ('available', 'JJ'), ('at', 'IN'), ('zero', None), ('cost', 'NN')]
>>> unigram_tagger = nltk.UnigramTagger(train_sents,backoff=DefaultTagger("bozo"))
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
NameError: name 'DefaultTagger' is not defined
>>> unigram_tagger = nltk.UnigramTagger(train_sents,backoff=nltk.DefaultTagger("bozo"))
>>> unigram_tagger.tag(sent.split())
[('Buckeye', 'bozo'), ('corpora', 'bozo'), ('are', 'VBP'), ('available', 'JJ'), ('at', 'IN'), ('zero', 'bozo'), ('cost', 'NN')]
>>> nltk.tag.accuracy
<function accuracy at 0x1250a70>
>>> nltk.tag.accuracy(unigram_tagger,test_sents)
0.82495143535506155
>>> unigram_tagger = nltk.UnigramTagger(train_sents,backoff=nltk.DefaultTagger("NN"))
>>> nltk.tag.accuracy(unigram_tagger,test_sents)
0.84964385927045116
>>> trigram_tagger = nltk.TrigramTagger(train_sents,backoff=nltk.DefaultTagger("bozo"))
>>> 
KeyboardInterrupt
>>> trigram_tagger = nltk.TrigramTagger(train_sents,backoff=nltk.DefaultTagger("NP"))
>>> nltk.tag.accuracy(unigram_tagger,test_sents)
0.84964385927045116
>>> nltk.tag.accuracy(trigram_tagger,test_sents)
0.049384847830779191
>>> bigram_tagger = nltk.BigramTagger(train_sents,backoff=nltk.DefaultTagger("bozo"))
>>> bigram_tagger = nltk.BigramTagger(train_sents,backoff=nltk.DefaultTagger("NP"))
^[[A>>> bigram_tagger = nltk.BigramTagger(train_sents,backoff=nltk.DefaultTagger("NN"))
>>> nltk.tag.accuracy(bigram_tagger,test_sents)
0.71810921649039494
>>> bigram_tagger = nltk.BigramTagger(train_sents,backoff=unigram_tagger)
>>> nltk.tag.accuracy(bigram_tagger,test_sents)
0.85335635657241526
>>>