Python state_union.raw函数代码示例

def POS_tagging(corpus):
    train_text = state_union.raw("2005-GWBush.txt")
    sample_text = corpus
    #print(train_text)
    custom_sentence_tokenizer = PunktSentenceTokenizer(train_text)

    # textfile = open("POS_tagged",'w')
    # textfile.write(train_text)
    # textfile.write("\n\n\n\n\n\n\n\n\n\n")
    # print(custom_sentence_tokenizer)

    tokenized = custom_sentence_tokenizer.tokenize(sample_text)
    tuples_list = []
    def process_content():
        try:
            for i in tokenized:
                words = nltk.word_tokenize(i)
                tagged = nltk.pos_tag(words)
                for w in tagged:
                    tuples_list.append(w)
        except Exception as e:
            c=0
            # print(str(e))
    process_content()
    return tuples_list

def main():
    training_text = state_union.raw('2005-GWBush.txt')
    sample_text = state_union.raw('2006-GWBush.txt')
    custom_sent_tokenizer = PunktSentenceTokenizer(training_text)
    tokenized = custom_sent_tokenizer.tokenize(sample_text)

    choice = 0
    while choice < 5:
        choice = input("1 for named_chunks. This provides some information about proper nouns.\n, 2 for process_chunks. This tells you if a noun phrase followed by n adverb occurs., \n3 for proccess content, this just prints stuff, 4 for...")
        if choice == 1:
            named_chunks(text_trained_tokenized(sample_text, training_text))
        elif choice == 2:
            process_chunks(text_trained_tokenized(sample_text, training_text))
        elif choice == 3:
            process_content(text_trained_tokenized(sample_text, training_text))
        elif choice == 4:
            print "try again, bitch!"

def main(argv):
    print("main")
    # namedEnts = named_ents("Bill went to the White House. He saw the President of the United States. Then he went to O'hare International Airport. He flew to The Democratic Republic of Congo. He will not go back to the White House any time soon. the President of the United States is dissapointed by this.")
    # print(namedEnts)
    f = open("north_korea.txt")
    text = f.read()
    # print(text)
    johnson = state_union.raw("1968-Johnson.txt")
    ent_list = text_ents(johnson)
    ent_freq = nltk.FreqDist(ent_list)
    print(ent_freq.most_common())
    print(ent_freq)
    print(list(ent_freq.values()))
    print(list(ent_freq.keys()))

def name_ent_recog(post):
    train_text = state_union.raw("2005-GWBush.txt")
    sample_text = post
    custom_sent_tokenizer = PunktSentenceTokenizer(train_text)
    tokenized = custom_sent_tokenizer.tokenize(sample_text)
    namedEnt = []
    try:
        for i in tokenized:
            words = nltk.word_tokenize(i)
            tagged = nltk.pos_tag(words)
            namedEnt.append(nltk.ne_chunk(tagged))
    except Exception as e:
        print(str(e))
    return namedEnt

def POS_tagging(corpus):
    train_text = state_union.raw("2005-GWBush.txt")
    sample_text = ""
    for i in corpus:
        sample_text = sample_text+i+" "
    tuples_list = []
    def process_content():
        try:
            words = nltk.word_tokenize(sample_text)
            tagged = nltk.pos_tag(words)
            for w in tagged:
                tuples_list.append(w)
        except Exception as e:
            print(str(e))
    process_content()
    return tuples_list

# -*- coding: utf-8 -*-
"""
Created on Thu Nov 19 09:15:11 2015

@author: nilakant
"""


import nltk
from nltk.corpus import state_union
from nltk.tokenize import PunktSentenceTokenizer
#unsupervised tokenizer
train_text = state_union.raw("2006-GWBush.txt")
sample_text = state_union.raw("2006-GWBush.txt")

custom_sent_tokenizer = PunktSentenceTokenizer(train_text)
tokenized = custom_sent_tokenizer.tokenize(sample_text)

def process_content():
    try:
        for i in tokenized:
            words = nltk.word_tokenize(i)
            tagged = nltk.pos_tag(words)
            
            chunkGram = r"""Chunk: {<.*>+}
                                    }<VB.?|IN|DT|TO>+{"""

            chunkParser = nltk.RegexpParser(chunkGram)
            chunked = chunkParser.parse(tagged)
            chunked.draw()
            

from nltk.corpus import state_union
#from nltk.corpus import PunktSentenceTokenizer
from nltk.stem import PorterStemmer     #this give the stem of the word to help “normalize’ text
from nltk.stem import WordNetLemmatizer #this is like stemming, but gives a complete word or synonym
from nltk.corpus import wordnet, movie_reviews #movie_reviews are 1000 positive and 1000 negative movie reviews
import random #this is to randomize the movie reviews as the first 1000 are positive and the other 1000 negative
import pickle





my_text = """The World Wide Web, or simply Web, is a way of accessing information over the medium of the Internet. It is an information-sharing model that is built on top of the Internet. The Web uses the HTTP protocol, only one of the languages spoken over the Internet, to transmit data. Web services, which use HTTP to allow applications to communicate in order to exchange business logic, use the the Web to share information. The Web also utilizes browsers, such as Internet Explorer or Firefox, to access Web documents called Web pages that are linked to each other via hyperlinks. Web documents also contain graphics, sounds, text and video.
The Web is just one of the ways that information can be disseminated over the Internet. The Internet, not the Web, is also used for e-mail, which relies on SMTP, Usenet news groups, instant messaging and FTP. So the Web is just a portion of the Internet, albeit a large portion, but the two terms are not synonymous and should not be confused."""

address = state_union.raw('2006-GWBush.txt')


def stem_text (text):
    """reduces the text to its stems and removes the stop words"""
    tokenized_text = word_tokenize(text)
    #this is a list comp that filters the stopwords from  tokenized text
    stopped_text = [word for word in tokenized_text if word not in stopwords.words('english')] #note english in stopwords
    stemmed_list =[]
    #this give the stem of the word to help “normalize’ text
    ps = PorterStemmer()
    for word in stopped_text:
        x = ps.stem(word)
        stemmed_list.append(x)
    print('text has been stemmed')
    return stemmed_list

from os import path

import nltk
from nltk.corpus import state_union
from nltk.tokenize import PunktSentenceTokenizer

import sys
from termcolor import *
import termcolor

import textblob
from textblob import TextBlob
from textblob.translate import Translator

#Training for then identifying verbs, nouns etc
train_text = state_union.raw("2005-GWBush.txt")
custom_sent_tokenizer = PunktSentenceTokenizer(train_text)

#Color Codes corresponding to Tags for Verbs, Nouns etc
TagCodes = {'CC': 6, 'CD': 1, 'DT': 6, 'EX': 6, 'FW': 6, 'IN': 6, 'JJ': 0, 'JJR': 0, 'JJS': 0, 'LS': 2, 'MD': 2, 'NN': 1, 'NNS': 1, 'NNP': 2, 'NNPS': 2, 'PDT': 6, 'POS': 6, 'PRP': 5, 'PRP$': 5, 'RB': 4, 'RBR': 4, 'RBS': 4, 'RP': 4, 'TO': 7, 'UH': 2, 'VB': 3, 'VBD': 3, 'VBG': 3, 'VBN': 3, 'VBP': 3, 'VBZ': 3, 'WDT': 6, 'WP': 5, 'WP$': 5, 'WRB': 5};

ColorCodes = {0: 'grey', 1: 'red', 2: 'green', 3: 'yellow', 4: 'blue', 5: 'magenta', 6: 'cyan', 7: 'white'}

#Each language is assigned a short code for translation
LanguageCodes = {'afrikaans' : 'af','albanian' : 'sq','arabic' : 'ar','armenian' : 'hy','azerbaijani' : 'az','basque' : 'eu','belarusian' : 'be','bengali' :'bn','bosnian' : 'bs','bulgarian' : 'bg','catalan' : 'ca','cebuano' : 'ceb','chichewa' : 'ny','chinese-simplified' : 'zh-CN','chinese-traditional' : 'zh-TW','croatian' : 'hr','czech' : 'cs','danish' : 'da','dutch' : 'nl','english' : 'en','esperanto' : 'eo','estonian' : 'et','filipino' : 'tl','finnish' : 'fi','french' : 'fr','galician' : 'gl','georgian' : 'ka','german' : 'de','greek' : 'el','gujarati' : 'gu','haitian-creole' : 'ht','hausa' : 'ha','hebrew' : 'iw','hindi' : 'hi','hmong' : 'hmn','hungarian' : 'hu','icelandic' : 'is','igbo' : 'ig','indonesian' : 'id','irish' : 'ga','italian' : 'it','japanese' : 'ja','javanese' : 'jw','kannada' :'kn','kazakh' : 'kk','khmer' : 'km','korean' : 'ko','lao' : 'lo','latin' : 'la','latvian' : 'lv','lithuanian' : 'lt','macedonian' : 'mk','malagasy' : 'mg','malay' : 'ms','malayalam' : 'ml','maltese' : 'mt','maori' : 'mi','marathi' : 'mr','mongolian' :'mn','burmese' : 'my','nepali' : 'ne','norwegian' : 'no','persian' : 'fa','polish' : 'pl','portuguese' : 'pt','punjabi' : 'ma','romanian' : 'ro','russian' : 'ru','serbian' : 'sr','sesotho' : 'st','sinhala' : 'si','slovak' : 'sk','slovenian' :'sl','somali' : 'so','spanish' : 'es','sudanese' : 'su','swahili' : 'sw','swedish' : 'sv','tajik' : 'tg','tamil' : 'ta','telugu' : 'te','thai' : 'th','turkish' : 'tr','ukrainian' : 'uk','urdu' : 'ur','uzbek' : 'uz','vietnamese' : 'vi','welsh' : 'cy','yiddish' : 'yi','yoruba' : 'yo','zulu' : 'zu'}


#Tags corresponding to Verbs, Nouns etc
'''
POS tag list:

#!/usr/bin/env python

import nltk
from nltk.corpus import state_union
from nltk.tokenize import PunktSentenceTokenizer #unsupervised tokenizer


train_text = state_union.raw('2005-GWBush.txt')

#print train_text

test_text = state_union.raw('2006-GWBush.txt')

custom_sent_token = PunktSentenceTokenizer(train_text)

tokenized = custom_sent_token.tokenize(test_text)

#print tokenized
#print type(tokenized)

def chunk():
	try:
		for i in tokenized:
			words = nltk.word_tokenize(i)
			tagged = nltk.pos_tag(words)

			regexp = r"""Chunk: {<RB.?>*<VB.?>*<NNP>+<NN>?} 
								}<VB.?|IN|DT|TO>+{"""

			parser = nltk.RegexpParser(regexp)

import nltk
from nltk.tokenize import PunktSentenceTokenizer
from nltk.corpus import state_union

train_text = state_union.raw('2005-GWBush.txt')
sample_text = state_union.raw('2006-GWBush.txt')

custom_sent_tokeniser = PunktSentenceTokenizer(train_text)
tokenized = custom_sent_tokeniser.tokenize(sample_text)

def process_content():
	try:
		for i in tokenized:
			words = nltk.word_tokenize(i)
			tagged = nltk.pos_tag(words)
			namedEntity = nltk.ne_chunk(tagged, binary=False)
			namedEntity.draw()
	except Exception as e:
		print str(e)

process_content()

def buildhtml(tokenized_sentence, sentence_count):
	html = ""
	starting_div = "<div class=\"panel panel-primary\"> <div class=\"panel-heading\"> Sentence "+ str(sentence_count) +"</div><div class=\"panel-body\">"
	ending_div = "</div></div>"
	html += starting_div
	try:
	    for token in tokenized_sentence:
	    	words = nltk.word_tokenize(token)
	    	tagged = nltk.pos_tag(words)
	    	for word in tagged:
	    		if word[1] in tagdict:
	    			html += "<a href=\"#\" data-toggle=\"tooltip\" title=\""+tagdict[word[1]][0]+"\">"+word[0]+"</a>"
	    	html += ending_div

	    	return html
	except Exception as e:
		print(str(e))

text = state_union.raw("/Users/ponrajuganesh/Desktop/data.txt") 
sent_detector = nltk.data.load('tokenizers/punkt/english.pickle')

tagdict = nltk.data.load("help/tagsets/" + "upenn_tagset" + ".pickle")
count = 0
fulldiv = ""
for sentence in sent_detector.tokenize(text):
	count += 1
	custom_sent_tokenizer = PunktSentenceTokenizer()
	fulldiv += buildhtml(custom_sent_tokenizer.tokenize(sentence), count)

print fulldiv

def getPresFromSpeech(speech_id):
    # 2001-GWBush-1.txt
    words = speech_id.split('.')

    if len(words) > 0:
        single_words = words[0].split('-')
        if len(single_words) > 0:
            for word in single_words:
                if word.isalpha():
                    return word
    return ""

all_words = {}
for speech_id in state_union.fileids():
    text = state_union.raw(speech_id)
    words = word_tokenize(text)
    for word in words:
        if word not in all_words.keys():
            all_words[word] = 1
        else:
            all_words[word] += 1

sent_len = []
word_len = []

pres_list = []
pres_sent_total = {}
pres_word_total = {}
pres_char_total = {}
pres_uniq_word = {}

from nltk.corpus import state_union
from nltk.tokenize import word_tokenize
from nltk.corpus import stopwords

total_word_freq = {}
word_freq_per_speech = {}
word_num_per_speech = {}

total_word_num = 0

en_stopwords = stopwords.words('english')

for fileid in state_union.fileids():
    word_freq_per_speech[fileid] = {}
    word_num = 0
    sample = state_union.raw(fileid)
    words = word_tokenize(sample)
    for word in words:
        lower_word = word.lower()
        if lower_word not in en_stopwords and lower_word.isalpha():
            word_num += 1
            if lower_word not in total_word_freq.keys():
                total_word_freq[lower_word] = 1
            else:
                total_word_freq[lower_word]+=1
            if lower_word not in word_freq_per_speech[fileid].keys():
                word_freq_per_speech[fileid][lower_word] = 1
            else:
                word_freq_per_speech[fileid][lower_word]+=1
    #print fileid, word_num
    word_num_per_speech[fileid] = word_num

    return entity_names

def extract_entities(taggedText):
    '''
    Create map with entity and their counts
    :param taggedText: Parsed text (output of ne chunker) in tree form
    :return: dict of entities and their freq counts
    '''
    entity_names = []
    for tree in taggedText:
        entity_names.extend(extract_entity_names(tree))
    return entity_names


#get year and words for each file
extracted= [(state_union.raw(fileid), int(fileid[:4])) for fileid in state_union.fileids()]
docs, years = zip(*extracted)

#break text down into sentences, tokens
tokens = [nltk.word_tokenize(text) for text in docs]
sents = [nltk.sent_tokenize(text.replace("\n", " ")) for text in docs]
senttokens = [[nltk.word_tokenize(sent) for sent in entry] for entry in sents]

#get counts of unique words and plot over time
unique = [len(set(words)) for words in tokens]
plt.scatter(years, unique)
plt.show()

#get unique/total ratio
ratios = [(float(len(set(words)))/float(len(words))) for words in tokens]
plt.scatter(years, ratios)