繼續學習NLP in Python

#coding=UTF-8
#上面一句解決中文註釋編碼錯誤問題
import nltk
#檢視獲取到的文字語料庫
nltk.corpus.gutenberg.fileids()
#給書名附一個簡短的名字emma
emma=nltk.corpus.gutenberg.words('austen-emma.txt')
#192427
len(emma)
#同樣利用前一章中的concordance
from nltk.corpus import gutenberg
emma = nltk.Text(gutenberg.words('austen-emma.txt'))
#如果不import，語句需要寫全：
#emma=nltk.Text(nltk.corpus.gutenberg.words('austen-emma.txt'))
emma.concordance("surprize")
#每個文字的三個統計量：平均詞長、平均句子長度和本文中每個詞出現的平均次數
for fileid in gutenberg.fileids():
	num_chars = len(gutenberg.raw(fileid))
	num_words = len(gutenberg.words(fileid))
	num_sents = len(gutenberg.sents(fileid))
	num_vocab = len(set([w.lower() for w in gutenberg.words(fileid)]))
	print int(num_chars/num_words), int(num_words/num_sents), int(num_words/num_vocab), fileid