#!/usr/bin/env python
# -*- coding: utf-8 -*-
from nltk.book import *

# 查詢特定詞語上下文
text1.concordance("monstrous")

# 相關詞查詢
text1.similar("monstrous")

# 查詢多個詞語的共同上下文
text2.common_contexts(["monstrous", "very"])

# 畫出詞語的離散圖
text4.dispersion_plot(["citizens", "democracy", "freedom", "duties", "America"])

# 產生隨機文字
text3.generate()
Traceback (most recent call last):
  File "E:/nlp/eg1.py", line 25, in <module>
    text3.generate()
TypeError: generate() missing 1 required positional argument: 'words'

# 單詞數量 識別符號總數
print(len(text3))

# 詞彙的種類及數量 用集合set顯示
print(sorted(set(text3)))
print(len(set(text3)))

# 測量平均每類詞語被使用的次數
from __future__ import division #本命令必須放在檔案的開始之初
print(len(text3)/len(set(text3)))

# 統計特定單詞在文字中出現的次數，並計算其佔比
print(text3.count("smote"))
print(100*text4.count('a')/len(text4))

# # 詞的頻率分佈
fdist1 = FreqDist(text1)
# # 輸出總的詞數
print(fdist1)
# In Python 3 dict.keys() returns an iteratable but not indexable object.
vac1 = list(fdist1.keys())
# # 輸出詞數最多的前五十個詞
print(vac1[:50])
# # 輸出whale的次數
print(fdist1["whale"])
# # 輸出前五十個詞的累積頻率圖

fdist1.plot(50)

# 查詢長度超過15個字元的詞
V = set(text1)
long_words = [w for w in V if len(w)>15]
print(sorted(long_words))

# 查詢長度超過7的詞且頻率超過7
fdist5 = FreqDist(text5)
print(sorted([ w for w in set(text5) if len(w)>7 and fdist5[w]>7]))

# 雙連詞的使用
from nltk import bigrams
# # 查了一下nltk官網上的函式說明，要加list()函式，結果才是書上的情況
print(list(bigrams(['more', 'is', 'said', 'than', 'done'])))

# 文字中常用的連線詞
print(text4.collocations())

print([len(w) for w in text1])
fdist = FreqDist([len(w) for w in text1])
print(fdist)
print(fdist.keys())
print(fdist.items())
print(fdist.max())
print(fdist[3])
print(fdist.freq(3))

print(sorted([w for w in set(text1) if w.endswith('ableness')]))

print(babelize_shell())