Last active
July 9, 2018 03:45
-
-
Save rockyzhengwu/732e25f0fada7574bb839d42d20fddc7 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import nltk | |
from nltk.tokenize import sent_tokenize,word_tokenize | |
from collections import defaultdict | |
import matplotlib.pyplot as plt | |
import math | |
import numpy as np | |
class BookStat(): | |
def __init__(self, book_path): | |
self.book_path = book_path | |
self.sents = [] | |
self.words = defaultdict(int) | |
self._load_book() | |
self.total_word = sum(self.words.values()) | |
self.word_prob = {k:v/self.total_word for k, v in self.words.items()} | |
def _load_book(self): | |
f = open(self.book_path) | |
self.sents = sent_tokenize(f.read()) | |
for sent in self.sents: | |
words = word_tokenize(sent) | |
for w in words: | |
self.words[w] += + 1 | |
def show_zipf(self): | |
sort_words = sorted(self.words.items(), key=lambda x:x[1], reverse=True) | |
x = [] | |
y = [] | |
count_dict = defaultdict(int) | |
for i, info in enumerate(sort_words): | |
x.append(math.log(i+1)) | |
y.append(math.log(info[1])) | |
count_dict[info[1]] += 1 | |
x = np.array(x) | |
y = np.array(y) | |
s_count = sorted(count_dict.items(), key=lambda x:x[0]) | |
count_num = [item[0] for item in s_count] | |
count_value = [item[1] for item in s_count] | |
plt.plot(x, y) | |
for info in sort_words[:100]: | |
print(info) | |
print(len(self.words)) | |
print(sum(self.words.values())) | |
print(count_num) | |
print(count_value) | |
plt.show() | |
def caculate_sent_entroy(self): | |
entroy_list = [] | |
for sent in self.sents: | |
entroy = 0 | |
sent_words = word_tokenize(sent) | |
for w in sent_words: | |
wp = self.word_prob[w] | |
entroy += -1*wp * math.log(wp) | |
entroy_list.append(entroy) | |
arg_index = np.argsort(entroy_list) | |
plt.figure() | |
plt.hist(entroy_list,bins=len(self.sents)) | |
total_entroy = sum(entroy_list) | |
tmp_entroy = 0.0 | |
counter = 0 | |
for i, index in enumerate(arg_index[::-1]): | |
tmp_entroy += entroy_list[index] | |
print(entroy_list[index]) | |
if tmp_entroy> total_entroy *0.8: | |
print(entroy_list[index]) | |
counter = i | |
print("80% count:", i) | |
break | |
for i in arg_index[len(self.sents)-counter:]: | |
words = word_tokenize(self.sents[i]) | |
print("#"*30+":%f"%(entroy_list[i]), " word count", len(words)) | |
print(self.sents[i]) | |
print("total_sent :", len(self.sents)) | |
print("counter: ", counter) | |
print(counter/len(self.sents)) | |
print("总的熵:", total_entroy) | |
if __name__ == "__main__": | |
book = BookStat("17500.txt.utf-8") | |
book.show_zipf() | |
book.caculate_sent_entroy() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment