You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
179 lines
3.5 KiB
Python
179 lines
3.5 KiB
Python
5 years ago
|
from __future__ import division
|
||
|
|
import glob
|
||
|
|
from nltk import *
|
||
|
|
import re
|
||
|
|
|
||
|
|
|
||
|
|
import nltk
|
||
|
|
import codecs
|
||
|
|
from nltk import sent_tokenize, word_tokenize, pos_tag
|
||
|
|
from nltk.probability import FreqDist
|
||
|
|
from nltk.corpus import stopwords
|
||
|
|
nltk.download('stopwords')
|
||
|
|
|
||
|
|
|
||
|
|
#open the txt file, read, and tokenize
|
||
|
|
file = open('faceapp.txt','r')
|
||
|
|
text = file.read()
|
||
|
|
|
||
|
|
#stopwords
|
||
|
|
default_stopwords = set(stopwords.words('english'))
|
||
|
|
custom_stopwords = set(codecs.open('stopwords.txt', 'r').read().splitlines())
|
||
|
|
all_stopwords = default_stopwords | custom_stopwords
|
||
|
|
|
||
|
|
print('''<!DOCTYPE html>
|
||
|
|
<html>
|
||
|
|
<head>
|
||
|
|
<meta charset="utf-8">
|
||
|
|
<title></title>
|
||
|
|
<style>
|
||
|
|
|
||
|
|
@font-face {
|
||
|
|
font-family: "Belgika";
|
||
|
|
src: url("http://bohyewoo.com/webfonts/belgika/belgika-40th-webfont.eot");
|
||
|
|
src: url("http://bohyewoo.com/webfonts/belgika/belgika-40th-webfont.woff") format("woff"),
|
||
|
|
url("http://bohyewoo.com/webfonts/belgika/belgika-40th-webfont.svg#filename") format("svg");
|
||
|
|
}
|
||
|
|
|
||
|
|
@font-face {
|
||
|
|
font-family: "Belgika";
|
||
|
|
src: url("http://bohyewoo.com/webfonts/belgika/belgika-16th-webfont.eot");
|
||
|
|
src: url("http://bohyewoo.com/webfonts/belgika/belgika-16th-webfont.woff") format("woff"),
|
||
|
|
url("http://bohyewoo.com/webfonts/belgika/belgika-16th-webfont.svg#filename") format("svg");
|
||
|
|
}
|
||
|
|
|
||
|
|
@font-face {
|
||
|
|
font-family: "Belgika";
|
||
|
|
src: url("http://bohyewoo.com/webfonts/belgika/belgika-8th-webfont.eot");
|
||
|
|
src: url("http://bohyewoo.com/webfonts/belgika/belgika-8th-webfont.woff") format("woff"),
|
||
|
|
url("http://bohyewoo.com/webfonts/belgika/belgika-8th-webfont.svg#filename") format("svg");
|
||
|
|
}
|
||
|
|
|
||
|
|
body {
|
||
|
|
font-family: helvetica;
|
||
|
|
font-weight: regular;
|
||
|
|
letter-spacing: 0.5px;
|
||
|
|
font-size: 20px;
|
||
|
|
line-height: 1.2;
|
||
|
|
|
||
|
|
}
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
.NNP {
|
||
|
|
background-color: pink;
|
||
|
|
}
|
||
|
|
|
||
|
|
.VBP {
|
||
|
|
background-color: gold;
|
||
|
|
}
|
||
|
|
|
||
|
|
.NN {
|
||
|
|
background-color: LightSkyBlue;
|
||
|
|
}
|
||
|
|
|
||
|
|
.NNS {
|
||
|
|
background-color: Aquamarine;
|
||
|
|
}
|
||
|
|
|
||
|
|
.paragraph {
|
||
|
|
width: 70%;
|
||
|
|
float: right;
|
||
|
|
}
|
||
|
|
|
||
|
|
.top_words {
|
||
|
|
font-size: 9pt;
|
||
|
|
width: 25%;
|
||
|
|
float: left;
|
||
|
|
}
|
||
|
|
|
||
|
|
</style>
|
||
|
|
</head>
|
||
|
|
<body>''')
|
||
|
|
|
||
|
|
|
||
|
|
# my stopwords are common words I don't want to count, like "a", "an", "the".
|
||
|
|
|
||
|
|
print('<div class ="paragraph">')
|
||
|
|
for sentence in sent_tokenize(text):
|
||
|
|
print('<span>')
|
||
|
|
|
||
|
|
tokenized = word_tokenize(sentence)
|
||
|
|
tagged = pos_tag(tokenized)
|
||
|
|
|
||
|
|
# for HTML
|
||
|
|
for word, pos in tagged:
|
||
|
|
print('<span class="{}">{}</span>'.format(pos, word))
|
||
|
|
|
||
|
|
print('</span>')
|
||
|
|
print('</div>')
|
||
|
|
|
||
|
|
# filtering stopwords
|
||
|
|
tokens_without_stopwords = nltk.FreqDist(words.lower() for words in tokenized if words.lower() not in all_stopwords)
|
||
|
|
print(tokens_without_stopwords)
|
||
|
|
|
||
|
|
# for read_whole_text in tokens_without_stopwords:
|
||
|
|
# whole_text_tokenized =
|
||
|
|
# print(whole_text_tokenized)
|
||
|
|
|
||
|
|
# #filtered words in sentence
|
||
|
|
# filtered_sentence = (" ").join(tokens_without_stopwords)
|
||
|
|
# print(filtered_sentence)
|
||
|
|
|
||
|
|
print('<div class="top_words"> colonial words:')
|
||
|
|
|
||
|
|
frequency_word = FreqDist(tokens_without_stopwords)
|
||
|
|
top_words = tokens_without_stopwords.most_common(10)
|
||
|
|
|
||
|
|
for chosen_words, frequency in top_words:
|
||
|
|
print('<br><span class="chosen_words">{}({}) </span>'.format(chosen_words, frequency))
|
||
|
|
|
||
|
|
|
||
|
|
print('''</div></body></html>''')
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
# for new_file in tokens_without_stopwords:
|
||
|
|
# appendFile = open('tokenized_words.txt', 'a')
|
||
|
|
# appendFile.write(" " + new_file)
|
||
|
|
# appendFile.close()
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
# #shows only stopwords
|
||
|
|
# processed_word_list = []
|
||
|
|
|
||
|
|
# for word in tokenized:
|
||
|
|
# # print(word)
|
||
|
|
# if word not in all_stopwords:
|
||
|
|
# processed_word_list.append('*')
|
||
|
|
# else:
|
||
|
|
# processed_word_list.append(word)
|
||
|
|
# print(processed_word_list)
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
# # # result putting in a graph
|
||
|
|
# top_words_plot = frequency_word.plot(10)
|
||
|
|
# print(top_words_plot)
|