Bohye.Woo
/
bo-graduation
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity
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.
master
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from '1a48ffc4d8'
${ noResults }
bo-graduation/website/tag_comparison.py

314 lines
7.7 KiB
Python
Raw Normal View History Unescape Escape

worked on tag_comparison.py
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
import base64
nltk.download('stopwords')
# infofile = open('faceapp_infos.txt','r')
# infotext = infofile.read()
#open the txt file, read, and tokenize
file = open('faceapp.txt','r')
text = file.read()
text split onto paragraphs
5 years ago
text_list = text.split("\n\n")
worked on tag_comparison.py
5 years ago
#not sure if this works..
x = 1
t_file = open('russia-estonia.txt', 'r')
t_text = t_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
# multi-line string HTML
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");
}
@font-face {
font-family: "SourceCodePro";
src: url("http://bohyewoo.com/webfonts/Source_Code_Pro/SourceCodePro-Regular.ttf");
}
body {
background-color: ghostwhite;
# font-family: Belgika;
# font-weight: 8th;
# letter-spacing: -0.3px;
font-size: 14px;
line-height: 1.2;
}
.tos_wrapper {
width: 50%;
float: left;
}
.t_wrapper {
width: 50%;
float: right;
}
.NNP {
background-color: pink;
}
.VBP {
}
.VBP:hover {
background-color: gold;
}
.NN {
background-color: LightSkyBlue;
}
.NNS {
background-color: Aquamarine;
}
.t_img {
font-family: SourceCodePro;
font-size: 10pt;
float: left;
}
.info {
font-family: SourceCodePro;
font-size: 10pt;
width: 60%;
float: left;
border: 1px solid black;
padding:10px;
margin-bottom: 50px;
}
.t_info {
font-family: SourceCodePro;
font-size: 10pt;
width: 90%;
float: left;
border: 1px solid black;
padding:10px;
margin-bottom: 50px;
}
.paragraph {
font-family: SourceCodePro;
font-weight: regular;
letter-spacing: -0.5px;
width: 70%;
float: right;
}
.t_paragraph {
font-family: SourceCodePro;
font-weight: regular;
letter-spacing: -0.5px;
width: 70%;
float: right;
}
.top_words {
font-family: Belgika;
font-weight: 8th;
font-size: 9pt;
width: 15%;
float: left;
}
.t_top_words {
font-family: Belgika;
font-weight: 8th;
font-size: 9pt;
width: 15%;
float: left;
}
</style>
</head>
<body>
<input type="checkbox" id="myCheck" onclick="myFunction()"> Noun
<p id="text" style="display:none">Checkbox is CHECKED!</p>
<script>
function myFunction() {
// Get the checkbox
var checkBox = document.getElementById("myCheck");
// Get the output text
var text = document.getElementById("text");
// If the checkbox is checked, display the output text
if (checkBox.checked == true){
text.style.display = "block";
} else {
text.style.display = "none";
}
}
</script>
''')
#wrapper
print('<div class ="tos_wrapper">')
#insert an image
# https://upload.wikimedia.org/wikipedia/commons/1/15/Joffe_signing_the_Treaty_of_Tartu.jpg
FaceApp_img_url = base64.b64encode(open('img/faceapp_logo.png', 'rb').read()).decode('utf-8')
FaceApp_image = '<div class="t_img"><h1>FaceApp<img style="width:90%" src="data:img/faceapp_logo.png;base64,{}"></div>'.format(FaceApp_img_url)
print(FaceApp_image)
#info box
print('<div class ="info">')
infotext = [('Service', 'FaceApp'), ('Type', 'Image editing'), ('Initial release', 'December 31, 2016'), ('Type', 'Image editing'), ('source', '<a href="https://www.faceapp.com/terms-en.html">link</a>'), ('Description', 'FaceApp is a mobile application for iOS and Android developed by Russian company Wireless Lab. The app generates highly realistic transformations of human faces in photographs by using neural networks based on artificial intelligence. The app can transform a face to make it smile, look younger, look older, or change gender.')]
for title, info in infotext:
print('<span class="info_{0}"><div class="info_title" style="-webkit-text-decoration-line: underline; text-decoration-line: underline;" >{0}</div><div class="info_content">{1}</div></span><br>'.format(title, info))
print('</div>')
#ToS text
print('<div class ="paragraph">')
text split onto paragraphs
5 years ago
for paragraph in text_list:
tokenized = word_tokenize(paragraph)
tagged = pos_tag(tokenized)
print('<p>')
for word, pos in tagged:
print('<span class="{}">{}</span>'.format(pos, word))
print('</p>')
worked on tag_comparison.py
5 years ago
print('</div>')
#colonial words list
print('<div class="top_words" > <span style="-webkit-text-decoration-line: underline; text-decoration-line: underline;" >colonial words:</span>')
tokens_without_stopwords = nltk.FreqDist(words.lower() for words in tokenized if words.lower() not in all_stopwords)
frequency_word = FreqDist(tokens_without_stopwords)
top_words = tokens_without_stopwords.most_common(20)
for chosen_words, frequency in top_words:
print('<br><span class="chosen_words" >{}({}) </span>'.format(chosen_words, frequency))
print('</div>')
test
5 years ago
#t_wrapper (second wrapper)
worked on tag_comparison.py
5 years ago
print('</div><div class="t_wrapper">')
#insert an image
# https://upload.wikimedia.org/wikipedia/commons/1/15/Joffe_signing_the_Treaty_of_Tartu.jpg
img_url = base64.b64encode(open('img/tartu.jpeg', 'rb').read()).decode('utf-8')
t_image = '<div class="t_img"><h1>Peace Treaty of Tartu<h1><img style="width:90%" src="data:img/tartu.jpeg;base64,{}"></div>'.format(img_url)
print(t_image)
#t_info box
print('<div class ="t_info">')
t_infotext = [('Name of Treaty', 'Peace Treaty of Tartu'), ('Date', 'February 2, 1920'), ('Location', 'Tartu, Estonia'), ('Signed', 'February 2, 1920'), ('Type', 'bilateral peace treaty'), ('source', '<a href="https://en.wikipedia.org/wiki/Treaty_of_Tartu_(Russian–Estonian)">link</a>'), ('Description', 'The Tartu Peace Treaty or Treaty of Tartu is a peace treaty between Estonia and Russian Soviet Federative Socialist Republic signed on 2 February 1920, ending the Estonian War of Independence.')]
for t_title, t_info in t_infotext:
print('<span class="t_info-{0}"><div class="info_t_title" style="-webkit-text-decoration-line: underline; text-decoration-line: underline;" >{0}</div><div class="t_info_content">{1}</div></span><br>'.format(t_title, t_info))
print('</div>')
#ToS text
print('<div class="t_paragraph">')
t_tokenized = word_tokenize(t_text)
t_tagged = pos_tag(t_tokenized)
for t_word, t_pos in t_tagged:
print('<span class="{}">{}</span>'.format(t_pos, t_word))
print('</div>')
#treaty colonial words list
print('<div class="t_top_words" > <span style="-webkit-text-decoration-line: underline; text-decoration-line: underline;" >colonial words:</span>')
t_tokens_without_stopwords = nltk.FreqDist(words.lower() for words in t_tokenized if words.lower() not in all_stopwords)
t_frequency_word = FreqDist(t_tokens_without_stopwords)
t_top_words = t_tokens_without_stopwords.most_common(20)
for t_chosen_words, t_frequency in t_top_words:
print('<br><span class="t_chosen_words" >{}({}) </span>'.format(t_chosen_words, t_frequency))
print('</div>')
print('</div>')
print('''</body></html>''')