Kristen Sheppard kshepp

## Scraping Twitter Statuses
import sys
import string
from twython import Twython

twitter = Twython('Insert Consumer Key Here',
'Insert Consumer Secret Key',oauth_version=2)
Access_token = twitter.obtain_access_token()
t = Twython('Insert Consumer Key', access_token=Access_token)

user_timeline = t.search(q='@puremichigan', count=20, include_rts=1)

## Token_Words.py
from __future__ import division
import nltk
import re
import pprint
from nltk import word_tokenize
from nltk.tokenize import RegexpTokenizer
import numpy as np


tokenizer = RegexpTokenizer(r'\w+') #this is important because it takes out the punctuation that Python can't read

## Scraping_Twitter_2
import sys
import string
from twython import Twython

twitter = Twython('Insert Consumer Key Here',
'Insert Consumer Secret Key',oauth_version=2)
Access_token = twitter.obtain_access_token()
t = Twython('Insert Consumer Key', access_token=Access_token)

#MAKE THE QUERY TO TWITTER TO PULL THE DATA

## nltk_parts_of_speech.py
from __future__ import division
import nltk, re
from nltk import FreqDist
from nltk import word_tokenize
from nltk.tokenize import RegexpTokenizer
from nltk.corpus import brown

tokenizer = RegexpTokenizer(r'\w+') # Takes out the punctuation that Python can't read
f= open('Conservative.txt').read().decode('utf-8') # open the file
text = word_tokenize(f)

## stanford-ner
java -mx1000m -jar stanford-ner.jar

## stanford-postagger
java -mx1000m -jar stanford-postagger.jar

## running_brat
python standalone.py

## repeatable_content.html
<!-- This loads of all of files that you call below from your 'static' folder -->
{% load staticfiles %}
<!--The static folder consists of your bootstrap files (.css, .js, fonts, etc)-->
<!--When you load the static folders is calls all those folders in the static files without having to code each one in individually-->

<html>
  <head>
    <!--This is the meta information which is good for SEO-->
    {% block head-meta %}
  	<meta charset="utf-8">

## extend_your_repeatable_content.html
{% extends "NAME OF YOUR PROJECT/repeatable_content.html" %}

## title.html
<!--Extend your file up here-->

{% block head-title %}
    Your title
{% endblock %}

<!--insert your body content code down here-->
	import sys
	import string
	from twython import Twython

	twitter = Twython('Insert Consumer Key Here',
	'Insert Consumer Secret Key',oauth_version=2)
	Access_token = twitter.obtain_access_token()
	t = Twython('Insert Consumer Key', access_token=Access_token)

	user_timeline = t.search(q='@puremichigan', count=20, include_rts=1)
	from __future__ import division
	import nltk
	import re
	import pprint
	from nltk import word_tokenize
	from nltk.tokenize import RegexpTokenizer
	import numpy as np


	tokenizer = RegexpTokenizer(r'\w+') #this is important because it takes out the punctuation that Python can't read
	from __future__ import division
	import nltk, re
	from nltk import FreqDist
	from nltk import word_tokenize
	from nltk.tokenize import RegexpTokenizer
	from nltk.corpus import brown

	tokenizer = RegexpTokenizer(r'\w+') # Takes out the punctuation that Python can't read
	f= open('Conservative.txt').read().decode('utf-8') # open the file
	text = word_tokenize(f)
	<!-- This loads of all of files that you call below from your 'static' folder -->
	{% load staticfiles %}
	<!--The static folder consists of your bootstrap files (.css, .js, fonts, etc)-->
	<!--When you load the static folders is calls all those folders in the static files without having to code each one in individually-->

	<html>
	<head>
	<!--This is the meta information which is good for SEO-->
	{% block head-meta %}
	<meta charset="utf-8">
	<!--Extend your file up here-->

	{% block head-title %}
	Your title
	{% endblock %}

	<!--insert your body content code down here-->