ptwobrussell

" Place this file in ~/.vimrc
" Get it with:
" wget --no-check-certificate https://gist.githubusercontent.com/ptwobrussell/05600f8d955be3423ba1/raw/374b960cea9c3cf28cb0757db6136ba4fce3b196/gistfile1.txt -O .vimrc

" When started as "evim", evim.vim will already have done these settings.
if v:progname =~? "evim"
  finish
endif

" Use Vim settings, rather then Vi settings (much better!).

ptwobrussell

BeautifulSoup==3.2.1
GnuPGInterface==0.3.2
JPype1==0.5.5.2
Landscape-Client==13.07.3
PAM==0.4.2
PyYAML==3.11
Twisted-Core==11.1.0
apt-xapian-index==0.44
argparse==1.2.1
boilerpipe==1.2.0.0

ptwobrussell

import json
import pymongo # pip install pymongo
from bson import json_util # Comes with pymongo
import re

# The basis of our query
FROM = "[email protected]" # As opposed to a value like "Coursera <[email protected]>"


client = pymongo.MongoClient()

ptwobrussell

"""
A modification of MTSW2E Example 6-3 (http://bit.ly/1aWYgAv) with the following modifications:

* Extra debugging information is written to sys.stderr to help isolate any problematic content
  that may be encountered.
* A (hopeful) fix to a blasted UnicodeEncodeError in cleanContent() that may be triggered from
  quopri.decodestring attempting to decode an already decoded Unicode value.
* The JSONification in jsonifyMessage now ignores any content that's not text. MIME-encoded content
  such as images, PDFs, and other non-text data that is not useful for textual analysis without 
  significant additional work is now no longer carried forward into the JSON for import into MongoDB.

ptwobrussell

import geojson
import sys

lines = [line.strip().split("\t") for line in open(sys.argv[1]).readlines()]

features = []
for (x, y, _id, text, screen_name, utc) in lines: 
    props = dict(text=text, screen_name=screen_name, utc=utc)

    features.append( geojson.Feature(id=_id, geometry=geojson.Point(coordinates=(x,y)), properties=props) )

ptwobrussell

########################################################################
#
# An example of how to deploy a custom predictive model to yhat
# and "predict" the summary for a news article.
# 
# Input: URL for a web page containing a news article
#
# Output: Summary of the "story" in the web page for the URL
#
# Example usage: $ python summarizer.py <username> <apikey> <url> 

ptwobrussell

# On a remote AWS VM, you'll need to create and save your 
# CSV connections to the the remote VM before executing Example 6
# since you're not using Vagrant (and since we won't be using SSH
# as part of the workshop.)

# Copy/paste your connections (or a large subset of them) into a string value
# that's bounded by triple quotes like the following example (which defines only
# a single contact for brevity.)

csv_as_string = \

ptwobrussell

ptwobrussell

ptwobrussell

# -*- coding: utf-8 -*-

# Studying this script might be helpful in understanding why UnicodeDecode errors
# sometimes happen when trying to capture utf-8 output to files with Python 2 even
# though the output prints to your (utf-8 capable) terminal.

# Note that the first line of this file is called the Byte Order Marker (BOM), which 
# is a directive to tell Python that it should treat this file as utf-8 (i.e. comments and 
# string values may be utf-8)