estasney

#!/usr/bin/env python

import datetime
import sys
sys.path.append("mysite")

from app_folder import create_app
from app_folder.models import YOUR_MODEL

app = create_app()

estasney

# -*- coding: utf-8 -*-
import itertools
import re
import urlparse
 
import boto
import warc
 
from boto.s3.key import Key
from gzipstream import GzipStreamFile

estasney

from collections import OrderedDict
from operator import itemgetter

class NameData(object):

    def __init__(self, data, name, priority, preprocessor=None):
        self.data = self.structure_data(data)
        self.name_set = self.generate_set(data)
        self.name = name
        self.priority = priority

estasney

# Given a StackOverflow tag, how often does it occur with other tags?
# See example query https://data.stackexchange.com/stackoverflow/query/868423/co-occurrence-of-tags
# Download CSV results

import pandas as pd
import re
from sklearn.feature_extraction.text import CountVectorizer

CSV_PATH = ""
TAG = ""

estasney

from gensim.utils import smart_open
from collections import defaultdict, OrderedDict
import csv
import xml.etree.ElementTree as ET

headers = ['AcceptedAnswerId', 'AnswerCount', 'ClosedDate', 'CommentCount', 'CommunityOwnedDate', 'CreationDate',
 'FavoriteCount', 'Id', 'LastActivityDate', 'LastEditDate', 'LastEditorDisplayName', 'LastEditorUserId', 
 'OwnerDisplayName', 'OwnerUserId', 'ParentId', 'PostTypeId', 'Score', 'Tags', 'Title', 'ViewCount']
 
file_path = ""

estasney

import math
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt

sns.set()

def node_type(x):
    if isinstance(x, str):
        return 2

estasney

{
  "manifest_version": 2,
  "name": "LinkedIn Profile Saver",
  "version": "1.0.0",
  "content_scripts": [{
    "matches": [
      "http://*.linkedin.com/in/*",
      "https://*.linkedin.com/in/*",
      "http://*.linkedin.com/profile/*",
      "https://*.linkedin.com/profile/*"

estasney

from cytoolz import groupby

class WordPair(object):
    
    PREFERRED = 'preferred'
    OTHERS = 'others'
    
    def __init__(self, preferred, others):
        self.preferred = preferred
        if isinstance(others, list):

estasney

import time
import random

class BackOffDecorator(object):

    def __init__(self, max_tries, delay, backoff_rate):
        self.max_tries = max_tries
        self.tries = 0
        self.delay = delay
        self.backoff_rate = backoff_rate

estasney

import pandas as pd
import os

SPREADSHEET_FOLDER = r"C:\Users"  # Which folder are these files located in?
OUTPUT_FILEPATH = r"C:\Users"  # Where should it go?

if not os.path.isdir(SPREADSHEET_FOLDER):
    raise NotADirectoryError
if '.xls' not in OUTPUT_FILEPATH and '.csv' not in OUTPUT_FILEPATH:
    raise Exception("Output path must have ext of .csv, .xls, or .xlsx")