johnb30

import os
from boto.s3.connection import S3Connection

conn = S3Connection('<aws access key>', '<aws secret key>')

mybucket = conn.get_bucket('oeda')

# Need to modify this line to make sure the directory is correct
directory = 'phox/'

johnb30

johnb30

johnb30

#!/bin/bash
for file in $1*
do
    genhash=`md5 "$file" | tail -c 33`
    if grep -q "$genhash" "$2"; then
        echo Found hash for "$file"
    else
        echo Did not find hash for "$file"
    fi
done

johnb30

johnb30

from path import path
import pandas as pd

unique_actors = dict()
lengths = list()
for in_file in path.getcwd().files('*.reduced.txt'):
    data = open(in_file, 'r')
    print "%s data read in...subsetting" % (in_file)
    for line in data:
        line = line.replace('\n', '')

johnb30

from path import path
import pandas as pd

allActors = ['AFG', 'ALA', 'ALB', 'DZA', 'ASM', 'AND', 'AGO', 'AIA', 'ATG', 
            'ARG', 'ARM', 'ABW', 'AUS', 'AUT', 'AZE', 'BHS', 'BHR', 'BGD', 
            'BRB', 'BLR', 'BEL', 'BLZ', 'BEN', 'BMU', 'BTN', 'BOL', 'BIH', 
            'BWA', 'BRA', 'VGB', 'BRN', 'BGR', 'BFA', 'BDI', 'KHM', 'CMR',
            'CAN', 'CPV', 'CYM', 'CAF', 'TCD', 'CHL', 'CHN', 'COL', 'COM', 
            'COD', 'COG', 'COK', 'CRI', 'CIV', 'HRV', 'CUB', 'CYP', 'CZE', 
            'DNK', 'DJI', 'DMA', 'DOM', 'TMP', 'ECU', 'EGY', 'SLV', 'GNQ', 

johnb30

{
 "metadata": {
  "name": "Scraping Tutorial"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {

johnb30

import numpy as np
from joblib import Parallel, delayed

def subset(file):
    dataOut = []
    data = open(file, 'r')
    data.readline()
    for line in data:
        splitLine = line.split('\t')
        if splitLine[3] == '57':

johnb30

from __future__ import division
import numpy as np
import pandas as pd
import random

def sample(data):
    sample = [random.choice(data) for _ in xrange(len(data))]
    return sample

def bootstrap_t_test(treatment, control, nboot = 1000, direction = "less"):