airbob airbob

## gist:26446e65143570f3e6930e3a8d140fc2
gid:skpFHMqbdVWSvGpDRXq7dG

## build.sh
#!/bin/sh
set -eo pipefail
IFS=$'\n\t'

# Constants
NOW=$(date +%s)
BUILD_FILE_NAME="MyApp-${NOW}"
SCHEME="MyApp"
WORKSPACE="MyApp"
PROJECT="MyApp"

## jasoncharleshill.py
# -*- coding: utf-8 -*-

import os
import re
import urllib
from bs4 import BeautifulSoup as Soup

URL_REG = re.compile(r'(https://[^/\\]+)', re.I)
IMG_REG = re.compile(r'<img[^>]*?src=([\'"])([^\1]*?)\1', re.I)

## readme.md

      
              3 files
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                airbob
                / readme.md
            
            
              Last active
              August 29, 2015 13:56
            
              
                python read&processing&write big files 
              
          
    background

Below is input File format(*.txt):


userID
month
date
hour
totalTW
totalQs
result


21535110
05
01
02
3
2
1


21535110
05
01
03
3
2
1


21535110
05
01
06
1
0
0


21535110
05
02
02
1
0
0


## setup_pandas_notebook.sh
#!/bin/sh

setup_brew () {
    if ![-f "/usr/local/bin/brew"]; then
        /usr/bin/ruby -e "$(/usr/bin/curl -fsSL https://raw.github.com/mxcl/homebrew/master/Library/Contributions/install_homebrew.rb)"
    fi
}

setup_ipython () {
    brew install readline

## csv_splitter.py
import os

def split(filehandler, delimiter=',', row_limit=10000,
    output_name_template='output_%s.csv', output_path='.', keep_headers=True):
    """
    Splits a CSV file into multiple pieces.

    A quick bastardization of the Python CSV library.

    Arguments:
	#!/bin/sh
	set -eo pipefail
	IFS=$'\n\t'

	# Constants
	NOW=$(date +%s)
	BUILD_FILE_NAME="MyApp-${NOW}"
	SCHEME="MyApp"
	WORKSPACE="MyApp"
	PROJECT="MyApp"
	# -- coding: utf-8 --

	import os
	import re
	import urllib
	from bs4 import BeautifulSoup as Soup

	URL_REG = re.compile(r'(https://[^/\\]+)', re.I)
	IMG_REG = re.compile(r'<img[^>]?src=([\'"])([^\1]?)\1', re.I)
userID	month	date	hour	totalTW	totalQs	result
21535110	05	01	02	3	2	1
21535110	05	01	03	3	2	1
21535110	05	01	06	1	0	0
21535110	05	02	02	1	0	0
	#!/bin/sh

	setup_brew () {
	if ![-f "/usr/local/bin/brew"]; then
	/usr/bin/ruby -e "$(/usr/bin/curl -fsSL https://raw.github.com/mxcl/homebrew/master/Library/Contributions/install_homebrew.rb)"
	fi
	}

	setup_ipython () {
	brew install readline
	import os

	def split(filehandler, delimiter=',', row_limit=10000,
	output_name_template='output_%s.csv', output_path='.', keep_headers=True):
	"""
	Splits a CSV file into multiple pieces.

	A quick bastardization of the Python CSV library.

	Arguments: