Dan McKean danlmarmot

## pandas_snippets.py
# Using Jupyter 4.2 and Python 3.5.1

# Firstly, Jupyter notebook stuff
#
# Make the notebook the width of the brower window
from IPython.core.display import HTML
HTML("<style>.container { width:100% !important; }</style>")

#-----
# Now pandas stuffs

## Chrome Gmail Bookmarklet
javascript:(function(){m='http://mail.google.com/mail/?view=cm&fs=1&tf=1&to=&su='+encodeURIComponent(document.title)+'&body='+encodeURIComponent(document.location);w=window.open(m,'addwindow','status=no,toolbar=no,width=575,height=545,resizable=yes');setTimeout(function(){w.focus();}, 250);})();

## simple_pyspark.py
#!/usr/bin/env python

'''
    Small demo of how to get a standalone Python script working in Spark 1.1 through the regular Python interpreter,
    rather than using bin/pyspark <filename.py>.

    Useful for interactive debugging and avoids messing with PYTHONPATH, I used this script to verify my PyCharm IDE
    was correctly configured.

    Note that Spark is installed at ~/bin/spark/current

## Anagram maker
__author__ = 'danlmarmot'

from itertools import permutations
import collections

INPUT_WORD = "deposit"
MIN_ANAGRAM_LEN = 4
WORD_DICT_FILEPATH = '/usr/share/dict/words'


## s3_download_changed_files.py
#!/usr/bin/python
import os
import sys
import logging
import time
import json
from time import mktime

from boto.s3.connection import S3Connection
from boto.exception import S3DataError, S3ResponseError

## file_pattern_s3_upload.sh
#!/bin/bash
#
patternMatches="foo/target/*.jar
bar/target/*.jar
baz/target/*.jar
"

bucket=my-bucketname
objectPath=bucketdir/subdir

## crontab-list.sh
#!/bin/bash
#
# cm-crontab-list
#
# Taken from yukondude's answer at
# http://stackoverflow.com/questions/134906/how-do-i-list-all-cron-jobs-for-all-users

# System-wide crontab file and cron job directory. Change these for your system.
CRONTAB='/etc/crontab'
CRONDIR='/etc/cron.d'

## filehash.py
__author__ = 'danlmarmot'
"""
This Python script measures hash performance, and attempts to answer this question:
'Given a hash function and a block size for reading, which is the fastest hash function and block size?'

There's no warm up, there's no cache/memory/whatever filling, just a simple way to explore performance for
commonly used functions with the timeit library

"""

## N2 - Gadfly GH.ipynb

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                danlmarmot
                / N2 - Gadfly GH.ipynb
            
            
              Created
              January 19, 2014 18:05
            
              
                iPython Notebook to demonstrate Gadfly visualization in Julia
              
          
      Sorry, something went wrong. Reload?
      Sorry, we cannot display this file.
      Sorry, this file is invalid so it cannot be displayed.
      
          Viewer requires iframe.
      
    
## gist:8458094
#!/usr/bin/python
from pymongo import Connection
from collections import defaultdict
import os, sys, time
import pprint
import requests
import urllib
import re

try: import simplejson as json
	# Using Jupyter 4.2 and Python 3.5.1

	# Firstly, Jupyter notebook stuff
	#
	# Make the notebook the width of the brower window
	from IPython.core.display import HTML
	HTML("<style>.container { width:100% !important; }</style>")

	#-----
	# Now pandas stuffs
	#!/usr/bin/env python

	'''
	Small demo of how to get a standalone Python script working in Spark 1.1 through the regular Python interpreter,
	rather than using bin/pyspark <filename.py>.

	Useful for interactive debugging and avoids messing with PYTHONPATH, I used this script to verify my PyCharm IDE
	was correctly configured.

	Note that Spark is installed at ~/bin/spark/current
	__author__ = 'danlmarmot'

	from itertools import permutations
	import collections

	INPUT_WORD = "deposit"
	MIN_ANAGRAM_LEN = 4
	WORD_DICT_FILEPATH = '/usr/share/dict/words'
	#!/usr/bin/python
	import os
	import sys
	import logging
	import time
	import json
	from time import mktime

	from boto.s3.connection import S3Connection
	from boto.exception import S3DataError, S3ResponseError
	#!/bin/bash
	#
	patternMatches="foo/target/*.jar
	bar/target/*.jar
	baz/target/*.jar
	"

	bucket=my-bucketname
	objectPath=bucketdir/subdir
	#!/bin/bash
	#
	# cm-crontab-list
	#
	# Taken from yukondude's answer at
	# http://stackoverflow.com/questions/134906/how-do-i-list-all-cron-jobs-for-all-users

	# System-wide crontab file and cron job directory. Change these for your system.
	CRONTAB='/etc/crontab'
	CRONDIR='/etc/cron.d'
	__author__ = 'danlmarmot'
	"""
	This Python script measures hash performance, and attempts to answer this question:
	'Given a hash function and a block size for reading, which is the fastest hash function and block size?'

	There's no warm up, there's no cache/memory/whatever filling, just a simple way to explore performance for
	commonly used functions with the timeit library

	"""
	#!/usr/bin/python
	from pymongo import Connection
	from collections import defaultdict
	import os, sys, time
	import pprint
	import requests
	import urllib
	import re

	try: import simplejson as json