jonathana

import sys, os, glob
from datetime import datetime

sys.path.append(os.environ.get("MAHOUT_CORE"))
for jar in glob.glob(os.environ.get("MAHOUT_JAR_DIR") + "/*.jar"):
	sys.path.append(jar)
	
from org.apache.mahout.common import RandomUtils
from org.apache.mahout.cf.taste.common import TasteException
from org.apache.mahout.cf.taste.eval import *

bnyeggen

#redundancy is the max number of survivable failures, so eg 1 for RAID5
#mtbf_array is an array of either actual mean-time-between-failures, or a nested RAID array

# RAID([100]*7,2) #7 disk RAID 6
# RAID([RAID([100]*3,1),RAID([1000]*3,1)],0) # RAID 50, 2 arrays of 3
# RAID([100,100,50,50],1) #RAID 5 with varying reliabilities

from random import random

class RAID(object):

bnyeggen

from multiprocessing import Pool
from functools import partial

def _pickle_method(method):
	func_name = method.im_func.__name__
	obj = method.im_self
	cls = method.im_class
	if func_name.startswith('__') and not func_name.endswith('__'): #deal with mangled names
		cls_name = cls.__name__.lstrip('_')
		func_name = '_' + cls_name + func_name

kachok

import urllib
import re

import time 

 
data = urllib.urlopen('http://bitly.measuredvoice.com/bitly_archive/?C=M;O=D').read()    
#print data

#datafiles name pattern - usagov_bitly_data2011-07-29-1311919454

xim

import sys

import numpy
from nltk.cluster import KMeansClusterer, GAAClusterer, euclidean_distance
import nltk.corpus
from nltk import decorators
import nltk.stem

stemmer_func = nltk.stem.EnglishStemmer().stem
stopwords = set(nltk.corpus.stopwords.words('english'))

paulmwatson

# Description: Consume a DataSift stream and save Twitter interactions to a Google Fusion Table
# Author: Paul M. Watson <paul.watson@storyful.com>
# Date: 2011/11/28
# Usage: 
  # ruby ds_to_gft.rb <DataSift stream id hash>
  # config.yml should contain;
  # datasift:
  #   username: datasift username
  #   api_key: datasift api key
  # googlefusiontables:

steipete

#include <sys/xattr.h>

/// Set a flag that the files shouldn't be backuped to iCloud.
+ (void)addSkipBackupAttributeToFile:(NSString *)filePath {
    u_int8_t b = 1;
    setxattr([filePath fileSystemRepresentation], "com.apple.MobileBackup", &b, 1, 0, 0);
}

/// Returns the legacy storage path, used when the com.apple.MobileBackup file attribute is not available.
+ (NSString *)legacyStoragePath {

aquarius

//
//  MNDocumentConflictResolutionViewController.h
//  MindNodeTouch
//
//  Created by Markus Müller on 15.12.11.
//  Copyright (c) 2011 __MyCompanyName__. All rights reserved.
//

#import <UIKit/UIKit.h>
@class MNDocumentReference;

michaelaguiar

var donutVal = 85;
    
    
    var donutFull = 100 - donutVal;
    var d3_category_socialmedia = ["#0054a6", "#dbdbdb"];
    
    
    if(donutVal < 50) {
    	donutVal = -donutVal;
    	donutFull = -donutFull;

chrishamant

#!/usr/bin/env python
"""Split large file into multiple pieces for upload to S3.

S3 only supports 5Gb files for uploading directly, so for larger CloudBioLinux
box images we need to use boto's multipart file support.

This parallelizes the task over available cores using multiprocessing.

Usage:
  s3_multipart_upload.py <file_to_transfer> <bucket_name> [<s3_key_name>]