kaja47

import breeze.linalg._
import breeze.stats
import breeze.numerics._

val dataFile = new File(???)
val userItems: Array[SparseVector[Double]] = loaderUserItemsWithRatings(dataFile, """[ ,:]""".r)
val itemUsers: Array[SparseVector[Double]] = transpose(userItems) map { vec => normalize(vec, 2) }

// weights
val N = DenseVector.fill[Double](itemIndex.size)(userIndex.size) // vector where total numbers of users is repeated

kaja47

import breeze._
import breeze.linalg._
import breeze.numerics._
import java.awt.image.BufferedImage
import javax.imageio.ImageIO

val f = ???
val img = javax.imageio.ImageIO.read(new File(f))
val gray = new BufferedImage(img.getWidth, img.getHeight, BufferedImage.TYPE_BYTE_GRAY)
val g = gray.createGraphics()

kaja47

// min-hash

val fs: Vector[Int => Int] // hash funkce

items map { it => fs map { f => f(it) } } fold (vectorPairwise(min), initialValue = Vector.fill(infinity))



// HyperLogLog

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):

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 {

michaelaguiar

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

darkseed

-- This is a Hive program. Hive is an SQL-like language that compiles
-- into Hadoop Map/Reduce jobs. It's very popular among analysts at
-- Facebook, because it allows them to query enormous Hadoop data
-- stores using a language much like SQL.

-- Our logs are stored on the Hadoop Distributed File System, in the
-- directory /logs/randomhacks.net/access.  They're ordinary Apache
-- logs in *.gz format.
--
-- We want to pretend that these gzipped log files are a database table,

darkseed

-- This is a Hive program. Hive is an SQL-like language that compiles
-- into Hadoop Map/Reduce jobs. It's very popular among analysts at
-- Facebook, because it allows them to query enormous Hadoop data
-- stores using a language much like SQL.

-- Our logs are stored on the Hadoop Distributed File System, in the
-- directory /logs/randomhacks.net/access.  They're ordinary Apache
-- logs in *.gz format.
--
-- We want to pretend that these gzipped log files are a database table,

NorthIsUp

"""
realertime.lib.spawn
~~~~~~~~~~~~~~~~~~~~

:author: Adam Hitchcock
:copyright: (c) 2012 DISQUS.
:license: Apache License 2.0, see LICENSE for more details.
"""

from __future__ import absolute_import

stucchio

from pylab import *
from numpy.random import dirichlet, rand, binomial, uniform, normal

def _unit_weight(dim):
    return ones(dim) / float(dim)

ONE_FRAC = 0.5
SQRT_TWO_INV = 1.0 / sqrt(2.0)
def _feature_vec(dim, method="bernoulli"):
    if method == "bernoulli":