huyng

### MATPLOTLIBRC FORMAT

# This is a sample matplotlib configuration file - you can find a copy
# of it on your system in
# site-packages/matplotlib/mpl-data/matplotlibrc.  If you edit it
# there, please note that it will be overridden in your next install.
# If you want to keep a permanent local copy that will not be
# over-written, place it in HOME/.matplotlib/matplotlibrc (unix/linux
# like systems) and C:\Documents and Settings\yourname\.matplotlib
# (win32 systems).

andrix

import itertools
from operator import itemgetter

def iunzip(iterable):
    """Iunzip is the same as zip(*iter) but returns iterators, instead of 
    expand the iterator. Mostly used for large sequence"""

    _tmp, iterable = itertools.tee(iterable, 2)
    iters = itertools.tee(iterable, len(_tmp.next()))
    return (itertools.imap(itemgetter(i), it) for i, it in enumerate(iters))

HarryR

#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <libgen.h>
#include <signal.h>

#include <err.h>
#include <assert.h>

#include <zmq.h>

justinkamerman

WRITE-MIME_MULTIPART=./bin/write-mime-multipart

.PHONY: clean

cloud-config.txt: ubuntu-config.txt hadoop-setup.sh
	$(WRITE-MIME_MULTIPART) --output=$@ $^

clean:
	$(RM) cloud-config.txt

pprett

{"error": 42716.2954, "samples": 506, "value": [22.532806324110698], "label": "RM <= 6.94", "type": "split", "children": [{"error": 17317.3210, "samples": 430, "value": [19.93372093023257], "label": "LSTAT <= 14.40", "type": "split", "children": [{"error": 6632.2175, "samples": 255, "value": [23.349803921568636], "label": "DIS <= 1.38", "type": "split", "children": [{"error": 390.7280, "samples": 5, "value": [45.58], "label": "CRIM <= 10.59", "type": "split", "children": [{"error": 0.0000, "samples": 4, "value": [50.0], "label": "Leaf - 4", "type": "leaf"}, {"error": 0.0000, "samples": 1, "value": [27.9], "label": "Leaf - 5", "type": "leaf"}]}, {"error": 3721.1632, "samples": 250, "value": [22.90520000000001], "label": "RM <= 6.54", "type": "split", "children": [{"error": 1636.0675, "samples": 195, "value": [21.629743589743576], "label": "LSTAT <= 7.57", "type": "split", "children": [{"error": 129.6307, "samples": 43, "value": [23.969767441860473], "label": "TAX <= 222.50", "type": "split", "children": [{"err

MLnick

import sys

from pyspark.context import SparkContext
from numpy import array, random as np_random
from sklearn import linear_model as lm
from sklearn.base import copy

N = 10000   # Number of data points
D = 10      # Numer of dimensions
ITERATIONS = 5

k1xme

class Solution{
  public static boolean isPermutation(String s1, String s2){
    if(s1 === null || s2 == null ) return false;
    if(s1.length() != s2.length()) return false;
    if(s1.length() == 0) return true; // If s1.length() == s2.length() and s1 is a empty string, s2 is the permutation of s1.
    
    char[] sc1 = s1.toCharArray();
    char[] sc2 = s2.toCharArray();
    
    HashMap<String, int> temp = new HashMap<String, boolean>();

vene

# Author: Vlad Niculae <vlad@vene.ro>
# Licence: BSD

from __future__ import division, print_function
import numpy as np
from sklearn.utils import check_random_state


class SquaredLoss(object):
    def loss(self, y, pred):

vasanthk

System Design Cheatsheet

Picking the right architecture = Picking the right battles + Managing trade-offs

Basic Steps

1. Clarify and agree on the scope of the system

• User cases (description of sequences of events that, taken together, lead to a system doing something useful)
  • Who is going to use it?
  • How are they going to use it?

yaroslavvb

"""Benchmark tensorflow distributed by adding vector of ones on worker2
to variable on worker1 as fast as possible.

On 2014 macbook, TensorFlow 0.10 this shows

Local rate:       2175.28 MB per second
Distributed rate: 107.13 MB per second

"""