upepo

기사 List up

12/13

NIPS2013

• 이번 NIPS가 성공적이었나 봅니다.
• 13 NIPS papers that caught our eye
• NIPS 2013: Interesting looking papers
• A good NIPS!

upepo

upepo

Data Wrangling (데이터 전처리)

Text Processing

데이터마이닝에 필요한 텍스느 전처리 기술 소개. 리눅스 환경에서 bash와 python을 이용하여 텍스트 데이터를 필요한 형태로 처리하는데 중점을 둔다.

upepo

2014

• Anscombe's quartet

  

• A modern guide to getting started with Data Science and Python

  • numpy -> pandas

upepo

### 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 overwritten in your next install.
# If you want to keep a permanent local copy that will not be
# overwritten, place it in HOME/.matplotlib/matplotlibrc (unix/linux
# like systems) and C:\Documents and Settings\yourname\.matplotlib
# (win32 systems).

upepo

hive memo 

String functions in hive 
- http://www.folkstalk.com/2011/11/string-functions-in-hive.html 

upepo

Terms

• AOV = total sales revenue / total number of sales

  • total sales revenue
  • total number of sales
  • http://www.inc.com/jeff-haden/is-there-a-value-to-average-order-value-aov-wed.html
  • http://www.funnelenvy.com/blog/2014/04/04/3-optimization-tips-increasing-average-order-value/

• ETC

  • risk - 측정이 가능한 경우

upepo

2015

2015/01/13

• The Internet of Things has four big data problems : 데이터가 파편화. 데이터가 많지만 한회사가 전체를 가지고 분석하기는 힘들걸? 그래서 inference도 더 필요하고, 데이터가지고 아전인수격의 결론도 많이 낼거다. (센싱데이터의 거래소가 생길까?...)
  1. Nobody will wear 50 devices

upepo

#!/usr/bin/env python 

import sys 
import random
import argparse

parser = argparse.ArgumentParser(description='')
parser.add_argument('--ratio','-r', type=float, nargs='?'
                           ,required=True
                           ,help='ratio for random sampling')

upepo

{
"IAB1": "Arts & Entertainment",
"IAB1-1": "Books & Literature",
"IAB1-2": "Celebrity Fan/Gossip",
"IAB1-3": "Fine Art",
"IAB1-4": "Humor",
"IAB1-5": "Movies",
"IAB1-6": "Music",
"IAB1-7": "Television",
"IAB2": "Automotive",