greeness

from datetime import datetime
import numpy as np

age_ranges = ['13-24', '25-35', '36-52', '53-64']
device_options = ['Phone', 'Tablet']
platform_options = ['a', 'i']

def weighted_choice(weights):
    totals = np.cumsum(weights)
    norm = totals[-1]

greeness

import json
from datetime import datetime
from copy import deepcopy
from random import random

def append_features_from_user_block(user_block, user_row):
    user_row["num_turns"] = len(user_block)
    user_row["min_balance"] = min([x["balance"] for x in user_block])
    user_row["max_balance"] = max([x["balance"] for x in user_block])
    user_row["min_level"] = min([x["level"] for x in user_block])

greeness

http://users.ics.aalto.fi/ella/publications/randproj_kdd.pdf

greeness

import json
from sys import stdout
from random import choice, seed, shuffle
from copy import deepcopy

basic_shapes = [
    [(0,0), (1,0), (2,0)], 
    [(0,0), (0,1), (0,2)],
    [(0,0), (-1,1), (-2,2)],
    [(0,0), (-1,0), (-2,0)],

greeness

[Python Scientific Lecture Notes]: (http://scipy-lectures.github.io/index.html)

greeness

% Exploiting feature covariance in high-dimensional online learning
% http://videolectures.net/aistats2010_ma_efcih/
% http://sysnet.ucsd.edu/projects/url/

function [err,mu,sigma,mem] = cw(X,Y,params)
% X is k features by N instances
% Y is 1 label in {-1,1} by N instances
% params is struct containing options

% err: cumulative mistakes after each example

greeness

# launch an ec2 instance with lucid (ubuntu 10.04) e.g. ami-ad36fbc4
# ssh to the machine

################################################################
# install java
# https://ccp.cloudera.com/display/CDHDOC/Java+Development+Kit+Installation
# RELEASE=lucid, which you can find by running lsb_release -c.
################################################################

$ sudo add-apt-repository "deb http://archive.canonical.com/ lucid partner"

greeness

dumbo start demo_dumbo.py -hadoop /usr/lib/hadoop -input shares -output video_demos -outputformat text -files hdfs://ec2-xxx-xx-xx-xx.compute-1.amazonaws.com:8020/user/ubuntu/users/part-m-00000

### piece of code in demo_dumbo.py
for line in file('part-m-00000'):
    print line

# ----------------
dumbo start demo_dumbo.py -hadoop /usr/lib/hadoop -input shares -output video_demos -outputformat text -files hdfs://ec2-xxx-xx-xx-xx.compute-1.amazonaws.com:8020/user/ubuntu/users

greeness

http://mrtopf.de/blog/en/a-small-introduction-to-python-eggs/

sudo apt-get install python-setuptools

python setup.py bdist_egg

greeness

sudo apt-get install gfortran libblas-dev liblapack-dev

cd scipy-0.10.0
python setupegg.py bdist_egg

# wait about 5 minutes on my machine