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).

ChrisWills

# GNU Screen - main configuration file 
# All other .screenrc files will source this file to inherit settings.
# Author: Christian Wills - [email protected]

# Allow bold colors - necessary for some reason
attrcolor b ".I"

# Tell screen how to set colors. AB = background, AF=foreground
termcapinfo xterm 'Co#256:AB=\E[48;5;%dm:AF=\E[38;5;%dm'

alexalemi

import math
class Welford(object):
    """ Implements Welford's algorithm for computing a running mean
    and standard deviation as described at: 
        http://www.johndcook.com/standard_deviation.html

    can take single values or iterables

    Properties:
        mean    - returns the mean

zhannes

# first, fetch the latest refs for all branches. And be sure we have latest master, etc

git checkout master
git fetch 

# If any changes from remote, catch our local version up

git rebase origin/master

# could also be done as

tonicebrian

# =============
# Introduction
# =============
# I've been doing some data mining lately and specially looking into `Gradient
# Boosting Trees <http://en.wikipedia.org/wiki/Gradient_boosting>`_ since it is
# claimed that this is one of the techniques with best performance out of the
# box.  In order to have a better understanding of the technique I've reproduced
# the example of section *10.14.1 California Housing* in the book `The Elements of Statistical Learning <http://www-stat.stanford.edu/~tibs/ElemStatLearn/>`_.
# Each point of this dataset represents the house value of a property with some
# attributes of that house. You can get the data and the description of those

mattbaggott

# Copyright 2012 Felix Schönbrodt
# All rights reserved.
#
# FreeBSD License
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are
# met:
#
# 1. Redistributions of source code must retain the above copyright

mattbaggott

##
## Example code for time-to-event analysis in R
## [email protected]
## Dec 28, 2012
##
## joineR package: analyzing longitudinal data where the response
## from each person is a time-sequence of repeated measurements 
## and we are interested in a possibly censored time-to-event outcome
##
## example: repeated ad viewings leading to a sale

mattbaggott

#
# Functions to make ggplot KM survivor curves made with survfit() in library(survival)
#
# code written by Ramon Saccilotto
# and included in his ggplot2 tutorial
# 2010-12-08

# define custom function to create a survival data.frame
createSurvivalFrame <- function(f.survfit){
  # initialise frame variable

mattbaggott

#
# PREDICTING LONG TERM CUSTOMER VALUE WITH BTYD PACKAGE
# Pareto/NBD (negative binomial distribution) modeling of 
# repeat-buying behavior in a noncontractual setting
#
# Matthew Baggott, [email protected]
#
# Accompanying slides at:
# http://www.slideshare.net/mattbagg/baggott-predict-customerinrpart1#
#

inkhorn

library(stringr)
library(plyr)
library(tm)
library(tm.plugin.mail)
library(SnowballC)
library(topicmodels)

# At this point, the python script should have been run, 
# creating about 126 thousand txt files.  I was very much afraid
# to import that many txt files into the tm package in R (my computer only