Mia datalove

## kaggle.aquire.scores.20140611
library(XML)
library(ggplot2)

url  <- "http://www.kaggle.com/c/acquire-valued-shoppers-challenge/leaderboard"
tree <- htmlTreeParse(url)
tbl  <- readHTMLTable(pagetree, stringsAsFactors = FALSE)[[1]]

colnames(tbl) <- gsub("[^a-zA-Z0-9#]","", colnames(tbl))
tbl$Score     <- as.numeric(tbl$Score)

## odds.p.from.ci
# calculation as per:
# http://www.bmj.com/content/343/bmj.d2304

get_odds_p <- function(est, cil, ciu) {
  se <- (log(ciu) - log(cil))/(2*1.96)
  z  <- abs(log(est)/se)
  p  <- exp(-0.717*z - 0.416*z^2)
  p
}

## evaluate_a_string.r
rm(list=ls())

rcode <- "x <- 1+1; y <- 2+2"

# running `eval` evaluates `rcode` into the parent environment
eval(parse(text = rcode))

print(x)
print(y)

## terr_create_spk_to_deploy.r
# Use autodetected proxy settings
setInternet2(TRUE)

# Get the SpotfireSPK package from the Spotfire Stats Server
install.packages("SpotfireSPK", repos = "http://MySpotfireServer:8080/SplusServer/update/TERR")

# Get a package you want to deploy from CRAN
install.packages("nortest", repos = "http://cran.us.r-project.org")

# Create a Debian Control File

## terr_RinR.r

# Download: http://tap.tibco.com/ -> "Samples" tab -> RinR -> "Try Now" button
# Docs:     http://docs.tibco.com/pub/enterprise-runtime-for-R/2.5.0/doc/html/RinR/RinR-package.html

########################################
# Setup
########################################

library(RinR)
library(Sdatasets)

## devtols_install_github_behind_proxy.R
library(httr)
library(devtools)

# make httr set CURL to ignore SSL verification problems
# (needed if the SSL proxy replaces certs with its own)

set_config(config(ssl.verifypeer = 0L))

# set proxy details
set_config(use_proxy("10.10.10.10",8080))

## how_to_build_ROracle_package.txt
TBD

## TERR_Expression_Function_Handling_Input_Columns.r
#######################################################
#
# Expression Functions in Spotfire can take arbitrarily
# many columns as input. Columns will be passed to TERR
# in order as 'input1', 'input2', etc.
#
# This shows how to capture an arbitrary number of
# columns and to put them into a data frame.
#
#######################################################

## TERR_Expression_Function_Mahalanobis_Distance.r
###################################################################
# Takes an arbitrarily long list of input columns and returns a
# boolean indicating whether or not each row is an outlier.
###################################################################

# create vector of inputs
inputs <- grep("^input[0-9]+$",ls(), value = TRUE)

# capture columns as a matrix
x <- sapply(inputs, function(y) {eval(parse(text = y))})

## TERR_Expression_Function_Mahalanobis_Outlier.r
########################################################
# Takes an arbitrarily long list of input columns and
# returns a boolean indicating whether or not each row
# is an outlier.
#
# The function uses the critical value for Mahalanobis
# Distance calculated from an upper tailed ChiSq
# distribution with p=0.001.
########################################################
	library(XML)
	library(ggplot2)

	url <- "http://www.kaggle.com/c/acquire-valued-shoppers-challenge/leaderboard"
	tree <- htmlTreeParse(url)
	tbl <- readHTMLTable(pagetree, stringsAsFactors = FALSE)[[1]]

	colnames(tbl) <- gsub("[^a-zA-Z0-9#]","", colnames(tbl))
	tbl$Score <- as.numeric(tbl$Score)
	# calculation as per:
	# http://www.bmj.com/content/343/bmj.d2304

	get_odds_p <- function(est, cil, ciu) {
	se <- (log(ciu) - log(cil))/(2*1.96)
	z <- abs(log(est)/se)
	p <- exp(-0.717z - 0.416z^2)
	p
	}
	rm(list=ls())

	rcode <- "x <- 1+1; y <- 2+2"

	# running `eval` evaluates `rcode` into the parent environment
	eval(parse(text = rcode))

	print(x)
	print(y)
	# Use autodetected proxy settings
	setInternet2(TRUE)

	# Get the SpotfireSPK package from the Spotfire Stats Server
	install.packages("SpotfireSPK", repos = "http://MySpotfireServer:8080/SplusServer/update/TERR")

	# Get a package you want to deploy from CRAN
	install.packages("nortest", repos = "http://cran.us.r-project.org")

	# Create a Debian Control File

	# Download: http://tap.tibco.com/ -> "Samples" tab -> RinR -> "Try Now" button
	# Docs: http://docs.tibco.com/pub/enterprise-runtime-for-R/2.5.0/doc/html/RinR/RinR-package.html

	########################################
	# Setup
	########################################

	library(RinR)
	library(Sdatasets)
	library(httr)
	library(devtools)

	# make httr set CURL to ignore SSL verification problems
	# (needed if the SSL proxy replaces certs with its own)

	set_config(config(ssl.verifypeer = 0L))

	# set proxy details
	set_config(use_proxy("10.10.10.10",8080))
	#######################################################
	#
	# Expression Functions in Spotfire can take arbitrarily
	# many columns as input. Columns will be passed to TERR
	# in order as 'input1', 'input2', etc.
	#
	# This shows how to capture an arbitrary number of
	# columns and to put them into a data frame.
	#
	#######################################################
	###################################################################
	# Takes an arbitrarily long list of input columns and returns a
	# boolean indicating whether or not each row is an outlier.
	###################################################################

	# create vector of inputs
	inputs <- grep("^input[0-9]+$",ls(), value = TRUE)

	# capture columns as a matrix
	x <- sapply(inputs, function(y) {eval(parse(text = y))})
	########################################################
	# Takes an arbitrarily long list of input columns and
	# returns a boolean indicating whether or not each row
	# is an outlier.
	#
	# The function uses the critical value for Mahalanobis
	# Distance calculated from an upper tailed ChiSq
	# distribution with p=0.001.
	########################################################