zachmayer

#Directory
setwd('~/wherever')

#Load Required Packages
library('caret')
library('glmnet')
library('ipred')
library('e1071')
library('caTools')

zachmayer

install.packages(c("caret","reshape2","plyr","caTools"),dependencies=c("Depends", "Imports", "LinkingTo", "Suggests", "Enhances"))

zachmayer

####################################
# Training parameters
####################################
MyTrainControl=trainControl(
		method = "repeatedCV",
		number=10,
		repeats=5,
		returnResamp = "all",
		classProbs = TRUE,
		summaryFunction=twoClassSummary

zachmayer

#Setup
rm(list = ls(all = TRUE)) #CLEAR WORKSPACE

#Directory
setwd("~/Overfitting")

#Load Required Packages
library('caTools')
library('caret')
library('glmnet')

zachmayer

library(quantmod)
getSymbols(c('AHETPI','CES0500000003','CPIAUCSL','GASREGM'),src = "FRED")
getSymbols('XAU/USD',src = "oanda")

#Definitions:
#AHETPI = Average Hourly Earnings of Production and Nonsupervisory Employees: Total Private
#CES0500000003 = Average Hourly Earnings of All Employees: Total Private
#CPIAUCSL = Consumer Price Index for All Urban Consumers: All Items
#GASREGM = US Regular All Formulations Gas Price
#XAUUSD USD per 1 oz of gold.  Last 500 days only

zachmayer

getNews <- function(symbol, number){

	# Warn about length
	if (number>300) {
		warning("May only get 300 stories from google")
	}

	# load libraries
	library(XML); library(plyr); library(stringr); library(lubridate);
	library(xts); library(RDSTK)

zachmayer

multiRF <- function(x,...) {
	foreach(i=x,.combine=combine,.packages='randomForest',
	.export=c('X','Y'),.inorder=FALSE) %dopar% {
		randomForest(X,Y,mtry=i,...)
	} 
}
multiRF(c(rep(3,10),rep(4,10),rep(5,10)),ntree=500)

zachmayer

#Code to re-create John Hussman's Recession warning index
#http://www.hussmanfunds.com/wmc/wmc110801.htm
#R code by Zach Mayer

rm(list = ls(all = TRUE)) #CLEAR WORKSPACE
library(quantmod)

#################################################
# 1. Credit spreads
#################################################

zachmayer

rm(list = ls(all = TRUE)) #CLEAR WORKSPACE
library(quantmod)

#Scrape data from the website
library(XML)
rawPMI <- readHTMLTable('http://www.ism.ws/ISMReport/content.cfm?ItemNumber=10752')
PMI <- data.frame(rawPMI[[1]])
names(PMI)[1] <- 'Year'

#Reshape

zachmayer

## Load googlepredictionapi and dependent libraries
library(rjson)
library(RCurl)
library(googlepredictionapi)

#Save dataframe to a file, upload to google storage, and train a model
write.csv(iris,'iris.csv')
model <- PredictionApiTrain(data='iris.csv', remote.file="gs://rdata/iris")

#Summarize model and predict for new data