New assignment

230620_JB_AssignmentSolution.R

# +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

## Step 1: Get row numbers for the training data ----

# +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

biofilm_data$mz <- round(biofilm_data$mz,digits=1)

setkeyv(biofilm_data,cols=c("file","indicator","mz"))

# This step takes a long time

biofilm_data[,.(int=sum(int)),

             by=c("file","indicator","mz")]

biofilm_data_wide <- dcast(biofilm_data, file + indicator ~ mz,value.var = "int")

biofilm_data_wide <- biofilm_data_wide[,-c("file")]

pcas <- prcomp(biofilm_data_wide)

trainRowNumbers <- createDataPartition(biofilm_data$indicator, p=0.8, list=FALSE,times=1)

trainRowNumbers <- createDataPartition(as.factor(biofilm_data_wide$indicator), p=0.8, list=FALSE,times=1)

# list: no list is returned

# times: you can do multiple times

# if the output is a factor splitting is done so that the the outcome variable is equally represented

# +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

## Step 2: Create the training  dataset ----

# +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

trainData <- biofilm_data[trainRowNumbers,]

# What are the frequencies?

table(biofilm_data$indicator)/length(biofilm_data$indicator)

table(trainData$indicator)/length(trainData$indicator)

trainData <- biofilm_data_wide[trainRowNumbers,]

# +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

## Step 3: Create the test dataset ----

# +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

testData <- biofilm_data[-trainRowNumbers,]

testData <- biofilm_data_wide[-trainRowNumbers,]

# What are the frequencies?

table(biofilm_data$indicator)/length(biofilm_data$indicator)

table(trainData$indicator)/length(trainData$indicator)

# The outcome variable Y for later use.

y = trainData$indicator

@Comment{$ biblatex control file $}

@Comment{$ biblatex bcf format version 3.10 $}

% Do not modify this file!

%

% This is an auxiliary file used by the 'biblatex' package.

% This file may safely be deleted. It will be recreated as

% required.

@Control{biblatex-control,

  options = {3.10:0:1:1:0:1:1:0:0:1:0:1:3:1:3:1:0:0:3:1:79:+:+:nty},

}

\relax 

\providecommand\hyper@newdestlabel[2]{}

\providecommand\HyperFirstAtBeginDocument{\AtBeginDocument}

\HyperFirstAtBeginDocument{\ifx\hyper@anchor\@undefined

\global\let\oldnewlabel\newlabel

\gdef\newlabel#1#2{\newlabelxx{#1}#2}

\gdef\newlabelxx#1#2#3#4#5#6{\oldnewlabel{#1}{{#2}{#3}}}

\AtEndDocument{\ifx\hyper@anchor\@undefined

\let\newlabel\oldnewlabel

\fi}

\fi}

\global\let\hyper@last\relax 

\gdef\HyperFirstAtBeginDocument#1{#1}

\providecommand\HyField@AuxAddToFields[1]{}

\providecommand\HyField@AuxAddToCoFields[2]{}

\bibstyle{biblatex}

\bibdata{ass7-blx}

\citation{biblatex-control}

\abx@aux@refcontext{nty/global//global/global}

\@writefile{toc}{\contentsline {section}{\numberline {Task 1:}Clone a git repository}{1}{section.1}\protected@file@percent }

\@writefile{toc}{\contentsline {section}{\numberline {Task 2:}The \texttt  {caret} package}{1}{section.2}\protected@file@percent }

\newlabel{step:extract}{{5}{2}{Getting to know the data}{Item.7}{}}

\newlabel{step:plot}{{6}{2}{Getting to know the data}{Item.8}{}}

\newlabel{split:step1}{{13}{2}{Splitting the data set based on the outcome variable}{Item.15}{}}

\newlabel{split:step2}{{14}{2}{Splitting the data set based on the outcome variable}{Item.16}{}}

\newlabel{split:freq}{{15}{2}{Splitting the data set based on the outcome variable}{Item.17}{}}

\abx@aux@read@bbl@mdfivesum{242E9DB92557AC81F6B30CE4F9334513}

\gdef \@abspage@last{2}