ltorgo/dmwr2

Functions and data supporting the 2nd edition of the book Data Mining with R by Luis Torgo, published by CRC Press

DMwR2

An R package with functions and data supporting the second edtion of the book Data Mining with R, by Luis Torgo, published by CRC Press.

To Install the Latest Oficial Stable Release do the following in R:

library(devtools)  # You need to install this package!
install_github("ltorgo/DMwR2",ref="master")

To Install the Latest Development Release do the following in R:

library(devtools)  # You need to install this package!
install_github("ltorgo/DMwR2",ref="develop")

After installation using any of the above procedures, the package can be used as any other R package by doing:

 library(DMwR2)

dmwr2's Issues

Error with sampleCSV because of space in directory name

I downloaded “flights14.csv” from the following site.
https://github.com/arunsrinivasan/flights/wiki/NYC-Flights-2014-data

I am working on macOS High Sierra Version 10.13.3. I am using R version 3.5.0 (2018-04-23) -- "Joy in Playing” with DMwR2_0.0.2. I created “test 1” as a subdirectory in “Users” as an example.
/Users/test 1

The following line does not execute with the “space” between “test” and “1” in the subdirectory name:
flights1000_1 <- sampleCSV(file = "/Users/test 1/flights14.csv", percORn = 1000, header = T)

The following message is displayed in the console.
wc: /Users/test: open: No such file or directory
wc: 1/flights14.csv: open: No such file or directory
sh: /Users/test: Permission denied
Error: '/Users/test 1/flights14.csv.tmp.csv' does not exist.
In addition: Warning message:
In system(paste("wc -l", f), intern = TRUE) :
running command 'wc -l /Users/test 1/flights14.csv' had status 1

sampleCSV not reading header

I downloaded “flights14.csv” from the following site.
https://github.com/arunsrinivasan/flights/wiki/NYC-Flights-2014-data

I am working on macOS High Sierra Version 10.13.3. I am using R version 3.5.0 (2018-04-23) -- "Joy in Playing” with DMwR2_0.0.2. I created “test2” as subdirectories in “Users” as an example.
/Users/test2

The column names are not displayed in the tibble when I run the following line. Instead it seems to be using one of the rows of flight data for the column names.
flights1000_2 <- sampleCSV(file = "/Users/test2/flights14.csv", percORn = 1000, header = T)

The following message is displayed in the console.
Parsed with column specification:
cols(
2014 = col_integer(),
1 = col_integer(),
1_1 = col_integer(),
847 = col_integer(),
-3 = col_integer(),
1036 = col_integer(),
1_2 = col_integer(),
0 = col_integer(),
AA = col_character(),
N553AA = col_character(),
313 = col_integer(),
LGA = col_character(),
ORD = col_character(),
139 = col_integer(),
733 = col_integer(),
8 = col_integer(),
47 = col_integer()
)
Warning message:
Duplicated column names deduplicated: '1' => '1_1' [3], '1' => '1_2' [7]

SMOTE creating floats from integers

Thank you for the time and effort you put into DWwR because it is incredibly useful. SMOTE has been especially useful.

Question
Do you have a suggestion for how to stop SMOTE from creating floats from columns where all distinct values are all integers? i.e. input integers into SMOTE and SMOTE returns int's and floats.

Problem
For example, running the following creates floats from columns containing only integers:
dataset.bal <- SMOTE(target ~ ., dataset, perc.over=675, perc.under=100);

Input

#distinct values in column 124 dataset are all integers 
levels(as.factor(dataset[,124]));

[1] "0" "4" "8" "12" "16" "20" "24" "28" "32" "36" "40" "44" "48" "52" "56" "60" "64" "68" "72" "76" "80" "84"

Output

#floats values have been added in column 124 in dataset.bal  
levels(as.factor(dataset.bal[,124]));

[1] "0" "4" "8" "12""16" "17.4798878207803"
[7] "17.8020473793149" "20""20.5099524259567" "20.6726439939812" "20.7490051034838" "21.7515262812376"
[13] "23.4109582398087" "23.5898735374212" "24""24.0396314188838" "24.0953625235707" "24.148680685088"
[19] "24.2740816418082" "24.3701336197555" "24.5072071170434" "24.5087074693292" "24.5124940760434" "24.7718890225515" etc..

Chapter 3: Monte Carlo workflow issue

Thanks for this second edition of DMwR book.

One of the more exciting parts (I think) is the monte carlo evalutions in chapter 3. My first step is to replicate the data runs from the book. However, I get stuck when executing MC workflow with this error. It feels like a simple error, but I've tried all sort of ways to make it work and I can't see where the missing values should be. Am I the only one in this forum who has got stuck on this part?

PERFORMANCE ESTIMATION USING MONTE CARLO

** PREDICTIVE TASK :: SP500

++ MODEL/WORKFLOW :: earthRegr.v1
Error in if (!missing(cluster) && !is.null(cluster) && getOption("parallelMap.status") == :
missing value where TRUE/FALSE needed