Fauzan_Assignment5_203A
Fauzan Budi Prasetya
2025-11-09
Show R versions and home directory
R version
R.version## _
## platform aarch64-apple-darwin20
## arch aarch64
## os darwin20
## system aarch64, darwin20
## status
## major 4
## minor 5.2
## year 2025
## month 10
## day 31
## svn rev 88974
## language R
## version.string R version 4.5.2 (2025-10-31)
## nickname [Not] Part in a RumbleShow home directory
Sys.getenv()## __CF_USER_TEXT_ENCODING
## 0x1F5:0x0:0x0
## __CFBundleIdentifier com.rstudio.desktop
## CLICOLOR_FORCE 1
## COMMAND_MODE unix2003
## DISPLAY :0
## DYLD_FALLBACK_LIBRARY_PATH
## /Library/Frameworks/R.framework/Resources/lib:/Library/Java/JavaVirtualMachines/jdk-11.0.18+10/Contents/Home/lib/server
## EDITOR vi
## GIT_ASKPASS rpostback-askpass
## HOME /Users/fauzan
## LANG en_US.UTF-8
## LC_CTYPE en_US.UTF-8
## LN_S ln -s
## LOGNAME fauzan
## MAKE make
## MallocNanoZone 0
## MPLENGINE tkAgg
## NOT_CRAN true
## ORIGINAL_XDG_CURRENT_DESKTOP
## undefined
## OSLogRateLimit 64
## PAGER /usr/bin/less
## PATH /usr/local/bin:/System/Cryptexes/App/usr/bin:/usr/bin:/bin:/usr/sbin:/sbin:/var/run/com.apple.security.cryptexd/codex.system/bootstrap/usr/local/bin:/var/run/com.apple.security.cryptexd/codex.system/bootstrap/usr/bin:/var/run/com.apple.security.cryptexd/codex.system/bootstrap/usr/appleinternal/bin:/Applications/quarto/bin:/Library/TeX/texbin:/usr/texbin:/private/var/folders/qb/_8p5wt4948x_q3ygct_d64mw0000gn/T/AppTranslocation/A009C335-F6B2-453D-A1DD-793EFECE87C0/d/RStudio.app/Contents/Resources/app/quarto/bin:/private/var/folders/qb/_8p5wt4948x_q3ygct_d64mw0000gn/T/AppTranslocation/A009C335-F6B2-453D-A1DD-793EFECE87C0/d/RStudio.app/Contents/Resources/app/bin/postback
## PWD /Users/fauzan
## PYTHONIOENCODING utf-8
## R_ARCH
## R_BROWSER /usr/bin/open
## R_BZIPCMD /usr/bin/bzip2
## R_CLI_HAS_HYPERLINK_IDE_HELP
## true
## R_CLI_HAS_HYPERLINK_IDE_RUN
## true
## R_CLI_HAS_HYPERLINK_IDE_VIGNETTE
## true
## R_DOC_DIR /Library/Frameworks/R.framework/Resources/doc
## R_GZIPCMD /usr/bin/gzip
## R_HOME /Library/Frameworks/R.framework/Resources
## R_INCLUDE_DIR /Library/Frameworks/R.framework/Resources/include
## R_LIBS /Library/Frameworks/R.framework/Versions/4.5-arm64/Resources/library
## R_LIBS_SITE /Library/Frameworks/R.framework/Resources/site-library
## R_LIBS_USER /Users/fauzan/Library/R/arm64/4.5/library
## R_PAPERSIZE a4
## R_PAPERSIZE_USER a4
## R_PDFVIEWER /usr/bin/open
## R_PLATFORM aarch64-apple-darwin20
## R_PRINTCMD lpr
## R_QPDF /Library/Frameworks/R.framework/Resources/bin/qpdf
## R_RD4PDF times,inconsolata,hyper
## R_RUNTIME
## R_SESSION_TMPDIR /var/folders/qb/_8p5wt4948x_q3ygct_d64mw0000gn/T//Rtmp3cAuWb
## R_SHARE_DIR /Library/Frameworks/R.framework/Resources/share
## R_STRIP_SHARED_LIB strip -x
## R_STRIP_STATIC_LIB strip -S
## R_TEXI2DVICMD /opt/R/arm64/bin/texi2dvi
## R_UNZIPCMD /usr/bin/unzip
## R_ZIPCMD /usr/bin/zip
## RMARKDOWN_MATHJAX_PATH
## /private/var/folders/qb/_8p5wt4948x_q3ygct_d64mw0000gn/T/AppTranslocation/A009C335-F6B2-453D-A1DD-793EFECE87C0/d/RStudio.app/Contents/Resources/app/resources/mathjax-27
## RMARKDOWN_PREVIEW_DIR /var/folders/qb/_8p5wt4948x_q3ygct_d64mw0000gn/T//RtmpS4zL4f
## RS_LOG_LEVEL WARN
## RS_RPOSTBACK_PATH /private/var/folders/qb/_8p5wt4948x_q3ygct_d64mw0000gn/T/AppTranslocation/A009C335-F6B2-453D-A1DD-793EFECE87C0/d/RStudio.app/Contents/Resources/app/bin/rpostback
## RS_SHARED_SECRET bd08d9e1-91ce-493e-ac63-3158599c870f
## RSTUDIO 1
## RSTUDIO_CHILD_PROCESS_PANE
## render
## RSTUDIO_CLI_HYPERLINKS
## true
## RSTUDIO_CONSOLE_COLOR 256
## RSTUDIO_CONSOLE_WIDTH 144
## RSTUDIO_DESKTOP_EXE /private/var/folders/qb/_8p5wt4948x_q3ygct_d64mw0000gn/T/AppTranslocation/A009C335-F6B2-453D-A1DD-793EFECE87C0/d/RStudio.app/Contents/MacOS/RStudio
## RSTUDIO_FALLBACK_LIBRARY_PATH
## /var/folders/qb/_8p5wt4948x_q3ygct_d64mw0000gn/T/rstudio-fallback-library-path-859225681
## RSTUDIO_LONG_VERSION 2025.09.2+418
## RSTUDIO_PANDOC /private/var/folders/qb/_8p5wt4948x_q3ygct_d64mw0000gn/T/AppTranslocation/A009C335-F6B2-453D-A1DD-793EFECE87C0/d/RStudio.app/Contents/Resources/app/quarto/bin/tools/aarch64
## RSTUDIO_PROGRAM_MODE desktop
## RSTUDIO_SESSION_PID 96394
## RSTUDIO_SESSION_PORT 39990
## RSTUDIO_USER_IDENTITY fauzan
## RSTUDIO_VERSION 2025.09.2.418
## RSTUDIOAPI_IPC_REQUESTS_FILE
## /var/folders/qb/_8p5wt4948x_q3ygct_d64mw0000gn/T/RtmpS4zL4f/rstudio-ipc-requests-1788a7836c1fa.rds
## RSTUDIOAPI_IPC_RESPONSE_FILE
## /var/folders/qb/_8p5wt4948x_q3ygct_d64mw0000gn/T/RtmpS4zL4f/rstudio-ipc-response-1788a52f941be.rds
## RSTUDIOAPI_IPC_SHARED_SECRET
## 86e50a56-5c4f-43f9-9d1e-5fb0013770dc
## SED /usr/bin/sed
## SF_PARTNER posit_rstudio
## SHELL /bin/zsh
## SHLVL 0
## SPARK_CONNECT_USER_AGENT
## posit-rstudio
## SSH_ASKPASS rpostback-askpass
## SSH_AUTH_SOCK /private/tmp/com.apple.launchd.hVLGjCKiJT/Listeners
## TAR /usr/bin/tar
## TERM xterm-256color
## TMPDIR /var/folders/qb/_8p5wt4948x_q3ygct_d64mw0000gn/T/
## TZDIR /usr/share/zoneinfo
## USER fauzan
## XPC_FLAGS 0x0
## XPC_SERVICE_NAME application.com.rstudio.desktop.17.22Run basic functions
read csv data
library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.1 ✔ stringr 1.6.0
## ✔ ggplot2 4.0.0 ✔ tibble 3.3.0
## ✔ lubridate 1.9.4 ✔ tidyr 1.3.1
## ✔ purrr 1.2.0
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errorsSLSII <- read_csv("/Users/fauzan/SLSII_PFT_clin_baseline.csv")## Rows: 97 Columns: 12
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (2): ScreenID, Treatment
## dbl (10): FVC_predicted, TLC_liter, DLCO_predicted, Male, age, mrss_n1, BDI,...
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.head(SLSII)## # A tibble: 6 × 12
## ScreenID Treatment FVC_predicted TLC_liter DLCO_predicted Male age mrss_n1
## <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 01-J-S-S… MMF 0.805 3.71 0.501 0 47.4 27
## 2 02-AGR-S… MMF 0.661 4.11 0.686 0 50.0 7
## 3 02-AML-S… CYC 0.811 4.01 0.801 0 54.9 32
## 4 02-CAB-S… MMF 0.610 2.92 0.462 0 40.0 10
## 5 02-ELT-S… MMF 0.525 3.52 0.466 0 70.4 39
## 6 02-ETM-S… CYC 0.680 2.94 0.867 0 55.0 2
## # ℹ 4 more variables: BDI <dbl>, disease_duration_yr <dbl>,
## # Raynaud_Diag_yn <dbl>, Ray_duration_yr <dbl>understanding the overview of data structure
str(SLSII)## spc_tbl_ [97 × 12] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
## $ ScreenID : chr [1:97] "01-J-S-S103" "02-AGR-S103" "02-AML-S122" "02-CAB-S104" ...
## $ Treatment : chr [1:97] "MMF" "MMF" "CYC" "MMF" ...
## $ FVC_predicted : num [1:97] 0.805 0.661 0.811 0.61 0.525 ...
## $ TLC_liter : num [1:97] 3.71 4.11 4.01 2.92 3.52 ...
## $ DLCO_predicted : num [1:97] 0.501 0.686 0.801 0.462 0.466 ...
## $ Male : num [1:97] 0 0 0 0 0 0 0 1 1 0 ...
## $ age : num [1:97] 47.4 50 54.9 40 70.4 ...
## $ mrss_n1 : num [1:97] 27 7 32 10 39 2 5 5 41 19 ...
## $ BDI : num [1:97] 9 9 12 7 8 9 6 6 10 8 ...
## $ disease_duration_yr: num [1:97] 2.58 2.25 1.02 1.85 4.92 ...
## $ Raynaud_Diag_yn : num [1:97] 1 1 1 1 1 1 1 1 1 1 ...
## $ Ray_duration_yr : num [1:97] 2.58 6.67 1.02 1.6 4.66 ...
## - attr(*, "spec")=
## .. cols(
## .. ScreenID = col_character(),
## .. Treatment = col_character(),
## .. FVC_predicted = col_double(),
## .. TLC_liter = col_double(),
## .. DLCO_predicted = col_double(),
## .. Male = col_double(),
## .. age = col_double(),
## .. mrss_n1 = col_double(),
## .. BDI = col_double(),
## .. disease_duration_yr = col_double(),
## .. Raynaud_Diag_yn = col_double(),
## .. Ray_duration_yr = col_double()
## .. )
## - attr(*, "problems")=<externalptr>another way of understanding the overview of data structure
glimpse(SLSII)## Rows: 97
## Columns: 12
## $ ScreenID <chr> "01-J-S-S103", "02-AGR-S103", "02-AML-S122", "02-C…
## $ Treatment <chr> "MMF", "MMF", "CYC", "MMF", "MMF", "CYC", "CYC", "…
## $ FVC_predicted <dbl> 0.8049215, 0.6609544, 0.8114863, 0.6095501, 0.5254…
## $ TLC_liter <dbl> 3.710000, 4.113333, 4.006667, 2.923333, 3.523333, …
## $ DLCO_predicted <dbl> 0.5008026, 0.6855451, 0.8005001, 0.4623120, 0.4659…
## $ Male <dbl> 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 1, 0, 0, 1, 1, 0,…
## $ age <dbl> 47.37534, 49.95617, 54.90411, 40.00548, 70.42740, …
## $ mrss_n1 <dbl> 27, 7, 32, 10, 39, 2, 5, 5, 41, 19, 6, 17, 5, 20, …
## $ BDI <dbl> 9, 9, 12, 7, 8, 9, 6, 6, 10, 8, 8, 7, 6, 10, 1, 9,…
## $ disease_duration_yr <dbl> 2.5753420, 2.2493150, 1.0191780, 1.8547950, 4.9150…
## $ Raynaud_Diag_yn <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,…
## $ Ray_duration_yr <dbl> 2.5753420, 6.6712330, 1.0191780, 1.6027400, 4.6630…understanding the number of row and column
dim(SLSII)## [1] 97 12understanding the number of row
nrow(SLSII)## [1] 97understanding the number of column
ncol(SLSII)## [1] 12selecting the data, row 1 to 3, and column 1 to 5
SLSII[1:3,1:5]## # A tibble: 3 × 5
## ScreenID Treatment FVC_predicted TLC_liter DLCO_predicted
## <chr> <chr> <dbl> <dbl> <dbl>
## 1 01-J-S-S103 MMF 0.805 3.71 0.501
## 2 02-AGR-S103 MMF 0.661 4.11 0.686
## 3 02-AML-S122 CYC 0.811 4.01 0.801show the mean of age column
mean(SLSII$age)## [1] 51.58783show the variance of age column
var(SLSII$age)## [1] 81.71442show the summary statistics of age column
summary(SLSII$age)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 29.99 44.43 51.88 51.59 58.39 70.43show the mean of age column, with removing the NA or missing values first
mean(SLSII$age,na.rm=T)## [1] 51.58783show the numeric data value distribution with stem and leaves plot, which shows the first and last digits
stem(SLSII$age)##
## The decimal point is 1 digit(s) to the right of the |
##
## 2 |
## 3 | 04
## 3 | 55567799
## 4 | 000012233344444
## 4 | 55677777899
## 5 | 0000111111222223333444
## 5 | 555555666777888999
## 6 | 0000001123334
## 6 | 5567778
## 7 | 0show the data distribution in boxplot, shows q1, median, and q3
boxplot(SLSII$age)
## show the data distribution in histogram plot
hist(SLSII$age)
## show the data frequency of categorical data, for one column
table(SLSII$Male)##
## 0 1
## 72 25show the data frequency of each value in categorical data, for multiple column
table(SLSII$Male, SLSII$Treatment)##
## CYC MMF
## 0 39 33
## 1 8 17show the data frequency proportion of value each respective row, in categorical data, for multiple column
prop.table(table(SLSII$Male, SLSII$Treatment), 1)##
## CYC MMF
## 0 0.5416667 0.4583333
## 1 0.3200000 0.6800000show the data frequency proportion of value each respective column, in categorical data, for multiple column
prop.table(table(SLSII$Male, SLSII$Treatment), 2)##
## CYC MMF
## 0 0.8297872 0.6600000
## 1 0.1702128 0.3400000show the data frequency proportion of value in grand total, in categorical data, for multiple column
prop.table(table(SLSII$Male, SLSII$Treatment))##
## CYC MMF
## 0 0.40206186 0.34020619
## 1 0.08247423 0.17525773