Analisis Pengaruh Gaya Hidup terhadap Kesehatan Tidur Menggunakan Metode Partial Least Squares (PLS)
Kelas 2024B Maris Al Sabina A. (24031554188) Dewanggi Erchinta Dwi Putri (24031554034) Naila Alya Furqon (24031554069) Nuri Maulidyatul Haliza (24031554160) Dosen Pengampu: Dinda Galuh Guminta, M.Stat.
r Sys.Date()
Import Library
#install.packages("readr")
#install.packages("dplyr")
#install.packages("ggplot2")
#install.packages("corrplot")
#install.packages("pls")
#install.packages("caret")
library(readr)
library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(ggplot2)
library(corrplot)## corrplot 0.95 loadedlibrary(pls)##
## Attaching package: 'pls'## The following object is masked from 'package:corrplot':
##
## corrplot## The following object is masked from 'package:stats':
##
## loadingslibrary(caret)## Loading required package: lattice##
## Attaching package: 'caret'## The following object is masked from 'package:pls':
##
## R2Load dataset
df <- read_csv("Sleep_health_and_lifestyle_dataset.csv")## Rows: 374 Columns: 13
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (5): Gender, Occupation, BMI Category, Blood Pressure, Sleep Disorder
## dbl (8): Person ID, Age, Sleep Duration, Quality of Sleep, Physical Activity...
##
## 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(df)## # A tibble: 6 × 13
## `Person ID` Gender Age Occupation `Sleep Duration` `Quality of Sleep`
## <dbl> <chr> <dbl> <chr> <dbl> <dbl>
## 1 1 Male 27 Software Engineer 6.1 6
## 2 2 Male 28 Doctor 6.2 6
## 3 3 Male 28 Doctor 6.2 6
## 4 4 Male 28 Sales Representa… 5.9 4
## 5 5 Male 28 Sales Representa… 5.9 4
## 6 6 Male 28 Software Engineer 5.9 4
## # ℹ 7 more variables: `Physical Activity Level` <dbl>, `Stress Level` <dbl>,
## # `BMI Category` <chr>, `Blood Pressure` <chr>, `Heart Rate` <dbl>,
## # `Daily Steps` <dbl>, `Sleep Disorder` <chr>Melihat informasi dataset
# melihat struktur data
str(df)## spc_tbl_ [374 × 13] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
## $ Person ID : num [1:374] 1 2 3 4 5 6 7 8 9 10 ...
## $ Gender : chr [1:374] "Male" "Male" "Male" "Male" ...
## $ Age : num [1:374] 27 28 28 28 28 28 29 29 29 29 ...
## $ Occupation : chr [1:374] "Software Engineer" "Doctor" "Doctor" "Sales Representative" ...
## $ Sleep Duration : num [1:374] 6.1 6.2 6.2 5.9 5.9 5.9 6.3 7.8 7.8 7.8 ...
## $ Quality of Sleep : num [1:374] 6 6 6 4 4 4 6 7 7 7 ...
## $ Physical Activity Level: num [1:374] 42 60 60 30 30 30 40 75 75 75 ...
## $ Stress Level : num [1:374] 6 8 8 8 8 8 7 6 6 6 ...
## $ BMI Category : chr [1:374] "Overweight" "Normal" "Normal" "Obese" ...
## $ Blood Pressure : chr [1:374] "126/83" "125/80" "125/80" "140/90" ...
## $ Heart Rate : num [1:374] 77 75 75 85 85 85 82 70 70 70 ...
## $ Daily Steps : num [1:374] 4200 10000 10000 3000 3000 3000 3500 8000 8000 8000 ...
## $ Sleep Disorder : chr [1:374] "None" "None" "None" "Sleep Apnea" ...
## - attr(*, "spec")=
## .. cols(
## .. `Person ID` = col_double(),
## .. Gender = col_character(),
## .. Age = col_double(),
## .. Occupation = col_character(),
## .. `Sleep Duration` = col_double(),
## .. `Quality of Sleep` = col_double(),
## .. `Physical Activity Level` = col_double(),
## .. `Stress Level` = col_double(),
## .. `BMI Category` = col_character(),
## .. `Blood Pressure` = col_character(),
## .. `Heart Rate` = col_double(),
## .. `Daily Steps` = col_double(),
## .. `Sleep Disorder` = col_character()
## .. )
## - attr(*, "problems")=<pointer: 0x000001f1319ff6b0># melihat dimensi data
dim(df)## [1] 374 13# statistik deskriptif
summary(df)## Person ID Gender Age Occupation
## Min. : 1.00 Length :374 Min. :27.00 Length :374
## 1st Qu.: 94.25 N.unique : 2 1st Qu.:35.25 N.unique : 11
## Median :187.50 N.blank : 0 Median :43.00 N.blank : 0
## Mean :187.50 Min.nchar: 4 Mean :42.18 Min.nchar: 5
## 3rd Qu.:280.75 Max.nchar: 6 3rd Qu.:50.00 Max.nchar: 20
## Max. :374.00 Max. :59.00
## Sleep Duration Quality of Sleep Physical Activity Level Stress Level
## Min. :5.800 Min. :4.000 Min. :30.00 Min. :3.000
## 1st Qu.:6.400 1st Qu.:6.000 1st Qu.:45.00 1st Qu.:4.000
## Median :7.200 Median :7.000 Median :60.00 Median :5.000
## Mean :7.132 Mean :7.313 Mean :59.17 Mean :5.385
## 3rd Qu.:7.800 3rd Qu.:8.000 3rd Qu.:75.00 3rd Qu.:7.000
## Max. :8.500 Max. :9.000 Max. :90.00 Max. :8.000
## BMI Category Blood Pressure Heart Rate Daily Steps
## Length :374 Length :374 Min. :65.00 Min. : 3000
## N.unique : 4 N.unique : 25 1st Qu.:68.00 1st Qu.: 5600
## N.blank : 0 N.blank : 0 Median :70.00 Median : 7000
## Min.nchar: 5 Min.nchar: 6 Mean :70.17 Mean : 6817
## Max.nchar: 13 Max.nchar: 6 3rd Qu.:72.00 3rd Qu.: 8000
## Max. :86.00 Max. :10000
## Sleep Disorder
## Length :374
## N.unique : 3
## N.blank : 0
## Min.nchar: 4
## Max.nchar: 11
## Cek missing value
colSums(is.na(df))## Person ID Gender Age
## 0 0 0
## Occupation Sleep Duration Quality of Sleep
## 0 0 0
## Physical Activity Level Stress Level BMI Category
## 0 0 0
## Blood Pressure Heart Rate Daily Steps
## 0 0 0
## Sleep Disorder
## 0Data Preprocessinng
# menghapus kolom person id
df <- df %>%
select(-`Person ID`)
head(df)## # A tibble: 6 × 12
## Gender Age Occupation `Sleep Duration` `Quality of Sleep`
## <chr> <dbl> <chr> <dbl> <dbl>
## 1 Male 27 Software Engineer 6.1 6
## 2 Male 28 Doctor 6.2 6
## 3 Male 28 Doctor 6.2 6
## 4 Male 28 Sales Representative 5.9 4
## 5 Male 28 Sales Representative 5.9 4
## 6 Male 28 Software Engineer 5.9 4
## # ℹ 7 more variables: `Physical Activity Level` <dbl>, `Stress Level` <dbl>,
## # `BMI Category` <chr>, `Blood Pressure` <chr>, `Heart Rate` <dbl>,
## # `Daily Steps` <dbl>, `Sleep Disorder` <chr># Encoding variabel kategorik
df$`BMI Category` <- as.numeric(
as.factor(df$`BMI Category`)
)EDA
# histogram quality of sleep
ggplot(df, aes(x = `Quality of Sleep`)) +
geom_histogram(bins = 10)
# Scatterplot Stress Level dan Quality of Sleep
ggplot(df,
aes(x = `Stress Level`,
y = `Quality of Sleep`)) +
geom_point()
# Boxplot BMI Category dan quality of sleep
ggplot(df,
aes(x = factor(`BMI Category`),
y = `Quality of Sleep`)) +
geom_boxplot()
# Heatmap korelasi
numeric_data <- df[, sapply(df, is.numeric)]
cor_matrix <- cor(numeric_data)
corrplot::corrplot(
cor_matrix,
method = "color",
type = "upper",
addCoef.col = "black",
tl.col = "black",
tl.cex = 0.7,
number.cex = 0.5
)
### Variabel dependen dan independen
# variabel independen
X <- df %>%
select(`Physical Activity Level`,
`Stress Level`,
`BMI Category`,
`Daily Steps`,
`Heart Rate`)
# variabel dependen
Y <- df$`Quality of Sleep`Model PLS
pls_model <- plsr(
Y ~ .,
data = data.frame(Y, X),
scale = TRUE,
validation = "CV"
)
summary(pls_model)## Data: X dimension: 374 5
## Y dimension: 374 1
## Fit method: kernelpls
## Number of components considered: 5
##
## VALIDATION: RMSEP
## Cross-validated using 10 random segments.
## (Intercept) 1 comps 2 comps 3 comps 4 comps 5 comps
## CV 1.199 0.5301 0.4702 0.4412 0.4358 0.4313
## adjCV 1.199 0.5296 0.4696 0.4408 0.4355 0.4310
##
## TRAINING: % variance explained
## 1 comps 2 comps 3 comps 4 comps 5 comps
## X 35.14 59.11 81.82 98.10 100.00
## Y 80.68 85.26 86.78 87.02 87.33Jumlah komponen terbaik
# plot validation
validationplot(pls_model, val.type = "MSEP")
#RMSEP
RMSEP(pls_model)## (Intercept) 1 comps 2 comps 3 comps 4 comps 5 comps
## CV 1.199 0.5301 0.4702 0.4412 0.4358 0.4313
## adjCV 1.199 0.5296 0.4696 0.4408 0.4355 0.4310Koefisien model
coef(pls_model)## , , 5 comps
##
## Y
## Physical.Activity.Level 0.17006882
## Stress.Level -0.99168461
## BMI.Category -0.19837465
## Daily.Steps 0.07029009
## Heart.Rate -0.08790154coef_df <- data.frame(
Variabel = rownames(coef(pls_model)),
Koefisien = as.vector(coef(pls_model))
)
coef_df## Variabel Koefisien
## 1 Physical.Activity.Level 0.17006882
## 2 Stress.Level -0.99168461
## 3 BMI.Category -0.19837465
## 4 Daily.Steps 0.07029009
## 5 Heart.Rate -0.08790154Visualisasi Koefisien Variabel
ggplot(coef_df,
aes(x = Variabel,
y = Koefisien)) +
geom_bar(stat = "identity") +
theme(axis.text.x = element_text(angle = 45,
hjust = 1))