Untitled

library(tidyverse)

## Warning: package 'tidyverse' was built under R version 4.5.3

## Warning: package 'tidyr' was built under R version 4.5.2

## Warning: package 'readr' was built under R version 4.5.3

## Warning: package 'purrr' was built under R version 4.5.2

## Warning: package 'forcats' was built under R version 4.5.3

## Warning: package 'lubridate' was built under R version 4.5.3

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.2.0
## ✔ forcats   1.0.1     ✔ stringr   1.5.2
## ✔ ggplot2   4.0.0     ✔ tibble    3.3.0
## ✔ lubridate 1.9.5     ✔ tidyr     1.3.2
## ✔ purrr     1.2.1     
## ── 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 errors

datars <- read_csv("C:/Users/LENOVO/Downloads/hospital_dataset.csv")

## Rows: 700 Columns: 8
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (5): Nama, Tanggal_Lahir, Tensi, Suhu_Tubuh_Celcius, Penyakit
## dbl (3): Skin_Stiffness_N_per_mm, Microcirculation_PU, Peak_Plantar_Pressure...
## 
## 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.

glimpse(datars)

## Rows: 700
## Columns: 8
## $ Nama                      <chr> "Michael Anderson", "N/A", "Tan Wei Ming", "…
## $ Tanggal_Lahir             <chr> "01/04/1957", "20/09/1975", "12/04/1965", "1…
## $ Tensi                     <chr> "112/67", "140 / 91", "134/72", "120/79", "9…
## $ Skin_Stiffness_N_per_mm   <dbl> 0.69, 1.50, 0.76, 1.92, 0.81, 0.61, 1.04, 2.…
## $ Microcirculation_PU       <dbl> 42.0, 41.9, 26.3, NA, 25.5, 42.2, 2.0, 9.5, …
## $ Suhu_Tubuh_Celcius        <chr> "37.6", "36.5°C", "37.5", "37.0", "36.0", "3…
## $ Penyakit                  <chr> "Non-Diabetic", "Non-Diabetic", "Non-Diabeti…
## $ Peak_Plantar_Pressure_kPa <dbl> 294.0, NA, 431.8, 577.5, 502.3, 201.4, 512.8…

summary(datars)

##      Nama           Tanggal_Lahir         Tensi          
##  Length:700         Length:700         Length:700        
##  Class :character   Class :character   Class :character  
##  Mode  :character   Mode  :character   Mode  :character  
##                                                          
##                                                          
##                                                          
##                                                          
##  Skin_Stiffness_N_per_mm Microcirculation_PU Suhu_Tubuh_Celcius
##  Min.   : -2.180         Min.   : -32.50     Length:700        
##  1st Qu.:  0.700         1st Qu.:  18.00     Class :character  
##  Median :  1.100         Median :  27.70     Mode  :character  
##  Mean   :  1.342         Mean   :  35.58                       
##  3rd Qu.:  1.595         3rd Qu.:  39.00                       
##  Max.   :150.000         Max.   :5000.00                       
##  NA's   :37              NA's   :50                            
##    Penyakit         Peak_Plantar_Pressure_kPa
##  Length:700         Min.   : -100.0          
##  Class :character   1st Qu.:  268.6          
##  Mode  :character   Median :  384.3          
##                     Mean   :  991.9          
##                     3rd Qu.:  508.5          
##                     Max.   :99999.0          
##                     NA's   :43

colSums(is.na(datars))

##                      Nama             Tanggal_Lahir                     Tensi 
##                        40                        42                        47 
##   Skin_Stiffness_N_per_mm       Microcirculation_PU        Suhu_Tubuh_Celcius 
##                        37                        50                        49 
##                  Penyakit Peak_Plantar_Pressure_kPa 
##                        45                        43

data_clean <- datars %>% drop_na()

df_clean <- datars %>% drop_na(Nama)

df_isimedian <- datars %>% 
  mutate(
    Microcirculation_PU = ifelse(
      is.na(Microcirculation_PU),
      median(Microcirculation_PU, na.rm = TRUE),
      Microcirculation_PU
    )
  )

df_duplicate <- datars %>% distinct()

df_clean <- datars %>% 
  mutate(
    Suhu_Tubuh_Celcius = str_extract(Suhu_Tubuh_Celcius, "[0-9.]+"),
    Suhu_Tubuh_Celcius = as.numeric(Suhu_Tubuh_Celcius))

df_clean <- datars %>% 
  mutate(
    Tensi = str_replace_all(Tensi, " ", "")
  )