Targel 10

library(ggplot2)
library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ lubridate 1.9.3     ✔ tibble    3.2.1
## ✔ purrr     1.0.2     ✔ tidyr     1.3.1
## ── 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

library(readxl)
library(janitor)

## 
## Attaching package: 'janitor'
## 
## The following objects are masked from 'package:stats':
## 
##     chisq.test, fisher.test

library(ggpubr)
library(gtsummary)
library(table1)

## 
## Attaching package: 'table1'
## 
## The following objects are masked from 'package:base':
## 
##     units, units<-

sleep <- read_excel("DATA/sleep_health_and_lifestyle_dataset.xlsx")
mean(sleep$`Duration of sleep`,na.rm = TRUE)

## [1] 7.046757

sleep_range <- range(sleep$`Duration of sleep`,na.rm = TRUE)
duration_70 <- quantile(sleep$`Duration of sleep`, probs = 0.7, na.rm = TRUE)  


sleep <- sleep %>%
  filter(!is.na(Occupation)) %>% 
  mutate(occupation_4cat = factor(ifelse(Occupation == "Doctor", "Doctor",
                                         ifelse(Occupation == "Nurse", "Nurse", "Other"))))
 sleeptable <- sleep %>%filter(!is.na(`Duration of sleep`)) %>% 
  mutate(quantile_group = case_when(
    `Duration of sleep` <= quantile(`Duration of sleep`, probs = 1/3, na.rm = TRUE) ~ "0.33",
    `Duration of sleep` > quantile(`Duration of sleep`, probs = 1/3, na.rm = TRUE) &
      `Duration of sleep` <= quantile(`Duration of sleep`, probs = 2/3, na.rm = TRUE) ~ "0.67",
    `Duration of sleep` > quantile(`Duration of sleep`, probs = 2/3, na.rm = TRUE) ~ "1"
  ))

 sleeptable3 <- sleeptable %>%
  group_by(occupation_4cat, quantile_group) %>%
  summarise(
    avg_sleep = mean(`Duration of sleep`, na.rm = TRUE)
  )

## `summarise()` has grouped output by 'occupation_4cat'. You can override using
## the `.groups` argument.

library(ggplot2)

graph <- ggplot(sleeptable3)+
  aes(x = quantile_group, y = avg_sleep,fill = quantile_group,group = quantile_group) +
  geom_bar(stat = "identity") +
  theme_minimal()+facet_wrap(vars(occupation_4cat))
graph

sleeptable <- sleeptable %>%clean_names()

sleeptable <- sleeptable %>%
  separate(blood_pressure, into = c("systolic", "diastolic"), sep = "/",remove = FALSE)

sleeptable<- sleeptable%>% mutate(
    systolic = as.numeric(systolic),  
    diastolic = as.numeric(diastolic) 
  )

quantile_values <- c(0.33, 0.67, 1) 

# Grouped quantile calculations
df_grouped <- sleeptable %>%
  group_by(gender) %>%
  reframe(
    quantile = quantile_values,                              
    systolic = quantile(systolic, probs = quantile_values, na.rm = TRUE),
    diastolic = quantile(diastolic, probs = quantile_values, na.rm = TRUE)
  ) %>%
  ungroup()
df_grouped<- df_grouped%>% filter(!is.na(gender))


BP_longer<- df_grouped%>% pivot_longer(
  cols = c(systolic,diastolic),
  names_to = "BP_type",
  values_to = "Quan"
)

BP_longer<- BP_longer%>% filter(!is.na(gender))
BP_longer <- BP_longer %>%
  mutate(Quan = as.numeric(Quan))
BP_longer <- BP_longer %>%
  mutate(quantile = as.numeric(quantile))


BP_longer%>%
ggplot (aes(x = quantile, y = Quan,fill=gender)) +
  geom_col(position ="dodge") +
  theme_minimal() +
  facet_wrap(~BP_type,scales ="free")+theme_classic()+
  labs(title = "BP QUANTILE PER GENDER",
       X="QUANTILE",
       Y= " BP",
       FILL=NULL)

bpwider<- BP_longer%>%
  pivot_wider(
    names_from = gender,
    values_from = Quan) %>%
    arrange(BP_type)

```