# solution WS 1 Data Management

# ex. 1
# a. importing file mgus2.xlsx from wd
library(readxl)
library(xlsx)
mgus2 = read_excel("path")

# b. list of variables
ls(data)

# c. meaning of variables
?mgus2

# d. checking categorical and numeric variables
#  categorical variables

data$sex <- factor(data$sex,
                      levels = c('F', 'M'),
                      labels = c('female', 'male'))
data$pstat <- factor(data$pstat,
                        levels = c('0', '1'),
                        labels = c('no', 'yes'))
data$death <- factor(data$death,
                        levels = c('0', '1'),
                        labels = c('no', 'yes'))

#  continuous variables 
data$hgb <- as.numeric(data$hgb)
data$creat <- as.numeric(data$creat)
data$mspike <- as.numeric(data$mspike)


# ex. 2
# a. subset female patients
female <- subset(data, data$sex == "female")

# b. save as excel file
write.xlsx(female, file = "E:/Malawi 2024/Summer School Malawi/Data/mgus2_female.xlsx")

# c. deleting variable id
data$id <- NULL

# d. add categorical variable "fu_cat"
data$fu_cat[data$futime < 60] <- 1
data$fu_cat[(data$futime >= 60) & (data$futime < 120)] <- 2
data$fu_cat[(data$futime >= 120) & (data$futime < 180)] <- 3
data$fu_cat[data$futime >= 180] <- 4
#  declaring new variable as categorial
data$fu_cat <- factor(data$fu_cat, 
                        levels = c('1', '2', '3', '4'),
                        labels = c('< 5 yrs', '5 - 10 yrs', '10 - 15 yrs', '> 15 yrs'))

# e. add categorical variable "age_qt" using quartiles
library(stats)
#  find quartiles
quantile(data$age)
#  create new variable
data$age_qt[data$age < 63] <- 1
data$age_qt[(data$age >= 63) & (data$age < 72)] <- 2
data$age_qt[(data$age >= 72) & (data$age < 79)] <- 3
data$age_qt[data$age >= 79] <- 4
# declare as categorical and change labels
data$age_qt <- factor(data$age_qt, 
                        levels = c('1', '2', '3', '4'),
                        labels = c('< 63 yrs', '63 - 71 yrs', '72 - 78 yrs', '> 78 yrs'))

View(data)

min(mgus2$age)
max(mgus2$age)

mgus2$agecat2[mgus2$age < 40] <- '< 40 yrs'
mgus2$agecat2[(mgus2$age >= 40) & (mgus2$age < 60)] <- 2
mgus2$agecat2[(mgus2$age >= 60) & (mgus2$age < 80)] <- 3
mgus2$agecat2[mgus2$age >= 80] <- 4

mgus2$agecat <- factor(mgus2$agecat, 
                      levels = c('1', '2', '3', '4'),
                      labels = c('< 40 yrs', '40 - 60 yrs', '60 - 80 yrs', '> 80 yrs'))
summary(mgus2$age)
table(mgus2$agecat)

par(mfrow=c(1,2))
hist(mgus2$age,
     breaks = 50, # variable to determine how many bars are used
     xlab = "age",
     main = "",
     probability = TRUE)
hist(mgus2$age,
     breaks = 50, # variable to determine how many bars are used
     xlab = "age",
     main = "",
     probability = FALSE)

curve(dnorm(x, mean = mean(mgus2$age, na.rm = T), sd = sd(mgus2$age, na.rm = T)), # use mean and sd of variable
      add = TRUE, # added to previous graph
      col = "red")