library(ISwR)
attach(stroke)

names(stroke)

is.data.frame(stroke)
stroke$age  # extract a single variable (indexing part of the data frame)
stroke[, "age"]  # equivalent to the previous one (indexing part of the data frame, array, list)
stroke[1:5, 1:3] # extract selected rows and selected column numbers
stroke[c(12, 20, 505), ] # extract selected rows and all columns

age_ordered <- stroke[order(stroke$age), ] # order the data frame

names(age_ordered)

head(stroke) 

stroke[age_ordered$age>80, c("age", "dgn", "coma", "diab")] # extract using the conditional logic 

age_ordered[age_ordered$age>80, c("age", "dgn", "coma", "diab")] # extract using the conditional logic 

nrow(stroke)
sum(is.na(stroke$diab)) # How to count the number of rows with NA's ('diab' column) in the data frame

sum(stroke$diab == 'Yes', na.rm=TRUE) # How to count the number of rows with 'Yes'  ("diab" column) in the data frame

sum(stroke$diab == 'No', na.rm=TRUE) # How to count the number of rows with 'No' ("diab" column) in the data frame

table(stroke$diab)    # frequency table
table(stroke['diab']) #  equivalent to the previous one - how to count the number of occurrences in a column

ls()

rm(list = ())
###################

library(dplyr)

# Create a data frame
df1 <- data.frame(sex= c('Male','Female', 'Male', 'Female'), num = c(1,2,3,4) )
df1

# Create a 1/0 variable from a chatracter variable (Male/Female)
df1$is_male <- (df1$sex %in% 'Male')*1

# Create a logical variable (RUE/FALSE) from a chatracter variable (Male/Female)
df2 <-  within(df1, (is_male = sex %in% 'Male')*1 )

# Create a 1/0 variable from a character variable (Male/Female)
df3 <- mutate(df1, is_male = (sex %in% 'Male')*1)

data.frame(df1$is_male, df2$is_male,  df3$is_male)


#############

setwd("C:/r-basics/Data")
getwd()


load ("class_x.rdata")
class <-class_x

class <- within(class, { gender_fac1 <- factor(sex,levels=c ('M','F'),
                                           labels=c('Male', 'Female'))                                   
})


class$gender_fac2 <- factor(class$sex, labels=c('Male Student', 'Female Student'))

class[order(class$gender_fac1), ]

library(Hmisc)
contents(class)

##########

setwd ("C:/r-basics/Data")
load("class_x.rdata")

t_class_x <- class_x
names(t_class_x)

library (Hmisc)
contents(t_class_x)

library(tidyverse)

# Create new variables
class <- t_class_x %>% 
  mutate(male_dummy = case_when(sex=="M" ~ 1,
                                sex=="F"~ 0),
         weight_cat=case_when((weight <= 100)      ~ '<=100',
                   (weight > 100) & (weight <= 115) ~ '100-115',
                   (weight > 115)               ~ '116+'),
         
         female_dummy = if_else(sex=='F', 1,0),
         age_cat= cut(age, breaks=c(11, 12, 13, 14, 16),
                      labels=c("11-12", "12-13", "14-15", "15-16"),
                  include.lowest=TRUE, stringsAsFactors = FALSE)
                ) 

   table(class$weight_cat)
   
  table(class$male_dummy)
  table(class$female_dummy)
  table(class$age_cat)
  
###########
test <- data.frame(vara1=1:10,varb1=2:11,vara2=3:12,varb2=4:13)
test
test[paste0("varc",1:2)] <- test[paste0("vara",1:2)]
        + test[paste0("varb",1:2)]
test

############
library(ISwR)
attach(stroke)
some_object <- as.data.frame(table(cut(age, c(1, 29, 49, 64, 96))))
some_object
ls()
search()
rm(list = ls() )