adult data

getwd()

[1] "C:/Users/Hariharan/Documents"

setwd("C:/Users/Hariharan/Documents")
adult.dataset<-read.csv('adult.csv')

##How many male are not married?
suppressMessages(
adult.dataset %>%
  group_by(gender,marital.status)%>%
  filter(marital.status=="Never-married")%>%
  summarise(gender_count = n()))

##find the summary of the data
summary(adult.dataset)

      age         workclass             fnlwgt         education         educational.num marital.status    
 Min.   :17.00   Length:48842       Min.   :  12285   Length:48842       Min.   : 1.00   Length:48842      
 1st Qu.:28.00   Class :character   1st Qu.: 117551   Class :character   1st Qu.: 9.00   Class :character  
 Median :37.00   Mode  :character   Median : 178145   Mode  :character   Median :10.00   Mode  :character  
 Mean   :38.64                      Mean   : 189664                      Mean   :10.08                     
 3rd Qu.:48.00                      3rd Qu.: 237642                      3rd Qu.:12.00                     
 Max.   :90.00                      Max.   :1490400                      Max.   :16.00                     
  occupation        relationship           race              gender           capital.gain  
 Length:48842       Length:48842       Length:48842       Length:48842       Min.   :    0  
 Class :character   Class :character   Class :character   Class :character   1st Qu.:    0  
 Mode  :character   Mode  :character   Mode  :character   Mode  :character   Median :    0  
                                                                             Mean   : 1079  
                                                                             3rd Qu.:    0  
                                                                             Max.   :99999  
  capital.loss    hours.per.week  native.country        income         
 Min.   :   0.0   Min.   : 1.00   Length:48842       Length:48842      
 1st Qu.:   0.0   1st Qu.:40.00   Class :character   Class :character  
 Median :   0.0   Median :40.00   Mode  :character   Mode  :character  
 Mean   :  87.5   Mean   :40.42                                        
 3rd Qu.:   0.0   3rd Qu.:45.00                                        
 Max.   :4356.0   Max.   :99.00                                        

##how many citizens are high qualified and what is their race?
suppressMessages(
adult.dataset%>%
  group_by(race,educational.num)%>%
  filter(educational.num>=16)%>%
  summarise(citizen_count = n()))

NA

##how many citizens are high qualified and what is their race?
adult.dataset%>%
  group_by(race,educational.num)%>%
  filter(educational.num>=10)%>%
  tally()

##what is the average working hour per week of a person?
mean(adult.dataset$hours.per.week)

[1] 40.42238

##what is the average working hour per week for male and female?
suppressMessages(
adult.dataset%>%
  group_by(gender)%>%
  summarise(mean(hours.per.week)))

NA

##what is the female to male ratio?
suppressMessages(
adult.dataset%>%
  group_by(gender)%>%
  summarise(adult = n()))

NA

##percentage of male citizen
per_male = sum(adult.dataset$gender=="Male")/length(adult.dataset$gender)*100
per_male

[1] 66.8482

##percentage of female
per_female = sum(adult.dataset$gender=="Female")/length(adult.dataset$gender)*100
per_female

[1] 33.1518

##who are never married where their age is above 30
filter(adult.dataset,age>30,marital.status=="Never-married")

##whose occupasion is Prof-specialty and sales
filter(adult.dataset,occupation=="Prof-specialty" | occupation=="sales")

##working hours for male & female
adult.dataset %>%
  select(gender,hours.per.week) %>%
  filter(gender=="Male")

adult.dataset %>%
  select(education,educational.num) %>%
  arrange(desc(educational.num))

adult.dataset%>%
  group_by(education,educational.num)%>%
  tally(sort = TRUE)