#Firstly I upload Tidyverse and call esoph data-set
library(tidyverse)
## Loading tidyverse: ggplot2
## Loading tidyverse: tibble
## Loading tidyverse: tidyr
## Loading tidyverse: readr
## Loading tidyverse: purrr
## Loading tidyverse: dplyr
## Conflicts with tidy packages ----------------------------------------------
## filter(): dplyr, stats
## lag(): dplyr, stats
esoph
## agegp alcgp tobgp ncases ncontrols
## 1 25-34 0-39g/day 0-9g/day 0 40
## 2 25-34 0-39g/day 10-19 0 10
## 3 25-34 0-39g/day 20-29 0 6
## 4 25-34 0-39g/day 30+ 0 5
## 5 25-34 40-79 0-9g/day 0 27
## 6 25-34 40-79 10-19 0 7
## 7 25-34 40-79 20-29 0 4
## 8 25-34 40-79 30+ 0 7
## 9 25-34 80-119 0-9g/day 0 2
## 10 25-34 80-119 10-19 0 1
## 11 25-34 80-119 30+ 0 2
## 12 25-34 120+ 0-9g/day 0 1
## 13 25-34 120+ 10-19 1 1
## 14 25-34 120+ 20-29 0 1
## 15 25-34 120+ 30+ 0 2
## 16 35-44 0-39g/day 0-9g/day 0 60
## 17 35-44 0-39g/day 10-19 1 14
## 18 35-44 0-39g/day 20-29 0 7
## 19 35-44 0-39g/day 30+ 0 8
## 20 35-44 40-79 0-9g/day 0 35
## 21 35-44 40-79 10-19 3 23
## 22 35-44 40-79 20-29 1 14
## 23 35-44 40-79 30+ 0 8
## 24 35-44 80-119 0-9g/day 0 11
## 25 35-44 80-119 10-19 0 6
## 26 35-44 80-119 20-29 0 2
## 27 35-44 80-119 30+ 0 1
## 28 35-44 120+ 0-9g/day 2 3
## 29 35-44 120+ 10-19 0 3
## 30 35-44 120+ 20-29 2 4
## 31 45-54 0-39g/day 0-9g/day 1 46
## 32 45-54 0-39g/day 10-19 0 18
## 33 45-54 0-39g/day 20-29 0 10
## 34 45-54 0-39g/day 30+ 0 4
## 35 45-54 40-79 0-9g/day 6 38
## 36 45-54 40-79 10-19 4 21
## 37 45-54 40-79 20-29 5 15
## 38 45-54 40-79 30+ 5 7
## 39 45-54 80-119 0-9g/day 3 16
## 40 45-54 80-119 10-19 6 14
## 41 45-54 80-119 20-29 1 5
## 42 45-54 80-119 30+ 2 4
## 43 45-54 120+ 0-9g/day 4 4
## 44 45-54 120+ 10-19 3 4
## 45 45-54 120+ 20-29 2 3
## 46 45-54 120+ 30+ 4 4
## 47 55-64 0-39g/day 0-9g/day 2 49
## 48 55-64 0-39g/day 10-19 3 22
## 49 55-64 0-39g/day 20-29 3 12
## 50 55-64 0-39g/day 30+ 4 6
## 51 55-64 40-79 0-9g/day 9 40
## 52 55-64 40-79 10-19 6 21
## 53 55-64 40-79 20-29 4 17
## 54 55-64 40-79 30+ 3 6
## 55 55-64 80-119 0-9g/day 9 18
## 56 55-64 80-119 10-19 8 15
## 57 55-64 80-119 20-29 3 6
## 58 55-64 80-119 30+ 4 4
## 59 55-64 120+ 0-9g/day 5 10
## 60 55-64 120+ 10-19 6 7
## 61 55-64 120+ 20-29 2 3
## 62 55-64 120+ 30+ 5 6
## 63 65-74 0-39g/day 0-9g/day 5 48
## 64 65-74 0-39g/day 10-19 4 14
## 65 65-74 0-39g/day 20-29 2 7
## 66 65-74 0-39g/day 30+ 0 2
## 67 65-74 40-79 0-9g/day 17 34
## 68 65-74 40-79 10-19 3 10
## 69 65-74 40-79 20-29 5 9
## 70 65-74 80-119 0-9g/day 6 13
## 71 65-74 80-119 10-19 4 12
## 72 65-74 80-119 20-29 2 3
## 73 65-74 80-119 30+ 1 1
## 74 65-74 120+ 0-9g/day 3 4
## 75 65-74 120+ 10-19 1 2
## 76 65-74 120+ 20-29 1 1
## 77 65-74 120+ 30+ 1 1
## 78 75+ 0-39g/day 0-9g/day 1 18
## 79 75+ 0-39g/day 10-19 2 6
## 80 75+ 0-39g/day 30+ 1 3
## 81 75+ 40-79 0-9g/day 2 5
## 82 75+ 40-79 10-19 1 3
## 83 75+ 40-79 20-29 0 3
## 84 75+ 40-79 30+ 1 1
## 85 75+ 80-119 0-9g/day 1 1
## 86 75+ 80-119 10-19 1 1
## 87 75+ 120+ 0-9g/day 2 2
## 88 75+ 120+ 10-19 1 1
#Taking a look at the summary of the data
summary(esoph)
## agegp alcgp tobgp ncases ncontrols
## 25-34:15 0-39g/day:23 0-9g/day:24 Min. : 0.000 Min. : 1.00
## 35-44:15 40-79 :23 10-19 :24 1st Qu.: 0.000 1st Qu.: 3.00
## 45-54:16 80-119 :21 20-29 :20 Median : 1.000 Median : 6.00
## 55-64:16 120+ :21 30+ :20 Mean : 2.273 Mean :11.08
## 65-74:15 3rd Qu.: 4.000 3rd Qu.:14.00
## 75+ :11 Max. :17.000 Max. :60.00
#Seems like I have 5 variables, and the cancer cases are shown by "ncases"
#Lets check the number of cases by alcohol consumption and show them according to age groups
qplot(x=ncases,y=alcgp, data=esoph)+
facet_wrap(~agegp)
#I would like to check mean of the cases by alcohol consumption.
alc <- group_by(esoph, alcgp)
alc
## # A tibble: 88 x 5
## # Groups: alcgp [4]
## agegp alcgp tobgp ncases ncontrols
## <ord> <ord> <ord> <dbl> <dbl>
## 1 25-34 0-39g/day 0-9g/day 0 40
## 2 25-34 0-39g/day 10-19 0 10
## 3 25-34 0-39g/day 20-29 0 6
## 4 25-34 0-39g/day 30+ 0 5
## 5 25-34 40-79 0-9g/day 0 27
## 6 25-34 40-79 10-19 0 7
## 7 25-34 40-79 20-29 0 4
## 8 25-34 40-79 30+ 0 7
## 9 25-34 80-119 0-9g/day 0 2
## 10 25-34 80-119 10-19 0 1
## # ... with 78 more rows
a <- summarise(alc,ncases_mean = mean(ncases))
a
## # A tibble: 4 x 2
## alcgp ncases_mean
## <ord> <dbl>
## 1 0-39g/day 1.260870
## 2 40-79 3.260870
## 3 80-119 2.428571
## 4 120+ 2.142857
#And I check the median
b <- summarize(alc,ncases_median=median(ncases))
b
## # A tibble: 4 x 2
## alcgp ncases_median
## <ord> <dbl>
## 1 0-39g/day 1
## 2 40-79 3
## 3 80-119 1
## 4 120+ 2
# ggplot the ncases and alcgp
ggplot(aes(ncases, alcgp), data=esoph)+
scale_x_continuous(lim = c(0,20))+
geom_point(color="purple")
# ggplot the ncases and tobgp
ggplot(aes(x=ncases, y=tobgp), data=esoph)+
scale_x_continuous(lim = c(0,50))+
geom_point(color="red")
#Finally I check the tobacco usage by grouping alcohol usage
ggplot(aes(x=ncases, y=tobgp), data=esoph)+
scale_x_continuous(lim = c(0,20))+
geom_point(color="pink")+
facet_wrap(~alcgp)
