R Notebook
attach(Exercise)#Exploring the Data
names(Exercise) #To check Variable names [1] "ID" "Analyse_result" "birth_date" "Gender" "slaughter_date"
[6] "n_movement" "herdsize" "mlkpct" "krypct" "kkrpct"
[11] "prodtype" "n_herd_1km" "n_cattle_1km" "n_sheep_1km" "n_goat_1km"
[16] "n_herd_5km" "n_cattle_5km" "n_sheep_5km" "n_goat_5km" "age"
[21] "res" "Breed_Type" "newres" "breed" "sex"
[26] "br_dy" "br_cr" "n_cattle1km" "n_sheep1km" "n_goat1km"
[31] "n_cattle5km" "n_sheep5km" "n_goat5km" "n_total1km" "n_total5km"
[36] "ht" str(Exercise) #To Check Variable typetibble [800 × 36] (S3: tbl_df/tbl/data.frame)
$ ID : num [1:800] 1.01e+09 1.02e+09 1.02e+09 1.03e+09 1.05e+09 ...
$ Analyse_result: num [1:800] 6.77 4.22 14.67 3.88 -2.01 ...
$ birth_date : POSIXct[1:800], format: "2011-05-07" "2010-09-13" ...
$ Gender : chr [1:800] "Male" "Male" "Male" "Male" ...
$ slaughter_date: POSIXct[1:800], format: "2012-09-18" "2012-10-01" ...
$ n_movement : num [1:800] 3 3 4 2 2 2 2 2 2 2 ...
$ herdsize : num [1:800] 14 196 97 5 7 65 13 52 68 28 ...
$ mlkpct : num [1:800] 64.4 73 45.1 0 0 ...
$ krypct : num [1:800] 22.1 27 17.8 32.5 100 ...
$ kkrpct : num [1:800] 13.4 0 37.1 67.5 0 ...
$ prodtype : chr [1:800] "m" "m" "m" "k" ...
$ n_herd_1km : num [1:800] 0 6 3 2 3 5 5 3 0 7 ...
$ n_cattle_1km : num [1:800] 0 4 1 1 2 4 1 2 0 4 ...
$ n_sheep_1km : num [1:800] 0 3 1 1 2 2 2 1 0 3 ...
$ n_goat_1km : num [1:800] 0 1 1 0 0 1 2 0 0 0 ...
$ n_herd_5km : num [1:800] 39 68 50 45 50 91 62 101 41 43 ...
$ n_cattle_5km : num [1:800] 16 38 33 25 19 67 33 65 20 21 ...
$ n_sheep_5km : num [1:800] 21 24 12 13 30 36 30 47 25 22 ...
$ n_goat_5km : num [1:800] 8 10 6 9 11 9 9 10 7 5 ...
$ age : num [1:800] 1.37 2.05 0.69 1 1.46 ...
$ res : chr [1:800] "Neg" "Neg" "Neg" "Neg" ...
$ Breed_Type : chr [1:800] "Dairy" "Dairy" "Dairy" "Beef" ...
$ newres : num [1:800] 1 1 1 1 1 1 1 1 1 1 ...
$ breed : chr [1:800] "RDM" "RDM" "HOL" "oth" ...
$ sex : num [1:800] 1 1 1 1 1 1 1 1 2 2 ...
$ br_dy : num [1:800] 2 2 2 1 1 2 1 1 1 1 ...
$ br_cr : num [1:800] 1 1 1 1 2 1 1 2 2 2 ...
$ n_cattle1km : num [1:800] 0 82 458 21 18 79 4 511 0 48 ...
$ n_sheep1km : num [1:800] 0 42 11 11 17 22 6 2 0 164 ...
$ n_goat1km : num [1:800] 0 9 1 0 0 9 10 0 0 0 ...
$ n_cattle5km : num [1:800] 385 826 4592 1339 320 ...
$ n_sheep5km : num [1:800] 367 259 140 642 356 380 658 914 580 394 ...
$ n_goat5km : num [1:800] 44 43 14 79 48 48 53 47 102 21 ...
$ n_total1km : num [1:800] 0 133 470 32 35 110 20 513 0 212 ...
$ n_total5km : num [1:800] 796 1128 4746 2060 724 ...
$ ht : chr [1:800] "Beeef" "Beeef" "Beeef" "Beeef" ...summary(Exercise) # TO find missing values ID Analyse_result birth_date Gender
Min. :1.010e+09 Min. : -2.990 Min. :1994-11-20 00:00:00 Length:800
1st Qu.:3.105e+09 1st Qu.: 2.045 1st Qu.:2010-03-04 18:00:00 Class :character
Median :4.840e+09 Median : 4.660 Median :2011-04-02 12:00:00 Mode :character
Mean :4.989e+09 Mean : 12.083 Mean :2010-03-04 20:36:36
3rd Qu.:6.443e+09 3rd Qu.: 8.693 3rd Qu.:2011-07-09 06:00:00
Max. :1.173e+10 Max. :402.000 Max. :2012-01-25 00:00:00
slaughter_date n_movement herdsize mlkpct
Min. :2012-07-02 00:00:00 Min. : 2.000 Min. : 1.0 Min. : 0.000
1st Qu.:2012-08-01 00:00:00 1st Qu.: 2.000 1st Qu.: 23.0 1st Qu.: 0.000
Median :2012-08-21 00:00:00 Median : 2.000 Median : 56.0 Median : 7.572
Mean :2012-08-24 03:41:24 Mean : 2.839 Mean : 119.3 Mean : 34.314
3rd Qu.:2012-09-19 00:00:00 3rd Qu.: 3.000 3rd Qu.: 133.0 3rd Qu.: 79.663
Max. :2012-10-16 00:00:00 Max. :11.000 Max. :1792.0 Max. :100.000
NA's :3
krypct kkrpct prodtype n_herd_1km n_cattle_1km
Min. : 0.000 Min. : 0.00 Length:800 Min. : 0.000 Min. :0.000
1st Qu.: 1.912 1st Qu.: 0.00 Class :character 1st Qu.: 1.000 1st Qu.:1.000
Median : 15.305 Median : 20.80 Mode :character Median : 2.000 Median :2.000
Mean : 27.599 Mean : 38.09 Mean : 2.612 Mean :1.933
3rd Qu.: 46.733 3rd Qu.: 82.11 3rd Qu.: 4.000 3rd Qu.:3.000
Max. :100.000 Max. :100.00 Max. :12.000 Max. :8.000
n_sheep_1km n_goat_1km n_herd_5km n_cattle_5km n_sheep_5km
Min. :0.0000 Min. :0.000 Min. : 0.00 Min. : 0.00 Min. : 0.00
1st Qu.:0.0000 1st Qu.:0.000 1st Qu.: 41.00 1st Qu.:28.00 1st Qu.: 8.00
Median :0.0000 Median :0.000 Median : 53.00 Median :39.00 Median :12.00
Mean :0.6388 Mean :0.335 Mean : 52.94 Mean :39.06 Mean :13.23
3rd Qu.:1.0000 3rd Qu.:1.000 3rd Qu.: 65.00 3rd Qu.:49.00 3rd Qu.:17.00
Max. :5.0000 Max. :5.000 Max. :101.00 Max. :76.00 Max. :47.00
n_goat_5km age res Breed_Type newres
Min. : 0.000 Min. : 0.611 Length:800 Length:800 Min. :1.000
1st Qu.: 4.000 1st Qu.: 1.110 Class :character Class :character 1st Qu.:1.000
Median : 5.000 Median : 1.390 Mode :character Mode :character Median :1.000
Mean : 6.051 Mean : 2.475 Mean :1.055
3rd Qu.: 8.000 3rd Qu.: 2.489 3rd Qu.:1.000
Max. :22.000 Max. :17.805 Max. :2.000
breed sex br_dy br_cr n_cattle1km
Length:800 Min. :1.000 Min. :1.000 Min. :1.000 Min. : 0.0
Class :character 1st Qu.:1.000 1st Qu.:1.000 1st Qu.:1.000 1st Qu.: 4.0
Mode :character Median :1.000 Median :1.000 Median :1.000 Median : 42.0
Mean :1.384 Mean :1.331 Mean :1.284 Mean : 178.2
3rd Qu.:2.000 3rd Qu.:2.000 3rd Qu.:2.000 3rd Qu.: 258.0
Max. :2.000 Max. :2.000 Max. :2.000 Max. :1399.0
n_sheep1km n_goat1km n_cattle5km n_sheep5km n_goat5km
Min. : 0.00 Min. : 0.000 Min. : 0 Min. : 0.0 Min. : 0.00
1st Qu.: 0.00 1st Qu.: 0.000 1st Qu.: 1441 1st Qu.: 87.0 1st Qu.: 11.00
Median : 0.00 Median : 0.000 Median : 3218 Median : 158.5 Median : 21.00
Mean : 11.09 Mean : 2.039 Mean : 3851 Mean : 289.7 Mean : 42.11
3rd Qu.: 6.25 3rd Qu.: 0.000 3rd Qu.: 5689 3rd Qu.: 311.0 3rd Qu.: 37.00
Max. :800.00 Max. :586.000 Max. :12292 Max. :3623.0 Max. :2005.00
n_total1km n_total5km ht
Min. : 0.00 Min. : 0 Length:800
1st Qu.: 10.75 1st Qu.: 1764 Class :character
Median : 57.50 Median : 3481 Mode :character
Mean : 191.37 Mean : 4183
3rd Qu.: 277.75 3rd Qu.: 5959
Max. :1422.00 Max. :13034
head(Exercise) # View the first few rows#Frequency Table
table(Gender)Gender
Female Male
307 493 table(prodtype)prodtype
k m x
302 299 199 table(res)res
Neg Pos
756 44 table(sex)sex
1 2
493 307 table(br_dy)br_dy
1 2
535 265 table(br_cr)br_cr
1 2
573 227 table(ht)ht
Beeef Dairy
716 84 # 2*2 table
con = table (Gender, res)
con res
Gender Neg Pos
Female 279 28
Male 477 16ftable(Gender~res + ht, data=Exercise) # a flat contingency table for three or more variables. Gender Female Male
res ht
Neg Beeef 223 461
Dairy 56 16
Pos Beeef 17 15
Dairy 11 1#Proportion
count = table(Gender)
countGender
Female Male
307 493 Proportion = count/800
ProportionGender
Female Male
0.38375 0.61625 #Another way
prop.table(table(Gender))Gender
Female Male
0.38375 0.61625 #Percent
Percent = Proportion * 100
PercentGender
Female Male
38.375 61.625 #Ratio
count3 = table(res)
count3res
Neg Pos
756 44 ratio = count3["Neg"]/count3["Pos"]
ratio Neg
17.18182 #Categorical data visualization, Bar Chart, pie chart, Stacked Bar Chart,Mosaic Plot, Dot Plot
#Bar Chart
library(ggplot2)
ggplot(data = Exercise, aes(x=Gender, y= , fill = Gender))+
geom_bar()+
scale_fill_manual(values = c("Female" = "red", "Male"= "green" ))+
labs(title = "Barchart of Male and Female", x = "Gender", y = "Frequency")+
theme_minimal()
# Pie Chart
pie(Percent, main = "Pie Chart of Prod Type", col = rainbow(length(Percent)))
# Stacked Bar Chart
ggplot(data = Exercise, aes(x=Gender, fill = res))+
geom_bar(position = "stack")+
labs(title = "Barchart of Male and Female", x = "Gender", y = "Frequency", fill = "Status")+
theme_minimal()
#Dot Plot
ggplot(data = Exercise, aes(x=Gender,fill = Gender))+
geom_dotplot()
#Dot Plot 2*2
ggplot(data = Exercise, aes(x=Gender,fill = ht))+
geom_dotplot()+
labs(fill = "Herd Type")+
theme_minimal()
#Mosaic Plot
mosaicplot(con, main="Mosaic Plot of Gender and Disease Status",xlab = "Gender", ylab = "Status", col= rainbow(length(con)))
detach(Exercise)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