databaru <- data.frame(datasets::Titanic)
databaru## Class Sex Age Survived Freq
## 1 1st Male Child No 0
## 2 2nd Male Child No 0
## 3 3rd Male Child No 35
## 4 Crew Male Child No 0
## 5 1st Female Child No 0
## 6 2nd Female Child No 0
## 7 3rd Female Child No 17
## 8 Crew Female Child No 0
## 9 1st Male Adult No 118
## 10 2nd Male Adult No 154
## 11 3rd Male Adult No 387
## 12 Crew Male Adult No 670
## 13 1st Female Adult No 4
## 14 2nd Female Adult No 13
## 15 3rd Female Adult No 89
## 16 Crew Female Adult No 3
## 17 1st Male Child Yes 5
## 18 2nd Male Child Yes 11
## 19 3rd Male Child Yes 13
## 20 Crew Male Child Yes 0
## 21 1st Female Child Yes 1
## 22 2nd Female Child Yes 13
## 23 3rd Female Child Yes 14
## 24 Crew Female Child Yes 0
## 25 1st Male Adult Yes 57
## 26 2nd Male Adult Yes 14
## 27 3rd Male Adult Yes 75
## 28 Crew Male Adult Yes 192
## 29 1st Female Adult Yes 140
## 30 2nd Female Adult Yes 80
## 31 3rd Female Adult Yes 76
## 32 Crew Female Adult Yes 20library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, uniondatabaru2 <- select(databaru, Class, Sex, Survived)
head(databaru2)## Class Sex Survived
## 1 1st Male No
## 2 2nd Male No
## 3 3rd Male No
## 4 Crew Male No
## 5 1st Female No
## 6 2nd Female Nodatabaru3 <- filter(databaru, Age == "Child")
databaru_sorted_asc <- arrange(databaru, Freq)
head(databaru_sorted_asc)## Class Sex Age Survived Freq
## 1 1st Male Child No 0
## 2 2nd Male Child No 0
## 3 Crew Male Child No 0
## 4 1st Female Child No 0
## 5 2nd Female Child No 0
## 6 Crew Female Child No 0#tanpa head(batas)
databaru3 <- filter(databaru, Age == "Child")
databaru_sorted_asc <- arrange(databaru, Freq)
(databaru_sorted_asc)## Class Sex Age Survived Freq
## 1 1st Male Child No 0
## 2 2nd Male Child No 0
## 3 Crew Male Child No 0
## 4 1st Female Child No 0
## 5 2nd Female Child No 0
## 6 Crew Female Child No 0
## 7 Crew Male Child Yes 0
## 8 Crew Female Child Yes 0
## 9 1st Female Child Yes 1
## 10 Crew Female Adult No 3
## 11 1st Female Adult No 4
## 12 1st Male Child Yes 5
## 13 2nd Male Child Yes 11
## 14 2nd Female Adult No 13
## 15 3rd Male Child Yes 13
## 16 2nd Female Child Yes 13
## 17 3rd Female Child Yes 14
## 18 2nd Male Adult Yes 14
## 19 3rd Female Child No 17
## 20 Crew Female Adult Yes 20
## 21 3rd Male Child No 35
## 22 1st Male Adult Yes 57
## 23 3rd Male Adult Yes 75
## 24 3rd Female Adult Yes 76
## 25 2nd Female Adult Yes 80
## 26 3rd Female Adult No 89
## 27 1st Male Adult No 118
## 28 1st Female Adult Yes 140
## 29 2nd Male Adult No 154
## 30 Crew Male Adult Yes 192
## 31 3rd Male Adult No 387
## 32 Crew Male Adult No 670databaru3 <- filter(databaru, Age == "Child")
databaru_sorted_desc <- arrange(databaru, desc (Freq))
head(databaru_sorted_desc)## Class Sex Age Survived Freq
## 1 Crew Male Adult No 670
## 2 3rd Male Adult No 387
## 3 Crew Male Adult Yes 192
## 4 2nd Male Adult No 154
## 5 1st Female Adult Yes 140
## 6 1st Male Adult No 118databaru_rename <- rename(databaru, Umur = Age)
databaru_rename## Class Sex Umur Survived Freq
## 1 1st Male Child No 0
## 2 2nd Male Child No 0
## 3 3rd Male Child No 35
## 4 Crew Male Child No 0
## 5 1st Female Child No 0
## 6 2nd Female Child No 0
## 7 3rd Female Child No 17
## 8 Crew Female Child No 0
## 9 1st Male Adult No 118
## 10 2nd Male Adult No 154
## 11 3rd Male Adult No 387
## 12 Crew Male Adult No 670
## 13 1st Female Adult No 4
## 14 2nd Female Adult No 13
## 15 3rd Female Adult No 89
## 16 Crew Female Adult No 3
## 17 1st Male Child Yes 5
## 18 2nd Male Child Yes 11
## 19 3rd Male Child Yes 13
## 20 Crew Male Child Yes 0
## 21 1st Female Child Yes 1
## 22 2nd Female Child Yes 13
## 23 3rd Female Child Yes 14
## 24 Crew Female Child Yes 0
## 25 1st Male Adult Yes 57
## 26 2nd Male Adult Yes 14
## 27 3rd Male Adult Yes 75
## 28 Crew Male Adult Yes 192
## 29 1st Female Adult Yes 140
## 30 2nd Female Adult Yes 80
## 31 3rd Female Adult Yes 76
## 32 Crew Female Adult Yes 20databaru_mutate <- mutate(databaru, Proporsi = Freq/sum(Freq))
head(databaru_mutate)## Class Sex Age Survived Freq Proporsi
## 1 1st Male Child No 0 0.00000000
## 2 2nd Male Child No 0 0.00000000
## 3 3rd Male Child No 35 0.01590186
## 4 Crew Male Child No 0 0.00000000
## 5 1st Female Child No 0 0.00000000
## 6 2nd Female Child No 0 0.00000000extra <- data.frame(Class = c("1st","2nd","3rd","Crew"),
Kapal = c("databaru","databaru","databaru","databaru"))
databaru_joined <- left_join(databaru, extra, by = "Class")
head(databaru_joined)## Class Sex Age Survived Freq Kapal
## 1 1st Male Child No 0 databaru
## 2 2nd Male Child No 0 databaru
## 3 3rd Male Child No 35 databaru
## 4 Crew Male Child No 0 databaru
## 5 1st Female Child No 0 databaru
## 6 2nd Female Child No 0 databaruextra <- data.frame(Class = c("1st","2nd","3rd","Crew"),
Kapal = c("databaru","databaru","databaru","databaru"))
databaru_joined <- right_join(databaru, extra, by = "Class")
head(databaru_joined)## Class Sex Age Survived Freq Kapal
## 1 1st Male Child No 0 databaru
## 2 2nd Male Child No 0 databaru
## 3 3rd Male Child No 35 databaru
## 4 Crew Male Child No 0 databaru
## 5 1st Female Child No 0 databaru
## 6 2nd Female Child No 0 databarudatabaru_summary <- databaru %>%
group_by(Class, Survived) %>%
summarise(total = sum(Freq))## `summarise()` has regrouped the output.
## ℹ Summaries were computed grouped by Class and Survived.
## ℹ Output is grouped by Class.
## ℹ Use `summarise(.groups = "drop_last")` to silence this message.
## ℹ Use `summarise(.by = c(Class, Survived))` for per-operation grouping
## (`?dplyr::dplyr_by`) instead.databaru_summary## # A tibble: 8 × 3
## # Groups: Class [4]
## Class Survived total
## <fct> <fct> <dbl>
## 1 1st No 122
## 2 1st Yes 203
## 3 2nd No 167
## 4 2nd Yes 118
## 5 3rd No 528
## 6 3rd Yes 178
## 7 Crew No 673
## 8 Crew Yes 212databaru_summary <- databaru %>%
group_by(Sex, Age) %>%
summarise(total = sum(Freq))## `summarise()` has regrouped the output.
## ℹ Summaries were computed grouped by Sex and Age.
## ℹ Output is grouped by Sex.
## ℹ Use `summarise(.groups = "drop_last")` to silence this message.
## ℹ Use `summarise(.by = c(Sex, Age))` for per-operation grouping
## (`?dplyr::dplyr_by`) instead.databaru_summary## # A tibble: 4 × 3
## # Groups: Sex [2]
## Sex Age total
## <fct> <fct> <dbl>
## 1 Male Child 64
## 2 Male Adult 1667
## 3 Female Child 45
## 4 Female Adult 425databaru_summary <- databaru %>%
group_by(Sex, Age, Survived, Class) %>%
summarise(total = sum(Freq))## `summarise()` has regrouped the output.
## ℹ Summaries were computed grouped by Sex, Age, Survived, and Class.
## ℹ Output is grouped by Sex, Age, and Survived.
## ℹ Use `summarise(.groups = "drop_last")` to silence this message.
## ℹ Use `summarise(.by = c(Sex, Age, Survived, Class))` for per-operation
## grouping (`?dplyr::dplyr_by`) instead.databaru_summary## # A tibble: 32 × 5
## # Groups: Sex, Age, Survived [8]
## Sex Age Survived Class total
## <fct> <fct> <fct> <fct> <dbl>
## 1 Male Child No 1st 0
## 2 Male Child No 2nd 0
## 3 Male Child No 3rd 35
## 4 Male Child No Crew 0
## 5 Male Child Yes 1st 5
## 6 Male Child Yes 2nd 11
## 7 Male Child Yes 3rd 13
## 8 Male Child Yes Crew 0
## 9 Male Adult No 1st 118
## 10 Male Adult No 2nd 154
## # ℹ 22 more rowsset.seed(123)
index <- sample(1:nrow(databaru), 0.7*nrow(databaru))
train_data <- databaru[index, ]
test_data <- databaru[-index, ]
nrow(train_data); nrow(test_data)## [1] 22## [1] 10