#Praktik 1 #Silahkan buat RMarkdown baru dan jawab setiap pertanyaan menggunakan fungsi-fungsi yang telah dipelajari pada RMarkdown tersebut dengan menampilkan kode dan outputnya. RMarkdown yang telah selesai lalu publikasi pada RPubs, dan link publikasi nya dapat dikirimkan di SIMARI pada tanggal 28 Mei 2026 dalam rentang 18.00-20.00 WITA.
#install.packages("tidyverse")
library(tidyverse)## Warning: package 'tidyverse' was built under R version 4.5.3## Warning: package 'ggplot2' was built under R version 4.5.3## Warning: package 'tidyr' was built under R version 4.5.3## Warning: package 'purrr' was built under R version 4.5.3## Warning: package 'dplyr' was built under R version 4.5.3## Warning: package 'stringr' was built under R version 4.5.3## Warning: package 'forcats' was built under R version 4.5.3## Warning: package 'lubridate' was built under R version 4.5.3## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.2.1 ✔ readr 2.2.0
## ✔ forcats 1.0.1 ✔ stringr 1.6.0
## ✔ ggplot2 4.0.2 ✔ tibble 3.3.1
## ✔ lubridate 1.9.5 ✔ tidyr 1.3.2
## ✔ purrr 1.2.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors# Menyimpan URL raw data Github ke dalam variabel
url <- "https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2020/2020-09-01/key_crop_yields.csv"
# Membaca data
df_crop <- read_csv(url)## Rows: 13075 Columns: 14
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (2): Entity, Code
## dbl (12): Year, Wheat (tonnes per hectare), Rice (tonnes per hectare), Maize...
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.#1. Menampilkan kolom Entity, Year, Potatoes, dan Cassava saja
select(df_crop,
Entity,
Year,
`Potatoes (tonnes per hectare)`,
`Cassava (tonnes per hectare)`)## # A tibble: 13,075 × 4
## Entity Year `Potatoes (tonnes per hectare)` Cassava (tonnes per hecta…¹
## <chr> <dbl> <dbl> <dbl>
## 1 Afghanistan 1961 8.67 NA
## 2 Afghanistan 1962 7.67 NA
## 3 Afghanistan 1963 8.13 NA
## 4 Afghanistan 1964 8.6 NA
## 5 Afghanistan 1965 8.8 NA
## 6 Afghanistan 1966 9.07 NA
## 7 Afghanistan 1967 9.8 NA
## 8 Afghanistan 1968 10 NA
## 9 Afghanistan 1969 10.2 NA
## 10 Afghanistan 1970 9.54 NA
## # ℹ 13,065 more rows
## # ℹ abbreviated name: ¹`Cassava (tonnes per hectare)`#2. Mengeliminasi kolom Soybeans, Beans, dan Peas dari tabel
select(df_crop,
-contains("Soybeans"),
-contains("Beans"),
-contains("Peas"))## # A tibble: 13,075 × 10
## Entity Code Year `Wheat (tonnes per hectare)` Rice (tonnes per hecta…¹
## <chr> <chr> <dbl> <dbl> <dbl>
## 1 Afghanistan AFG 1961 1.02 1.52
## 2 Afghanistan AFG 1962 0.974 1.52
## 3 Afghanistan AFG 1963 0.832 1.52
## 4 Afghanistan AFG 1964 0.951 1.73
## 5 Afghanistan AFG 1965 0.972 1.73
## 6 Afghanistan AFG 1966 0.867 1.52
## 7 Afghanistan AFG 1967 1.12 1.92
## 8 Afghanistan AFG 1968 1.16 1.95
## 9 Afghanistan AFG 1969 1.19 1.98
## 10 Afghanistan AFG 1970 0.956 1.81
## # ℹ 13,065 more rows
## # ℹ abbreviated name: ¹`Rice (tonnes per hectare)`
## # ℹ 5 more variables: `Maize (tonnes per hectare)` <dbl>,
## # `Potatoes (tonnes per hectare)` <dbl>,
## # `Cassava (tonnes per hectare)` <dbl>, `Barley (tonnes per hectare)` <dbl>,
## # `Bananas (tonnes per hectare)` <dbl>#3. Tahun berapa saja hasil panen padi (Rice) di Indonesia yang nilainya di bawah 2 ton
filter(df_crop,
Entity=="Indonesia",
`Rice (tonnes per hectare)` < 2) %>%
select(Entity,
Year,
`Rice (tonnes per hectare)`)## # A tibble: 7 × 3
## Entity Year `Rice (tonnes per hectare)`
## <chr> <dbl> <dbl>
## 1 Indonesia 1961 1.76
## 2 Indonesia 1962 1.79
## 3 Indonesia 1963 1.72
## 4 Indonesia 1964 1.76
## 5 Indonesia 1965 1.77
## 6 Indonesia 1966 1.77
## 7 Indonesia 1967 1.76#4. Negara yang punya hasil gandum (Wheat) di atas 5 ton pada tahun 2000 ke atas
filter(df_crop,
Year > 2000,
`Wheat (tonnes per hectare)` > 5) %>%
select(Entity,
Year,
`Wheat (tonnes per hectare)`)## # A tibble: 406 × 3
## Entity Year `Wheat (tonnes per hectare)`
## <chr> <dbl> <dbl>
## 1 Austria 2001 5.24
## 2 Austria 2004 5.92
## 3 Austria 2005 5.03
## 4 Austria 2008 5.69
## 5 Austria 2010 5.01
## 6 Austria 2011 5.85
## 7 Austria 2013 5.37
## 8 Austria 2014 5.92
## 9 Austria 2015 5.70
## 10 Austria 2016 6.25
## # ℹ 396 more rows#Nomor 5 #5. Menampilkan data negara Indonesia dan Malaysia khusus tahun 2015
filter(df_crop,
(Entity=="Indonesia" | Entity=="Malaysia"),
Year==2015)## # A tibble: 2 × 14
## Entity Code Year `Wheat (tonnes per hectare)` `Rice (tonnes per hectare)`
## <chr> <chr> <dbl> <dbl> <dbl>
## 1 Indonesia IDN 2015 NA 5.34
## 2 Malaysia MYS 2015 NA 4.02
## # ℹ 9 more variables: `Maize (tonnes per hectare)` <dbl>,
## # `Soybeans (tonnes per hectare)` <dbl>,
## # `Potatoes (tonnes per hectare)` <dbl>, `Beans (tonnes per hectare)` <dbl>,
## # `Peas (tonnes per hectare)` <dbl>, `Cassava (tonnes per hectare)` <dbl>,
## # `Barley (tonnes per hectare)` <dbl>,
## # `Cocoa beans (tonnes per hectare)` <dbl>,
## # `Bananas (tonnes per hectare)` <dbl>#6. Negara dengan hasil jagung (Maize) paling rendah di tahun 2020
filter(df_crop,
Year==2020) %>%
arrange(`Maize (tonnes per hectare)`) %>%
select(Entity,
Year,
`Maize (tonnes per hectare)`)## # A tibble: 0 × 3
## # ℹ 3 variables: Entity <chr>, Year <dbl>, Maize (tonnes per hectare) <dbl>#7. Mengurutkan data Indonesia dari hasil kentang (Potatoes) paling tinggi
filter(df_crop,
Entity=="Indonesia") %>%
arrange(desc(`Potatoes (tonnes per hectare)`))## # A tibble: 58 × 14
## Entity Code Year `Wheat (tonnes per hectare)` Rice (tonnes per hectare…¹
## <chr> <chr> <dbl> <dbl> <dbl>
## 1 Indonesia IDN 2018 NA 5.19
## 2 Indonesia IDN 2016 NA 5.24
## 3 Indonesia IDN 2015 NA 5.34
## 4 Indonesia IDN 2014 NA 5.13
## 5 Indonesia IDN 2006 NA 4.62
## 6 Indonesia IDN 2008 NA 4.89
## 7 Indonesia IDN 1995 NA 4.35
## 8 Indonesia IDN 2012 NA 5.14
## 9 Indonesia IDN 2009 NA 5.00
## 10 Indonesia IDN 2005 NA 4.57
## # ℹ 48 more rows
## # ℹ abbreviated name: ¹`Rice (tonnes per hectare)`
## # ℹ 9 more variables: `Maize (tonnes per hectare)` <dbl>,
## # `Soybeans (tonnes per hectare)` <dbl>,
## # `Potatoes (tonnes per hectare)` <dbl>, `Beans (tonnes per hectare)` <dbl>,
## # `Peas (tonnes per hectare)` <dbl>, `Cassava (tonnes per hectare)` <dbl>,
## # `Barley (tonnes per hectare)` <dbl>, …#8. Membuat kolom Rice_Status
df_crop %>%
mutate(Rice_Status = ifelse(`Rice (tonnes per hectare)` > 4,
"Tinggi",
"Rendah")) %>%
select(Entity,
Year,
`Rice (tonnes per hectare)`,
Rice_Status)## # A tibble: 13,075 × 4
## Entity Year `Rice (tonnes per hectare)` Rice_Status
## <chr> <dbl> <dbl> <chr>
## 1 Afghanistan 1961 1.52 Rendah
## 2 Afghanistan 1962 1.52 Rendah
## 3 Afghanistan 1963 1.52 Rendah
## 4 Afghanistan 1964 1.73 Rendah
## 5 Afghanistan 1965 1.73 Rendah
## 6 Afghanistan 1966 1.52 Rendah
## 7 Afghanistan 1967 1.92 Rendah
## 8 Afghanistan 1968 1.95 Rendah
## 9 Afghanistan 1969 1.98 Rendah
## 10 Afghanistan 1970 1.81 Rendah
## # ℹ 13,065 more rows#9. Rata-rata hasil panen pisang (Bananas) di Indonesia
filter(df_crop,
Entity=="Indonesia") %>%
summarise(`Mean Bananas` = mean(`Bananas (tonnes per hectare)`,
na.rm = TRUE))## # A tibble: 1 × 1
## `Mean Bananas`
## <dbl>
## 1 30.5#10. Menampilkan data jagung mulai tahun 2010 kemudian menghitung simpangan baku per negara
filter(df_crop,
Year >= 2010) %>%
group_by(Entity) %>%
summarise(`SD Maize` = sd(`Maize (tonnes per hectare)`,
na.rm = TRUE)) %>%
arrange(desc(`SD Maize`))## # A tibble: 242 × 2
## Entity `SD Maize`
## <chr> <dbl>
## 1 Kuwait 9.24
## 2 United Arab Emirates 9.19
## 3 Jordan 7.03
## 4 Israel 4.80
## 5 Saint Vincent and the Grenadines 2.89
## 6 Qatar 2.74
## 7 French Guiana 2.50
## 8 New Caledonia 2.29
## 9 Slovakia 1.68
## 10 Oman 1.61
## # ℹ 232 more rows