Menggunakan package 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   4.0.3     ✔ 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

Menyiapkan file data

# Menyimpan URL raw data GitHub ke dalam variabel
url <- "https://raw.githubusercontent.com/rfordatascience/tidytuesday/main/data/2020/2020-09-01/key_crop_yields.csv"

# Membaca data read_csv
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.
# Melihat data
glimpse(df_crop)
## Rows: 13,075
## Columns: 14
## $ Entity                             <chr> "Afghanistan", "Afghanistan", "Afgh…
## $ Code                               <chr> "AFG", "AFG", "AFG", "AFG", "AFG", …
## $ Year                               <dbl> 1961, 1962, 1963, 1964, 1965, 1966,…
## $ `Wheat (tonnes per hectare)`       <dbl> 1.0220, 0.9735, 0.8317, 0.9510, 0.9…
## $ `Rice (tonnes per hectare)`        <dbl> 1.5190, 1.5190, 1.5190, 1.7273, 1.7…
## $ `Maize (tonnes per hectare)`       <dbl> 1.4000, 1.4000, 1.4260, 1.4257, 1.4…
## $ `Soybeans (tonnes per hectare)`    <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA,…
## $ `Potatoes (tonnes per hectare)`    <dbl> 8.6667, 7.6667, 8.1333, 8.6000, 8.8…
## $ `Beans (tonnes per hectare)`       <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA,…
## $ `Peas (tonnes per hectare)`        <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA,…
## $ `Cassava (tonnes per hectare)`     <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA,…
## $ `Barley (tonnes per hectare)`      <dbl> 1.0800, 1.0800, 1.0800, 1.0857, 1.0…
## $ `Cocoa beans (tonnes per hectare)` <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA,…
## $ `Bananas (tonnes per hectare)`     <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA,…
# Mengubah semua kolom berkarakter (character) menjadi factor
df_crop$Entity <- as.factor(df_crop$Entity)
df_crop$Code <- as.factor(df_crop$Code)

# Periksa apakah ada perubahan
glimpse(df_crop)
## Rows: 13,075
## Columns: 14
## $ Entity                             <fct> "Afghanistan", "Afghanistan", "Afgh…
## $ Code                               <fct> AFG, AFG, AFG, AFG, AFG, AFG, AFG, …
## $ Year                               <dbl> 1961, 1962, 1963, 1964, 1965, 1966,…
## $ `Wheat (tonnes per hectare)`       <dbl> 1.0220, 0.9735, 0.8317, 0.9510, 0.9…
## $ `Rice (tonnes per hectare)`        <dbl> 1.5190, 1.5190, 1.5190, 1.7273, 1.7…
## $ `Maize (tonnes per hectare)`       <dbl> 1.4000, 1.4000, 1.4260, 1.4257, 1.4…
## $ `Soybeans (tonnes per hectare)`    <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA,…
## $ `Potatoes (tonnes per hectare)`    <dbl> 8.6667, 7.6667, 8.1333, 8.6000, 8.8…
## $ `Beans (tonnes per hectare)`       <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA,…
## $ `Peas (tonnes per hectare)`        <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA,…
## $ `Cassava (tonnes per hectare)`     <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA,…
## $ `Barley (tonnes per hectare)`      <dbl> 1.0800, 1.0800, 1.0800, 1.0857, 1.0…
## $ `Cocoa beans (tonnes per hectare)` <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA,…
## $ `Bananas (tonnes per hectare)`     <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA,…
# Semua char jadi factor

Menampilkan kolom Entity, Year, Potatoes, dan Cassava saja.

data_select <- select(df_crop, Entity, Year, `Potatoes (tonnes per hectare)`, `Cassava (tonnes per hectare)`)
data_select
## # A tibble: 13,075 × 4
##    Entity       Year `Potatoes (tonnes per hectare)` Cassava (tonnes per hecta…¹
##    <fct>       <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)`

Mengeliminasi kolom Soybeans, Beans, dan Peas dari tabel.

select(df_crop, -c(`Soybeans (tonnes per hectare)`, `Beans (tonnes per hectare)`, `Peas (tonnes per hectare)`))
## # A tibble: 13,075 × 11
##    Entity      Code   Year `Wheat (tonnes per hectare)` Rice (tonnes per hecta…¹
##    <fct>       <fct> <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 6 more variables: `Maize (tonnes per hectare)` <dbl>,
## #   `Potatoes (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>

Menampilkan tahun ketika hasil panen padi (Rice) di Indonesia nilainya di bawah 2 ton

df_crop %>% filter(Entity == "Indonesia", `Rice (tonnes per hectare)` < 2) %>% select(Year)
## # A tibble: 7 × 1
##    Year
##   <dbl>
## 1  1961
## 2  1962
## 3  1963
## 4  1964
## 5  1965
## 6  1966
## 7  1967

Menampilkan negara yang punya hasil gandum (Wheat) di atas 5 ton pada tahun 2000 ke atas

#distinct untuk menampilkan nama yang unik saja, jadi tidak ada nama berulang
df_crop %>% filter(`Wheat (tonnes per hectare)` > 5, Year >= 2000) %>% distinct(Entity)
## # A tibble: 36 × 1
##    Entity         
##    <fct>          
##  1 Austria        
##  2 Belgium        
##  3 Bulgaria       
##  4 Central America
##  5 Chile          
##  6 China          
##  7 Croatia        
##  8 Czech Republic 
##  9 Denmark        
## 10 Eastern Asia   
## # ℹ 26 more rows

Cara memunculkan data negara Indonesia dan Malaysia khusus untuk tahun 2015 saja

df_crop %>% filter(Entity %in% c("Indonesia", "Malaysia"), Year == 2015)
## # A tibble: 2 × 14
##   Entity    Code   Year `Wheat (tonnes per hectare)` `Rice (tonnes per hectare)`
##   <fct>     <fct> <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>

Menampilkan negara yang punya hasil jagung (Maize) paling rendah di tahun 2020

df_crop %>% 
  filter(Year == 2020) %>% 
  filter(`Maize (tonnes per hectare)` ==  min(`Maize (tonnes per hectare)`, na.rm = TRUE)) %>%
  select(Entity, `Maize (tonnes per hectare)`)
## Warning: There was 1 warning in `filter()`.
## ℹ In argument: `==...`.
## Caused by warning in `min()`:
## ! no non-missing arguments to min; returning Inf
## # A tibble: 0 × 2
## # ℹ 2 variables: Entity <fct>, Maize (tonnes per hectare) <dbl>

Memang tidak ada output yang sesuai kriteria

Mengurutkan data Indonesia dari hasil kentang (Potatoes) yang paling tinggi.

df_crop %>% 
  filter(Entity == 'Indonesia') %>% 
  arrange(desc(`Potatoes (tonnes per hectare)`))
## # A tibble: 58 × 14
##    Entity    Code   Year `Wheat (tonnes per hectare)` Rice (tonnes per hectare…¹
##    <fct>     <fct> <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>, …

Membuat kolom Rice_Status berisi teks “Tinggi” jika padi > 4 ton, dan “Rendah” jika di bawahnya.

df_crop %>% 
  mutate(Rice_Status = ifelse(`Wheat (tonnes per hectare)` > 4, "Tinggi", "Rendah")) %>% select(Code,Year,Rice_Status)
## # A tibble: 13,075 × 3
##    Code   Year Rice_Status
##    <fct> <dbl> <chr>      
##  1 AFG    1961 Rendah     
##  2 AFG    1962 Rendah     
##  3 AFG    1963 Rendah     
##  4 AFG    1964 Rendah     
##  5 AFG    1965 Rendah     
##  6 AFG    1966 Rendah     
##  7 AFG    1967 Rendah     
##  8 AFG    1968 Rendah     
##  9 AFG    1969 Rendah     
## 10 AFG    1970 Rendah     
## # ℹ 13,065 more rows

Menampilkan rata-rata hasil panen pisang (Bananas) di Indonesia dari seluruh tahun yang ada

df_crop %>% 
  filter(Entity == 'Indonesia') %>% 
  summarise(`Bananas (tonnes per hectare)` = mean(`Bananas (tonnes per hectare)`, na.rm = TRUE))
## # A tibble: 1 × 1
##   `Bananas (tonnes per hectare)`
##                            <dbl>
## 1                           30.5

Menampilkan data jagung mulai tahun 2010, lalu menghitung simpangan baku per negara, dan mengurutkannya dari nilai yang paling besar

df_crop %>% 
  filter(Year >= 2010) %>%
  group_by(Entity) %>% 
  summarise(`Simpangan Baku Jagung` = sd(`Maize (tonnes per hectare)`, na.rm = TRUE)) %>%
  arrange(desc(`Simpangan Baku Jagung`))
## # A tibble: 242 × 2
##    Entity                           `Simpangan Baku Jagung`
##    <fct>                                              <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