#install.packages("tidyverse")
library(tidyverse)
## ── 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

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 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,…
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,…

1. 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)`

2. 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>

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)`
##   <fct>     <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 apa saja 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: 424 × 3
##    Entity   Year `Wheat (tonnes per hectare)`
##    <fct>   <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 414 more rows

5. Bagaimana cara memunculkan data negara Indonesia dan Malaysia khusus untuk tahun 2015 saja?

filter(df_crop,
       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>

6. Negara mana yang punya 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)`)%>%
slice(1)
## # A tibble: 0 × 3
## # ℹ 3 variables: Entity <fct>, Year <dbl>, Maize (tonnes per hectare) <dbl>

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

filter(df_crop,
       Entity == "Indonesia") %>%
  arrange(desc(`Potatoes (tonnes per hectare)`)) %>%
  select(Entity, Year, `Potatoes (tonnes per hectare)`)
## # A tibble: 58 × 3
##    Entity     Year `Potatoes (tonnes per hectare)`
##    <fct>     <dbl>                           <dbl>
##  1 Indonesia  2018                            18.7
##  2 Indonesia  2016                            18.3
##  3 Indonesia  2015                            18.2
##  4 Indonesia  2014                            17.7
##  5 Indonesia  2006                            16.9
##  6 Indonesia  2008                            16.7
##  7 Indonesia  1995                            16.6
##  8 Indonesia  2012                            16.6
##  9 Indonesia  2009                            16.5
## 10 Indonesia  2005                            16.4
## # ℹ 48 more rows

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

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
##    <fct>       <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. Berapa rata-rata hasil panen pisang (Bananas) di Indonesia dari seluruh tahun yang ada?

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

10. Tampilkan 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(`SD Maize` =
              sd(`Maize (tonnes per hectare)`,
                 na.rm = TRUE)) %>%
  filter(!is.na(`SD Maize`)) %>%
  arrange(desc(`SD Maize`))
## # A tibble: 202 × 2
##    Entity                           `SD Maize`
##    <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 192 more rows