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# 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,…#1.Menampilkan kolom Entity, Year, Potatoes, dan Cassava saja.
data_select1 <- select(df_crop, Entity, Year,`Potatoes (tonnes per hectare)`,
`Cassava (tonnes per hectare)`)
data_select1## # 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.
data_select2 <- select(df_crop, -c(`Soybeans (tonnes per hectare)`,
`Beans (tonnes per hectare)`,
`Peas (tonnes per hectare)`))
data_select2## # A tibble: 13,075 × 11
## 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 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?
data_filter3 <- filter(df_crop, Entity=="Indonesia", `Rice (tonnes per hectare)` < 2)
data_filter3## # A tibble: 7 × 14
## Entity Code Year `Wheat (tonnes per hectare)` `Rice (tonnes per hectare)`
## <chr> <chr> <dbl> <dbl> <dbl>
## 1 Indonesia IDN 1961 NA 1.76
## 2 Indonesia IDN 1962 NA 1.79
## 3 Indonesia IDN 1963 NA 1.72
## 4 Indonesia IDN 1964 NA 1.76
## 5 Indonesia IDN 1965 NA 1.77
## 6 Indonesia IDN 1966 NA 1.77
## 7 Indonesia IDN 1967 NA 1.76
## # 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>#4.Negara apa saja yang punya hasil gandum (Wheat) di atas 5 ton pada tahun 2000 ke atas?
data_filter4 <- filter(df_crop, Year >= 2000, `Wheat (tonnes per hectare)` > 5)
data_filter4## # A tibble: 424 × 14
## Entity Code Year `Wheat (tonnes per hectare)` `Rice (tonnes per hectare)`
## <chr> <chr> <dbl> <dbl> <dbl>
## 1 Austria AUT 2001 5.24 NA
## 2 Austria AUT 2004 5.92 NA
## 3 Austria AUT 2005 5.03 NA
## 4 Austria AUT 2008 5.69 NA
## 5 Austria AUT 2010 5.01 NA
## 6 Austria AUT 2011 5.85 NA
## 7 Austria AUT 2013 5.37 NA
## 8 Austria AUT 2014 5.92 NA
## 9 Austria AUT 2015 5.70 NA
## 10 Austria AUT 2016 6.25 NA
## # ℹ 414 more rows
## # 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>, …#5.Bagaimana cara memunculkan data negara Indonesia dan Malaysia khusus untuk tahun 2015 saja?
data_filter5 <- filter(df_crop, Entity %in% c("Indonesia","Malaysia"), Year == 2015)
data_filter5## # 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 mana yang punya hasil jagung (Maize) paling rendah di tahun 2020?
data_filter6 <- df_crop %>%
filter(Year == 2020, !is.na(`Maize (tonnes per hectare)`)) %>%
arrange(`Maize (tonnes per hectare)`) %>%
select(Entity, Year, `Maize (tonnes per hectare)`)
data_filter6## # A tibble: 0 × 3
## # ℹ 3 variables: Entity <chr>, Year <dbl>, Maize (tonnes per hectare) <dbl>#7.Mengurutkan data Indonesia dari hasil kentang (Potatoes) yang paling tinggi.
data_filter7 <- df_crop %>%
filter(Entity == "Indonesia", !is.na(`Potatoes (tonnes per hectare)`)) %>%
arrange(desc(`Potatoes (tonnes per hectare)`)) %>%
select(Entity, Year, `Potatoes (tonnes per hectare)`)
data_filter7## # A tibble: 58 × 3
## Entity Year `Potatoes (tonnes per hectare)`
## <chr> <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.
data_mutate8 <- df_crop %>%
mutate(Rice_Status = ifelse(`Rice (tonnes per hectare)` > 4, "Tinggi", "Rendah"))%>%
select(Entity, Year, `Rice (tonnes per hectare)`, Rice_Status)
data_mutate8## # 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.Berapa rata-rata hasil panen pisang (Bananas) di Indonesia dari seluruh tahun yang ada?
data_filter9 <- df_crop %>%
filter(Entity == "Indonesia", !is.na(`Bananas (tonnes per hectare)`)) %>%
summarise(`Rata-rata Bananas` = mean(`Bananas (tonnes per hectare)`, na.rm = TRUE))
data_filter9## # A tibble: 1 × 1
## `Rata-rata 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
data_filter10 <- df_crop %>%
filter(Year >= 2010, !is.na(`Maize (tonnes per hectare)`)) %>%
group_by(Entity) %>%
summarise(Simpangan_Baku = sd(`Maize (tonnes per hectare)`, na.rm = TRUE)) %>%
arrange(desc(Simpangan_Baku))
data_filter10## # A tibble: 202 × 2
## Entity Simpangan_Baku
## <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 192 more rows