url <- "https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2020/2020-09-01/key_crop_yields.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.
#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,
-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
## <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?
df_crop %>%
filter(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 apa saja yang punya hasil gandum (Wheat) di atas 5 ton pada tahun 2000 ke atas?
df_crop %>%
filter(`Wheat (tonnes per hectare)` > 5, Year >= 2000) %>%
select(Entity, Year, `Wheat (tonnes per hectare)`) %>%
arrange(desc(`Wheat (tonnes per hectare)`))
## # A tibble: 424 × 3
## Entity Year `Wheat (tonnes per hectare)`
## <chr> <dbl> <dbl>
## 1 Ireland 2015 10.7
## 2 Ireland 2017 10.2
## 3 Belgium 2015 10.0
## 4 Ireland 2014 10.0
## 5 Zambia 2008 9.94
## 6 Ireland 2004 9.92
## 7 New Zealand 2017 9.86
## 8 Ireland 2011 9.86
## 9 Ireland 2016 9.54
## 10 Belgium 2009 9.47
## # ℹ 414 more rows
#5.Bagaimana 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)`
## <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?
df_crop %>%
filter(Year == 2020, !is.na(`Maize (tonnes per hectare)`)) %>%
arrange(`Maize (tonnes per hectare)`) %>%
select(Entity, Year, `Maize (tonnes per hectare)`) %>%
slice(1)
## # A tibble: 0 × 3
## # ℹ 3 variables: Entity <chr>, Year <dbl>, Maize (tonnes per hectare) <dbl>
print("Tidak ada data tahun 2020 karena dataset hanya tersedia dari tahun 1961 sampai 2018.")
## [1] "Tidak ada data tahun 2020 karena dataset hanya tersedia dari tahun 1961 sampai 2018."
#7.Mengurutkan data Indonesia dari hasil kentang (Potatoes) yang paling tinggi.
df_crop %>%
filter(Entity == "Indonesia") %>%
select(Entity, Year, `Potatoes (tonnes per hectare)`) %>%
arrange(desc(`Potatoes (tonnes per hectare)`))
## # 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.
df_crop %>%
filter(Entity == "Indonesia") %>%
mutate(Rice_Status = ifelse(`Rice (tonnes per hectare)` > 4,
"Tinggi",
"Rendah")) %>%
select(Entity, Year, `Rice (tonnes per hectare)`, Rice_Status)
## # A tibble: 58 × 4
## Entity Year `Rice (tonnes per hectare)` Rice_Status
## <chr> <dbl> <dbl> <chr>
## 1 Indonesia 1961 1.76 Rendah
## 2 Indonesia 1962 1.79 Rendah
## 3 Indonesia 1963 1.72 Rendah
## 4 Indonesia 1964 1.76 Rendah
## 5 Indonesia 1965 1.77 Rendah
## 6 Indonesia 1966 1.77 Rendah
## 7 Indonesia 1967 1.76 Rendah
## 8 Indonesia 1968 2.14 Rendah
## 9 Indonesia 1969 2.25 Rendah
## 10 Indonesia 1970 2.38 Rendah
## # ℹ 48 more rows
#9.Berapa rata-rata hasil panen pisang (Bananas) di Indonesia dari seluruh tahun yang ada?
df_crop %>%
filter(Entity == "Indonesia") %>%
summarise(rata_rata_Bananas =
mean(`Bananas (tonnes per hectare)`, na.rm = TRUE))
## # 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.
df_crop %>%
filter(Year >= 2010,
!is.na(`Maize (tonnes per hectare)`)) %>%
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
## <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