praktik 1 komstat
2026-05-22
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 errorsurl <- "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.data_select <- select(df_crop, Entity, Year, `Potatoes (tonnes per hectare)`, `Cassava (tonnes per hectare)` ) #1
data_select## # 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)`select(df_crop, -c(`Soybeans (tonnes per hectare)`, `Beans (tonnes per hectare)`, 'Peas (tonnes per hectare)')) #2## # 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>filter(df_crop,Code=="IDN" , `Rice (tonnes per hectare)` <2.0 ) #3## # 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>filter(df_crop, Year > 2000, `Wheat (tonnes per hectare)` >5.0 ) #4## # A tibble: 406 × 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 396 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>, …df_crop %>%
filter(Code %in% c("IDN", "MYS"), Year == 2015) #5## # 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>df_crop %>%
filter(Year == 2020) %>%
arrange(`Maize (tonnes per hectare)`) #6## # A tibble: 0 × 14
## # ℹ 14 variables: Entity <chr>, Code <chr>, Year <dbl>,
## # Wheat (tonnes per hectare) <dbl>, Rice (tonnes per hectare) <dbl>,
## # 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>df_crop %>%
filter(Code == "IDN") %>%
arrange(desc(`Potatoes (tonnes per hectare)`)) %>%
select(Entity, Code, Year, `Potatoes (tonnes per hectare)`) #7## # A tibble: 58 × 4
## Entity Code Year `Potatoes (tonnes per hectare)`
## <chr> <chr> <dbl> <dbl>
## 1 Indonesia IDN 2018 18.7
## 2 Indonesia IDN 2016 18.3
## 3 Indonesia IDN 2015 18.2
## 4 Indonesia IDN 2014 17.7
## 5 Indonesia IDN 2006 16.9
## 6 Indonesia IDN 2008 16.7
## 7 Indonesia IDN 1995 16.6
## 8 Indonesia IDN 2012 16.6
## 9 Indonesia IDN 2009 16.5
## 10 Indonesia IDN 2005 16.4
## # ℹ 48 more rowsmutate(df_crop, `Wheat (kg per hectare)` = `Wheat (tonnes per hectare)` * 1000)## # A tibble: 13,075 × 15
## 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 10 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>, …df_crop %>%
mutate( Rice_Status = ifelse(`Wheat (tonnes per hectare)` > 4, "Tinggi", "Rendah")) %>% select(Code,Year, Rice_Status) #8## # A tibble: 13,075 × 3
## Code Year Rice_Status
## <chr> <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 rowsdf_crop %>%
filter(Code == "IDN") %>%
group_by(Code) %>%
summarise(`Mean Bananas (tonnes per hectare)` = mean(`Bananas (tonnes per hectare)`, na.rm = TRUE)) #9## # A tibble: 1 × 2
## Code `Mean Bananas (tonnes per hectare)`
## <chr> <dbl>
## 1 IDN 30.5df_crop %>%
filter(Year >= 2010) %>%
group_by(Entity) %>%
summarise(`SD Maize` = sd(`Maize (tonnes per hectare)`, na.rm = TRUE)) %>%
arrange(desc(`SD Maize`)) #10## # 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 rowsR Markdown
This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.
When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:
summary(cars)## speed dist
## Min. : 4.0 Min. : 2.00
## 1st Qu.:12.0 1st Qu.: 26.00
## Median :15.0 Median : 36.00
## Mean :15.4 Mean : 42.98
## 3rd Qu.:19.0 3rd Qu.: 56.00
## Max. :25.0 Max. :120.00Including Plots
You can also embed plots, for example:
Note that the echo = FALSE parameter was added to the
code chunk to prevent printing of the R code that generated the
plot.