list.files("C:/Users/Lenovo/Documents/CuadernosR", pattern=c('csv'))
## [1] "co.csv"
## [2] "Evaluaciones_Agropecuarias_Municipales_EVA.csv"
## [3] "narino_platanos_2020.csv"
## [4] "narino_tuberculosyplatanos_2020.csv"
library(tidyverse)
## -- Attaching packages --------------------------------------- tidyverse 1.3.1 --
## v ggplot2 3.3.5 v purrr 0.3.4
## v tibble 3.1.6 v dplyr 1.0.8
## v tidyr 1.2.0 v stringr 1.4.0
## v readr 2.1.2 v forcats 0.5.1
## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()
(eva = read_csv("C:/Users/Lenovo/Documents/CuadernosR/Evaluaciones_Agropecuarias_Municipales_EVA.csv", col_names = TRUE,
show_col_types = FALSE))
names(eva)
## [1] "CÓD. \nDEP."
## [2] "DEPARTAMENTO"
## [3] "CÓD. MUN."
## [4] "MUNICIPIO"
## [5] "GRUPO \nDE CULTIVO"
## [6] "SUBGRUPO \nDE CULTIVO"
## [7] "CULTIVO"
## [8] "DESAGREGACIÓN REGIONAL Y/O SISTEMA PRODUCTIVO"
## [9] "AÑO"
## [10] "PERIODO"
## [11] "Área Sembrada\n(ha)"
## [12] "Área Cosechada\n(ha)"
## [13] "Producción\n(t)"
## [14] "Rendimiento\n(t/ha)"
## [15] "ESTADO FISICO PRODUCCION"
## [16] "NOMBRE \nCIENTIFICO"
## [17] "CICLO DE CULTIVO"
eva %>% dplyr::select('CÓD. MUN.':'ESTADO FISICO PRODUCCION') -> eva.tmp
eva.tmp
eva.tmp %>% dplyr::rename('Cod_Mun' = 'CÓD. MUN.',
'Grupo' = 'GRUPO \nDE CULTIVO',
'Subgrupo' = 'SUBGRUPO \nDE CULTIVO',
'Year' = 'AÑO',
'AreaSembrada' = 'Área Sembrada\n(ha)',
'AreaCosechada' = 'Área Sembrada\n(ha)',
'Produccion' = 'Producción\n(t)', 'Rendimiento' = 'Rendimiento\n(t/ha)',
'Sistema' = 'DESAGREGACIÓN REGIONAL Y/O SISTEMA PRODUCTIVO',
'Estado' = 'ESTADO FISICO PRODUCCION') -> new_eva
new_eva
new_eva %>%
group_by(Grupo) %>%
summarize(total_produccion = sum(Produccion)) %>%
arrange(desc(total_produccion))
new_eva %>%
group_by(Grupo) %>%
summarize(total_produccion = sum(Produccion)) -> PT
PT %>%
filter(total_produccion > 1000000) -> main.groups
(value = sum(main.groups$total_produccion))
## [1] 13775235
main.groups$percent = main.groups$total_produccion/value
library(ggplot2)
bp<- ggplot(main.groups, aes(x="", y=percent, fill=Grupo))+
geom_bar(width = 1, stat = "identity")
pie <- bp + coord_polar("y", start=0)
pie
new_eva %>%
group_by(Grupo, MUNICIPIO) %>%
summarize(total_prod = sum(Produccion, na.rm = TRUE)) %>%
slice(which.max(total_prod)) %>%
arrange(desc(total_prod))
## `summarise()` has grouped output by 'Grupo'. You can override using the
## `.groups` argument.
new_eva %>%
group_by(Grupo, MUNICIPIO) %>%
summarize(total_prod = sum(Produccion, na.rm = TRUE)) %>%
slice(which.max(total_prod)) -> leaders
## `summarise()` has grouped output by 'Grupo'. You can override using the
## `.groups` argument.
leaders
leaders %>%
filter(total_prod > 50000) -> main.leaders
p<-ggplot(data=main.leaders, aes(x=MUNICIPIO, y=total_prod)) +
geom_bar(stat="identity")
p
new_eva %>%
filter(MUNICIPIO=="TUQUERRES" & CULTIVO=="PAPA") %>%
group_by(Year, CULTIVO) %>%
select(MUNICIPIO, CULTIVO, Produccion, Year) -> papa_tuq
papa_tuq
g <- ggplot(aes(x=Year, y=Produccion/1000), data = papa_tuq) + geom_bar(stat='identity') + labs(y='Produccion de Papa [Ton x 1000]')
g + ggtitle("Evolution of Potato Crop Production in Tuquerres from 2007 to 2018") + labs(caption= "Based on EVA data (Minagricultura, 2020)")
library(rsconnect)
#Bibliography #Lizarazo, I., 2022. Understanding dynamic productivity of crops. Available at https://rpubs.com/ials2un/production_dyn_v1