Casos COVID Talara
library(readxl)
## Warning: package 'readxl' was built under R version 4.0.4
library(tidyverse)
## Warning: package 'tidyverse' was built under R version 4.0.5
## -- Attaching packages --------------------------------------- tidyverse 1.3.1 --
## v ggplot2 3.3.3 v purrr 0.3.4
## v tibble 3.1.1 v dplyr 1.0.5
## v tidyr 1.1.3 v stringr 1.4.0
## v readr 1.4.0 v forcats 0.5.1
## Warning: package 'ggplot2' was built under R version 4.0.5
## Warning: package 'tibble' was built under R version 4.0.5
## Warning: package 'tidyr' was built under R version 4.0.4
## Warning: package 'readr' was built under R version 4.0.4
## Warning: package 'purrr' was built under R version 4.0.4
## Warning: package 'dplyr' was built under R version 4.0.4
## Warning: package 'stringr' was built under R version 4.0.4
## Warning: package 'forcats' was built under R version 4.0.4
## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()
read_csv2("data/positivos_covid.csv")
## i Using '\',\'' as decimal and '\'.\'' as grouping mark. Use `read_delim()` for more control.
##
## -- Column specification --------------------------------------------------------
## cols(
## FECHA_CORTE = col_double(),
## UUID = col_character(),
## DEPARTAMENTO = col_character(),
## PROVINCIA = col_character(),
## DISTRITO = col_character(),
## METODODX = col_character(),
## EDAD = col_double(),
## SEXO = col_character(),
## FECHA_RESULTADO = col_double()
## )
## # A tibble: 2,019,716 x 9
## FECHA_CORTE UUID DEPARTAMENTO PROVINCIA DISTRITO METODODX EDAD SEXO
## <dbl> <chr> <chr> <chr> <chr> <chr> <dbl> <chr>
## 1 20210616 7320cabdc~ LIMA LIMA LIMA PR 35 FEME~
## 2 20210616 e81602051~ LIMA LIMA PACHACAMAC PR 36 FEME~
## 3 20210616 cecdbf100~ LIMA LIMA LIMA PR 36 FEME~
## 4 20210616 71ecb6bcc~ LIMA LIMA LIMA PR 37 FEME~
## 5 20210616 566af4276~ LIMA LIMA LIMA PR 37 FEME~
## 6 20210616 027561e9d~ LIMA LIMA PACHACAMAC PR 38 FEME~
## 7 20210616 f016889b9~ LIMA LIMA PACHACAMAC PR 38 FEME~
## 8 20210616 971f8e129~ LIMA LIMA CARABAYLLO PR 35 FEME~
## 9 20210616 bc45b71b0~ LIMA LIMA LIMA PR 35 FEME~
## 10 20210616 0e2a1928d~ LIMA LIMA SAN JUAN ~ PR 35 FEME~
## # ... with 2,019,706 more rows, and 1 more variable: FECHA_RESULTADO <dbl>
positivos_covid <- read_csv2("data/positivos_covid.csv")
## i Using '\',\'' as decimal and '\'.\'' as grouping mark. Use `read_delim()` for more control.
##
## -- Column specification --------------------------------------------------------
## cols(
## FECHA_CORTE = col_double(),
## UUID = col_character(),
## DEPARTAMENTO = col_character(),
## PROVINCIA = col_character(),
## DISTRITO = col_character(),
## METODODX = col_character(),
## EDAD = col_double(),
## SEXO = col_character(),
## FECHA_RESULTADO = col_double()
## )
positivos_covid %>%
select(FECHA_RESULTADO, PROVINCIA, DISTRITO, SEXO, EDAD) %>%
filter (PROVINCIA == "TALARA") %>%
group_by(DISTRITO) %>%
summarise(total_casos = n()) %>%
arrange(desc(total_casos))
## # A tibble: 6 x 2
## DISTRITO total_casos
## <chr> <int>
## 1 PARIÑAS 3223
## 2 MANCORA 690
## 3 LOS ORGANOS 518
## 4 LA BREA 515
## 5 EL ALTO 289
## 6 LOBITOS 65
positivos_covid %>%
select(FECHA_RESULTADO, PROVINCIA, DISTRITO, SEXO, EDAD) %>%
filter (PROVINCIA == "TALARA") %>%
group_by(DISTRITO) %>%
summarise(total_casos = n()) %>%
arrange(desc(total_casos)) %>%
ungroup() %>%
ggplot(aes(DISTRITO, total_casos, fill = DISTRITO)) +
geom_col() +
labs (title = "Casos COVID-19 positivos", subtitle = "Talara según distritos", x = "Distrito", y = "N° de casos")
IDH Talara
read_xlsx("data/idh_distritos_2019.xlsx")
## New names:
## * `` -> ...2
## # A tibble: 1,874 x 15
## UBIGEO ...2 Distrito habitantes ranking_hab IDH ranking_IDH años
## <chr> <dbl> <chr> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 010101 1 Chachapoyas 33038. 171 0.642 125 72.2
## 2 010102 2 Asuncion 267. 1861 0.423 765 71.4
## 3 010103 3 Balsas 1467. 1443 0.315 1355 68.6
## 4 010104 4 Cheto 585. 1749 0.346 1159 77.5
## 5 010105 5 Chiliquin 391. 1829 0.275 1563 72.5
## 6 010106 6 Chuquibamba 1789. 1365 0.269 1593 67.0
## 7 010107 7 Granada 337. 1844 0.358 1091 66.2
## 8 010108 8 Huancas 1457. 1448 0.415 806 73.1
## 9 010109 9 La Jalca 4279. 899 0.295 1459 73.1
## 10 010110 10 Leimebamba 3855. 963 0.399 881 70.3
## # ... with 1,864 more rows, and 7 more variables: ranking_años <dbl>,
## # edu_sec_porc <dbl>, edu_ranking <dbl>, años_edu <dbl>,
## # ranking_años_edu <dbl>, ing_fam_pc <dbl>, ranking_ing <dbl>
idh_distritos_2019 <- read_xlsx("data/idh_distritos_2019.xlsx")
## New names:
## * `` -> ...2
idh_talara <- idh_distritos_2019 %>%
filter( Distrito %in% c("El Alto", "La Brea", "Lobitos", "Los Organos", "Mancora", "Pariñas")) %>%
select(Distrito, IDH, habitantes) %>%
mutate(Distrito = str_to_upper(Distrito)) %>%
mutate(DISTRITO = Distrito) %>%
select("IDH", "DISTRITO", "habitantes")
idh_talara %>%
arrange(desc(IDH))
## # A tibble: 6 x 3
## IDH DISTRITO habitantes
## <dbl> <chr> <dbl>
## 1 0.592 LOBITOS 1553.
## 2 0.590 PARIÑAS 89997.
## 3 0.588 LA BREA 10993.
## 4 0.575 EL ALTO 7348.
## 5 0.563 LOS ORGANOS 9570.
## 6 0.561 MANCORA 14045.
idh_talara %>%
ggplot(aes(DISTRITO, IDH)) +
geom_col(fill = "red")+
labs(title= "IDH Talara", subtitle = "Según distritos", x = "Distritos", y = "IDH")
Componentes IDH, habitantes, ingreso
idh_talara_hab <- idh_distritos_2019 %>%
select(Distrito, habitantes) %>%
filter(c(Distrito %in% c("El Alto", "La Brea", "Lobitos", "Los Organos", "Mancora", "Pariñas"))) %>%
arrange(desc(habitantes))
idh_talara_hab
## # A tibble: 6 x 2
## Distrito habitantes
## <chr> <dbl>
## 1 Pariñas 89997.
## 2 Mancora 14045.
## 3 La Brea 10993.
## 4 Los Organos 9570.
## 5 El Alto 7348.
## 6 Lobitos 1553.
idh_talara_hab %>%
ggplot(aes( Distrito, habitantes)) +
geom_col(fill = "red")+
labs(title= "Habitantes", subtitle = "Según distritos", x = "Distritos", y = "Habitantes")
idh_talara_ing <- idh_distritos_2019 %>%
select(Distrito, ing_fam_pc) %>%
filter(c(Distrito %in% c("El Alto", "La Brea", "Lobitos", "Los Organos", "Mancora", "Pariñas"))) %>%
arrange(desc(ing_fam_pc))
idh_talara_ing
## # A tibble: 6 x 2
## Distrito ing_fam_pc
## <chr> <dbl>
## 1 Lobitos 1021.
## 2 Pariñas 1001.
## 3 El Alto 929.
## 4 Mancora 905.
## 5 La Brea 896.
## 6 Los Organos 894.
idh_talara_ing %>%
ggplot(aes( Distrito, ing_fam_pc)) +
geom_col(fill = "red")+
labs(title= "Ingreso Familiar per Cápita", subtitle = "Según distritos", x = "Distritos", y = "Ingresos")
