title: "Desarrollo tarea06"
author: "ingrid castaño"
date: "2024-07-26"
output: html_document
library(dplyr)
##
## Adjuntando el paquete: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(dslabs)
library(viridisLite)
library(RColorBrewer)
library(readr)
Indice_pobreza <-read_csv("test_values.csv")
## Rows: 8400 Columns: 59
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (5): country, religion, relationship_to_hh_head, employment_category_la...
## dbl (17): row_id, age, education_level, share_hh_income_provided, num_times_...
## lgl (37): is_urban, female, married, literacy, can_add, can_divide, can_calc...
##
## 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.
#Indice_pobreza<-Indice_pobreza %>% mutate_if()
# delimitar por ; ya que es el delimitador que maneja el archivo
Indice_pobreza %>% head(10)
## # A tibble: 10 × 59
## row_id country is_urban age female married religion relationship_to_hh_head
## <dbl> <chr> <lgl> <dbl> <lgl> <lgl> <chr> <chr>
## 1 0 F FALSE 57 TRUE TRUE X Father/Mother
## 2 1 C FALSE 40 FALSE TRUE P Head
## 3 2 I FALSE 35 TRUE TRUE Q Spouse
## 4 3 I TRUE 19 TRUE FALSE Q Son/Daughter
## 5 4 A FALSE 61 TRUE TRUE Q Father/Mother
## 6 5 A TRUE 16 TRUE FALSE Q Son/Daughter
## 7 6 F FALSE 40 FALSE TRUE Q Head
## 8 7 C FALSE 27 TRUE TRUE P Spouse
## 9 8 A TRUE 35 FALSE TRUE Q Head
## 10 9 J FALSE 72 TRUE FALSE X Head
## # ℹ 51 more variables: education_level <dbl>, literacy <lgl>, can_add <lgl>,
## # can_divide <lgl>, can_calc_percents <lgl>, can_calc_compounding <lgl>,
## # employed_last_year <lgl>, employment_category_last_year <chr>,
## # employment_type_last_year <chr>, share_hh_income_provided <dbl>,
## # income_ag_livestock_last_year <lgl>, income_friends_family_last_year <lgl>,
## # income_government_last_year <lgl>, income_own_business_last_year <lgl>,
## # income_private_sector_last_year <lgl>, …
str(Indice_pobreza)
## spc_tbl_ [8,400 × 59] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
## $ row_id : num [1:8400] 0 1 2 3 4 5 6 7 8 9 ...
## $ country : chr [1:8400] "F" "C" "I" "I" ...
## $ is_urban : logi [1:8400] FALSE FALSE FALSE TRUE FALSE TRUE ...
## $ age : num [1:8400] 57 40 35 19 61 16 40 27 35 72 ...
## $ female : logi [1:8400] TRUE FALSE TRUE TRUE TRUE TRUE ...
## $ married : logi [1:8400] TRUE TRUE TRUE FALSE TRUE FALSE ...
## $ religion : chr [1:8400] "X" "P" "Q" "Q" ...
## $ relationship_to_hh_head : chr [1:8400] "Father/Mother" "Head" "Spouse" "Son/Daughter" ...
## $ education_level : num [1:8400] 3 0 1 3 0 2 0 0 3 1 ...
## $ literacy : logi [1:8400] TRUE TRUE FALSE TRUE FALSE TRUE ...
## $ can_add : logi [1:8400] TRUE TRUE TRUE TRUE FALSE TRUE ...
## $ can_divide : logi [1:8400] TRUE TRUE TRUE TRUE FALSE TRUE ...
## $ can_calc_percents : logi [1:8400] TRUE FALSE FALSE FALSE FALSE FALSE ...
## $ can_calc_compounding : logi [1:8400] TRUE FALSE FALSE FALSE FALSE TRUE ...
## $ employed_last_year : logi [1:8400] TRUE TRUE FALSE TRUE FALSE FALSE ...
## $ employment_category_last_year : chr [1:8400] "employed" "employed" "housewife_or_student" "employed" ...
## $ employment_type_last_year : chr [1:8400] "salaried" "salaried" "not_working" "salaried" ...
## $ share_hh_income_provided : num [1:8400] NA 3 5 1 1 1 5 2 5 4 ...
## $ income_ag_livestock_last_year : logi [1:8400] FALSE FALSE FALSE FALSE TRUE FALSE ...
## $ income_friends_family_last_year : logi [1:8400] TRUE FALSE TRUE TRUE TRUE FALSE ...
## $ income_government_last_year : logi [1:8400] TRUE FALSE FALSE FALSE FALSE TRUE ...
## $ income_own_business_last_year : logi [1:8400] FALSE FALSE FALSE FALSE FALSE FALSE ...
## $ income_private_sector_last_year : logi [1:8400] FALSE FALSE FALSE TRUE FALSE FALSE ...
## $ income_public_sector_last_year : logi [1:8400] TRUE TRUE FALSE FALSE FALSE FALSE ...
## $ num_times_borrowed_last_year : num [1:8400] 1 1 1 0 1 1 0 0 0 2 ...
## $ borrowing_recency : num [1:8400] 2 2 2 0 2 2 0 0 0 2 ...
## $ formal_savings : logi [1:8400] FALSE TRUE FALSE FALSE FALSE FALSE ...
## $ informal_savings : logi [1:8400] FALSE FALSE TRUE FALSE FALSE FALSE ...
## $ cash_property_savings : logi [1:8400] FALSE FALSE TRUE FALSE FALSE FALSE ...
## $ has_insurance : logi [1:8400] FALSE FALSE FALSE FALSE FALSE FALSE ...
## $ has_investment : logi [1:8400] FALSE FALSE FALSE FALSE FALSE FALSE ...
## $ bank_interest_rate : num [1:8400] NA NA NA NA NA NA NA NA NA NA ...
## $ mm_interest_rate : num [1:8400] NA NA NA NA NA NA NA NA NA NA ...
## $ mfi_interest_rate : num [1:8400] NA NA NA NA NA NA NA NA NA NA ...
## $ other_fsp_interest_rate : num [1:8400] NA NA NA NA NA NA NA NA NA NA ...
## $ num_shocks_last_year : num [1:8400] 2 0 0 1 0 0 0 0 1 3 ...
## $ avg_shock_strength_last_year : num [1:8400] 2 0 0 5 0 0 0 0 2 5 ...
## $ borrowed_for_emergency_last_year : logi [1:8400] FALSE FALSE FALSE FALSE FALSE TRUE ...
## $ borrowed_for_daily_expenses_last_year: logi [1:8400] FALSE FALSE TRUE FALSE TRUE TRUE ...
## $ borrowed_for_home_or_biz_last_year : logi [1:8400] FALSE FALSE FALSE FALSE FALSE TRUE ...
## $ phone_technology : num [1:8400] 1 1 1 0 0 0 0 0 2 1 ...
## $ can_call : logi [1:8400] TRUE FALSE TRUE TRUE FALSE TRUE ...
## $ can_text : logi [1:8400] TRUE FALSE TRUE FALSE FALSE TRUE ...
## $ can_use_internet : logi [1:8400] TRUE FALSE FALSE FALSE FALSE TRUE ...
## $ can_make_transaction : logi [1:8400] TRUE FALSE FALSE FALSE FALSE TRUE ...
## $ phone_ownership : num [1:8400] 2 2 2 1 1 1 0 0 2 2 ...
## $ advanced_phone_use : logi [1:8400] TRUE FALSE FALSE FALSE FALSE FALSE ...
## $ reg_bank_acct : logi [1:8400] FALSE TRUE FALSE FALSE FALSE FALSE ...
## $ reg_mm_acct : logi [1:8400] FALSE FALSE FALSE FALSE FALSE FALSE ...
## $ reg_formal_nbfi_account : logi [1:8400] FALSE FALSE FALSE FALSE FALSE FALSE ...
## $ financially_included : logi [1:8400] FALSE TRUE FALSE FALSE FALSE FALSE ...
## $ active_bank_user : logi [1:8400] FALSE FALSE FALSE FALSE FALSE FALSE ...
## $ active_mm_user : logi [1:8400] FALSE FALSE FALSE FALSE FALSE FALSE ...
## $ active_formal_nbfi_user : logi [1:8400] FALSE FALSE FALSE FALSE FALSE FALSE ...
## $ active_informal_nbfi_user : logi [1:8400] FALSE FALSE TRUE TRUE FALSE FALSE ...
## $ nonreg_active_mm_user : logi [1:8400] FALSE FALSE TRUE FALSE FALSE FALSE ...
## $ num_formal_institutions_last_year : num [1:8400] 0 0 1 0 0 0 0 1 2 2 ...
## $ num_informal_institutions_last_year : num [1:8400] 0 0 1 1 0 0 0 0 0 0 ...
## $ num_financial_activities_last_year : num [1:8400] 0 0 2 0 0 0 0 1 2 4 ...
## - attr(*, "spec")=
## .. cols(
## .. row_id = col_double(),
## .. country = col_character(),
## .. is_urban = col_logical(),
## .. age = col_double(),
## .. female = col_logical(),
## .. married = col_logical(),
## .. religion = col_character(),
## .. relationship_to_hh_head = col_character(),
## .. education_level = col_double(),
## .. literacy = col_logical(),
## .. can_add = col_logical(),
## .. can_divide = col_logical(),
## .. can_calc_percents = col_logical(),
## .. can_calc_compounding = col_logical(),
## .. employed_last_year = col_logical(),
## .. employment_category_last_year = col_character(),
## .. employment_type_last_year = col_character(),
## .. share_hh_income_provided = col_double(),
## .. income_ag_livestock_last_year = col_logical(),
## .. income_friends_family_last_year = col_logical(),
## .. income_government_last_year = col_logical(),
## .. income_own_business_last_year = col_logical(),
## .. income_private_sector_last_year = col_logical(),
## .. income_public_sector_last_year = col_logical(),
## .. num_times_borrowed_last_year = col_double(),
## .. borrowing_recency = col_double(),
## .. formal_savings = col_logical(),
## .. informal_savings = col_logical(),
## .. cash_property_savings = col_logical(),
## .. has_insurance = col_logical(),
## .. has_investment = col_logical(),
## .. bank_interest_rate = col_double(),
## .. mm_interest_rate = col_double(),
## .. mfi_interest_rate = col_double(),
## .. other_fsp_interest_rate = col_double(),
## .. num_shocks_last_year = col_double(),
## .. avg_shock_strength_last_year = col_double(),
## .. borrowed_for_emergency_last_year = col_logical(),
## .. borrowed_for_daily_expenses_last_year = col_logical(),
## .. borrowed_for_home_or_biz_last_year = col_logical(),
## .. phone_technology = col_double(),
## .. can_call = col_logical(),
## .. can_text = col_logical(),
## .. can_use_internet = col_logical(),
## .. can_make_transaction = col_logical(),
## .. phone_ownership = col_double(),
## .. advanced_phone_use = col_logical(),
## .. reg_bank_acct = col_logical(),
## .. reg_mm_acct = col_logical(),
## .. reg_formal_nbfi_account = col_logical(),
## .. financially_included = col_logical(),
## .. active_bank_user = col_logical(),
## .. active_mm_user = col_logical(),
## .. active_formal_nbfi_user = col_logical(),
## .. active_informal_nbfi_user = col_logical(),
## .. nonreg_active_mm_user = col_logical(),
## .. num_formal_institutions_last_year = col_double(),
## .. num_informal_institutions_last_year = col_double(),
## .. num_financial_activities_last_year = col_double()
## .. )
## - attr(*, "problems")=<externalptr>
## Agrupación de nivel educación y calculo de la media de edades por educación
tabla1<-Indice_pobreza %>%
select(pais = country,
vivienda_urbana=is_urban,
religion,
Relacion_cabeza_famlia=relationship_to_hh_head,
Nivel_educacion=education_level,
lee_libros=literacy,
edad=age)%>%
group_by(Nivel_educacion)%>%
summarise(edades_promedio = mean(edad, na.rm = TRUE))
print(tabla1)
## # A tibble: 5 × 2
## Nivel_educacion edades_promedio
## <dbl> <dbl>
## 1 0 44.9
## 2 1 37.7
## 3 2 31.3
## 4 3 32.1
## 5 NA 34.3
barplot_1<-barplot(tabla1$edades_promedio,
names.arg = tabla1$Nivel_educacion,
main="Promedio edades por nivel educativo",
ylab="Edad Promedio",
xlab ="Nivel Educativo",
ylim = c(0, max(tabla1$edades_promedio) + 5),
col=brewer.pal(10,"Set1"))
## Warning in brewer.pal(10, "Set1"): n too large, allowed maximum for palette Set1 is 9
## Returning the palette you asked for with that many colors
text(x = barplot_1,
y = tabla1$edades_promedio + 1.8,
labels = round(tabla1$edades_promedio))
# La religión mas predominante
# Datos de ejemplo
tabla2 <- Indice_pobreza %>%
select(religion) %>%
count(religion) %>%
arrange(desc(n)) %>%
mutate(porcentaje = (n / sum(n)) * 100)
# Ajustar la paleta de colores
num_colores <- min(9, nrow(tabla2)) # Usar máximo 9 colores
colores <- brewer.pal(num_colores, "Set1")
# Crear gráfico circular
pie(tabla2$n,
labels = paste0(round(tabla2$porcentaje, 2), "%"),
col = colores,
main = "Frecuencia Religiones",
cex = 0.8
)
# Añadir leyenda
legend("topright",
legend = tabla2$religion,
cex = 0.8,
fill = colores
)
# La religión mas predominante
tabla2 <- Indice_pobreza %>%
select(religion) %>%
count(religion) %>%
arrange(desc(n))%>%
mutate(porcentaje = (n / sum(n)) * 100)
print(tabla2)
## # A tibble: 5 × 3
## religion n porcentaje
## <chr> <int> <dbl>
## 1 Q 3693 44.0
## 2 X 3464 41.2
## 3 P 1151 13.7
## 4 O 62 0.738
## 5 N 30 0.357
barplot_2<-barplot(tabla2$n,
names.arg = tabla2$religion,
main="Religiones",
ylim = c(0, max(tabla2$n) + 300),
xlab ="Religion",
col=brewer.pal(10,"Set1"))
## Warning in brewer.pal(10, "Set1"): n too large, allowed maximum for palette Set1 is 9
## Returning the palette you asked for with that many colors
text(x = barplot_2,
y = tabla2$n + 150,
labels = paste0(round(tabla2$porcentaje, 1), "%"))
## porcentaje de la media de población que con base a el nivel eduactivo leen libros
tabla3 <-Indice_pobreza %>%
select(Nivel_educacion = education_level,
lee_libros = literacy,
Sabe_sumar = can_add) %>%
group_by(Nivel_educacion) %>%
summarise(lectura_libros = mean(lee_libros) * 100)
barplot_3 <-barplot(tabla3$lectura_libros,
names.arg = tabla3$Nivel_educacion,
main = "Porcentaje de Lectura de Libros por Nivel Educativo",
ylim = c(0, max(tabla3$lectura_libros) + 20),
xlab = "Nivel Educativo",
ylab = "Porcentaje",
col = brewer.pal(n = nrow(tabla3), "Set1"))
text(x = barplot_3,
y = tabla3$lectura_libros + 9,
labels = paste0(round(tabla3$lectura_libros, 1), "%"))
