CONFIDENCE

UNIVERSIDAD CENTRAL DEL ECUADOR

PROYECTO: FOCOS DE CALOR EN EL ECUADOR

AUTORES: GUERRERO MARIA GABRIELA,PUCHAICELA MONICA, ZURITA JOHANNA

FECHA: 14/05/2025

datos <- read.csv("maate_focosdecalor_bdd_2021diciembre.csv",
                  header = T, sep = ",", dec = ".")

#Estructura de los datos 
str(datos)
## 'data.frame':    22476 obs. of  17 variables:
##  $ MES_REPORT: int  11 11 8 6 5 6 11 9 3 3 ...
##  $ DIA_REPORT: int  20 20 6 10 28 10 20 29 22 22 ...
##  $ DPA_DESPRO: chr  "ZAMORA CHINCHIPE" "ZAMORA CHINCHIPE" "ZAMORA CHINCHIPE" "ZAMORA CHINCHIPE" ...
##  $ DPA_DESCAN: chr  "CHINCHIPE" "CHINCHIPE" "CHINCHIPE" "CHINCHIPE" ...
##  $ DPA_DESPAR: chr  "CHITO" "CHITO" "PUCAPAMBA" "PUCAPAMBA" ...
##  $ TXT_1     : chr  "PARROQUIA RURAL" "PARROQUIA RURAL" "PARROQUIA RURAL" "PARROQUIA RURAL" ...
##  $ LATITUDE  : chr  "-4,981720000000000" "-4,969160000000000" "-4,958520000000000" "-4,957820000000000" ...
##  $ LONGITUDE : chr  "-79,041280000000000" "-79,049490000000006" "-79,118430000000004" "-79,111859999999993" ...
##  $ BRIGHTNESS: chr  "354,759999999999990" "342,009999999999990" "331,860000000000010" "331,399999999999980" ...
##  $ SCAN      : chr  "0,510000000000000" "0,510000000000000" "0,150000000000000" "0,540000000000000" ...
##  $ TRACK     : chr  "0,490000000000000" "0,490000000000000" "0,380000000000000" "0,420000000000000" ...
##  $ SATELLITE : chr  "1" "1" "1" "1" ...
##  $ CONFIDENCE: chr  "n" "n" "n" "n" ...
##  $ VERSION   : chr  "2.0NRT" "2.0NRT" "2.0NRT" "2.0NRT" ...
##  $ BRIGHT_T31: chr  "299,420000000000020" "298,149999999999980" "299,160000000000030" "296,800000000000010" ...
##  $ FRP       : chr  "12,100000000000000" "6,870000000000000" "3,770000000000000" "5,500000000000000" ...
##  $ DAYNIGHT  : chr  "D" "D" "D" "D" ...
#Extraer la variable nominal
CONFIDENCE <- datos$CONFIDENCE


#EDA variable nominal
#Tabla de Distribucion de Frecuencia
TDFCONFIDENCE<- table(CONFIDENCE)
TDFCONFIDENCE
## CONFIDENCE
##     h     l     n 
##   641   811 21024
TDFfinalCONFIDENCE <- as.data.frame(TDFCONFIDENCE)
colnames(TDFfinalCONFIDENCE) <- c("variable", "ni")


hi <- TDFfinalCONFIDENCE$ni / sum(TDFfinalCONFIDENCE$ni)
hi <- hi*100
sum(hi)
## [1] 100
TDFfinalCONFIDENCE$hi <- (TDFfinalCONFIDENCE$ni / sum(TDFfinalCONFIDENCE$ni)) * 100
TDFfinalCONFIDENCE <- subset(TDFfinalCONFIDENCE, variable != "Total")
ni <- TDFfinalCONFIDENCE$ni
sum(ni)
## [1] 22476
variable <- c("h", "n", "l")
ni <- c("641","21024","811") # Frecuencia absoluta
ni_num <- as.numeric(ni)
hi <- round(ni_num / sum(ni_num) * 100, 1)  # Frecuencia relativa (porcentaje)

# Crear data frame
TDFfinalCONFIDENCE <- data.frame(variable, ni, hi)

# AGREGAR FILA TOTAL

total_ni <- sum(ni_num)
total_hi <- sum(hi)

TDFfinalDCONFIDENCE <- rbind(
  TDFfinalCONFIDENCE,
  data.frame(variable = "Total", ni = total_ni, hi = total_hi)
)

library(stringi)

# Verificar codificación UTF-8
if (any(!stri_enc_isutf8(TDFfinalCONFIDENCE$variable))) {
  warning("Quedan cadenas con problemas de codificación")
} else {
  message("Codificación UTF-8 correcta")
}
## Codificación UTF-8 correcta
library(dplyr)  
## 
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
## 
##     filter, lag
## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union
library(gt) 

tabla_Confidence <- TDFfinalDCONFIDENCE %>%
  gt() %>%
  tab_header(
    title = md("Tabla Nro. 6"),
    subtitle = md("*Tabla de distribución de frecuencias de Grado de Confiabilidad*")
  ) %>%
  tab_source_note(
    source_note = md("Autor: Grupo 3")
  ) %>%
  tab_options(
    table.border.top.color = "black",
    table.border.bottom.color = "black",
    table.border.top.style = "solid",
    table.border.bottom.style = "solid",
    column_labels.border.top.color = "black",
    column_labels.border.bottom.color = "black",
    column_labels.border.bottom.width = px(2),
    row.striping.include_table_body = TRUE,
    heading.border.bottom.color = "black",
    heading.border.bottom.width = px(2),
    table_body.hlines.color = "gray",
    table_body.border.bottom.color = "black"
  ) %>%
  tab_style(
    style = cell_text(weight = "bold"),
    locations = cells_body(
      rows = variable == "Total"
    )
  )

tabla_Confidence
Tabla Nro. 6
Tabla de distribución de frecuencias de Grado de Confiabilidad
variable ni hi
h 641 2.9
n 21024 93.5
l 811 3.6
Total 22476 100.0
Autor: Grupo 3 
# Eliminar Total para graficar
TDFfinalCONFIDENCE <- subset(TDFfinalCONFIDENCE, variable != "Total")

# Reordenar niveles
orden_deseado <- c("h", "n", "l")
TDFfinalCONFIDENCE$variable <- factor(TDFfinalCONFIDENCE$variable, levels = orden_deseado)
TDFfinalCONFIDENCE <- TDFfinalCONFIDENCE[order(TDFfinalCONFIDENCE$variable), ]

# Codificación segura
TDFfinalCONFIDENCE$variable <- iconv(TDFfinalCONFIDENCE$variable, from = "latin1", to = "UTF-8", sub = "")

# GDF
class(TDFfinalCONFIDENCE$ni)
## [1] "character"
# If not numeric, convert it
TDFfinalCONFIDENCE$ni <- as.numeric(as.character(TDFfinalCONFIDENCE$ni))

# 6.1. Diagrama de barras - Frecuencia absoluta
barplot(
  height = TDFfinalCONFIDENCE$ni,
  names.arg = TDFfinalCONFIDENCE$variable,
  main = "Gráfica N°6.1: Distribución de Grado de Confianza",
  xlab = "",
  ylab = "Cantidad",
  col = heat.colors(length(TDFfinalCONFIDENCE$ni)),
  las = 2,
  cex.names = 0.8
)

mtext("Grado de Confianza", side = 1, line = 2, cex = 1)

# 6.2. Diagrama de barras - Frecuencia absoluta (colores definidos)
barplot(
  height = TDFfinalCONFIDENCE$ni,
  names.arg = TDFfinalCONFIDENCE$variable,
  main = "Gráfica N°6.2: Distribución Global del Grado de Confianza",
  xlab = "",
  ylab = "Cantidad",
  col = c("yellow", "orange", "red"),
  ylim = c(0, 22500),
  las = 2,
  cex.names = 0.8
)
mtext("Grado de Confianza", side = 1, line = 2, cex = 1)

# 6.3. Diagrama de barras - Frecuencia relativa (%)
barplot(
  height = TDFfinalCONFIDENCE$hi,
  names.arg = TDFfinalCONFIDENCE$variable,
  main = "Gráfica N°6.3: Distribución Porcentual del Grado de Confianza",
  xlab = "",
  ylab = "Porcentaje (%)",
  col = c("yellow", "orange", "red"),
  ylim = c(0, 95),
  las = 2,
  cex.names = 0.7
)
mtext("Grado de Confianza", side = 1, line = 2, cex = 1)

# 6.4. Diagrama de barras - Frecuencia relativa (%)
barplot(
  height = TDFfinalCONFIDENCE$hi,
  names.arg = TDFfinalCONFIDENCE$variable,
  main = "Gráfica N°6.4: Distribución Porcentual del Grado de Confianza",
  xlab = "",
  ylab = "Porcentaje (%)",
  col = c("yellow", "orange", "red"),
  ylim = c(0, 100),
  las = 2,
  cex.names = 0.7
)
mtext("Grado de Confianza", side = 1, line = 2, cex = 1)

# 6.5. Diagrama de pastel - Distribución porcentual
hi_grupo <- TDFfinalCONFIDENCE$hi
etiquetas <- paste0(TDFfinalCONFIDENCE$variable, ": ", round(hi_grupo, 1), "%")
colores <- rev(heat.colors(length(hi_grupo)))

pie(
  hi_grupo,
  labels = etiquetas,
  main = "Gráfica N°6.5: Distribución Porcentual del Grado de Confianza",
  col = colores
)

legend(
  "bottomright",
  legend = TDFfinalCONFIDENCE$variable,
  title = "Grado de Confianza",
  fill = colores,
  cex = 1,
  border = "black"
)

#INDICADORES
moda <- function(x) {
  ux <- unique(x)
  ux[which.max(tabulate(match(x, ux)))]
}

# Aplicar moda a CONFIDENCE
moda_DPA <- moda(datos$CONFIDENCE)
print(moda_DPA)
## [1] "n"