COMPOSICIÓN DE DESECHOS ORGÁNICOS

# =========================
# CARGAR LIBRERÍA
# =========================

library(gt)

# =========================
# CARGAR DATOS
# =========================

datos <- read.csv(
  "waterPollution.csv",
  sep = ",",
  stringsAsFactors = FALSE
)

# =========================
# VARIABLE CUANTITATIVA CONTINUA
# =========================

composition_food_organic_waste_percent <- as.numeric(
  datos$composition_food_organic_waste_percent
)

# Eliminar datos vacíos

composition_food_organic_waste_percent <- na.omit(
  composition_food_organic_waste_percent
)

# =========================
# NÚMERO DE INTERVALOS
# =========================

k <- 9

# =========================
# VALORES BÁSICOS
# =========================

min_val <- min(
  composition_food_organic_waste_percent
)

max_val <- max(
  composition_food_organic_waste_percent
)

R <- max_val - min_val

A <- R / k

# =========================
# LÍMITES DE CLASE
# =========================

Li <- round(
  seq(
    from = min_val,
    to = max_val - A,
    by = A
  ),
  2
)

Ls <- round(
  seq(
    from = min_val + A,
    to = max_val,
    by = A
  ),
  2
)

# Marca de clase

MC <- round((Li + Ls) / 2, 2)

# =========================
# FRECUENCIA ABSOLUTA
# =========================

ni <- numeric(length(Li))

for(i in 1:length(Li)){
  
  if(i < length(Li)){
    
    ni[i] <- sum(
      composition_food_organic_waste_percent >= Li[i] &
      composition_food_organic_waste_percent < Ls[i]
    )
    
  } else {
    
    ni[i] <- sum(
      composition_food_organic_waste_percent >= Li[i] &
      composition_food_organic_waste_percent <= max_val
    )
  }
}

# =========================
# FRECUENCIA RELATIVA
# =========================

hi <- (ni / sum(ni)) * 100

# =========================
# FRECUENCIAS ACUMULADAS
# =========================

Niasc <- cumsum(ni)
Nidsc <- rev(cumsum(rev(ni)))

Hiasc <- round(cumsum(hi), 2)
Hidsc <- round(rev(cumsum(rev(hi))), 2)

# Forzar acumulados a 100

Hiasc[length(Hiasc)] <- 100
Hidsc[1] <- 100

# Redondear hi para mostrar

hi <- round(hi, 2)

# =========================
# CREAR TABLA
# =========================

TDF_Organic <- data.frame(
  Li,
  Ls,
  MC,
  ni,
  hi,
  Niasc,
  Nidsc,
  Hiasc,
  Hidsc
)

# =========================
# AGREGAR TOTAL
# =========================

totales <- TDF_Organic[1, ]

totales[1, ] <- c(
  "TOTAL",
  "",
  "",
  sum(ni),
  100,
  "",
  "",
  "",
  ""
)

TDF_Organic <- rbind(TDF_Organic, totales)

# =========================
# NOMBRES COLUMNAS
# =========================

colnames(TDF_Organic) <- c(
  "Li",
  "Ls",
  "MC",
  "ni",
  "hi(%)",
  "Ni_asc",
  "Ni_desc",
  "Hi_asc(%)",
  "Hi_desc(%)"
)

# =========================
# TABLA FINAL
# =========================

TDF_Organic %>%
  
  gt() %>%
  
  tab_header(
    
    title = md("*Tabla N°1*"),
    
    subtitle = md(
      "**Distribución de frecuencias de la Composición de Desechos Orgánicos (%)**"
    )
  ) %>%
  
  tab_source_note(
    
    source_note = md("Autor: Grupo 3")
  ) %>%
  
  tab_style(
    
    style = cell_text(weight = "bold"),
    
    locations = cells_body(
      rows = Li == "TOTAL"
    )
  )

Tabla N°1
Distribución de frecuencias de la Composición de Desechos Orgánicos (%)
Li	Ls	MC	ni	hi(%)	Ni_asc	Ni_desc	Hi_asc(%)	Hi_desc(%)
12.78	18.28	15.53	4371	21.97	4371	19893	21.97	100
18.28	23.78	21.03	171	0.86	4542	15522	22.83	78.03
23.78	29.29	26.54	344	1.73	4886	15351	24.56	77.17
29.29	34.79	32.04	10433	52.45	15319	15007	77.01	75.44
34.79	40.29	37.54	527	2.65	15846	4574	79.66	22.99
40.29	45.79	43.04	228	1.15	16074	4047	80.8	20.34
45.79	51.3	48.55	3223	16.2	19297	3819	97	19.2
51.3	56.8	54.05	117	0.59	19414	596	97.59	3
56.8	62.3	59.55	479	2.41	19893	479	100	2.41
TOTAL			19893	100
Autor: Grupo 3