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 <- floor(
  1 + 3.3 * log10(
    length(composition_food_organic_waste_percent)
  )
)

# =========================
# 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 <- round((ni / sum(ni)) * 100, 2)

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

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

Hiasc <- round(cumsum(hi), 2)
Hidsc <- round(rev(cumsum(rev(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	16.08	14.43	370	1.86	370	19893	1.86	100
16.08	19.38	17.73	4001	20.11	4371	19523	21.97	98.14
19.38	22.68	21.03	0	0	4371	15522	21.97	78.03
22.68	25.99	24.34	493	2.48	4864	15522	24.45	78.03
25.99	29.29	27.64	22	0.11	4886	15029	24.56	75.55
29.29	32.59	30.94	10332	51.94	15218	15007	76.5	75.44
32.59	35.89	34.24	460	2.31	15678	4675	78.81	23.5
35.89	39.19	37.54	168	0.84	15846	4215	79.65	21.19
39.19	42.49	40.84	228	1.15	16074	4047	80.8	20.35
42.49	45.79	44.14	0	0	16074	3819	80.8	19.2
45.79	49.09	47.44	3223	16.2	19297	3819	97	19.2
49.09	52.4	50.75	0	0	19297	596	97	3
52.4	55.7	54.05	0	0	19297	596	97	3
55.7	59	57.35	117	0.59	19414	596	97.59	3
59	62.3	60.65	479	2.41	19893	479	100	2.41
TOTAL			19893	100
Autor: Grupo 3