Temperatura

UNIVERSIDAD CENTRAL DEL ECUADOR

ESTUDIO ESTADÍSTICO DE LA CONTAMINACIÓN DEL SUELO Y SU IMPACTO EN LA SALUD

FECHA: 19/11/2025

# =========================
# ESTADÍSTICA Descriptiva
# Fecha: 19/11/2025
# =========================

# -------------------------
# Cargar datos
# -------------------------
setwd("C:/Users/Alexander/Downloads")

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

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


Temperatura <- datos$Temperature_C

# ================================
# TABLA Nº1 (Cálculo manual)
# ================================

k <- 1 + (3.3 * log10(3000))
k <- floor(k)

min <- min(Temperatura)
max <- max(Temperatura)

R <- max - min
A <- R / k

Li <- round(seq(from = min, to = max - A, by = A), 4)
Ls <- round(seq(from = min + A, to = max, by = A), 4)
MC <- round((Li + Ls) / 2, 2)

ni <- numeric(length(Li))

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

ni[length(Li)] <- sum(Temperatura >= Li[length(Li)] & Temperatura <= max)

hi <- ni / sum(ni) * 100

Niasc <- cumsum(ni)
Nidsc <- rev(cumsum(rev(ni)))
Hiasc <- round(cumsum(hi))
Hidsc <- round(rev(cumsum(rev(hi))))

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

TDF_Temperatura_Completo <- rbind(
  TDF_Temperatura,
  data.frame(Li = "Total", Ls = " ", MC = " ",
             ni = sum(ni), hi = 100,
             Niasc = " ", Nidsc = " ",
             Hiasc = " ", Hidsc = " ")
)

library(gt)
library(dplyr)

tabla_Temperatura <- TDF_Temperatura_Completo %>%
  gt() %>%
  tab_header(
    title = md("*Tabla Nº1*"),
    subtitle = md("**Tabla de distribución de Frecuencias de la Temperatura (°C)**")
  ) %>%
  tab_source_note(
    source_note = md("Autor: Grupo 3")
  )

tabla_Temperatura

Tabla Nº1
Tabla de distribución de Frecuencias de la Temperatura (°C)
Li	Ls	MC	ni	hi	Niasc	Nidsc	Hiasc	Hidsc
10	12.9167	11.46	258	8.600000	258	3000	9	100
12.9167	15.8333	14.38	266	8.866667	524	2742	17	91
15.8333	18.75	17.29	251	8.366667	775	2476	26	83
18.75	21.6667	20.21	241	8.033333	1016	2225	34	74
21.6667	24.5833	23.12	262	8.733333	1278	1984	43	66
24.5833	27.5	26.04	260	8.666667	1538	1722	51	57
27.5	30.4167	28.96	234	7.800000	1772	1462	59	49
30.4167	33.3333	31.88	257	8.566667	2029	1228	68	41
33.3333	36.25	34.79	253	8.433333	2282	971	76	32
36.25	39.1667	37.71	249	8.300000	2531	718	84	24
39.1667	42.0833	40.62	218	7.266667	2749	469	92	16
42.0833	45	43.54	251	8.366667	3000	251	100	8
Total			3000	100.000000
Autor: Grupo 3

# =========================
# HISTOGRAMA Nº1 (7 intervalos)
# =========================

histoP <- hist(
  Temperatura,
  breaks = 7,   # 👈 EXACTAMENTE 7 INTERVALOS
  main = "Gráfica Nº1: Distribución de la Temperatura (°C)",
  xlab = "Temperatura (°C)",
  ylab = "Cantidad",
  col = "blue"
)

# =========================
# TABLA Nº2 (Basada en Histograma)
# =========================

Limites <- histoP$breaks
LimInf <- Limites[1:(length(Limites) - 1)]
LimSup <- Limites[2:length(Limites)]
Mc <- histoP$mids
ni <- histoP$counts
hi <- round(ni / sum(ni) * 100, 2)

Ni_asc <- cumsum(ni)
Ni_dsc <- rev(cumsum(rev(ni)))
Hi_asc <- round(cumsum(hi), 2)
Hi_dsc <- round(rev(cumsum(rev(hi))), 2)

TDF_Histo_Temperatura <- data.frame(LimInf, LimSup, Mc, ni, hi, Ni_asc, Ni_dsc, Hi_asc, Hi_dsc)

TDF_Histo_Temperatura_Completo <- rbind(
  TDF_Histo_Temperatura,
  data.frame(LimInf = "Total",
             LimSup = " ", Mc = " ",
             ni = sum(ni),
             hi = 100,
             Ni_asc = " ",
             Ni_dsc = " ",
             Hi_asc = " ",
             Hi_dsc = " ")
)

tabla_Histo_Temperatura <- TDF_Histo_Temperatura_Completo %>%
  gt() %>%
  tab_header(
    title = md("*Tabla Nº2*"),
    subtitle = md("**Tabla simplificada de distribución de la Temperatura (7 intervalos)**")
  ) %>%
  tab_source_note(
    source_note = md("Autor: Grupo 3")
  )

tabla_Histo_Temperatura

Tabla Nº2
Tabla simplificada de distribución de la Temperatura (7 intervalos)
LimInf	LimSup	Mc	ni	hi	Ni_asc	Ni_dsc	Hi_asc	Hi_dsc
10	15	12.5	448	14.93	448	3000	14.93	100
15	20	17.5	451	15.03	899	2552	29.96	85.07
20	25	22.5	429	14.30	1328	2101	44.26	70.04
25	30	27.5	417	13.90	1745	1672	58.16	55.74
30	35	32.5	428	14.27	2173	1255	72.43	41.84
35	40	37.5	414	13.80	2587	827	86.23	27.57
40	45	42.5	413	13.77	3000	413	100	13.77
Total			3000	100.00
Autor: Grupo 3

# =========================
# HISTOGRAMA Nº2 (LOCAL)
# =========================

hist(
  Temperatura,
  breaks = 7,
  main = "Gráfica Nº2: Frecuencia de la Temperatura (Local)",
  xlab = "Temperatura (°C)",
  ylab = "Frecuencia",
  col = "#4A90E2"
)

# =========================
# HISTOGRAMA Nº3 (GLOBAL)
# =========================

hist(
  Temperatura,
  breaks = 7,
  main = "Gráfica Nº3: Frecuencia de la Temperatura (Global)",
  xlab = "Temperatura (°C)",
  ylab = "Frecuencia",
  col = "green",
  ylim = c(0, 3000)
)

# =========================
# GRÁFICAS PORCENTUALES (Basadas en Tabla 2)
# =========================

barplot(
  TDF_Histo_Temperatura$hi,
  space = 0,
  col = "skyblue",
  main = "Gráfica Nº4: Porcentaje de la Temperatura (Local)",
  xlab = "Intervalos",
  ylab = "Porcentaje (%)",
  names.arg = TDF_Histo_Temperatura$Mc
)

barplot(
  TDF_Histo_Temperatura$hi,
  space = 0,
  col = "yellow",
  main = "Gráfica Nº5: Porcentaje de la Temperatura (Global)",
  xlab = "Intervalos",
  ylab = "Porcentaje (%)",
  names.arg = TDF_Histo_Temperatura$Mc,
  ylim = c(0, 100)
)

# =========================
# BOXPLOT
# =========================

boxplot(
  Temperatura,
  horizontal = TRUE,
  col = "pink",
  main = "Gráfica Nº6: Distribución de la Temperatura",
  xlab = "Temperatura (°C)"
)

# =========================
# OJIVAS
# =========================

plot(
  LimInf, Ni_dsc,
  main = "Gráfica Nº7: Ojiva Ascendente y Descendente de la Temperatura",
  xlab = "Temperatura (°C)",
  ylab = "Cantidad",
  col = "red",
  type = "o",
  lwd = 2
)

lines(LimSup, Ni_asc, col = "green", type = "o", lwd = 2)

# =========================
# OJIVAS PORCENTUALES vs TEMPERATURA
# =========================

# Ojiva Ascendente (usar límites superiores)
plot(
  LimSup,
  Hi_asc,
  type = "o",
  col = "blue",
  pch = 16,
  ylim = c(0,100),
  main = "Gráfica Nº5: Ojivas Porcentuales - Temperatura (°C)",
  xlab = "Temperatura (°C)",
  ylab = "Frecuencia Acumulada (%)"
)

# Ojiva Descendente (usar límites inferiores)
lines(
  LimInf,
  Hi_dsc,
  type = "o",
  col = "red",
  pch = 17
)

grid()

legend(
  "right",
  legend = c("Ojiva Ascendente (%)", "Ojiva Descendente (%)"),
  col = c("blue", "red"),
  pch = c(16,17),
  lty = 1
)

# =========================
# INDICADORES ESTADÍSTICOS
# =========================

media <- round(mean(Temperatura), 2)
mediana <- median(Temperatura)

Tabla_Temp <- as.data.frame(table(Temperatura))
max_frecuencia <- max(Tabla_Temp$Freq)
moda <- Tabla_Temp$Temperatura[Tabla_Temp$Freq == max_frecuencia]

varianza <- var(Temperatura)
sd <- sd(Temperatura)
cv <- round((sd / media) * 100, 2)

library(e1071)
asimetria <- skewness(Temperatura, type = 2)
curtosis <- kurtosis(Temperatura)


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

tabla_indicadores <- data.frame(
  "Variable" = c("Temperatura"),
  "Rango" = c(paste0("[", min(Temperatura), " ; ", max(Temperatura), "]")),
  "X" = c(media),
  "Me" = c(round(mediana, 2)),
  "Mo" = c(paste(moda, collapse = ", ")),
  "V" = c(round(varianza, 2)),
  "Sd" = c(round(sd, 2)),
  "Cv" = c(cv),
  "As" = c(round(asimetria, 2)),
  "K" = c(round(curtosis, 2)),
  "Valores_Atipicos" = "No hay presencia de valores atípicos"
)

tabla_indicadores_gt <- tabla_indicadores %>%
  gt() %>%
  tab_header(
    title = md("*Tabla Nº3*"),
    subtitle = md("**Indicadores estadísticos de la Temperatura (°C)**")
  ) %>%
  tab_source_note(
    source_note = md("Autor: Grupo 3")
  )

tabla_indicadores_gt

Tabla Nº3
Indicadores estadísticos de la Temperatura (°C)
Variable	Rango	X	Me	Mo	V	Sd	Cv	As	K	Valores_Atipicos
Temperatura	[10 ; 45]	27.23	27	40.5	101.7	10.08	37.03	0.03	-1.2	No hay presencia de valores atípicos
Autor: Grupo 3

##============##
## CONCLUSION ##
##============##
# La variable Temperatura fluctua entre 10 y 45 y gira entorno a 27.23 con una desviación estandar de 10.08 siendo un conjuto de datos homogeneo, los valores de acumulan de manera debil en la parte media de la variable. Sin presencia de valores atípicos.