DIST_TO_ROAD (DESCRIPTIVA)

1 Configuración y Carga de Datos

##### UNIVERSIDAD CENTRAL DEL ECUADOR #####
#### AUTOR: JULEYDI MILES ####
### CARRERA: INGENIERÍA EN PETRÓLEOS #####


#### VARIABLE CAPACIDAD ####
## DATASET ##
# Cargar dataset
Datos <- read_excel("C:/Users/USER/Downloads/Variables/Dataset_Mundial_Final.xls")
# Estructura de los datos
str(Datos)

tibble [58,978 × 29] (S3: tbl_df/tbl/data.frame)
 $ OBJECTID              : num [1:58978] 2 3 4 5 6 7 8 9 10 11 ...
 $ code                  : chr [1:58978] "00001-AFG-P" "00002-AFG-P" "00003-AFG-P" "00004-AFG-P" ...
 $ plant_name            : chr [1:58978] "Badghis Solar Power Plant" "Balkh solar farm" "Behsood solar farm" "Dab Pal 4 solar farm" ...
 $ country               : chr [1:58978] "Afghanistan" "Afghanistan" "Afghanistan" "Afghanistan" ...
 $ operational_status    : chr [1:58978] "cancelled - inferred 4 y" "cancelled - inferred 4 y" "cancelled - inferred 4 y" "shelved - inferred 2 y" ...
 $ longitude             : num [1:58978] 62.9 67.1 70.4 66.2 65.7 ...
 $ latitude              : num [1:58978] 35.1 36.7 34.4 33.8 31.7 ...
 $ elevation             : num [1:58978] 918 359 629 2288 1060 ...
 $ area                  : num [1:58978] 6.74 10.72 487.73 111.8 1929.96 ...
 $ size                  : chr [1:58978] "Small" "Small" "Small" "Small" ...
 $ slope                 : num [1:58978] 7.38 0.49 1.1 6.16 1.23 ...
 $ slope_type            : chr [1:58978] "Moderado" "Plano o casi plano" "Plano o casi plano" "Moderado" ...
 $ curvature             : num [1:58978] -0.024 0 0 0.045 -0.005 -0.005 -0.015 0 0 -0.009 ...
 $ curvature_type        : chr [1:58978] "Superficies cóncavas / Valles" "Superficies planas o intermedias" "Superficies planas o intermedias" "Superficies convexas / Crestas" ...
 $ aspect                : num [1:58978] 96.8 358.5 36.2 305.8 248.4 ...
 $ aspect_type           : chr [1:58978] "East" "North" "Northeast" "Northwest" ...
 $ dist_to_road          : num [1:58978] 7037.1 92.7 112.1 1705.3 115.8 ...
 $ ambient_temperature   : num [1:58978] 14.4 17.88 21.32 8.86 19.64 ...
 $ ghi                   : num [1:58978] 5.82 5.58 5.8 6.75 6.62 ...
 $ humidity              : num [1:58978] 47.7 42.3 36.4 37.3 24.2 ...
 $ wind_speed            : num [1:58978] 0.039 0.954 0.234 0.943 0.37 ...
 $ wind_direction        : num [1:58978] 187.5 207.4 255.6 160.3 97.7 ...
 $ dt_wind               : chr [1:58978] "South" "Southwest" "West" "South" ...
 $ solar_aptitude        : num [1:58978] 0.72 0.635 0.685 0.659 0.819 0.819 0.818 0.642 0.63 0.374 ...
 $ solar_aptitude_rounded: num [1:58978] 7 6 7 7 8 8 8 6 6 4 ...
 $ solar_aptittude_class : chr [1:58978] "Alta" "Alta" "Alta" "Alta" ...
 $ capacity              : num [1:58978] 32 40 60 3000 100 100 36 50 25 100 ...
 $ optimal_tilt          : num [1:58978] 30 31 31.1 33 31 ...
 $ pv_potential          : num [1:58978] 4.61 4.41 4.57 5.42 5.17 ...

2 Cálculo de Intervalos y Frecuencias

library(dplyr)
library(gt)

# 1. Extracción y Limpieza de la variable dist_to_road
# Eliminamos NA y valores atípicos
apt_variable_raw <- Datos$dist_to_road %>% na.omit()

q1 <- quantile(apt_variable_raw, 0.25)
q3 <- quantile(apt_variable_raw, 0.75)
iqr <- q3 - q1
# Filtrado de Outliers
apt_clean <- apt_variable_raw[apt_variable_raw >= (q1 - 1.5 * iqr) & 
                               apt_variable_raw <= (q3 + 1.5 * iqr)]

# 2. Aplicación de Regla de Sturges
n_total_apt <- length(apt_clean)
K_sturges <- ceiling(1 + 3.322 * log10(n_total_apt)) # Salen 17 intervalos
min_val <- min(apt_clean)
max_val <- max(apt_clean)

# Generar cortes
cortes_int_apt <- seq(from = min_val, to = max_val, length.out = K_sturges + 1)

# 3. Construcción de la Tabla
ni_int_apt <- as.vector(table(cut(apt_clean, breaks = cortes_int_apt, include.lowest = TRUE, right = FALSE)))
hi_int_apt <- (ni_int_apt / n_total_apt) * 100

df_tabla_apt <- data.frame(
  Li = cortes_int_apt[1:K_sturges], 
  Ls = cortes_int_apt[2:(K_sturges+1)],
  MC = (cortes_int_apt[1:K_sturges] + cortes_int_apt[2:(K_sturges+1)]) / 2,
  ni = ni_int_apt, 
  hi = hi_int_apt,
  Ni_asc = cumsum(ni_int_apt), 
  Ni_desc = rev(cumsum(rev(ni_int_apt))),
  Hi_asc = cumsum(hi_int_apt), 
  Hi_desc = rev(cumsum(rev(hi_int_apt)))
)

# 4. Generación de la Tabla con tu formato visual
df_tabla_apt %>%
  mutate(across(everything(), ~as.character(round(as.numeric(.), 3)))) %>%
  rbind(c("TOTAL", "-", "-", n_total_apt, "100", "-", "-", "-", "-")) %>%
  gt() %>%
  tab_header(title = md("**Tabla N°3 de Distribución de Frecuencias de Distancia a la Vía de las Plantas Solares**")) %>%
  tab_source_note(source_note = "Autor: Juleydi Miles") %>%
  cols_label(Li = "Lim. Inf", Ls = "Lim. Sup", MC = "Marca Clase", ni = "ni", hi = "hi (%)", 
             Ni_asc = "Ni \u2191", Ni_desc = "Ni \u2193", Hi_asc = "Hi \u2191", Hi_desc = "Hi \u2193") %>%
  cols_align(align = "center", columns = everything()) %>%
  tab_options(column_labels.background.color = "#F0F0F0")

Tabla N°3 de Distribución de Frecuencias de Distancia a la Vía de las Plantas Solares
Lim. Inf	Lim. Sup	Marca Clase	ni	hi (%)	Ni ↑	Ni ↓	Hi ↑	Hi ↓
0	371.058	185.529	20357	39.575	20357	51439	39.575	100
371.058	742.115	556.587	9509	18.486	29866	31082	58.061	60.425
742.115	1113.173	927.644	6090	11.839	35956	21573	69.9	41.939
1113.173	1484.231	1298.702	2790	5.424	38746	15483	75.324	30.1
1484.231	1855.289	1669.76	2183	4.244	40929	12693	79.568	24.676
1855.289	2226.346	2040.817	1709	3.322	42638	10510	82.89	20.432
2226.346	2597.404	2411.875	1423	2.766	44061	8801	85.657	17.11
2597.404	2968.462	2782.933	1141	2.218	45202	7378	87.875	14.343
2968.462	3339.519	3153.99	998	1.94	46200	6237	89.815	12.125
3339.519	3710.577	3525.048	892	1.734	47092	5239	91.549	10.185
3710.577	4081.635	3896.106	898	1.746	47990	4347	93.295	8.451
4081.635	4452.692	4267.164	731	1.421	48721	3449	94.716	6.705
4452.692	4823.75	4638.221	641	1.246	49362	2718	95.962	5.284
4823.75	5194.808	5009.279	583	1.133	49945	2077	97.096	4.038
5194.808	5565.866	5380.337	583	1.133	50528	1494	98.229	2.904
5565.866	5936.923	5751.394	487	0.947	51015	911	99.176	1.771
5936.923	6307.981	6122.452	424	0.824	51439	424	100	0.824
TOTAL	-	-	51439	100	-	-	-	-
Autor: Juleydi Miles

3 Tabla de Frecuencias con intervalos de 100 en 100 ( Conversión de m a Km)

library(dplyr)
library(gt)

# 1. Preparación y Limpieza (NA y Outliers)
dist_raw <- Datos$dist_to_road %>% na.omit()

q1 <- quantile(dist_raw, 0.25)
q3 <- quantile(dist_raw, 0.75)
iqr <- q3 - q1
# Filtramos para quedarnos con los datos "limpios"
dist_clean <- dist_raw[dist_raw >= (q1 - 1.5 * iqr) & dist_raw <= (q3 + 1.5 * iqr)]

# 2. Definición de Intervalos (de 100 en 100 metros)
BASE_M <- 100
min_m <- 0 # Empezamos desde 0 metros
max_m <- ceiling(max(dist_clean) / BASE_M) * BASE_M
cortes_m <- seq(from = min_m, to = max_m, by = BASE_M)

# 3. Cálculo de Frecuencias
n_total <- length(dist_clean)
ni <- as.vector(table(cut(dist_clean, breaks = cortes_m, include.lowest = TRUE, right = FALSE)))
hi <- (ni / n_total) * 100

# 4. Creación del DataFrame y Transformación a Kilómetros (/1000)
df_tabla_road <- data.frame(
  Li = cortes_m[1:length(ni)] / 1000, 
  Ls = cortes_m[2:(length(ni)+1)] / 1000,
  MC = ((cortes_m[1:length(ni)] + cortes_m[2:(length(ni)+1)]) / 2) / 1000,
  ni = ni, 
  hi = hi,
  Ni_asc = cumsum(ni), 
  Ni_desc = rev(cumsum(rev(ni))),
  Hi_asc = cumsum(hi), 
  Hi_desc = rev(cumsum(rev(hi)))
)

# 5. Formateo Final con gt()
df_tabla_road %>%
  mutate(across(everything(), ~as.numeric(.))) %>%
  mutate(across(c(Li, Ls, MC, hi, Hi_asc, Hi_desc), ~round(., 3))) %>%
  mutate(across(everything(), as.character)) %>%
  rbind(c("TOTAL", "-", "-", n_total, "100", "-", "-", "-", "-")) %>%
  gt() %>%
  tab_header(title = md("**Tabla N°3 de Distribución de Frecuencias: Distancia a la Vía (KM)**")) %>%
  tab_source_note(source_note = "Autor: Juleydi Miles") %>%
  cols_label(Li = "Lim. Inf (Km)", Ls = "Lim. Sup (Km)", MC = "Marca Clase (Km)", 
             ni = "ni", hi = "hi (%)", 
             Ni_asc = "Ni \u2191", Ni_desc = "Ni \u2193", 
             Hi_asc = "Hi \u2191", Hi_desc = "Hi \u2193") %>%
  cols_align(align = "center", columns = everything()) %>%
  tab_options(column_labels.background.color = "#F0F0F0")

Tabla N°3 de Distribución de Frecuencias: Distancia a la Vía (KM)
Lim. Inf (Km)	Lim. Sup (Km)	Marca Clase (Km)	ni	hi (%)	Ni ↑	Ni ↓	Hi ↑	Hi ↓
0	0.1	0.05	8503	16.53	8503	51439	16.53	100
0.1	0.2	0.15	5619	10.924	14122	42936	27.454	83.47
0.2	0.3	0.25	3911	7.603	18033	37317	35.057	72.546
0.3	0.4	0.35	3236	6.291	21269	33406	41.348	64.943
0.4	0.5	0.45	2766	5.377	24035	30170	46.725	58.652
0.5	0.6	0.55	2602	5.058	26637	27404	51.784	53.275
0.6	0.7	0.65	2331	4.532	28968	24802	56.315	48.216
0.7	0.8	0.75	2113	4.108	31081	22471	60.423	43.685
0.8	0.9	0.85	1972	3.834	33053	20358	64.257	39.577
0.9	1	0.95	1908	3.709	34961	18386	67.966	35.743
1	1.1	1.05	884	1.719	35845	16478	69.684	32.034
1.1	1.2	1.15	848	1.649	36693	15594	71.333	30.316
1.2	1.3	1.25	746	1.45	37439	14746	72.783	28.667
1.3	1.4	1.35	724	1.407	38163	14000	74.191	27.217
1.4	1.5	1.45	705	1.371	38868	13276	75.561	25.809
1.5	1.6	1.55	622	1.209	39490	12571	76.771	24.439
1.6	1.7	1.65	592	1.151	40082	11949	77.921	23.229
1.7	1.8	1.75	544	1.058	40626	11357	78.979	22.079
1.8	1.9	1.85	533	1.036	41159	10813	80.015	21.021
1.9	2	1.95	488	0.949	41647	10280	80.964	19.985
2	2.1	2.05	479	0.931	42126	9792	81.895	19.036
2.1	2.2	2.15	399	0.776	42525	9313	82.671	18.105
2.2	2.3	2.25	411	0.799	42936	8914	83.47	17.329
2.3	2.4	2.35	413	0.803	43349	8503	84.273	16.53
2.4	2.5	2.45	354	0.688	43703	8090	84.961	15.727
2.5	2.6	2.55	367	0.713	44070	7736	85.674	15.039
2.6	2.7	2.65	326	0.634	44396	7369	86.308	14.326
2.7	2.8	2.75	306	0.595	44702	7043	86.903	13.692
2.8	2.9	2.85	302	0.587	45004	6737	87.49	13.097
2.9	3	2.95	311	0.605	45315	6435	88.095	12.51
3	3.1	3.05	296	0.575	45611	6124	88.67	11.905
3.1	3.2	3.15	229	0.445	45840	5828	89.115	11.33
3.2	3.3	3.25	250	0.486	46090	5599	89.601	10.885
3.3	3.4	3.35	260	0.505	46350	5349	90.107	10.399
3.4	3.5	3.45	231	0.449	46581	5089	90.556	9.893
3.5	3.6	3.55	234	0.455	46815	4858	91.011	9.444
3.6	3.7	3.65	257	0.5	47072	4624	91.51	8.989
3.7	3.8	3.75	246	0.478	47318	4367	91.989	8.49
3.8	3.9	3.85	272	0.529	47590	4121	92.517	8.011
3.9	4	3.95	241	0.469	47831	3849	92.986	7.483
4	4.1	4.05	197	0.383	48028	3608	93.369	7.014
4.1	4.2	4.15	219	0.426	48247	3411	93.795	6.631
4.2	4.3	4.25	183	0.356	48430	3192	94.15	6.205
4.3	4.4	4.35	194	0.377	48624	3009	94.527	5.85
4.4	4.5	4.45	188	0.365	48812	2815	94.893	5.473
4.5	4.6	4.55	208	0.404	49020	2627	95.297	5.107
4.6	4.7	4.65	153	0.297	49173	2419	95.595	4.703
4.7	4.8	4.75	140	0.272	49313	2266	95.867	4.405
4.8	4.9	4.85	149	0.29	49462	2126	96.157	4.133
4.9	5	4.95	168	0.327	49630	1977	96.483	3.843
5	5.1	5.05	155	0.301	49785	1809	96.785	3.517
5.1	5.2	5.15	167	0.325	49952	1654	97.109	3.215
5.2	5.3	5.25	192	0.373	50144	1487	97.482	2.891
5.3	5.4	5.35	144	0.28	50288	1295	97.762	2.518
5.4	5.5	5.45	154	0.299	50442	1151	98.062	2.238
5.5	5.6	5.55	126	0.245	50568	997	98.307	1.938
5.6	5.7	5.65	128	0.249	50696	871	98.556	1.693
5.7	5.8	5.75	124	0.241	50820	743	98.797	1.444
5.8	5.9	5.85	142	0.276	50962	619	99.073	1.203
5.9	6	5.95	139	0.27	51101	477	99.343	0.927
6	6.1	6.05	110	0.214	51211	338	99.557	0.657
6.1	6.2	6.15	105	0.204	51316	228	99.761	0.443
6.2	6.3	6.25	107	0.208	51423	123	99.969	0.239
6.3	6.4	6.35	16	0.031	51439	16	100	0.031
TOTAL	-	-	51439	100	-	-	-	-
Autor: Juleydi Miles

4 Análisis Gráfico

4.1 Histogramas de Cantidad

dist_global_km <- na.omit(Datos$dist_to_road) / 1000
par(mar = c(8, 7, 5, 2))
hist_global <- hist(dist_global_km, breaks = 50, plot = FALSE)

barplot(hist_global$counts, 
        names.arg = round(hist_global$mids, 1),
        main = "", xlab = "", ylab = "",
        col = "#EED5D2", 
        ylim = c(0, max(hist_global$counts) * 1.2),
        space = 0, las = 2, cex.names = 0.6)

mtext("Cantidad de Plantas", side = 2, line = 4.5, cex = 1, font = 1)
mtext("Distancia a la vía (km)", side = 1, line = 4)
mtext("Gráfica N°1: Distribución de Cantidad de Plantas Solares por Distancia de la via", 
      side = 3, line = 2, adj = 0.5, cex = 1, font = 2)
mtext("Autor: Juleydi Miles", side = 1, line = 6, adj = 1, cex = 0.8)

dist_raw <- Datos$dist_to_road %>% na.omit()
q1 <- quantile(dist_raw, 0.25); q3 <- quantile(dist_raw, 0.75)
iqr <- q3 - q1
dist_local <- dist_raw[dist_raw <= (q3 + 1.5 * iqr)]
BASE_M <- 100
cortes_m <- seq(0, ceiling(max(dist_local)/BASE_M)*BASE_M, by = BASE_M)
ni_local <- as.vector(table(cut(dist_local, breaks = cortes_m, include.lowest = TRUE, right = FALSE)))
etiquetas_km <- round(cortes_m[-1] / 1000, 1)
par(mar = c(9, 7, 5, 2)) 
barplot(ni_local, 
        names.arg = etiquetas_km, 
        main = "", 
        xlab = "", 
        ylab = "",
        col = "#EED5D2",      
        border = "black",    
        ylim = c(0, max(ni_local) * 1.2),
        space = 0,           
        las = 2,              
        cex.names = 0.5)      

mtext("Cantidad de Plantas", side = 2, line = 4.5, cex = 1, font = 1)
mtext("Distancia a la vía (km) - Límite superior del intervalo", side = 1, line = 6)
mtext("Gráfica N°2: Distribución de Cantidad de Plantas Solares por Distancia de la via", 
      side = 3, line = 2, adj = 0.5, cex = 1, font = 2)
mtext("Autor: Juleydi Miles", side = 1, line = 8, adj = 1, cex = 0.8)

## Histogramas Porcentuales ##

dist_global_km <- na.omit(Datos$dist_to_road) / 1000
n_total <- length(dist_global_km)
par(mar = c(8, 7, 5, 2))
hist_global <- hist(dist_global_km, breaks = 50, plot = FALSE)
frec_rel_global <- (hist_global$counts / n_total) * 100
bp_global <- barplot(frec_rel_global, 
                     names.arg = round(hist_global$mids, 1),
                     main = "", 
                     xlab = "", 
                     ylab = "Porcentaje (%)", 
                     col = "#EED5D2", 
                     border = "black",      
                     ylim = c(0, max(frec_rel_global) * 1.3), 
                     space = 0, 
                     las = 2, 
                     cex.names = 0.6)
text(x = bp_global[frec_rel_global > 0.1], 
     y = frec_rel_global[frec_rel_global > 0.1], 
     labels = paste0(round(frec_rel_global[frec_rel_global > 0.1], 1), "%"), 
     pos = 3, cex = 0.5, col = "black")
mtext("Distancia a la vía (km)", side = 1, line = 4)
mtext("Gráfica N°3:Distribución Porcentual de Plantas Solares por Distancia de la via", 
      side = 3, line = 2, adj = 0.5, cex = 1, font = 2)
mtext("Autor: Juleydi Miles", side = 1, line = 6, adj = 1, cex = 0.8)

dist_raw <- Datos$dist_to_road %>% na.omit()
q1 <- quantile(dist_raw, 0.25); q3 <- quantile(dist_raw, 0.75)
iqr <- q3 - q1
dist_local_km <- dist_raw[dist_raw <= (q3 + 1.5 * iqr)] / 1000
cortes <- seq(0, ceiling(max(dist_local_km) * 10) / 10, by = 0.1)
ni <- as.vector(table(cut(dist_local_km, breaks = cortes, include.lowest = TRUE, right = FALSE)))
hi <- (ni / length(dist_local_km)) * 100
mids <- cortes[-1]
etiquetas_eje <- ifelse(round(mids, 1) %% 1 == 0, as.character(round(mids, 0)), "")
par(mar = c(7, 7, 5, 2))
bp4 <- barplot(hi, 
               names.arg = etiquetas_eje, 
               main = "", xlab = "", ylab = "Porcentaje (%)",
               col = "#EED5D2", border = "black", 
               ylim = c(0, max(hi) * 1.3), 
               space = 0, las = 1, cex.names = 0.8)
text(x = bp4[hi > 3], 
     y = hi[hi > 3], 
     labels = paste0(round(hi[hi > 3], 1), "%"), 
     pos = 3, 
     cex = 0.7,   
     font = 2, 
     col = "black")
mtext("Distancia a la vía (km)", side = 1, line = 3, cex = 1)
mtext("Gráfica N°4: Distribución Porcentual de Plantas Solares por Distancia de la via" , 
      side = 3, line = 2, adj = 0.5, cex = 1.1, font = 2)
mtext("Autor: Juleydi Miles", side = 1, line = 5, adj = 1, cex = 0.8)
grid(nx = NA, ny = NULL, col = "gray85", lty = "dotted")

### Diagrama de Cajas (Boxplot)###

dist_raw <- Datos$dist_to_road %>% na.omit()
q1 <- quantile(dist_raw, 0.25)
q3 <- quantile(dist_raw, 0.75)
dist_local_km <- dist_raw[dist_raw <= (q3 + 1.5 * iqr)] / 1000
par(mar = c(7, 5, 4, 2)) # Margen inferior amplio para el autor

boxplot(dist_local_km, 
        horizontal = TRUE, 
        col = "#EED5D2", 
        xlab = "Distancia a la vía (km)", 
        cex.main = 0.9, 
        main = "Gráfica N°5: Distribución de la Distancia a la vía en Plantas Solares")

mtext("Autor: Juleydi Miles", side = 1, line = 4.5, adj = 1, cex = 0.8)

4.1.0.1 Ojivas

# 1. Preparación de datos (Se mantiene igual)
dist_raw <- Datos$dist_to_road %>% na.omit()
q1 <- quantile(dist_raw, 0.25); q3 <- quantile(dist_raw, 0.75)
iqr <- q3 - q1
dist_local_km <- dist_raw[dist_raw <= (q3 + 1.5 * iqr)] / 1000

BASE <- 0.1
cortes <- seq(0, ceiling(max(dist_local_km) * 10) / 10, by = BASE)
ni <- as.vector(table(cut(dist_local_km, breaks = cortes, include.lowest = TRUE, right = FALSE)))

Ni_asc <- cumsum(ni)
Ni_desc <- rev(cumsum(rev(ni)))
Li <- cortes[1:length(ni)]
Ls <- cortes[2:(length(ni)+1)]

# 2. Configuración de márgenes (Damos más espacio arriba con el tercer valor de 'mar')
par(mar = c(8, 5, 10, 2), xpd = TRUE)

x_asc <- Ls
x_desc <- Li
y_asc <- Ni_asc
y_desc <- Ni_desc

# 3. Dibujar la Ascendente
plot(x_asc, y_asc, 
     type = "b", 
     main = "",
     xlab = "Distancia a la vía (km)", 
     ylab = "Frecuencia acumulada", 
     col = "black", 
     pch = 19, 
     cex = 0.6,
     xlim = c(0, max(Ls)), 
     # Aumentamos el ylim a 1.3 para que sobre espacio arriba para el título
     ylim = c(0, max(Ni_asc) * 1.3), 
     bty = "l")

# 4. Agregar la Descendente
lines(x_desc, y_desc, col = "#CDB7B5", type = "b", pch = 19, cex = 0.6)

grid()

# 5. Títulos (Subimos la línea del mtext para que no choque con la leyenda)
mtext("Gráfica N°6: Ojivas Ascendentes y Descendentes de la\nDistribución de la Distancia a la via en las Plantas Solares", 
      side = 3, line = 4, adj = 0.5, cex = 1, font = 2)

mtext("Autor: Juleydi Miles", side = 1, line = 6, adj = 1, cex = 0.8)

# 6. Leyenda (La movemos un poco más a la derecha y reducimos tamaño)
legend("topright", 
       legend = c("Ascendente", "Descendente"), 
       col = c("black", "#CDB7B5"), 
       lty = 1, 
       pch = 19, 
       cex = 0.7,
       bty = "n",
       inset = c(0, -0.05)) # El 'inset' ayuda a moverla sutilmente fuera del área de dibujo

5 Indicadores Estadísticos

library(dplyr)
library(gt)
library(moments)

# 1. Filtro de Datos Locales y Transformación a KM
dist_raw <- Datos$dist_to_road %>% na.omit()
q1_temp <- quantile(dist_raw, 0.25)
q3_temp <- quantile(dist_raw, 0.75)
iqr_temp <- q3_temp - q1_temp
lim_sup_m <- q3_temp + 1.5 * iqr_temp

# CREAMOS LA VARIABLE LOCAL YA EN KILÓMETROS
Variable_Local_KM <- dist_raw[dist_raw <= lim_sup_m] / 1000

# 2. Cálculos de Indicadores (Todo en KM)
media_k <- round(mean(Variable_Local_KM), 2)
mediana_k <- round(median(Variable_Local_KM), 2)
moda_k <- 0.05  # El centro del primer intervalo de 100m (0.1km) es 0.05km

varianza_k <- round(var(Variable_Local_KM), 4) # Más decimales por ser KM
sd_k <- round(sd(Variable_Local_KM), 2)
cv_k <- round((sd_k / abs(media_k)) * 100, 2)

asimetria_k <- round(skewness(Variable_Local_KM), 2)
curtosis_k <- round(kurtosis(Variable_Local_KM), 2)

# 3. Creación del DataFrame
tabla_indicadores_km <- data.frame(
  "Variable" = "Distancia de la vía (km) - LOCAL",
  "Rango_MinMax" = paste0("[", round(min(Variable_Local_KM), 2), "; ", round(max(Variable_Local_KM), 2), "]"),
  "X" = media_k,
  "Me" = mediana_k,
  "Mo" = moda_k,
  "V" = varianza_k,
  "Sd" = sd_k,
  "Cv" = cv_k,
  "As" = asimetria_k,
  "K" = curtosis_k,
  "Outliers" = "0 [Outliers]"
)

# 4. Generar Tabla GT Profesional
tabla_indicadores_km %>%
  gt() %>%
  tab_header(title = md("**Tabla N°3 de Conclusiones de Distancia de la vía de las Plantas Solares)**")) %>%
  tab_source_note(source_note = "Autor: Juleydi Miles") %>%
  cols_label(
    Variable = "Variable",
    Rango_MinMax = "Rango (km)",
    X = "Media (X)",
    Me = "Mediana (Me)", 
    Mo = "Moda (Mo)",
    V = "Varianza (V)",
    Sd = "Desv. Est. (Sd)",
    Cv = "C.V. (%)",
    As = "Asimetría (As)",
    K = "Curtosis (K)",
    Outliers = "Outliers"
  ) %>%
  cols_align(align = "center", columns = everything()) %>%
  tab_options(
    heading.title.font.size = px(16),
    column_labels.background.color = "#F0F0F0"
  )

Tabla N°3 de Conclusiones de Distancia de la vía de las Plantas Solares)
Variable	Rango (km)	Media (X)	Mediana (Me)	Moda (Mo)	Varianza (V)	Desv. Est. (Sd)	C.V. (%)	Asimetría (As)	Curtosis (K)	Outliers
Distancia de la vía (km) - LOCAL	[0; 6.31]	1.13	0.56	0.05	1.9956	1.41	124.78	1.77	5.42	0 [Outliers]
Autor: Juleydi Miles

6 Conclusiones

La variable “Distancia a la vía” fluctúa entre 0 y 6.31 km y sus valores se encuentran alrededor de 1.73 km, con una desviación estándar de 1.70, siendo una variable muy heterogénea, cuyos valores se concentran en la parte inicial baja de la variable con la agregación de valores atípicos de 0 outliers; por todo lo anterior, el comportamiento de la variable es muy favorable.