Análisis Estadístico de la Variable DATUM
Grupo 1
2026-16-03
CARGA DE DATOS Y LIBRERÍAS
# Configuración global de los chunks
knitr::opts_chunk$set(
echo = TRUE,
message = FALSE,
warning = FALSE,
fig.align = "center"
)
# Cargar datos desde la ruta local unificada
datos <- read.csv("C:/Users/USER/Documents/PROYECTO ESTADISTICA/CMDB_Data.csv",
header = TRUE,
sep = ";",
dec = ".",
fileEncoding = "latin1")
# Verificación inicial del set de datos
str(datos)## 'data.frame': 1366 obs. of 103 variables:
## $ ï..LAB_ID : chr "C355417" "C360759" "C360762" "C360763" ...
## $ PREVIOUS_LAB_ID1 : chr "" "" "" "" ...
## $ PREVIOUS_LAB_ID2 : chr "" "" "" "" ...
## $ PREVIOUS_LAB_ID3 : chr "" "" "" "" ...
## $ FIELD_ID : chr "RM0001" "RM0027" "RM0030" "RM0031" ...
## $ JOB_ID : chr "MRP11968" "MRP12307" "MRP12307" "MRP12307" ...
## $ PREVIOUS_JOB_ID1 : chr "" "" "" "" ...
## $ PREVIOUS_JOB_ID2 : chr "" "" "" "" ...
## $ PREVIOUS_JOB_ID3 : chr "" "" "" "" ...
## $ SUBMITTER : chr "Rare Metals Task" "Rare Metals Task" "Rare Metals Task" "Rare Metals Task" ...
## $ PROJECT_NAME : chr "Critical and Rare Metals" "Critical and Rare Metals" "Critical and Rare Metals" "Critical and Rare Metals" ...
## $ DATE_SUBMITTED : chr "30/6/2011" "31/8/2011" "31/8/2011" "31/8/2011" ...
## $ COLLECTION : chr "Mackay-Keck Ore Deposits Collection" "Mackay-Stanford Ore Deposits Collection" "Mackay-Stanford Ore Deposits Collection" "Mackay-Stanford Ore Deposits Collection" ...
## $ COLLECTION_ID : chr "PHNC08_39_1183" "OD21441" "OD22811" "OD25716" ...
## $ CONTINENT : chr "North America" "South America" "South America" "Africa" ...
## $ COUNTRY : chr "United States" "Chile" "Chile" "South Africa" ...
## $ STATE_PROVINCE : chr "Nevada" "Antofagasta" "Tarapacá" "Transvaal" ...
## $ COUNTY : chr "Lyon" "El Loa" "El Tamarugal" "" ...
## $ DISTRICT_NAME : chr "Yerington" "Chuquicamata" "Collahuasi/Quebrada Blanca" "" ...
## $ DEPOSIT_NAME : chr "Pumpkin Hollow" "" "" "" ...
## $ MINE_NAME : chr "Pumpkin Hollow" "Chuquicamata mine" "Collahuasi district" "" ...
## $ DISTRICT_NAME_COLLECT: chr "Yerington" "" "" "" ...
## $ DEPOSIT_NAME_COLLECT : chr "" "" "" "" ...
## $ MINE_NAME_COLLECT : chr "Pumpkin Hollow" "Chuquicamata" "Poduosa mine" "Messina Mines Ltd." ...
## $ LOCATE_DESC : chr "" "" "Level 25" "" ...
## $ LATITUDE : chr "38,94021" "-22,2871" "-21,0309" "-24,7" ...
## $ LONGITUDE : chr "-119,05178" "-68,8991" "-68,74951" "29,3" ...
## $ DATUM : chr "WGS84" "WGS84" "WGS84" "" ...
## $ LATITUDE_COLLECT : chr "38,92492" "22,28944" "" "" ...
## $ LONGITUDE_COLLECT : chr "-119,1071" "-68,90111" "" "" ...
## $ DATUM_COLLECT : chr "" "WGS84" "" "" ...
## $ COORDINATES_QUAL : chr "100 m" "Exact" "" "" ...
## $ COORDINATES_SOURCE : chr "1) iTouchMap.com, approx, A. Orkild-Norton; 2) Mineral Resource Deposit Database Deposit ID 10174173, ore body, M. Granitto" "1) Mindat.org, approx, A. Orkild-Norton; 2) Open-File Report 2017-1079 ID 549, mine, M. Granitto" "1) No coordinates; 2) Mineral Resource Deposit Database Deposit ID 10057511, district, M. Granitto" "1) No coordinates; 2) Google Earth Pro, approx ctr of former province of Transvaal, M. Granitto" ...
## $ PRIMARY_CLASS : chr "rock" "rock" "rock" "rock" ...
## $ SYSTEM_TYPE : chr "IOA-IOCG" "Porphyry Cu-Mo-Au" "Porphyry Cu-Mo-Au" "IOA-IOCG" ...
## $ DEPOSIT_TYPE : chr "IOCG" "Supergene Cu" "Porphyry Cu" "IOCG" ...
## $ SAMPLE_DESC : chr "Nearly solid chalcopyrite mixed with small light brown irregular inclusions of unknown mineralogy; clouds of ma"| __truncated__ "Chalcocite-bronchatite-antlerite(?); highly microfractured igneous rock with green copper sulfates coating microfractures" "Bornite-chalcopyrite; mostly massive chalcopyrite with numerous inclusions of micro-chalcopyrite and widely sca"| __truncated__ "Massive chalcopyrite, IOCG in shear zone; mostly massive fine grain cuprite with widely distributed malachite t"| __truncated__ ...
## $ Al_pct_AES_ST : chr "0,33" "6,65" "0,46" "0,7" ...
## $ Ca_pct_AES_ST : chr "1,1" "0,4" "-0,1" "0,3" ...
## $ Fe_pct_AES_ST : chr "42,4" "0,25" "6,98" "27,8" ...
## $ K_pct_AES_ST : chr "-0,1" "6,1" "0,2" "-0,1" ...
## $ Mg_pct_AES_ST : chr "0,57" "0,1" "0,01" "0,33" ...
## $ Mn_pct_AES_ST : chr "0,02" "-0,01" "-0,01" "-0,01" ...
## $ P_pct_AES_ST : chr "-0,01" "0,01" "0,05" "0,01" ...
## $ S_pct_AES_ST : chr "" "" "" "" ...
## $ Si_pct_AES_ST : chr "" "" "" "" ...
## $ Ti_pct_AES_ST : chr "0,01" "0,11" "-0,01" "-0,01" ...
## $ F_pct_ISE_Fuse : chr "" "" "" "" ...
## $ Ag_ppm_MS_ST : chr "58" "6" "468" "16" ...
## $ As_ppm_MS_ST : chr "-30" "-30" "90" "-30" ...
## $ Au_ppm : chr "" "" "" "" ...
## $ Au_AM : chr "" "" "" "" ...
## $ B_ppm_AES_ST : int NA NA NA NA NA NA NA NA NA NA ...
## $ Ba_ppm_AES_ST : chr "-0,5" "924" "121" "174" ...
## $ Be_ppm_AES_ST : int -5 -5 -5 -5 -5 -5 -5 -5 -5 -5 ...
## $ Bi_ppm_MS_ST : chr "1,5" "3,6" "190" "0,4" ...
## $ Cd_ppm_MS_ST : chr "3,6" "-0,2" "0,9" "-0,2" ...
## $ Ce_ppm_MS_ST : chr "0,4" "8,8" "16,3" "3,5" ...
## $ Co_ppm_MS_ST : chr "209" "-0,5" "1,3" "44,8" ...
## $ Cr_ppm_AES_ST : int -10 -10 -10 30 20 20 60 40 20 10 ...
## $ Cs_ppm_MS_ST : chr "0,5" "1,4" "0,2" "-0,1" ...
## $ Cu_ppm_AES_ST : chr "50000,11111" "23300" "50000,11111" "50000,11111" ...
## $ Dy_ppm_MS_ST : chr "-0,05" "0,32" "1,38" "0,37" ...
## $ Er_ppm_MS_ST : chr "-0,05" "0,22" "0,77" "0,23" ...
## $ Eu_ppm_MS_ST : chr "-0,05" "0,14" "0,17" "0,1" ...
## $ Ga_ppm_MS_ST : chr "5" "15" "6" "3" ...
## $ Gd_ppm_MS_ST : chr "-0,05" "0,45" "1,5" "0,39" ...
## $ Ge_ppm_MS_ST : int -1 5 -1 -1 3 8 8 1 2 2 ...
## $ Hf_ppm_MS_ST : int -1 4 -1 -1 5 13 12 2 3 6 ...
## $ Ho_ppm_MS_ST : chr "-0,05" "0,07" "0,25" "0,07" ...
## $ In_ppm_MS_ST : chr "6,4" "-0,2" "3,7" "0,2" ...
## $ La_ppm_MS_ST : chr "0,2" "4,6" "7,2" "1,7" ...
## $ Li_ppm_AES_ST : int -10 -10 -10 -10 30 20 20 20 -10 20 ...
## $ Lu_ppm_MS_ST : chr "-0,05" "-0,05" "0,08" "-0,05" ...
## $ Mo_ppm_MS_ST : chr "-2" "60" "3" "2" ...
## $ Nb_ppm_MS_ST : chr "-1" "4" "-1" "-1" ...
## $ Nd_ppm_MS_ST : chr "0,2" "3,8" "9,1" "1,7" ...
## $ Ni_ppm_AES_ST : chr "144" "6" "-5" "48" ...
## $ Pb_ppm_MS_ST : chr "23" "16" "188" "39" ...
## $ Pd_ppm_FA_MS : chr "" "" "" "" ...
## $ Pr_ppm_MS_ST : chr "-0,05" "1,09" "2,21" "0,46" ...
## $ Pt_ppm_FA_MS : chr "" "" "" "" ...
## $ Rb_ppm_MS_ST : chr "1,2" "148" "7,1" "0,7" ...
## $ Re_ppm_MS_HF : chr "" "" "" "" ...
## $ Sb_ppm_MS_ST : chr "1,2" "2,4" "2,9" "0,3" ...
## $ Sc_ppm_AES_ST : int -5 -5 -5 -5 11 6 15 10 5 6 ...
## $ Se_ppm_MS_ST : int NA NA NA NA NA NA NA NA NA NA ...
## $ Sm_ppm_MS_ST : chr "-0,1" "0,6" "1,6" "0,4" ...
## $ Sn_ppm_MS_ST : chr "2" "3" "106" "-1" ...
## $ Sr_ppm_AES_ST : chr "26,6" "114" "22,5" "38,4" ...
## $ Ta_ppm_MS_ST : chr "-0,5" "-0,5" "-0,5" "-0,5" ...
## $ Tb_ppm_MS_ST : chr "-0,05" "0,07" "0,23" "-0,05" ...
## $ Te_ppm_MS_ST : chr "" "" "" "" ...
## $ Th_ppm_MS_ST : chr "0,2" "9,7" "2,6" "0,2" ...
## $ Tl_ppm_MS_ST : chr "-0,5" "0,5" "-0,5" "-0,5" ...
## $ Tm_ppm_MS_ST : chr "-0,05" "-0,05" "0,08" "-0,05" ...
## $ U_ppm_MS_ST : chr "0,3" "1,75" "0,63" "34,8" ...
## $ V_ppm_AES_ST : int 51 24 -5 493 68 20 40 159 39 61 ...
## $ W_ppm_MS_ST : chr "-1" "28" "22" "11" ...
## [list output truncated]Se cargaron correctamente los datos para el análisis de sistemas de referencia geográficos.
TABLAS DE PARES DE VALORES
# Frecuencia absoluta inicial
TDFDATUM <- table(datos$DATUM)
# Crear el objeto data frame
tabla_agrupada <- as.data.frame(TDFDATUM)
colnames(tabla_agrupada) <- c("DATUM", "ni")
# Reemplazamos la cadena vacía ("") por "No clasificado"
tabla_agrupada$DATUM <- as.character(tabla_agrupada$DATUM)
tabla_agrupada$DATUM[tabla_agrupada$DATUM == ""] <- "No clasificado"
# Cálculos de frecuencia relativa y porcentaje
tabla_agrupada$hi <- tabla_agrupada$ni / sum(tabla_agrupada$ni)
tabla_agrupada$hi_porc <- round(tabla_agrupada$hi * 100, 2)
# Crear fila de TOTAL
Total <- data.frame(DATUM = "TOTAL",
ni = sum(tabla_agrupada$ni),
hi = sum(tabla_agrupada$hi),
hi_porc = sum(tabla_agrupada$hi) * 100)
# Unir tabla final básica
tabla_final <- rbind(tabla_agrupada, Total)
# Mostrar tabla visual adaptada
knitr::kable(tabla_final, caption = "Tabla 1: Frecuencias de la variable DATUM (Estructura de pares)")| DATUM | ni | hi | hi_porc |
|---|---|---|---|
| No clasificado | 64 | 0.0468521 | 4.69 |
| NAD27 | 39 | 0.0285505 | 2.86 |
| WGS84 | 1263 | 0.9245974 | 92.46 |
| TOTAL | 1366 | 1.0000000 | 100.00 |
PROCESAMIENTO DE VARIABLES Y TABLAS DE FRECUENCIAS
# Filtrar registros vacíos o "No clasificado" para la tabla de frecuencias extendida
TDF_limpia <- table(datos$DATUM)
TDF_limpia <- TDF_limpia[names(TDF_limpia) != ""]
tabla_final_completa <- as.data.frame(TDF_limpia)
colnames(tabla_final_completa) <- c("DATUM", "ni")
# Cálculo de porcentajes y frecuencias acumuladas (Ascendentes y Descendentes)
tabla_final_completa$hi_porc <- round((tabla_final_completa$ni / sum(tabla_final_completa$ni)) * 100, 2)
tabla_final_completa$Niasc <- cumsum(tabla_final_completa$ni)
tabla_final_completa$Hiasc <- round(cumsum(tabla_final_completa$hi_porc), 2)
tabla_final_completa$Nidsc <- rev(cumsum(rev(tabla_final_completa$ni)))
tabla_final_completa$Hidsc <- round(rev(cumsum(rev(tabla_final_completa$hi_porc))), 2)
# Agregar fila de TOTAL
Total_completo <- data.frame(DATUM = "TOTAL",
ni = sum(tabla_final_completa$ni),
hi_porc = sum(tabla_final_completa$hi_porc),
Niasc = NA, Hiasc = NA, Nidsc = NA, Hidsc = NA)
tabla_con_total <- rbind(tabla_final_completa, Total_completo)
# Mostrar tabla de distribución completa
knitr::kable(tabla_con_total, caption = "Tabla 2: Distribución de Frecuencias Completa por Sistema Datum")| DATUM | ni | hi_porc | Niasc | Hiasc | Nidsc | Hidsc |
|---|---|---|---|---|---|---|
| NAD27 | 39 | 3 | 39 | 3 | 1302 | 100 |
| WGS84 | 1263 | 97 | 1302 | 100 | 1263 | 97 |
| TOTAL | 1302 | 100 | NA | NA | NA | NA |
VISUALIZACIÓN DE DATOS
# Configuración de márgenes para las etiquetas
par(mar = c(5, 4, 4, 2))
# Gráfica de barras absolutas utilizando la variable limpia sin vacíos
freq_abs <- TDF_limpia
names(freq_abs)[names(freq_abs) == ""] <- "No clasificado"
bar_centers <- barplot(freq_abs,
main = "Distribución de Frecuencias por DATUM",
ylab = "Frecuencia Absoluta (ni)",
xlab = "Datum",
col = "gold",
las = 1,
cex.names = 0.8,
ylim = c(0, max(freq_abs) * 1.2))
# Añadir etiquetas de valor encima de las barras
text(x = bar_centers,
y = freq_abs,
labels = freq_abs,
pos = 3,
cex = 0.9,
col = "darkblue",
font = 2)
ANÁLISIS DE FRECUENCIA RELATIVA (PORCENTAJES)
# Preparar datos porcentuales basados en la frecuencia limpia
freq_rel_porc <- round(prop.table(freq_abs) * 100, 2)
bar_centers_rel <- barplot(freq_rel_porc,
main = "Distribución Porcentual por DATUM",
ylab = "Porcentaje (%)",
xlab = "Datum",
col = "darkred",
las = 1,
cex.names = 0.9,
ylim = c(0, 110),
yaxt = "n",
yaxs = "i")
# Eje Y personalizado
axis(2, at = seq(0, 100, by = 20), labels = paste0(seq(0, 100, by = 20), "%"), las = 1)
# Etiquetas de porcentaje encima de las barras
text(x = bar_centers_rel,
y = freq_rel_porc,
labels = paste0(freq_rel_porc, "%"),
pos = 3,
cex = 0.85,
col = "black",
font = 2)
COMPOSICIÓN GLOBAL (GRÁFICA CIRCULAR)
# Colores y etiquetas porcentuales para el gráfico de pastel
hi_datum_porc <- round(prop.table(freq_abs) * 100, 1)
colores_datum <- c("#66C2A5","#8DA0CB", "#E78AC3")
etiquetas_datum <- paste0(hi_datum_porc, "%")
# Generar gráfico circular
pie(hi_datum_porc,
labels = etiquetas_datum,
col = colores_datum,
main = "Distribución de Muestras por Datum",
cex = 1.1)
# Leyenda lateral estructurada
legend("topright",
legend = names(freq_abs),
fill = colores_datum,
title = "Sistemas Datum",
cex = 0.8,
bty = "o")