library(readxl)
setwd("C:/Users/Usuario/Downloads")
datos <- read_excel("database.xlsx")
## Warning: Expecting numeric in C2189 / R2189C3: got 'Accident Year'
## Warning: Expecting numeric in C2215 / R2215C3: got 'Accident Year'
#================================
# VARIABLE 3: LIQUID NAME
# ===============================
# Extraer la variable
liquid_name <- datos$`Liquid Name`
# Tablas
tabla_freq_name <- table(liquid_name)
View(tabla_freq_name)
tabla_rel_name <- prop.table(tabla_freq_name)
View(tabla_rel_name)
tabla_porcent_name <- prop.table(tabla_freq_name) * 100
View(tabla_porcent_name)
# Unir en un solo data frame
tabla_completa_name <- data.frame(
Liquid_Name = names(tabla_freq_name),
Frecuencia = as.vector(tabla_freq_name),
Frec_Relativa = round(as.vector(tabla_rel_name), 4),
Porcentaje = round(as.vector(tabla_porcent_name), 2)
)
View(tabla_completa_name)
tabla_completa_name
## Liquid_Name Frecuencia Frec_Relativa Porcentaje
## 1 (LCO) LIGHT CYCLE OIL 1 0.0045 0.45
## 2 14# NATURAL GASOLINE 2 0.0090 0.90
## 3 98.7% ETHANE, .97% METHANE, .36% PROPANE 1 0.0045 0.45
## 4 ACETIC ACID 1 0.0045 0.45
## 5 ATMOSPHERIC GAS OIL 1 0.0045 0.45
## 6 BUTADIENE 1 0.0045 0.45
## 7 BUTANE 12 0.0541 5.41
## 8 CONDENSATE 13 0.0586 5.86
## 9 CRUDE CONDENSATE 1 0.0045 0.45
## 10 CYCLOHEXANE 1 0.0045 0.45
## 11 DEMETHANIZED RAW FEED 1 0.0045 0.45
## 12 DILUENT 1 0.0045 0.45
## 13 DILUTE PROPYLENE 4 0.0180 1.80
## 14 DILUTE PROPYLENE (PROPYLENE PROPANE MIX) 1 0.0045 0.45
## 15 DILUTE PROPYLENE (PROPYLENE/PROPANE MIX) 1 0.0045 0.45
## 16 ETHANE 24 0.1081 10.81
## 17 ETHANE (80%) PROPANE (20%) MIX 1 0.0045 0.45
## 18 ETHANE / PROPANE 1 0.0045 0.45
## 19 ETHANE / PROPANE MIX 1 0.0045 0.45
## 20 ETHANE PROPANE MIX 1 0.0045 0.45
## 21 ETHANE/PROPANE 3 0.0135 1.35
## 22 ETHANE/PROPANE BLEND 2 0.0090 0.90
## 23 ETHANE/PROPANE MIX 3 0.0135 1.35
## 24 ETHYLENE 17 0.0766 7.66
## 25 FULL RANGE NAPTHA 1 0.0045 0.45
## 26 GAS BLEND STOCK 1 0.0045 0.45
## 27 GASOLINE-DIESEL MIX 1 0.0045 0.45
## 28 HIGH SULFUR VACUUM GAS OIL 1 0.0045 0.45
## 29 HP PROPYLENE 1 0.0045 0.45
## 30 ISO-BUTANE 1 0.0045 0.45
## 31 ISO BUTANE 1 0.0045 0.45
## 32 ISOBUTANE 4 0.0180 1.80
## 33 JET FUEL 1 0.0045 0.45
## 34 LIGHT CYCLE OIL (LCO) 1 0.0045 0.45
## 35 LIGHT NAPHTHA (GASOLINE COMPONENT) 1 0.0045 0.45
## 36 LIGHT NAPTHA 1 0.0045 0.45
## 37 LIQUID PROPANE/PROPYLENE MIX / C3 MIX 1 0.0045 0.45
## 38 MIXTURE OF LIQUID PROPANE AND BUTANE 1 0.0045 0.45
## 39 NAPHTA 1 0.0045 0.45
## 40 NAPHTHA 3 0.0135 1.35
## 41 NAPTHA 1 0.0045 0.45
## 42 NATURAL GASOLINE 12 0.0541 5.41
## 43 NO 6 FUEL OIL 1 0.0045 0.45
## 44 NORMAL BUTANE 1 0.0045 0.45
## 45 PP MIX 1 0.0045 0.45
## 46 PROPANE 26 0.1171 11.71
## 47 PROPANE / PROPYLENE MIXTURE 1 0.0045 0.45
## 48 PROPANE/BUTANE MIX 1 0.0045 0.45
## 49 PROPANE/PROPYLENE MIX 1 0.0045 0.45
## 50 PROPYLENE 15 0.0676 6.76
## 51 PROPYLENE, CHEMICAL GRADE 1 0.0045 0.45
## 52 PYGAS 1 0.0045 0.45
## 53 RAFFINATE 1 0.0045 0.45
## 54 RAW FEED 1 0.0045 0.45
## 55 REFINERY GRADE BUTANE 1 0.0045 0.45
## 56 REFINERY GRADE BUTANE (RGB) 1 0.0045 0.45
## 57 REFINERY GRADE PROPYLENE (RGP) 3 0.0135 1.35
## 58 RESIDUAL VAPORS 1 0.0045 0.45
## 59 RGP 1 0.0045 0.45
## 60 STAR 12 LUBE OIL 1 0.0045 0.45
## 61 TYPE OF PRODUCT WAS NOT IDENTIFIED 1 0.0045 0.45
## 62 ULTRA LOW SULFUR DIESEL 1 0.0045 0.45
## 63 VACUUM GAS OIL 3 0.0135 1.35
## 64 VACUUM GAS OIL (VGO) 1 0.0045 0.45
## 65 VINYL ACETATE MONOMER 1 0.0045 0.45
## 66 Y-GRADE 23 0.1036 10.36
## 67 Y-GRADE (RAW FEED) 1 0.0045 0.45
## 68 Y GRADE 3 0.0135 1.35
library(ggplot2)
library(dplyr)
##
## Adjuntando el paquete: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
# Convertimos la tabla a data.frame
df_liquids <- data.frame(
Liquid_Name = names(tabla_freq_name),
Frecuencia = as.vector(tabla_freq_name)
)
# Seleccionamos solo los top 10 líquidos por frecuencia
df_top <- df_liquids %>%
arrange(desc(Frecuencia)) %>%
slice(1:10)
# Gráfica de barras con los top 10 líquidos
ggplot(df_top, aes(x = reorder(Liquid_Name, Frecuencia), y = Frecuencia)) +
geom_bar(stat = "identity", fill = "steelblue") +
coord_flip() + # gira la gráfica para que sea más legible
labs(title = "Frecuencia de Nombre Liquido ",
x = "Nombre del Liquido",
y = "Frecuencia") +
theme_minimal(base_size = 13) +
theme(axis.text.y = element_text(size = 10))
library(dplyr)
library(ggplot2)
# Crear df_grouped
df_grouped <- data.frame(
Subtype = names(tabla_rel_name),
Proporcion = as.vector(tabla_rel_name)
) %>%
arrange(desc(Proporcion))
# Seleccionar solo los 7 más importantes
df_top <- df_grouped %>% slice(1:7)
# Gráfica limpia y ordenada
ggplot(df_top,
aes(x = reorder(Subtype, Proporcion), y = Proporcion)) +
geom_bar(stat = "identity", fill = "yellow") +
coord_flip() +
labs(title = "Proporción de Nombre Liquido ",
x = "Nombre del Liquido",
y = "Proporción") +
theme_minimal(base_size = 13) +
theme(axis.text.y = element_text(size = 9))
library(dplyr)
library(ggplot2)
# Crear df_grouped con el porcentaje
df_grouped <- data.frame(
Subtype = names(tabla_porcent_name),
Porcentaje = as.vector(tabla_porcent_name)
) %>%
arrange(desc(Porcentaje))
# Seleccionar los 7 más importantes
df_top <- df_grouped %>% slice(1:7)
# Gráfica final
ggplot(df_top,
aes(x = reorder(Subtype, Porcentaje), y = Porcentaje)) +
geom_bar(stat = "identity", fill = "orange") +
coord_flip() +
labs(title = "Porcentaje de Nombre Liquido",
x = "Nombre del Liquido",
y = "Porcentaje (%)") +
theme_minimal(base_size = 13) +
theme(axis.text.y = element_text(size = 9))
