library(readxl)
todo <- read_excel("Datos Rentas Prob y Est.xlsx", sheet = "Datos")
cali <- read_excel("Datos Rentas Prob y Est.xlsx", sheet = "Cali")
bogota <- read_excel("Datos Rentas Prob y Est.xlsx", sheet = "Bogotá D.C.")
medellin <- read_excel("Datos Rentas Prob y Est.xlsx", sheet = "Medellín")
header=TRUE
# Indicadores de tendencia central todos los datos (rent_price)
media_todo <- mean(todo$rent_price)
mediana_todo <- median(todo$rent_price)
moda_todo <- table(todo$rent_price)
moda_todo <- as.numeric(names(moda_todo)[which.max(moda_todo)])
# Indicadores de dispersión todos los datos (rent_price)
rango_todo <- range(todo$rent_price)
desviacion_estandar_todo <- sd(todo$rent_price)
varianza_todo <- var(todo$rent_price)
# Indicadores de posición todos p´polos datos (rent_price)
cuartiles_todo <- quantile(todo$rent_price, c(0.25, 0.5, 0.75))
percentiles_todo <- quantile(todo$rent_price, c(0.25, 0.5, 0.75, 0.90, 0.95, 0.99))
# Verificar valores faltantes
colSums(is.na(todo))
## rent_price area build_area rooms baths garages
## 0 0 0 0 0 0
## city zone neighborhood
## 0 0 0
colSums(is.na(cali))
## rent_price area build_area rooms baths garages
## 0 0 0 0 0 0
## city zone neighborhood
## 0 0 0
colSums(is.na(bogota))
## rent_price area build_area rooms baths garages
## 0 0 0 0 0 0
## city zone neighborhood
## 0 0 0
colSums(is.na(medellin))
## rent_price area build_area rooms baths garages
## 0 0 0 0 0 0
## city zone neighborhood
## 0 0 0
# Imputación de valores faltantes para variables numéricas
numeric_vars <- c("rent_price", "area", "build_area", "rooms", "baths", "garages")
for (var in numeric_vars) {
todo[[var]] <- ifelse(is.na(todo[[var]]),
mean(todo[[var]], na.rm = TRUE),
todo[[var]])
}
numeric_vars <- c("rent_price", "area", "build_area", "rooms", "baths", "garages")
for (var in numeric_vars) {
cali[[var]] <- ifelse(is.na(cali[[var]]),
mean(cali[[var]], na.rm = TRUE),
cali[[var]])
}
numeric_vars <- c("rent_price", "area", "build_area", "rooms", "baths", "garages")
for (var in numeric_vars) {
bogota[[var]] <- ifelse(is.na(bogota[[var]]),
mean(bogota[[var]], na.rm = TRUE),
bogota[[var]])
numeric_vars <- c("rent_price", "area", "build_area", "rooms", "baths", "garages")
for (var in numeric_vars) {
medellin[[var]] <- ifelse(is.na(medellin[[var]]),
mean(medellin[[var]], na.rm = TRUE),
medellin[[var]])
}
}
# Imputación de valores faltantes para variables categóricas
categorical_vars <- c("city", "zone", "neighborhood")
for (var in categorical_vars) {
todo[[var]] <- ifelse(is.na(todo[[var]]),
names(which.max(table(todo[[var]]))),
todo[[var]])
}
categorical_vars <- c("city", "zone", "neighborhood")
for (var in categorical_vars) {
cali[[var]] <- ifelse(is.na(cali[[var]]),
names(which.max(table(cali[[var]]))),
cali[[var]])
}
categorical_vars <- c("city", "zone", "neighborhood")
for (var in categorical_vars) {
bogota[[var]] <- ifelse(is.na(bogota[[var]]),
names(which.max(table(bogota[[var]]))),
bogota[[var]])
}
categorical_vars <- c("city", "zone", "neighborhood")
for (var in categorical_vars) {
medellin[[var]] <- ifelse(is.na(medellin[[var]]),
names(which.max(table(medellin[[var]]))),
medellin[[var]])
}
# Mostrar resumen después del preprocesamiento
summary(todo)
## rent_price area build_area rooms
## Min. : 111111 Length:300 Length:300 Min. :1.000
## 1st Qu.:1000000 Class :character Class :character 1st Qu.:1.000
## Median :1250000 Mode :character Mode :character Median :2.000
## Mean :2375569 Mean :2.273
## 3rd Qu.:3700000 3rd Qu.:3.000
## Max. :8000000 Max. :5.000
## baths garages city zone
## Min. :0.000 Min. :0.0000 Length:300 Length:300
## 1st Qu.:1.000 1st Qu.:0.0000 Class :character Class :character
## Median :2.000 Median :1.0000 Mode :character Mode :character
## Mean :1.957 Mean :0.7233
## 3rd Qu.:2.000 3rd Qu.:1.0000
## Max. :5.000 Max. :4.0000
## neighborhood
## Length:300
## Class :character
## Mode :character
##
##
##
summary(cali)
## rent_price area build_area rooms
## Min. : 269000 Length:100 Length:100 Min. :1.00
## 1st Qu.: 772500 Class :character Class :character 1st Qu.:1.00
## Median :1100000 Mode :character Mode :character Median :2.00
## Mean :1677580 Mean :2.22
## 3rd Qu.:2350000 3rd Qu.:3.00
## Max. :5000000 Max. :5.00
## baths garages city zone
## Min. :1.00 Min. :0.00 Length:100 Length:100
## 1st Qu.:1.00 1st Qu.:0.00 Class :character Class :character
## Median :2.00 Median :0.00 Mode :character Mode :character
## Mean :1.95 Mean :0.59
## 3rd Qu.:2.00 3rd Qu.:1.00
## Max. :5.00 Max. :2.00
## neighborhood
## Length:100
## Class :character
## Mode :character
##
##
##
summary(bogota)
## rent_price area build_area rooms
## Min. : 500000 Length:100 Length:100 Min. :1.0
## 1st Qu.: 800000 Class :character Class :character 1st Qu.:1.0
## Median :1100000 Mode :character Mode :character Median :2.0
## Mean :1928816 Mean :1.9
## 3rd Qu.:1250000 3rd Qu.:3.0
## Max. :7000000 Max. :3.0
## baths garages city zone
## Min. :1.00 Min. :0.00 Length:100 Length:100
## 1st Qu.:1.00 1st Qu.:0.00 Class :character Class :character
## Median :1.00 Median :0.00 Mode :character Mode :character
## Mean :1.64 Mean :0.67
## 3rd Qu.:2.00 3rd Qu.:1.00
## Max. :5.00 Max. :4.00
## neighborhood
## Length:100
## Class :character
## Mode :character
##
##
##
summary(medellin)
## rent_price area build_area rooms
## Min. : 111111 Length:100 Length:100 Min. :1.0
## 1st Qu.:1550000 Class :character Class :character 1st Qu.:2.0
## Median :3600000 Mode :character Mode :character Median :3.0
## Mean :3520311 Mean :2.7
## 3rd Qu.:6025000 3rd Qu.:3.0
## Max. :8000000 Max. :5.0
## baths garages city zone
## Min. :0.00 Min. :0.00 Length:100 Length:100
## 1st Qu.:1.00 1st Qu.:0.00 Class :character Class :character
## Median :2.00 Median :1.00 Mode :character Mode :character
## Mean :2.28 Mean :0.91
## 3rd Qu.:3.00 3rd Qu.:2.00
## Max. :5.00 Max. :3.00
## neighborhood
## Length:100
## Class :character
## Mode :character
##
##
##
install.packages("ggplot2")
## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.3'
## (as 'lib' is unspecified)
# Gráficas
library(ggplot2)
# Histograma rent_price
c <- ggplot(data = todo, mapping = aes(rent_price))
c + geom_histogram(aes(y = ..density..), col = "blue", bins = 10) +
theme_classic() +
labs(title = "Histograma de la variable rent_price") +
geom_density(kernel = "gaussian", col = "red")
## Warning: The dot-dot notation (`..density..`) was deprecated in ggplot2 3.4.0.
## ℹ Please use `after_stat(density)` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.

# Diagrama de Cajas para rent_price por Ciudad
ggplot(data = todo, mapping = aes(x = city, y = rent_price)) +
geom_boxplot(color = "blue") +
labs(title = "Diagrama de cajas rent_price por Ciudad")

# Diagrama de Cajas para build_area por Ciudad
ggplot(data = todo, mapping = aes(x = city, y = build_area)) +
geom_boxplot(color = "green") +
labs(title = "Diagrama de cajas build_area por Ciudad")

# Diagrama de Dispersión entre area y rent_price
ggplot(data = todo, mapping = aes(x = area, y = rent_price)) +
geom_point(color = "blue") +
geom_smooth(method = lm, color = "red") +
labs(title = "Diagrama de dispersión entre area y rent_price")
## `geom_smooth()` using formula = 'y ~ x'

# Otros gráficos relacionados con las variables mencionadas se pueden agregar de manera similar.
# Puedes repetir estos patrones para los conjuntos de datos cali, bogota y medellin.