Random Forest

Teoría

Random Forest es un algoritmo de aprendizaje a.utmático supervisado que se sa para clasificar y/o hacer regresiones. Se basas en la creación de multiples arboles de decison y combina sus resultados para hacer predicciones más precisas y estables.

Paquetes y librerias

library("dplyr") 
library("tidyverse")
library("randomForest")#Bosques Aleatorios
library("caret") #Entrenamiento de ML

Importar base de datos

df<-read.csv("houseprices.csv")

Entender la base de datos

summary(df)

##        Id           MSSubClass       MSZoning            LotArea      
##  Min.   :   0.0   Min.   : 20.00   Length:2919        Min.   :  1300  
##  1st Qu.: 729.5   1st Qu.: 20.00   Class :character   1st Qu.:  7478  
##  Median :1459.0   Median : 50.00   Mode  :character   Median :  9453  
##  Mean   :1459.0   Mean   : 57.14                      Mean   : 10168  
##  3rd Qu.:2188.5   3rd Qu.: 70.00                      3rd Qu.: 11570  
##  Max.   :2918.0   Max.   :190.00                      Max.   :215245  
##                                                                       
##   LotConfig           BldgType          OverallCond      YearBuilt   
##  Length:2919        Length:2919        Min.   :1.000   Min.   :1872  
##  Class :character   Class :character   1st Qu.:5.000   1st Qu.:1954  
##  Mode  :character   Mode  :character   Median :5.000   Median :1973  
##                                        Mean   :5.565   Mean   :1971  
##                                        3rd Qu.:6.000   3rd Qu.:2001  
##                                        Max.   :9.000   Max.   :2010  
##                                                                      
##   YearRemodAdd  Exterior1st          BsmtFinSF2       TotalBsmtSF    
##  Min.   :1950   Length:2919        Min.   :   0.00   Min.   :   0.0  
##  1st Qu.:1965   Class :character   1st Qu.:   0.00   1st Qu.: 793.0  
##  Median :1993   Mode  :character   Median :   0.00   Median : 989.5  
##  Mean   :1984                      Mean   :  49.58   Mean   :1051.8  
##  3rd Qu.:2004                      3rd Qu.:   0.00   3rd Qu.:1302.0  
##  Max.   :2010                      Max.   :1526.00   Max.   :6110.0  
##                                    NA's   :1         NA's   :1       
##    SalePrice     
##  Min.   : 34900  
##  1st Qu.:129975  
##  Median :163000  
##  Mean   :180921  
##  3rd Qu.:214000  
##  Max.   :755000  
##  NA's   :1459

head(df)

##   Id MSSubClass MSZoning LotArea LotConfig BldgType OverallCond YearBuilt
## 1  0         60       RL    8450    Inside     1Fam           5      2003
## 2  1         20       RL    9600       FR2     1Fam           8      1976
## 3  2         60       RL   11250    Inside     1Fam           5      2001
## 4  3         70       RL    9550    Corner     1Fam           5      1915
## 5  4         60       RL   14260       FR2     1Fam           5      2000
## 6  5         50       RL   14115    Inside     1Fam           5      1993
##   YearRemodAdd Exterior1st BsmtFinSF2 TotalBsmtSF SalePrice
## 1         2003     VinylSd          0         856    208500
## 2         1976     MetalSd          0        1262    181500
## 3         2002     VinylSd          0         920    223500
## 4         1970     Wd Sdng          0         756    140000
## 5         2000     VinylSd          0        1145    250000
## 6         1995     VinylSd          0         796    143000

# Convertir múltiples columnas a factor
df <- df %>%
  mutate(
    MSZoning = as.factor(MSZoning),
    LotConfig = as.factor(LotConfig),
    BldgType = as.factor(BldgType),
    Exterior1st = as.factor(Exterior1st),
    SalesPrice = as.numeric(SalePrice)
  )

str(df)

## 'data.frame':    2919 obs. of  14 variables:
##  $ Id          : int  0 1 2 3 4 5 6 7 8 9 ...
##  $ MSSubClass  : int  60 20 60 70 60 50 20 60 50 190 ...
##  $ MSZoning    : Factor w/ 6 levels "","C (all)","FV",..: 5 5 5 5 5 5 5 5 6 5 ...
##  $ LotArea     : int  8450 9600 11250 9550 14260 14115 10084 10382 6120 7420 ...
##  $ LotConfig   : Factor w/ 5 levels "Corner","CulDSac",..: 5 3 5 1 3 5 5 1 5 1 ...
##  $ BldgType    : Factor w/ 5 levels "1Fam","2fmCon",..: 1 1 1 1 1 1 1 1 1 2 ...
##  $ OverallCond : int  5 8 5 5 5 5 5 6 5 6 ...
##  $ YearBuilt   : int  2003 1976 2001 1915 2000 1993 2004 1973 1931 1939 ...
##  $ YearRemodAdd: int  2003 1976 2002 1970 2000 1995 2005 1973 1950 1950 ...
##  $ Exterior1st : Factor w/ 16 levels "","AsbShng","AsphShn",..: 14 10 14 15 14 14 14 8 5 10 ...
##  $ BsmtFinSF2  : int  0 0 0 0 0 0 0 32 0 0 ...
##  $ TotalBsmtSF : int  856 1262 920 756 1145 796 1686 1107 952 991 ...
##  $ SalePrice   : int  208500 181500 223500 140000 250000 143000 307000 200000 129900 118000 ...
##  $ SalesPrice  : num  208500 181500 223500 140000 250000 ...

df<-na.omit(df)

Entrenar el modelo

#Semilla para reproducibilidad
set.seed(123)

#Dividir los datos en entrenamiento y prueba
r_train <- createDataPartition(df$SalePrice, p=0.7, list=FALSE)
train <- df[r_train, ]
test <- df[-r_train, ]
modelo <- randomForest(SalesPrice ~., data=train)

# Evaluar un modelo de regresión
library(Metrics)

## 
## Adjuntando el paquete: 'Metrics'

## The following objects are masked from 'package:caret':
## 
##     precision, recall

# Predicciones (numéricas)
pred_train <- predict(modelo, train)
real_train <- train$SalePrice

# Calcular RMSE en train
rmse_train <- rmse(real_train, pred_train)
cat("RMSE en train:", rmse_train, "\n")

## RMSE en train: 7650.706

# Calcular R^2 en train
r2_train <- cor(real_train, pred_train)^2
cat("R^2 en train:", r2_train, "\n")

## R^2 en train: 0.992778

# Realizar predicciones en el conjunto de test
pred_test <- predict(modelo, test)

# Evaluar el desempeño en test usando postResample (RMSE, R², MAE)
metrics_test <- postResample(pred = pred_test, obs = test$SalePrice)
print(metrics_test)

##         RMSE     Rsquared          MAE 
## 1.319967e+04 9.769294e-01 5.807615e+03

# Alternativamente, usando el paquete Metrics:
rmse_test <- rmse(test$SalePrice, pred_test)
mae_test  <- mae(test$SalePrice, pred_test)
r2_test   <- cor(test$SalePrice, pred_test)^2

cat("Test RMSE:", rmse_test, "\n")

## Test RMSE: 13199.67

cat("Test MAE:", mae_test, "\n")

## Test MAE: 5807.615

cat("Test R²:", r2_test, "\n")

## Test R²: 0.9769294