MODELO
16040461
26/4/2020
#Practica MODELOS
#VERGARA HERNANDEZ JESUS ALEJANDRO
#NUMERO DE CONTROL: 16040461
#Objetivo
#Crear predicciones de precioes de casas con técnicas regresión múltiple y árboles de regresión.
#Descripcion
#Crear predicciones con el modelo de regresión lineal y con el modelo de árboles de regresión utilizando para ello, el conjunto de datos de Melborne únicamente con variables del tipo numérica y recibiendo un uevo conjunto de 5 datos para alguans variables del conjunto de datos.
#Predecir:
#Para cuando las variables siguientes tengan estos valores ¿cuál es la predicción del precio de venta de la propiedad utilizando ambos modelos?.
# Arboles de regresion de prediccion de casas
# install.packages("rpart", "rpart.plot", "caret")
library(rpart) # Arboles
library(rpart.plot) # Visualizar y represenar árboles## Warning: package 'rpart.plot' was built under R version 3.6.3library(caret) # Para llevar a cabo particiones de conjuntos de datos en caso de...## Warning: package 'caret' was built under R version 3.6.3## Loading required package: lattice## Loading required package: ggplot2## Warning: package 'ggplot2' was built under R version 3.6.3library(dplyr) # Para select, filter, mutate, arange ....## Warning: package 'dplyr' was built under R version 3.6.3##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(readr) # Para leer datos
library(ggplot2) # Para grafica mas vistosas
library(reshape) # Para renombrar columnas##
## Attaching package: 'reshape'## The following object is masked from 'package:dplyr':
##
## rename#Los datos entrena = datos de entrenamiento valida = datos de validación Vemos los datos con head() y tail() datos datos <- read.csv(“https://raw.githubusercontent.com/rpizarrog/FundamentosMachineLearning/master/datos/melb_data.csv”) Cargarlos de manera local porque se tarda desde Web
datos <- read.csv("https://raw.githubusercontent.com/rpizarrog/FundamentosMachineLearning/master/datos/melb_data.csv")
head(datos)## Suburb Address Rooms Type Price Method SellerG Date
## 1 Abbotsford 85 Turner St 2 h 1480000 S Biggin 3/12/2016
## 2 Abbotsford 25 Bloomburg St 2 h 1035000 S Biggin 4/02/2016
## 3 Abbotsford 5 Charles St 3 h 1465000 SP Biggin 4/03/2017
## 4 Abbotsford 40 Federation La 3 h 850000 PI Biggin 4/03/2017
## 5 Abbotsford 55a Park St 4 h 1600000 VB Nelson 4/06/2016
## 6 Abbotsford 129 Charles St 2 h 941000 S Jellis 7/05/2016
## Distance Postcode Bedroom2 Bathroom Car Landsize BuildingArea YearBuilt
## 1 2.5 3067 2 1 1 202 NA NA
## 2 2.5 3067 2 1 0 156 79 1900
## 3 2.5 3067 3 2 0 134 150 1900
## 4 2.5 3067 3 2 1 94 NA NA
## 5 2.5 3067 3 1 2 120 142 2014
## 6 2.5 3067 2 1 0 181 NA NA
## CouncilArea Lattitude Longtitude Regionname Propertycount
## 1 Yarra -37.7996 144.9984 Northern Metropolitan 4019
## 2 Yarra -37.8079 144.9934 Northern Metropolitan 4019
## 3 Yarra -37.8093 144.9944 Northern Metropolitan 4019
## 4 Yarra -37.7969 144.9969 Northern Metropolitan 4019
## 5 Yarra -37.8072 144.9941 Northern Metropolitan 4019
## 6 Yarra -37.8041 144.9953 Northern Metropolitan 4019tail(datos)## Suburb Address Rooms Type Price Method SellerG Date
## 13575 Westmeadows 9 Black St 3 h 582000 S Red 26/08/2017
## 13576 Wheelers Hill 12 Strada Cr 4 h 1245000 S Barry 26/08/2017
## 13577 Williamstown 77 Merrett Dr 3 h 1031000 SP Williams 26/08/2017
## 13578 Williamstown 83 Power St 3 h 1170000 S Raine 26/08/2017
## 13579 Williamstown 96 Verdon St 4 h 2500000 PI Sweeney 26/08/2017
## 13580 Yarraville 6 Agnes St 4 h 1285000 SP Village 26/08/2017
## Distance Postcode Bedroom2 Bathroom Car Landsize BuildingArea YearBuilt
## 13575 16.5 3049 3 2 2 256 NA NA
## 13576 16.7 3150 4 2 2 652 NA 1981
## 13577 6.8 3016 3 2 2 333 133 1995
## 13578 6.8 3016 3 2 4 436 NA 1997
## 13579 6.8 3016 4 1 5 866 157 1920
## 13580 6.3 3013 4 1 1 362 112 1920
## CouncilArea Lattitude Longtitude Regionname Propertycount
## 13575 -37.67917 144.8939 Northern Metropolitan 2474
## 13576 -37.90562 145.1676 South-Eastern Metropolitan 7392
## 13577 -37.85927 144.8790 Western Metropolitan 6380
## 13578 -37.85274 144.8874 Western Metropolitan 6380
## 13579 -37.85908 144.8930 Western Metropolitan 6380
## 13580 -37.81188 144.8845 Western Metropolitan 6543#Explorar los conjuntos de datos
summary(datos)## Suburb Address Rooms Type
## Reservoir : 359 1/1 Clarendon St: 3 Min. : 1.000 h:9449
## Richmond : 260 13 Robinson St : 3 1st Qu.: 2.000 t:1114
## Bentleigh East: 249 14 Arthur St : 3 Median : 3.000 u:3017
## Preston : 239 2 Bruce St : 3 Mean : 2.938
## Brunswick : 222 28 Blair St : 3 3rd Qu.: 3.000
## Essendon : 220 36 Aberfeldie St: 3 Max. :10.000
## (Other) :12031 (Other) :13562
## Price Method SellerG Date
## Min. : 85000 PI:1564 Nelson :1565 27/05/2017: 473
## 1st Qu.: 650000 S :9022 Jellis :1316 3/06/2017 : 395
## Median : 903000 SA: 92 hockingstuart:1167 12/08/2017: 387
## Mean :1075684 SP:1703 Barry :1011 17/06/2017: 374
## 3rd Qu.:1330000 VB:1199 Ray : 701 27/11/2016: 362
## Max. :9000000 Marshall : 659 29/07/2017: 341
## (Other) :7161 (Other) :11248
## Distance Postcode Bedroom2 Bathroom
## Min. : 0.00 Min. :3000 Min. : 0.000 Min. :0.000
## 1st Qu.: 6.10 1st Qu.:3044 1st Qu.: 2.000 1st Qu.:1.000
## Median : 9.20 Median :3084 Median : 3.000 Median :1.000
## Mean :10.14 Mean :3105 Mean : 2.915 Mean :1.534
## 3rd Qu.:13.00 3rd Qu.:3148 3rd Qu.: 3.000 3rd Qu.:2.000
## Max. :48.10 Max. :3977 Max. :20.000 Max. :8.000
##
## Car Landsize BuildingArea YearBuilt
## Min. : 0.00 Min. : 0.0 Min. : 0 Min. :1196
## 1st Qu.: 1.00 1st Qu.: 177.0 1st Qu.: 93 1st Qu.:1940
## Median : 2.00 Median : 440.0 Median : 126 Median :1970
## Mean : 1.61 Mean : 558.4 Mean : 152 Mean :1965
## 3rd Qu.: 2.00 3rd Qu.: 651.0 3rd Qu.: 174 3rd Qu.:1999
## Max. :10.00 Max. :433014.0 Max. :44515 Max. :2018
## NA's :62 NA's :6450 NA's :5375
## CouncilArea Lattitude Longtitude
## :1369 Min. :-38.18 Min. :144.4
## Moreland :1163 1st Qu.:-37.86 1st Qu.:144.9
## Boroondara :1160 Median :-37.80 Median :145.0
## Moonee Valley: 997 Mean :-37.81 Mean :145.0
## Darebin : 934 3rd Qu.:-37.76 3rd Qu.:145.1
## Glen Eira : 848 Max. :-37.41 Max. :145.5
## (Other) :7109
## Regionname Propertycount
## Southern Metropolitan :4695 Min. : 249
## Northern Metropolitan :3890 1st Qu.: 4380
## Western Metropolitan :2948 Median : 6555
## Eastern Metropolitan :1471 Mean : 7454
## South-Eastern Metropolitan: 450 3rd Qu.:10331
## Eastern Victoria : 53 Max. :21650
## (Other) : 73summary(datos)## Suburb Address Rooms Type
## Reservoir : 359 1/1 Clarendon St: 3 Min. : 1.000 h:9449
## Richmond : 260 13 Robinson St : 3 1st Qu.: 2.000 t:1114
## Bentleigh East: 249 14 Arthur St : 3 Median : 3.000 u:3017
## Preston : 239 2 Bruce St : 3 Mean : 2.938
## Brunswick : 222 28 Blair St : 3 3rd Qu.: 3.000
## Essendon : 220 36 Aberfeldie St: 3 Max. :10.000
## (Other) :12031 (Other) :13562
## Price Method SellerG Date
## Min. : 85000 PI:1564 Nelson :1565 27/05/2017: 473
## 1st Qu.: 650000 S :9022 Jellis :1316 3/06/2017 : 395
## Median : 903000 SA: 92 hockingstuart:1167 12/08/2017: 387
## Mean :1075684 SP:1703 Barry :1011 17/06/2017: 374
## 3rd Qu.:1330000 VB:1199 Ray : 701 27/11/2016: 362
## Max. :9000000 Marshall : 659 29/07/2017: 341
## (Other) :7161 (Other) :11248
## Distance Postcode Bedroom2 Bathroom
## Min. : 0.00 Min. :3000 Min. : 0.000 Min. :0.000
## 1st Qu.: 6.10 1st Qu.:3044 1st Qu.: 2.000 1st Qu.:1.000
## Median : 9.20 Median :3084 Median : 3.000 Median :1.000
## Mean :10.14 Mean :3105 Mean : 2.915 Mean :1.534
## 3rd Qu.:13.00 3rd Qu.:3148 3rd Qu.: 3.000 3rd Qu.:2.000
## Max. :48.10 Max. :3977 Max. :20.000 Max. :8.000
##
## Car Landsize BuildingArea YearBuilt
## Min. : 0.00 Min. : 0.0 Min. : 0 Min. :1196
## 1st Qu.: 1.00 1st Qu.: 177.0 1st Qu.: 93 1st Qu.:1940
## Median : 2.00 Median : 440.0 Median : 126 Median :1970
## Mean : 1.61 Mean : 558.4 Mean : 152 Mean :1965
## 3rd Qu.: 2.00 3rd Qu.: 651.0 3rd Qu.: 174 3rd Qu.:1999
## Max. :10.00 Max. :433014.0 Max. :44515 Max. :2018
## NA's :62 NA's :6450 NA's :5375
## CouncilArea Lattitude Longtitude
## :1369 Min. :-38.18 Min. :144.4
## Moreland :1163 1st Qu.:-37.86 1st Qu.:144.9
## Boroondara :1160 Median :-37.80 Median :145.0
## Moonee Valley: 997 Mean :-37.81 Mean :145.0
## Darebin : 934 3rd Qu.:-37.76 3rd Qu.:145.1
## Glen Eira : 848 Max. :-37.41 Max. :145.5
## (Other) :7109
## Regionname Propertycount
## Southern Metropolitan :4695 Min. : 249
## Northern Metropolitan :3890 1st Qu.: 4380
## Western Metropolitan :2948 Median : 6555
## Eastern Metropolitan :1471 Mean : 7454
## South-Eastern Metropolitan: 450 3rd Qu.:10331
## Eastern Victoria : 53 Max. :21650
## (Other) : 73#Elegimos sólo las variables numéricas Un conjunto de datos únicamente con las variables numéricas del conjunto de datos original
datos.Num <- select(datos, Price, Rooms, Distance, Bedroom2, Bathroom, Car, Landsize, BuildingArea, YearBuilt, Propertycount)
head(datos.Num)## Price Rooms Distance Bedroom2 Bathroom Car Landsize BuildingArea YearBuilt
## 1 1480000 2 2.5 2 1 1 202 NA NA
## 2 1035000 2 2.5 2 1 0 156 79 1900
## 3 1465000 3 2.5 3 2 0 134 150 1900
## 4 850000 3 2.5 3 2 1 94 NA NA
## 5 1600000 4 2.5 3 1 2 120 142 2014
## 6 941000 2 2.5 2 1 0 181 NA NA
## Propertycount
## 1 4019
## 2 4019
## 3 4019
## 4 4019
## 5 4019
## 6 4019str(datos.Num)## 'data.frame': 13580 obs. of 10 variables:
## $ Price : num 1480000 1035000 1465000 850000 1600000 ...
## $ Rooms : int 2 2 3 3 4 2 3 2 1 2 ...
## $ Distance : num 2.5 2.5 2.5 2.5 2.5 2.5 2.5 2.5 2.5 2.5 ...
## $ Bedroom2 : num 2 2 3 3 3 2 4 2 1 3 ...
## $ Bathroom : num 1 1 2 2 1 1 2 1 1 1 ...
## $ Car : num 1 0 0 1 2 0 0 2 1 2 ...
## $ Landsize : num 202 156 134 94 120 181 245 256 0 220 ...
## $ BuildingArea : num NA 79 150 NA 142 NA 210 107 NA 75 ...
## $ YearBuilt : num NA 1900 1900 NA 2014 ...
## $ Propertycount: num 4019 4019 4019 4019 4019 ...#Depurar, limpiar los datos Hay algunos NA que pueden afectar al modelo? Las varraiables Car, BuildingArea y YearBuilding tienen NA summary() Primero encontrar los registros y columnas que tienen NA Actualizar conforme a su mediana, ¿porqué?, decisión del analista, y la finalidad es que no afecten al modelo, que mejor que tengan un valor (la mediana) a que no tengan nada
mediana.BA <- median(datos.Num$BuildingArea, na.rm = TRUE) # summary(datos.Num$BuildingArea)[3], como otra alternativa
mediana.YB <- median(datos.Num$YearBuilt, na.rm = TRUE) # summary(datos.Num$YearBuilt)[3], , como otra alternativa
mediana.C <- median(datos.Num$Car, na.rm = TRUE) # summary(datos.Num$Car)[3], , como otra alternativa
#Actualizar mutate() los NA por la medianas Las vaiables que tienen NAs
head(datos.Num, 10) # Los primeros 10, se observan NAs## Price Rooms Distance Bedroom2 Bathroom Car Landsize BuildingArea YearBuilt
## 1 1480000 2 2.5 2 1 1 202 NA NA
## 2 1035000 2 2.5 2 1 0 156 79 1900
## 3 1465000 3 2.5 3 2 0 134 150 1900
## 4 850000 3 2.5 3 2 1 94 NA NA
## 5 1600000 4 2.5 3 1 2 120 142 2014
## 6 941000 2 2.5 2 1 0 181 NA NA
## 7 1876000 3 2.5 4 2 0 245 210 1910
## 8 1636000 2 2.5 2 1 2 256 107 1890
## 9 300000 1 2.5 1 1 1 0 NA NA
## 10 1097000 2 2.5 3 1 2 220 75 1900
## Propertycount
## 1 4019
## 2 4019
## 3 4019
## 4 4019
## 5 4019
## 6 4019
## 7 4019
## 8 4019
## 9 4019
## 10 4019datos.Num<- datos.Num %>%
mutate (BuildingArea = ifelse(is.na(BuildingArea), mediana.BA, BuildingArea))
datos.Num <- datos.Num %>%
mutate (YearBuilt = ifelse(is.na(YearBuilt), mediana.YB, YearBuilt))
datos.Num <- datos.Num %>%
mutate (Car = ifelse(is.na(Car), mediana.C, Car))
head(datos.Num, 10) # # Los primeros 10, YA NO se observan NAs## Price Rooms Distance Bedroom2 Bathroom Car Landsize BuildingArea YearBuilt
## 1 1480000 2 2.5 2 1 1 202 126 1970
## 2 1035000 2 2.5 2 1 0 156 79 1900
## 3 1465000 3 2.5 3 2 0 134 150 1900
## 4 850000 3 2.5 3 2 1 94 126 1970
## 5 1600000 4 2.5 3 1 2 120 142 2014
## 6 941000 2 2.5 2 1 0 181 126 1970
## 7 1876000 3 2.5 4 2 0 245 210 1910
## 8 1636000 2 2.5 2 1 2 256 107 1890
## 9 300000 1 2.5 1 1 1 0 126 1970
## 10 1097000 2 2.5 3 1 2 220 75 1900
## Propertycount
## 1 4019
## 2 4019
## 3 4019
## 4 4019
## 5 4019
## 6 4019
## 7 4019
## 8 4019
## 9 4019
## 10 4019#Crear conjuntos de entrenamiento y conjuntos de validación Ya se tienen los datos limpios, sin NAs Primero determinas el 70% de los registros para entrenamiento y 30% estante para validación Se muestran con head y número de registros respectivamente Los datos de entrenamiento representan el 70% Los datos de validación representan el 30% restante
set.seed(2020) # Semilla
entrena <- createDataPartition(datos.Num$Price, p=0.7, list = FALSE)
head(entrena)## Resample1
## [1,] 1
## [2,] 3
## [3,] 4
## [4,] 5
## [5,] 7
## [6,] 9nrow(entrena)## [1] 9508# Los registros que no estén en entrena serán los de validación
head(datos.Num[-entrena,])## Price Rooms Distance Bedroom2 Bathroom Car Landsize BuildingArea YearBuilt
## 2 1035000 2 2.5 2 1 0 156 79 1900
## 6 941000 2 2.5 2 1 0 181 126 1970
## 8 1636000 2 2.5 2 1 2 256 107 1890
## 12 1350000 3 2.5 3 2 2 214 190 2005
## 13 750000 2 2.5 2 2 1 0 94 2009
## 20 890000 2 2.5 2 1 1 150 73 1985
## Propertycount
## 2 4019
## 6 4019
## 8 4019
## 12 4019
## 13 4019
## 20 4019nrow(datos.Num[-entrena,])## [1] 4072# Ver los primeros seis datos con sólo variables numéricas
head(datos.Num)## Price Rooms Distance Bedroom2 Bathroom Car Landsize BuildingArea YearBuilt
## 1 1480000 2 2.5 2 1 1 202 126 1970
## 2 1035000 2 2.5 2 1 0 156 79 1900
## 3 1465000 3 2.5 3 2 0 134 150 1900
## 4 850000 3 2.5 3 2 1 94 126 1970
## 5 1600000 4 2.5 3 1 2 120 142 2014
## 6 941000 2 2.5 2 1 0 181 126 1970
## Propertycount
## 1 4019
## 2 4019
## 3 4019
## 4 4019
## 5 4019
## 6 4019# Ahora a determinar conjuntos de datos de entrenamiento y luego head()
datos.Entrena <- datos.Num[entrena,]
head(datos.Entrena)## Price Rooms Distance Bedroom2 Bathroom Car Landsize BuildingArea YearBuilt
## 1 1480000 2 2.5 2 1 1 202 126 1970
## 3 1465000 3 2.5 3 2 0 134 150 1900
## 4 850000 3 2.5 3 2 1 94 126 1970
## 5 1600000 4 2.5 3 1 2 120 142 2014
## 7 1876000 3 2.5 4 2 0 245 210 1910
## 9 300000 1 2.5 1 1 1 0 126 1970
## Propertycount
## 1 4019
## 3 4019
## 4 4019
## 5 4019
## 7 4019
## 9 4019summary(datos.Entrena)## Price Rooms Distance Bedroom2
## Min. : 85000 Min. : 1.000 Min. : 0.00 Min. : 0.000
## 1st Qu.: 650000 1st Qu.: 2.000 1st Qu.: 6.10 1st Qu.: 2.000
## Median : 903000 Median : 3.000 Median : 9.20 Median : 3.000
## Mean :1078063 Mean : 2.937 Mean :10.13 Mean : 2.911
## 3rd Qu.:1330000 3rd Qu.: 3.000 3rd Qu.:13.00 3rd Qu.: 3.000
## Max. :9000000 Max. :10.000 Max. :47.40 Max. :10.000
## Bathroom Car Landsize BuildingArea
## Min. :0.000 Min. : 0.000 Min. : 0.0 Min. : 0.0
## 1st Qu.:1.000 1st Qu.: 1.000 1st Qu.: 178.0 1st Qu.: 123.0
## Median :1.000 Median : 2.000 Median : 443.5 Median : 126.0
## Mean :1.529 Mean : 1.613 Mean : 579.6 Mean : 136.8
## 3rd Qu.:2.000 3rd Qu.: 2.000 3rd Qu.: 650.0 3rd Qu.: 129.0
## Max. :8.000 Max. :10.000 Max. :433014.0 Max. :6791.0
## YearBuilt Propertycount
## Min. :1830 Min. : 389
## 1st Qu.:1960 1st Qu.: 4386
## Median :1970 Median : 6567
## Mean :1967 Mean : 7453
## 3rd Qu.:1975 3rd Qu.:10331
## Max. :2018 Max. :21650# y conjunto de datos de validación y luego head()
datos.Valida <- datos.Num[-entrena,]
head(datos.Valida)## Price Rooms Distance Bedroom2 Bathroom Car Landsize BuildingArea YearBuilt
## 2 1035000 2 2.5 2 1 0 156 79 1900
## 6 941000 2 2.5 2 1 0 181 126 1970
## 8 1636000 2 2.5 2 1 2 256 107 1890
## 12 1350000 3 2.5 3 2 2 214 190 2005
## 13 750000 2 2.5 2 2 1 0 94 2009
## 20 890000 2 2.5 2 1 1 150 73 1985
## Propertycount
## 2 4019
## 6 4019
## 8 4019
## 12 4019
## 13 4019
## 20 4019summary(datos.Valida)## Price Rooms Distance Bedroom2
## Min. : 170000 Min. :1.000 Min. : 0.00 Min. : 0.000
## 1st Qu.: 649500 1st Qu.:2.000 1st Qu.: 6.20 1st Qu.: 2.000
## Median : 902500 Median :3.000 Median : 9.20 Median : 3.000
## Mean :1070130 Mean :2.941 Mean :10.15 Mean : 2.923
## 3rd Qu.:1330000 3rd Qu.:4.000 3rd Qu.:13.00 3rd Qu.: 3.000
## Max. :8000000 Max. :8.000 Max. :48.10 Max. :20.000
## Bathroom Car Landsize BuildingArea
## Min. :0.000 Min. : 0.00 Min. : 0.0 Min. : 0.0
## 1st Qu.:1.000 1st Qu.: 1.00 1st Qu.: 173.0 1st Qu.: 120.0
## Median :1.000 Median : 2.00 Median : 435.0 Median : 126.0
## Mean :1.547 Mean : 1.61 Mean : 508.9 Mean : 146.2
## 3rd Qu.:2.000 3rd Qu.: 2.00 3rd Qu.: 653.0 3rd Qu.: 130.0
## Max. :8.000 Max. :10.00 Max. :44500.0 Max. :44515.0
## YearBuilt Propertycount
## Min. :1196 Min. : 249
## 1st Qu.:1960 1st Qu.: 4217
## Median :1970 Median : 6543
## Mean :1967 Mean : 7457
## 3rd Qu.:1972 3rd Qu.:10331
## Max. :2017 Max. :21650#Contruir el MODELO árbol El comando para generar un modelo de árbol de decisión, usando la librería rpart La función lleva el mismo nombre
set.seed(2020) # Semilla
arbol <- rpart(formula = Price ~ ., data = datos.Entrena)
arbol## n= 9508
##
## node), split, n, deviance, yval
## * denotes terminal node
##
## 1) root 9508 3.905176e+15 1078063.0
## 2) Rooms< 3.5 7161 1.741856e+15 931007.8
## 4) Rooms< 2.5 3023 3.911722e+14 724213.1
## 8) Landsize< 85.5 1214 6.222679e+13 559018.9 *
## 9) Landsize>=85.5 1809 2.735839e+14 835073.1 *
## 5) Rooms>=2.5 4138 1.126966e+15 1082081.0
## 10) Distance>=11.9 1576 2.382967e+14 832810.4 *
## 11) Distance< 11.9 2562 7.305050e+14 1235418.0
## 22) BuildingArea< 156.5 2230 5.283540e+14 1181265.0 *
## 23) BuildingArea>=156.5 332 1.516845e+14 1599162.0 *
## 3) Rooms>=3.5 2347 1.535971e+15 1526746.0
## 6) Distance>=11.45 1075 2.619142e+14 1136763.0 *
## 7) Distance< 11.45 1272 9.723911e+14 1856331.0
## 14) BuildingArea< 246.5 1025 5.968351e+14 1695057.0
## 28) Landsize< 708.5 803 3.644950e+14 1566809.0 *
## 29) Landsize>=708.5 222 1.713594e+14 2158948.0 *
## 15) BuildingArea>=246.5 247 2.382655e+14 2525584.0 *#Visualizar el árbol de regresión Vamos a verlo gráficamente rpart.
prp(arbol, type = 2, nn = TRUE,
fallen.leaves = TRUE, faclen = 4,
varlen = 8, shadow.col = "gray")
#Ver las importancia de las variables en el modelo ctable LA tabla significa resultados comprensibles de los árboles con diferentes números de nodos, el promedio y la desviación STd para cada uno de los árboles con tamaño especificaco CP Factor de complejidad el árbol Número de divisiones en el mejor árbol El error relativo El XError otro error STD La desviació estándard
arbol$cptable## CP nsplit rel error xerror xstd
## 1 0.16064529 0 1.0000000 1.0001908 0.03335304
## 2 0.07724771 1 0.8393547 0.8397732 0.02940088
## 3 0.05728747 2 0.7621070 0.7627294 0.02731604
## 4 0.04050130 3 0.7048195 0.7055469 0.02633946
## 5 0.03515605 4 0.6643182 0.6669834 0.02651936
## 6 0.01561538 5 0.6291622 0.6395277 0.02549443
## 7 0.01417645 6 0.6135468 0.6211866 0.02488627
## 8 0.01292296 7 0.5993704 0.6079174 0.02482012
## 9 0.01000000 8 0.5864474 0.5990287 0.02442405#Podar el árbol prune() Más simple que el primer arbol ¿Cómo elegir la poda? Sumar el último valor XError = 0.5990287 + xstd = 0.02442405 0.6234527 = 0.5990287 + 0.02442405 El primer árbol que esta por encima de dicho valor El registro 7 encontrar su CP actoe de complejidad
plotcp(arbol)
arbol.Recortado <- prune(arbol, cp = 0.01417645)
prp(arbol.Recortado, type = 2, nn = TRUE,
fallen.leaves = TRUE, faclen = 4,
varlen = 8, shadow.col = "gray")
summary(datos.Valida)## Price Rooms Distance Bedroom2
## Min. : 170000 Min. :1.000 Min. : 0.00 Min. : 0.000
## 1st Qu.: 649500 1st Qu.:2.000 1st Qu.: 6.20 1st Qu.: 2.000
## Median : 902500 Median :3.000 Median : 9.20 Median : 3.000
## Mean :1070130 Mean :2.941 Mean :10.15 Mean : 2.923
## 3rd Qu.:1330000 3rd Qu.:4.000 3rd Qu.:13.00 3rd Qu.: 3.000
## Max. :8000000 Max. :8.000 Max. :48.10 Max. :20.000
## Bathroom Car Landsize BuildingArea
## Min. :0.000 Min. : 0.00 Min. : 0.0 Min. : 0.0
## 1st Qu.:1.000 1st Qu.: 1.00 1st Qu.: 173.0 1st Qu.: 120.0
## Median :1.000 Median : 2.00 Median : 435.0 Median : 126.0
## Mean :1.547 Mean : 1.61 Mean : 508.9 Mean : 146.2
## 3rd Qu.:2.000 3rd Qu.: 2.00 3rd Qu.: 653.0 3rd Qu.: 130.0
## Max. :8.000 Max. :10.00 Max. :44500.0 Max. :44515.0
## YearBuilt Propertycount
## Min. :1196 Min. : 249
## 1st Qu.:1960 1st Qu.: 4217
## Median :1970 Median : 6543
## Mean :1967 Mean : 7457
## 3rd Qu.:1972 3rd Qu.:10331
## Max. :2017 Max. :21650prediccion.price <- predict(arbol, newdata = datos.Valida
)
# La predicción para la casa 1
datos.Valida[1,]## Price Rooms Distance Bedroom2 Bathroom Car Landsize BuildingArea YearBuilt
## 2 1035000 2 2.5 2 1 0 156 79 1900
## Propertycount
## 2 4019prediccion.price[1]## 2
## 835073.1#Una predicción con nuevos datos ??? Rooms Distance Bedroom2 Bathroom Car Landsize BuildingArea YearBuilt Propertycount
Rooms=c(3,2,4,5,2)
Distance=c(7,6,8,9,5)
Bedroom2=c(3,4,2,3,2)
Bathroom=c(2,1,3,4,3)
Car=c(3,2,3,4,5)
Landsize=c(400,450,460,480,500)
BuildingArea=c(120,130,150,180,190)
YearBuilt=c(1930,1940,1950,1960,1970)
Propertycount=c(5000,5400,5600,5800,6000)
nuevo.Dato <- data.frame(Rooms, Distance, Bedroom2, Bathroom, Car, Landsize, BuildingArea, YearBuilt,
Propertycount)
colnames(nuevo.Dato) <- c( "Rooms", "Distance", "Bedroom2", "Bathroom", "Car", "Landsize", "BuildingArea", "YearBuilt", "Propertycount")
nuevo.Dato## Rooms Distance Bedroom2 Bathroom Car Landsize BuildingArea YearBuilt
## 1 3 7 3 2 3 400 120 1930
## 2 2 6 4 1 2 450 130 1940
## 3 4 8 2 3 3 460 150 1950
## 4 5 9 3 4 4 480 180 1960
## 5 2 5 2 3 5 500 190 1970
## Propertycount
## 1 5000
## 2 5400
## 3 5600
## 4 5800
## 5 6000prediccion.price <- predict(arbol, newdata = nuevo.Dato)
# La predicción para la casa 1
datos.Valida[1,]## Price Rooms Distance Bedroom2 Bathroom Car Landsize BuildingArea YearBuilt
## 2 1035000 2 2.5 2 1 0 156 79 1900
## Propertycount
## 2 4019prediccion.price[1]## 1
## 1181265R Markdown
This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.
When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:
Including Plots
You can also embed plots, for example:
Note that the echo = FALSE parameter was added to the code chunk to prevent printing of the R code that generated the plot.