#Importar la base de datos de csv
data <- read.csv("C:\\Users\\Emili\\Downloads\\HousePriceData.csv")
# Usar file.choose()
# Entender la base de datos
str(data)## 'data.frame': 905 obs. of 10 variables:
## $ Observation : int 1 2 3 4 5 6 7 8 9 10 ...
## $ Dist_Taxi : int 9796 8294 11001 8301 10510 6665 13153 5882 7495 8233 ...
## $ Dist_Market : int 5250 8186 14399 11188 12629 5142 11869 9948 11589 7067 ...
## $ Dist_Hospital: int 10703 12694 16991 12289 13921 9972 17811 13315 13370 11400 ...
## $ Carpet : int 1659 1461 1340 1451 1770 1442 1542 1261 1090 1030 ...
## $ Builtup : int 1961 1752 1609 1748 2111 1733 1858 1507 1321 1235 ...
## $ Parking : chr "Open" "Not Provided" "Not Provided" "Covered" ...
## $ City_Category: chr "CAT B" "CAT B" "CAT A" "CAT B" ...
## $ Rainfall : int 530 210 720 620 450 760 1030 1020 680 1130 ...
## $ House_Price : int 6649000 3982000 5401000 5373000 4662000 4526000 7224000 3772000 4631000 4415000 ...summary(data)## Observation Dist_Taxi Dist_Market Dist_Hospital
## Min. : 1.0 Min. : 146 Min. : 1666 Min. : 3227
## 1st Qu.:237.0 1st Qu.: 6477 1st Qu.: 9367 1st Qu.:11302
## Median :469.0 Median : 8228 Median :11149 Median :13189
## Mean :468.4 Mean : 8235 Mean :11022 Mean :13091
## 3rd Qu.:700.0 3rd Qu.: 9939 3rd Qu.:12675 3rd Qu.:14855
## Max. :932.0 Max. :20662 Max. :20945 Max. :23294
##
## Carpet Builtup Parking City_Category
## Min. : 775 Min. : 932 Length:905 Length:905
## 1st Qu.: 1317 1st Qu.: 1579 Class :character Class :character
## Median : 1478 Median : 1774 Mode :character Mode :character
## Mean : 1511 Mean : 1794
## 3rd Qu.: 1654 3rd Qu.: 1985
## Max. :24300 Max. :12730
## NA's :7
## Rainfall House_Price
## Min. :-110.0 Min. : 1492000
## 1st Qu.: 600.0 1st Qu.: 4623000
## Median : 780.0 Median : 5860000
## Mean : 786.9 Mean : 6083992
## 3rd Qu.: 970.0 3rd Qu.: 7200000
## Max. :1560.0 Max. :150000000
## regresion <- lm(House_Price ~ factor(Parking) + factor(City_Category) +
Dist_Taxi + Dist_Market + Dist_Hospital +
Carpet + Builtup + Rainfall, data = data)
summary(regresion)##
## Call:
## lm(formula = House_Price ~ factor(Parking) + factor(City_Category) +
## Dist_Taxi + Dist_Market + Dist_Hospital + Carpet + Builtup +
## Rainfall, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3586934 -837542 -65314 784513 4577689
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5.568e+06 3.688e+05 15.097 < 2e-16 ***
## factor(Parking)No Parking -6.170e+05 1.393e+05 -4.429 1.06e-05 ***
## factor(Parking)Not Provided -5.077e+05 1.239e+05 -4.096 4.58e-05 ***
## factor(Parking)Open -2.597e+05 1.131e+05 -2.297 0.0218 *
## factor(City_Category)CAT B -1.883e+06 9.641e+04 -19.529 < 2e-16 ***
## factor(City_Category)CAT C -2.902e+06 1.062e+05 -27.321 < 2e-16 ***
## Dist_Taxi 2.834e+01 2.694e+01 1.052 0.2931
## Dist_Market 1.237e+01 2.089e+01 0.592 0.5538
## Dist_Hospital 5.071e+01 3.021e+01 1.679 0.0936 .
## Carpet 9.907e+03 1.428e+02 69.398 < 2e-16 ***
## Builtup -7.575e+03 2.412e+02 -31.403 < 2e-16 ***
## Rainfall -9.984e+01 1.548e+02 -0.645 0.5191
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1228000 on 886 degrees of freedom
## (7 observations deleted due to missingness)
## Multiple R-squared: 0.9429, Adjusted R-squared: 0.9422
## F-statistic: 1329 on 11 and 886 DF, p-value: < 2.2e-16#Generar pronostico
datos_nuevos <- data.frame(
Parking = "Open",
City_Category = "CAT B",
Dist_Taxi = 8000,
Dist_Market = 11000,
Dist_Hospital = 13000,
Carpet = 1500,
Builtup = 1800,
Rainfall = 780
)
prediccion <- predict(regresion, datos_nuevos)
cat("El precio estimado para la casa es:", prediccion)## El precio estimado para la casa es: 5595150#El tamaño del área interna (Carpet) y la Categoría de la Ciudad son los factores que más afectan el precio. Las casas en CAT A son significativamente más caras que en B o C.
#Tener un estacionamiento techado (Covered) aumenta el valor de la propiedad en comparación con no tenerlo o tenerlo abierto.
#Las distancias (al hospital, mercado o taxi) y el nivel de lluvia (Rainfall) no influyen significativamente en el precio final según los datos.
#El modelo tiene un R-cuadrado de 0.94, lo que significa que explica el 94% de la variación de los precios, siendo muy confiable para hacer predicciones.