# Regresión Lineal
# Importar la base de datos de csv
data <- read.csv("/Users/edu_sssedu/Desktop/HousePriceData.csv")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~Dist_Taxi+Dist_Market+Dist_Hospital+Carpet+factor(Parking)+factor(City_Category)+Rainfall, data=data)
summary(regresion)##
## Call:
## lm(formula = House_Price ~ Dist_Taxi + Dist_Market + Dist_Hospital +
## Carpet + factor(Parking) + factor(City_Category) + Rainfall,
## data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4364144 -1142134 -44127 1154032 12009747
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -2.142e+06 3.998e+05 -5.357 1.08e-07 ***
## Dist_Taxi 6.083e+01 3.911e+01 1.555 0.12020
## Dist_Market 4.530e+01 3.031e+01 1.494 0.13545
## Dist_Hospital 1.640e+01 4.386e+01 0.374 0.70858
## Carpet 5.735e+03 7.593e+01 75.536 < 2e-16 ***
## factor(Parking)No Parking -5.502e+05 2.023e+05 -2.719 0.00667 **
## factor(Parking)Not Provided -3.146e+05 1.798e+05 -1.749 0.08060 .
## factor(Parking)Open -1.458e+05 1.642e+05 -0.888 0.37466
## factor(City_Category)CAT B -1.990e+06 1.400e+05 -14.214 < 2e-16 ***
## factor(City_Category)CAT C -2.979e+06 1.543e+05 -19.313 < 2e-16 ***
## Rainfall 1.508e+02 2.246e+02 0.672 0.50200
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1784000 on 887 degrees of freedom
## (7 observations deleted due to missingness)
## Multiple R-squared: 0.8793, Adjusted R-squared: 0.8779
## F-statistic: 646.1 on 10 and 887 DF, p-value: < 2.2e-16Por cada pie cuadrado aumenta 5735 dólares.
Cuando la casa no cuenta con estacionamiento el precio de la casa se ve
reducido en 550,200 dólares.
Comparado con CAT A, CAT B reduce el precio esperado ≈ $1,989,647 y CAT
C ≈ $2,979,123.
# Generar pronósticos
datos_nuevos <- data.frame(Dist_Taxi=9796, Dist_Market=5250, Dist_Hospital=10703, Carpet=1659, Rainfall=530, Parking= "Open",City_Category= "CAT B")
predict(regresion, datos_nuevos)## 1
## 6326530