Renta de Casas

Renta de Casas

1. Importar Bases de datos

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

2. Entender la base de datos

library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

summary(df)

##   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  
## 

count(df, Parking, sort=TRUE)

##        Parking   n
## 1         Open 355
## 2 Not Provided 225
## 3      Covered 184
## 4   No Parking 141

count(df, City_Category, sort=TRUE)

##   City_Category   n
## 1         CAT B 351
## 2         CAT A 320
## 3         CAT C 234

#Cuantos NA tenemos en la base de datos?
sum(is.na(df))

## [1] 7

# Cuantos NA tengo por variable?
sapply(df, function(x) sum(is.na(x)))

##   Observation     Dist_Taxi   Dist_Market Dist_Hospital        Carpet 
##             0             0             0             0             7 
##       Builtup       Parking City_Category      Rainfall   House_Price 
##             0             0             0             0             0

# Eliminar NA
df <- na.omit(df)

#Eliminar el registro del precio atípico
df <- df[df$House_Price<12000000,]

# Eliminar el registro de lluvia atípico
df <- df[df$Rainfall>=0,]

#Gráficas 
boxplot(df$House_Price, horizontal=TRUE)

3. Generar la regresión lineal

regresion <- lm(House_Price ~ Dist_Taxi+Dist_Market + Dist_Hospital + Carpet + Builtup + Parking + City_Category + Rainfall , data=df)

summary(regresion)

## 
## Call:
## lm(formula = House_Price ~ Dist_Taxi + Dist_Market + Dist_Hospital + 
##     Carpet + Builtup + Parking + City_Category + Rainfall, data = df)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -3572009  -800792   -65720   761534  4401585 
## 
## Coefficients:
##                       Estimate Std. Error t value Pr(>|t|)    
## (Intercept)          5.599e+06  3.672e+05  15.246  < 2e-16 ***
## Dist_Taxi            3.009e+01  2.682e+01   1.122   0.2622    
## Dist_Market          1.285e+01  2.081e+01   0.618   0.5370    
## Dist_Hospital        4.864e+01  3.008e+01   1.617   0.1062    
## Carpet              -7.997e+02  3.476e+03  -0.230   0.8181    
## Builtup              1.339e+03  2.901e+03   0.462   0.6444    
## ParkingNo Parking   -6.040e+05  1.389e+05  -4.348 1.53e-05 ***
## ParkingNot Provided -4.924e+05  1.235e+05  -3.988 7.22e-05 ***
## ParkingOpen         -2.632e+05  1.126e+05  -2.338   0.0196 *  
## City_CategoryCAT B  -1.877e+06  9.598e+04 -19.554  < 2e-16 ***
## City_CategoryCAT C  -2.890e+06  1.059e+05 -27.300  < 2e-16 ***
## Rainfall            -1.175e+02  1.550e+02  -0.758   0.4484    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1222000 on 884 degrees of freedom
## Multiple R-squared:  0.5007, Adjusted R-squared:  0.4945 
## F-statistic: 80.58 on 11 and 884 DF,  p-value: < 2.2e-16

4. Construir un modelo predictivo

datos <- data.frame(Dist_Taxi=8278,Dist_Market=16251, Dist_Hospital=13857, Carpet = 1455, Builtup = 1764, Parking="Covered",City_Category = "CAT A", Rainfall= 390)

predict(regresion,datos)

##       1 
## 7883860