##2. Informacion
## hora dia mes año
## Min. : 0.00 Min. : 1.000 Min. : 1.000 Min. :2011
## 1st Qu.: 6.00 1st Qu.: 5.000 1st Qu.: 4.000 1st Qu.:2011
## Median :12.00 Median :10.000 Median : 7.000 Median :2012
## Mean :11.54 Mean : 9.993 Mean : 6.521 Mean :2012
## 3rd Qu.:18.00 3rd Qu.:15.000 3rd Qu.:10.000 3rd Qu.:2012
## Max. :23.00 Max. :19.000 Max. :12.000 Max. :2012
## estacion dia_de_la_semana asueto temperatura
## Min. :1.000 Min. :1.000 Min. :0.00000 Min. : 0.82
## 1st Qu.:2.000 1st Qu.:2.000 1st Qu.:0.00000 1st Qu.:13.94
## Median :3.000 Median :4.000 Median :0.00000 Median :20.50
## Mean :2.507 Mean :4.014 Mean :0.02857 Mean :20.23
## 3rd Qu.:4.000 3rd Qu.:6.000 3rd Qu.:0.00000 3rd Qu.:26.24
## Max. :4.000 Max. :7.000 Max. :1.00000 Max. :41.00
## sensacion_termica humedad velocidad_del_viento
## Min. : 0.76 Min. : 0.00 Min. : 0.000
## 1st Qu.:16.66 1st Qu.: 47.00 1st Qu.: 7.002
## Median :24.24 Median : 62.00 Median :12.998
## Mean :23.66 Mean : 61.89 Mean :12.799
## 3rd Qu.:31.06 3rd Qu.: 77.00 3rd Qu.:16.998
## Max. :45.45 Max. :100.00 Max. :56.997
## rentas_de_no_registrados rentas_de_registrados rentas_totales
## Min. : 0.00 Min. : 0.0 Min. : 1.0
## 1st Qu.: 4.00 1st Qu.: 36.0 1st Qu.: 42.0
## Median : 17.00 Median :118.0 Median :145.0
## Mean : 36.02 Mean :155.6 Mean :191.6
## 3rd Qu.: 49.00 3rd Qu.:222.0 3rd Qu.:284.0
## Max. :367.00 Max. :886.0 Max. :977.0observaciones: 1. Los dias llegan hasta el 19
##3. generar la regresion lineal
regresion <- lm(rentas_totales ~ hora + dia + mes + año + estacion + dia_de_la_semana + sensacion_termica + humedad + velocidad_del_viento, data= df)
summary (regresion)##
## Call:
## lm(formula = rentas_totales ~ hora + dia + mes + año + estacion +
## dia_de_la_semana + sensacion_termica + humedad + velocidad_del_viento,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -304.52 -93.34 -27.52 61.53 648.27
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -1.662e+05 5.495e+03 -30.246 < 2e-16 ***
## hora 7.733e+00 2.070e-01 37.356 < 2e-16 ***
## dia 3.925e-01 2.481e-01 1.582 0.113735
## mes 1.009e+01 1.672e+00 6.035 1.64e-09 ***
## año 8.264e+01 2.732e+00 30.254 < 2e-16 ***
## estacion -8.030e+00 5.144e+00 -1.561 0.118567
## dia_de_la_semana 5.270e-01 6.792e-01 0.776 0.437775
## sensacion_termica 6.183e+00 1.692e-01 36.551 < 2e-16 ***
## humedad -2.123e+00 7.870e-02 -26.973 < 2e-16 ***
## velocidad_del_viento 6.121e-01 1.773e-01 3.452 0.000559 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 141.7 on 10876 degrees of freedom
## Multiple R-squared: 0.3889, Adjusted R-squared: 0.3884
## F-statistic: 769.2 on 9 and 10876 DF, p-value: < 2.2e-16##4 ajustar el modelo
regresion <- lm(rentas_totales ~ hora + mes + año + sensacion_termica + humedad + velocidad_del_viento, data= df)
summary(regresion)##
## Call:
## lm(formula = rentas_totales ~ hora + mes + año + sensacion_termica +
## humedad + velocidad_del_viento, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -308.60 -93.85 -28.34 61.05 648.09
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -1.662e+05 5.496e+03 -30.250 < 2e-16 ***
## hora 7.734e+00 2.070e-01 37.364 < 2e-16 ***
## mes 7.574e+00 4.207e-01 18.002 < 2e-16 ***
## año 8.266e+01 2.732e+00 30.258 < 2e-16 ***
## sensacion_termica 6.172e+00 1.689e-01 36.539 < 2e-16 ***
## humedad -2.121e+00 7.858e-02 -26.988 < 2e-16 ***
## velocidad_del_viento 6.208e-01 1.771e-01 3.506 0.000457 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 141.7 on 10879 degrees of freedom
## Multiple R-squared: 0.3886, Adjusted R-squared: 0.3883
## F-statistic: 1153 on 6 and 10879 DF, p-value: < 2.2e-16##5. Conrstruir modelo
datos <- data.frame(hora = 11.54, mes = 1:12, año =2013, sensacion_termica=23.66,humedad=61.89, velocidad_del_viento=12.799)
predict(regresion,datos)## 1 2 3 4 5 6 7 8
## 273.6001 281.1738 288.7475 296.3213 303.8950 311.4687 319.0424 326.6161
## 9 10 11 12
## 334.1898 341.7635 349.3372 356.9110##2. Informacion
## 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
## ##3. generar la regresion lineal
regresion2 <- lm(House_Price ~ Dist_Taxi + Dist_Market+ Dist_Hospital + Carpet+ Builtup+ Parking+ City_Category + Rainfall, data= house)
summary (regresion2)##
## Call:
## lm(formula = House_Price ~ Dist_Taxi + Dist_Market + Dist_Hospital +
## Carpet + Builtup + Parking + City_Category + Rainfall, data = house)
##
## 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 ***
## 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 ***
## ParkingNo Parking -6.170e+05 1.393e+05 -4.429 1.06e-05 ***
## ParkingNot Provided -5.077e+05 1.239e+05 -4.096 4.58e-05 ***
## ParkingOpen -2.597e+05 1.131e+05 -2.297 0.0218 *
## City_CategoryCAT B -1.883e+06 9.641e+04 -19.529 < 2e-16 ***
## City_CategoryCAT C -2.902e+06 1.062e+05 -27.321 < 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##4 ajustar el modelo
##
## Call:
## lm(formula = House_Price ~ Carpet + Builtup, data = house)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4212263 -1302730 -59144 1288045 5568443
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4905496.3 346227.7 14.17 <2e-16 ***
## Carpet 10054.6 198.1 50.76 <2e-16 ***
## Builtup -7804.7 335.9 -23.23 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1720000 on 895 degrees of freedom
## (7 observations deleted due to missingness)
## Multiple R-squared: 0.8868, Adjusted R-squared: 0.8865
## F-statistic: 3505 on 2 and 895 DF, p-value: < 2.2e-16##5. Conrstruir modelo
## 1
## 5920662