data <- read.csv("C:\\Users\\marco\\Downloads\\rentadebicis.csv")
#file.choose()str(data)## 'data.frame': 10886 obs. of 14 variables:
## $ hora : int 0 1 2 3 4 5 6 7 8 9 ...
## $ dia : int 1 1 1 1 1 1 1 1 1 1 ...
## $ mes : int 1 1 1 1 1 1 1 1 1 1 ...
## $ año : int 2011 2011 2011 2011 2011 2011 2011 2011 2011 2011 ...
## $ estacion : int 1 1 1 1 1 1 1 1 1 1 ...
## $ dia_de_la_semana : int 6 6 6 6 6 6 6 6 6 6 ...
## $ asueto : int 0 0 0 0 0 0 0 0 0 0 ...
## $ temperatura : num 9.84 9.02 9.02 9.84 9.84 ...
## $ sensacion_termica : num 14.4 13.6 13.6 14.4 14.4 ...
## $ humedad : int 81 80 80 75 75 75 80 86 75 76 ...
## $ velocidad_del_viento : num 0 0 0 0 0 ...
## $ rentas_de_no_registrados: int 3 8 5 3 0 0 2 1 1 8 ...
## $ rentas_de_registrados : int 13 32 27 10 1 1 0 2 7 6 ...
## $ rentas_totales : int 16 40 32 13 1 1 2 3 8 14 ...summary(data)## 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. :977.0regresion <- lm(rentas_totales~factor(hora)+factor(dia)+factor(mes)+año+factor(dia_de_la_semana)+humedad+velocidad_del_viento, data=data)
summary(regresion)##
## Call:
## lm(formula = rentas_totales ~ factor(hora) + factor(dia) + factor(mes) +
## año + factor(dia_de_la_semana) + humedad + velocidad_del_viento,
## data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -380.68 -64.10 -6.11 52.63 437.58
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -1.852e+05 3.991e+03 -46.410 < 2e-16 ***
## factor(hora)1 -1.955e+01 6.827e+00 -2.864 0.004198 **
## factor(hora)2 -3.079e+01 6.851e+00 -4.495 7.04e-06 ***
## factor(hora)3 -4.312e+01 6.914e+00 -6.237 4.62e-10 ***
## factor(hora)4 -4.484e+01 6.881e+00 -6.517 7.51e-11 ***
## factor(hora)5 -2.992e+01 6.842e+00 -4.373 1.24e-05 ***
## factor(hora)6 2.851e+01 6.832e+00 4.173 3.04e-05 ***
## factor(hora)7 1.636e+02 6.828e+00 23.962 < 2e-16 ***
## factor(hora)8 3.105e+02 6.825e+00 45.491 < 2e-16 ***
## factor(hora)9 1.651e+02 6.829e+00 24.180 < 2e-16 ***
## factor(hora)10 1.131e+02 6.844e+00 16.521 < 2e-16 ***
## factor(hora)11 1.432e+02 6.867e+00 20.853 < 2e-16 ***
## factor(hora)12 1.853e+02 6.892e+00 26.881 < 2e-16 ***
## factor(hora)13 1.834e+02 6.921e+00 26.499 < 2e-16 ***
## factor(hora)14 1.673e+02 6.942e+00 24.107 < 2e-16 ***
## factor(hora)15 1.779e+02 6.946e+00 25.615 < 2e-16 ***
## factor(hora)16 2.408e+02 6.943e+00 34.674 < 2e-16 ***
## factor(hora)17 3.954e+02 6.922e+00 57.118 < 2e-16 ***
## factor(hora)18 3.599e+02 6.898e+00 52.171 < 2e-16 ***
## factor(hora)19 2.483e+02 6.865e+00 36.177 < 2e-16 ***
## factor(hora)20 1.644e+02 6.844e+00 24.023 < 2e-16 ***
## factor(hora)21 1.123e+02 6.829e+00 16.451 < 2e-16 ***
## factor(hora)22 7.519e+01 6.823e+00 11.020 < 2e-16 ***
## factor(hora)23 3.317e+01 6.819e+00 4.865 1.16e-06 ***
## factor(dia)2 1.970e+00 6.090e+00 0.324 0.746314
## factor(dia)3 5.920e+00 6.093e+00 0.972 0.331228
## factor(dia)4 1.290e+01 6.089e+00 2.119 0.034146 *
## factor(dia)5 7.117e+00 6.086e+00 1.169 0.242307
## factor(dia)6 8.837e+00 6.085e+00 1.452 0.146455
## factor(dia)7 8.653e-01 6.084e+00 0.142 0.886909
## factor(dia)8 -2.300e+00 6.079e+00 -0.378 0.705156
## factor(dia)9 7.021e+00 6.084e+00 1.154 0.248484
## factor(dia)10 5.009e+00 6.099e+00 0.821 0.411503
## factor(dia)11 7.814e+00 6.106e+00 1.280 0.200689
## factor(dia)12 6.451e+00 6.090e+00 1.059 0.289472
## factor(dia)13 8.305e+00 6.100e+00 1.362 0.173357
## factor(dia)14 1.000e+01 6.091e+00 1.642 0.100642
## factor(dia)15 1.702e+01 6.084e+00 2.798 0.005151 **
## factor(dia)16 1.027e+01 6.086e+00 1.688 0.091527 .
## factor(dia)17 2.338e+01 6.084e+00 3.842 0.000123 ***
## factor(dia)18 8.713e+00 6.118e+00 1.424 0.154422
## factor(dia)19 9.242e+00 6.083e+00 1.519 0.128747
## factor(mes)2 2.133e+01 4.878e+00 4.372 1.24e-05 ***
## factor(mes)3 6.127e+01 4.878e+00 12.560 < 2e-16 ***
## factor(mes)4 9.888e+01 4.865e+00 20.326 < 2e-16 ***
## factor(mes)5 1.476e+02 4.920e+00 30.007 < 2e-16 ***
## factor(mes)6 1.581e+02 4.870e+00 32.467 < 2e-16 ***
## factor(mes)7 1.502e+02 4.880e+00 30.780 < 2e-16 ***
## factor(mes)8 1.553e+02 4.887e+00 31.767 < 2e-16 ***
## factor(mes)9 1.646e+02 4.956e+00 33.216 < 2e-16 ***
## factor(mes)10 1.566e+02 4.937e+00 31.709 < 2e-16 ***
## factor(mes)11 1.125e+02 4.874e+00 23.084 < 2e-16 ***
## factor(mes)12 1.030e+02 4.932e+00 20.880 < 2e-16 ***
## año 9.211e+01 1.984e+00 46.424 < 2e-16 ***
## factor(dia_de_la_semana)2 2.161e+00 3.725e+00 0.580 0.561889
## factor(dia_de_la_semana)3 2.933e+00 3.711e+00 0.790 0.429355
## factor(dia_de_la_semana)4 4.577e+00 3.720e+00 1.230 0.218594
## factor(dia_de_la_semana)5 6.463e+00 3.734e+00 1.731 0.083479 .
## factor(dia_de_la_semana)6 1.035e+01 3.691e+00 2.803 0.005068 **
## factor(dia_de_la_semana)7 -7.645e+00 3.699e+00 -2.067 0.038760 *
## humedad -1.301e+00 6.396e-02 -20.335 < 2e-16 ***
## velocidad_del_viento -8.519e-01 1.312e-01 -6.493 8.78e-11 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 102.9 on 10824 degrees of freedom
## Multiple R-squared: 0.6791, Adjusted R-squared: 0.6773
## F-statistic: 375.5 on 61 and 10824 DF, p-value: < 2.2e-16datos_nuevos <- data.frame(hora=12, dia=1, mes=1:12, año=2013,
dia_de_la_semana=1, sensacion_termica=24, humedad=62,
velocidad_del_viento=13)
predict(regresion, datos_nuevos)## 1 2 3 4 5 6 7 8
## 262.8833 284.2087 324.1540 361.7610 410.5029 421.0070 413.0892 418.1406
## 9 10 11 12
## 427.4932 419.4437 375.3979 365.8574Modelo altamente significativo con un poder explicativo del
69%.
Poder explicativo del modelo = 69%.
Efectos del horario: picos de renta en horarios de 8 am y 5-6 pm.
Efectos mensual con fuerte estacionalidad.
Clima afecta de forma positiva y la humedad y velocidad del viento de
forma negativa.