#Usar FILE.CHOOSE() PARA ENCONTRAR LA DIRECCIÓN DEL DOC (de preferencia en la consola)
data <- read.csv("/Users/eduardojuniormedinahernandez/Downloads/rentadebicis.csv")
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. :977.0#Nivel de confiabilidad = 1-Nivel de significancia
#El nivel de significacnia sale del simbolo derecho de cada coeficiente y su valor esta en la descripcion
regresion <- lm(rentas_totales~factor(hora)+factor(dia)+factor(mes)+año+temperatura+sensacion_termica+humedad+velocidad_del_viento, data=data)
summary(regresion)##
## Call:
## lm(formula = rentas_totales ~ factor(hora) + factor(dia) + factor(mes) +
## año + temperatura + sensacion_termica + humedad + velocidad_del_viento,
## data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -380.09 -62.00 -6.52 52.64 440.33
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -1.752e+05 3.989e+03 -43.915 < 2e-16 ***
## factor(hora)1 -1.763e+01 6.745e+00 -2.614 0.008967 **
## factor(hora)2 -2.753e+01 6.771e+00 -4.066 4.82e-05 ***
## factor(hora)3 -3.836e+01 6.836e+00 -5.611 2.06e-08 ***
## factor(hora)4 -3.892e+01 6.807e+00 -5.717 1.11e-08 ***
## factor(hora)5 -2.257e+01 6.773e+00 -3.333 0.000861 ***
## factor(hora)6 3.617e+01 6.765e+00 5.347 9.12e-08 ***
## factor(hora)7 1.698e+02 6.755e+00 25.140 < 2e-16 ***
## factor(hora)8 3.133e+02 6.745e+00 46.447 < 2e-16 ***
## factor(hora)9 1.636e+02 6.747e+00 24.243 < 2e-16 ***
## factor(hora)10 1.071e+02 6.771e+00 15.821 < 2e-16 ***
## factor(hora)11 1.327e+02 6.814e+00 19.476 < 2e-16 ***
## factor(hora)12 1.711e+02 6.862e+00 24.931 < 2e-16 ***
## factor(hora)13 1.658e+02 6.917e+00 23.975 < 2e-16 ***
## factor(hora)14 1.476e+02 6.959e+00 21.216 < 2e-16 ***
## factor(hora)15 1.576e+02 6.970e+00 22.616 < 2e-16 ***
## factor(hora)16 2.214e+02 6.959e+00 31.806 < 2e-16 ***
## factor(hora)17 3.783e+02 6.918e+00 54.688 < 2e-16 ***
## factor(hora)18 3.453e+02 6.872e+00 50.247 < 2e-16 ***
## factor(hora)19 2.372e+02 6.815e+00 34.802 < 2e-16 ***
## factor(hora)20 1.560e+02 6.779e+00 23.007 < 2e-16 ***
## factor(hora)21 1.065e+02 6.755e+00 15.761 < 2e-16 ***
## factor(hora)22 7.151e+01 6.744e+00 10.603 < 2e-16 ***
## factor(hora)23 3.158e+01 6.738e+00 4.687 2.80e-06 ***
## factor(dia)2 4.115e+00 6.008e+00 0.685 0.493343
## factor(dia)3 1.075e+01 6.020e+00 1.785 0.074300 .
## factor(dia)4 1.415e+01 6.008e+00 2.355 0.018541 *
## factor(dia)5 9.417e+00 6.007e+00 1.568 0.116995
## factor(dia)6 1.317e+01 6.016e+00 2.189 0.028625 *
## factor(dia)7 3.379e+00 6.001e+00 0.563 0.573420
## factor(dia)8 7.148e-02 6.007e+00 0.012 0.990506
## factor(dia)9 1.130e+01 6.005e+00 1.883 0.059793 .
## factor(dia)10 8.864e+00 6.024e+00 1.471 0.141221
## factor(dia)11 1.323e+01 6.034e+00 2.192 0.028415 *
## factor(dia)12 1.143e+01 6.016e+00 1.900 0.057513 .
## factor(dia)13 1.172e+01 6.025e+00 1.945 0.051821 .
## factor(dia)14 1.209e+01 6.009e+00 2.012 0.044210 *
## factor(dia)15 1.767e+01 6.010e+00 2.940 0.003290 **
## factor(dia)16 1.170e+01 6.002e+00 1.950 0.051235 .
## factor(dia)17 2.636e+01 6.034e+00 4.369 1.26e-05 ***
## factor(dia)18 7.887e+00 6.036e+00 1.307 0.191323
## factor(dia)19 9.206e+00 6.003e+00 1.534 0.125133
## factor(mes)2 1.157e+01 4.854e+00 2.384 0.017121 *
## factor(mes)3 3.138e+01 5.153e+00 6.090 1.17e-09 ***
## factor(mes)4 5.375e+01 5.508e+00 9.760 < 2e-16 ***
## factor(mes)5 8.376e+01 6.237e+00 13.429 < 2e-16 ***
## factor(mes)6 7.427e+01 7.103e+00 10.456 < 2e-16 ***
## factor(mes)7 4.833e+01 8.002e+00 6.040 1.59e-09 ***
## factor(mes)8 6.097e+01 7.789e+00 7.827 5.46e-15 ***
## factor(mes)9 8.688e+01 6.904e+00 12.583 < 2e-16 ***
## factor(mes)10 1.011e+02 5.942e+00 17.016 < 2e-16 ***
## factor(mes)11 8.579e+01 5.084e+00 16.874 < 2e-16 ***
## factor(mes)12 8.165e+01 5.035e+00 16.215 < 2e-16 ***
## año 8.709e+01 1.983e+00 43.912 < 2e-16 ***
## temperatura 1.486e+00 8.575e-01 1.733 0.083086 .
## sensacion_termica 3.096e+00 7.152e-01 4.329 1.51e-05 ***
## humedad -1.297e+00 6.283e-02 -20.650 < 2e-16 ***
## velocidad_del_viento -7.830e-01 1.329e-01 -5.893 3.92e-09 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 101.7 on 10828 degrees of freedom
## Multiple R-squared: 0.6867, Adjusted R-squared: 0.685
## F-statistic: 416.4 on 57 and 10828 DF, p-value: < 2.2e-16datos_nuevos <- data.frame(
hora = 12,
dia = 1,
mes = 1:12,
año = 2013,
estacion = 1,
dia_de_la_semana = 1,
asueto = 0,
temperatura = 25,
sensacion_termica = 24,
humedad = 62,
velocidad_del_viento = 13
)
predict(regresion, datos_nuevos)## 1 2 3 4 5 6 7 8
## 306.0648 317.6388 337.4445 359.8187 389.8275 380.3322 354.3967 367.0306
## 9 10 11 12
## 392.9444 407.1744 391.8518 387.7119Modelo altamente significativo (pi value) con un poder explicativo del 69% Picos de rentas en horarios de 8am y 5-6pm Efecto mensual con fuerte estacionalidad