require (ggplot2)
## Loading required package: ggplot2
require(plotly)
## Loading required package: plotly
##
## Attaching package: 'plotly'
## The following object is masked from 'package:ggplot2':
##
## last_plot
## The following object is masked from 'package:stats':
##
## filter
## The following object is masked from 'package:graphics':
##
## layout
require(datarium)
## Loading required package: datarium
data("marketing")
head(marketing)
## youtube facebook newspaper sales
## 1 276.12 45.36 83.04 26.52
## 2 53.40 47.16 54.12 12.48
## 3 20.64 55.08 83.16 11.16
## 4 181.80 49.56 70.20 22.20
## 5 216.96 12.96 70.08 15.48
## 6 10.44 58.68 90.00 8.64
promedio=mean(marketing$sales)
desviacion=sd(marketing$sales)
data.frame(promedio,desviacion)
## promedio desviacion
## 1 16.827 6.260948
g1 = ggplot(data = marketing, mapping = aes(x = sales)) +
geom_histogram(fill = "purple") +
theme_bw()
ggplotly(g1)
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
g2=ggplot(data = marketing,mapping = aes(x=newspaper,y=sales))+geom_point()+theme_bw()+geom_smooth()
ggplotly(g2)
## `geom_smooth()` using method = 'loess' and formula = 'y ~ x'
cor(marketing$newspaper, marketing$sales)
## [1] 0.228299
g3=ggplot(data=marketing,mapping = aes (x=facebook,y=sales))+geom_point()+theme_bw()+geom_smooth()
ggplotly(g3)
## `geom_smooth()` using method = 'loess' and formula = 'y ~ x'
cor(marketing$facebook, marketing$sales)
## [1] 0.5762226
g4=ggplot(data=marketing,mapping = aes(x=youtube,y=sales))+geom_point()+theme_bw()+geom_smooth(method = "lm")
ggplotly(g4)
## `geom_smooth()` using formula = 'y ~ x'
cor(marketing$youtube, marketing$sales)
## [1] 0.7822244
mod_you=lm(sales~youtube,data=marketing)
mod_you
##
## Call:
## lm(formula = sales ~ youtube, data = marketing)
##
## Coefficients:
## (Intercept) youtube
## 8.43911 0.04754
summary(mod_you)
##
## Call:
## lm(formula = sales ~ youtube, data = marketing)
##
## Residuals:
## Min 1Q Median 3Q Max
## -10.0632 -2.3454 -0.2295 2.4805 8.6548
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 8.439112 0.549412 15.36 <2e-16 ***
## youtube 0.047537 0.002691 17.67 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 3.91 on 198 degrees of freedom
## Multiple R-squared: 0.6119, Adjusted R-squared: 0.6099
## F-statistic: 312.1 on 1 and 198 DF, p-value: < 2.2e-16
predict(mod_you,list (youtube=65),interval = "confidence",level = 0.95)
## fit lwr upr
## 1 11.52899 10.72462 12.33337
##Paso 1 ~ Segmentar Los Datos
id_modelar=sample(1:200, size = 160)
marketing_modelar=marketing[id_modelar,]
marketing_validar=marketing[-id_modelar,]
##Paso 2 - Estimar el Modelo Set de Modelar
mod_you_modelar=lm(sales~youtube,data=marketing_modelar)
##Paso 3 - Predeccir Set de Validación
sales_pred=predict(mod_you_modelar,list(youtube=marketing_validar$youtube))
##Paso 4 - Comparar Ventas del Modelo y Reales
sales_real=marketing_validar$sales
error=sales_real-sales_pred
res=data.frame(sales_real, sales_pred,error)
#apaso 5 - Calcular Indicador de Evaluación de la Predicción
MAE=mean(abs(error)) #Mean Absolut Error (Error Medio Absoluto)
MAE
## [1] 3.01698
Interpretación
B0 = intercepto: 8,43 –> En promedio, las ventas serán 8,42 mill USD si no hay inversión publicidasd youtube
B1 = Pendiente = 0,04 –> Por un millón dolar adicional invirtiendo en publicidad youtube, las ventas aumentan 0,04 millones USD