1 Cargar los paquetes necesarios
2 Cargar base de datos
df <- read.csv("Sample - Superstore.csv")
head(df)
## Row.ID Order.ID Order.Date Ship.Date Ship.Mode Customer.ID
## 1 1 CA-2016-152156 11/8/2016 11/11/2016 Second Class CG-12520
## 2 2 CA-2016-152156 11/8/2016 11/11/2016 Second Class CG-12520
## 3 3 CA-2016-138688 6/12/2016 6/16/2016 Second Class DV-13045
## 4 4 US-2015-108966 10/11/2015 10/18/2015 Standard Class SO-20335
## 5 5 US-2015-108966 10/11/2015 10/18/2015 Standard Class SO-20335
## 6 6 CA-2014-115812 6/9/2014 6/14/2014 Standard Class BH-11710
## Customer.Name Segment Country City State
## 1 Claire Gute Consumer United States Henderson Kentucky
## 2 Claire Gute Consumer United States Henderson Kentucky
## 3 Darrin Van Huff Corporate United States Los Angeles California
## 4 Sean O'Donnell Consumer United States Fort Lauderdale Florida
## 5 Sean O'Donnell Consumer United States Fort Lauderdale Florida
## 6 Brosina Hoffman Consumer United States Los Angeles California
## Postal.Code Region Product.ID Category Sub.Category
## 1 42420 South FUR-BO-10001798 Furniture Bookcases
## 2 42420 South FUR-CH-10000454 Furniture Chairs
## 3 90036 West OFF-LA-10000240 Office Supplies Labels
## 4 33311 South FUR-TA-10000577 Furniture Tables
## 5 33311 South OFF-ST-10000760 Office Supplies Storage
## 6 90032 West FUR-FU-10001487 Furniture Furnishings
## Product.Name Sales
## 1 Bush Somerset Collection Bookcase 261.9600
## 2 Hon Deluxe Fabric Upholstered Stacking Chairs, Rounded Back 731.9400
## 3 Self-Adhesive Address Labels for Typewriters by Universal 14.6200
## 4 Bretford CR4500 Series Slim Rectangular Table 957.5775
## 5 Eldon Fold 'N Roll Cart System 22.3680
## 6 Eldon Expressions Wood and Plastic Desk Accessories, Cherry Wood 48.8600
## Quantity Discount Profit
## 1 2 0.00 41.9136
## 2 3 0.00 219.5820
## 3 2 0.00 6.8714
## 4 5 0.45 -383.0310
## 5 2 0.20 2.5164
## 6 7 0.00 14.1694
3 Modificacion de columnas
# Nota: la prediccion que vamos a hacer considera valores corrientes
df_mod <- df %>% #Llama la base de datos
filter(State == "California") %>% # ESTE ES EL PASO NUEVO
select(Order.Date, Sales) %>% # Selecciona dos columnas Order.Date y Sales
mutate(Order.Date = mdy(Order.Date)) %>% # Cambia formato a fecha
mutate(Fecha = floor_date(Order.Date, unit = "month")) %>% # Asigna las fechas a primero de mes
group_by(Fecha) %>%
summarise(Ventas = sum(Sales)) %>%
mutate(Mes = seq_along(Fecha)) # Crear variable x para facilitar la regresion
head(df_mod)
## # A tibble: 6 × 3
## Fecha Ventas Mes
## <date> <dbl> <int>
## 1 2014-01-01 2455. 1
## 2 2014-02-01 309. 2
## 3 2014-03-01 7239. 3
## 4 2014-04-01 8165. 4
## 5 2014-05-01 5960. 5
## 6 2014-06-01 4379. 6
4 Visualizacion del objetivo
df_mod %>%
ggplot(., aes(x=Mes, y=Ventas)) +
geom_point() +
geom_line() +
geom_smooth(method = "lm", formula = "y ~ x")
Graficas de caja y bigotes
# Esta grafica me sirve para detectar valores aripicos
df_mod %>%
ggplot(., aes(x=Ventas)) +
geom_boxplot()
Analisis de normalidad
# Revisar que la variable y tenga una distribucion mas o menos normal
df_mod %>%
ggplot(., aes(x = Ventas)) +
geom_histogram(bins = 30, aes(y=..density..)) +
geom_density()
## Warning: The dot-dot notation (`..density..`) was deprecated in ggplot2 3.4.0.
## ℹ Please use `after_stat(density)` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
7 Analisis de correlacion
# Calculamos el coeficiente de correlacion de Pearson
with(df_mod, cor.test(Mes, Ventas))
##
## Pearson's product-moment correlation
##
## data: Mes and Ventas
## t = 4.0151, df = 46, p-value = 0.0002173
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.2634175 0.6932186
## sample estimates:
## cor
## 0.5094238
# La correlacion va de -1 a 1
# Valores extremos indican correlacion mas fuerte
# Puede ser positiva (suben o bajan juntas) o
# negativa (si una suba la otra baja y viceversa)
8 Modelo de regresion
modelo_lineal <- lm(Ventas ~ Mes, data = df_mod)
stargazer(modelo_lineal, type= "text")
##
## ===============================================
## Dependent variable:
## ---------------------------
## Ventas
## -----------------------------------------------
## Mes 197.337***
## (49.148)
##
## Constant 4,700.394***
## (1,383.306)
##
## -----------------------------------------------
## Observations 48
## R2 0.260
## Adjusted R2 0.243
## Residual Std. Error 4,717.228 (df = 46)
## F Statistic 16.121*** (df = 1; 46)
## ===============================================
## Note: *p<0.1; **p<0.05; ***p<0.01
# El modelo que buscamos estimar es: y = a + bx
# En este caso
# Constant = a
# Pendiente = b
# Mes = x
9 Coeficientes del modelo
# Obtener los coeficientes del modelo, es decir a y b
coeficientes <- coef(modelo_lineal)
intercepto <- coeficientes["(Intercept)"]
pendiente <- coeficientes["Mes"]
# Crear el texto de la ecuacion
ecuacion <- paste0("y = ",
round(intercepto, 2),
" + ",
round(pendiente, 2),
"x")
ecuacion
## [1] "y = 4700.39 + 197.34x"
10 Generacion de preddiciones
# Vamos a extender la serie temporal 6 meses
df_futuro <- data.frame(Fecha = seq.Date(from = max(df_mod$Fecha) + months(1),
by = "month",
length.out = 6),
Mes = seq(from = 49, to = 54, by = 1))
# Generar las predicciones para 6 meses con intervalos de confianza
predicciones <- predict(modelo_lineal,
newdata = df_futuro,
interval = "confidence")
predicciones
## fit lwr upr
## 1 14369.92 11585.47 17154.37
## 2 14567.26 11696.28 17438.24
## 3 14764.60 11806.31 17722.89
## 4 14961.94 11915.63 18008.24
## 5 15159.27 12024.30 18294.25
## 6 15356.61 12132.37 18580.85
11 Juntar datos
# Convertir a data frame
df_predicciones <- as.data.frame(predicciones)
colnames(df_predicciones) <- c("Ventas", "Bajo", "Alto")
# Unir las predicciones con las fechas
df_futuro<- cbind(df_futuro, df_predicciones) # cbind unir por columnas
# Unir con la base de datos original
df_total <- bind_rows(df_mod, df_futuro)
tail(df_total, 7)
## # A tibble: 7 × 5
## Fecha Ventas Mes Bajo Alto
## <date> <dbl> <dbl> <dbl> <dbl>
## 1 2017-12-01 19318. 48 NA NA
## 2 2018-01-01 14370. 49 11585. 17154.
## 3 2018-02-01 14567. 50 11696. 17438.
## 4 2018-03-01 14765. 51 11806. 17723.
## 5 2018-04-01 14962. 52 11916. 18008.
## 6 2018-05-01 15159. 53 12024. 18294.
## 7 2018-06-01 15357. 54 12132. 18581.
12 Visualizacion
df_total %>%
ggplot(., aes(x = Fecha, y = Ventas)) +
geom_point(dara = df_mod) + # Valores historicos
geom_line(data = df_mod) + # Linea de valores historicos
geom_smooth(method = "lm", formula = y ~ x, color = "blue", data = df_mod) +
geom_ribbon(data = df_futuro, aes(ymin = Bajo, ymax = Alto),
fill = "lightblue") +
geom_point(data = df_futuro, aes(y = Ventas), color = "red") + # Valores predichos
geom_line(data = df_futuro, aes(y = Ventas), color = "red", linetype = "dashed") +
labs(title = "Prediccion de ventas enero-junio 2018",
x = "Mes",
y = "Ventas")
## Warning in geom_point(dara = df_mod): Ignoring unknown parameters: `dara`
