Practica
Rocio Jimenez Gonzalez
2024-11-13
1 Cargar los paquetes necesarios
2 Cargar base de datos
df <- read.csv("C:/Users/chio0/Desktop/tito/Aplicaciones/Documents/7 semestre/P. Antonio/tema que falte/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 14.16943 Modificacion de columnas
df_mod <- df %>% # Llamar a la base de datos
filter(State == "Michigan") %>% # Este es el paso
select(Order.Date, Sales) %>% # Llamar a la base de datos
mutate(Order.Date = mdy(Order.Date)) %>% # Seleccionamos dos columnas Order.date y sales
mutate(Fecha = floor_date(Order.Date, unit= "month")) %>% # Regresar al inicio de mes
group_by(Fecha) %>% # Agrupar por mes
summarise(Ventas = sum(Sales)) %>% # Hacer la suma
mutate(Mes = month(Fecha)) # Extraer solo el mes de la fecha
head(df_mod)## # A tibble: 6 × 3
## Fecha Ventas Mes
## <date> <dbl> <dbl>
## 1 2014-01-01 949. 1
## 2 2014-03-01 22.4 3
## 3 2014-04-01 855. 4
## 4 2014-05-01 104. 5
## 5 2014-06-01 930. 6
## 6 2014-08-01 1129. 84 Visualizacion
df_mod %>%
ggplot(., aes(x=Mes, y=Ventas)) +
geom_point() +
geom_line() +
geom_smooth(method = "lm", formula = "y ~ x")
# 5 Grafica de caja y bigotes
#Esta grafica me sirve para encontrar valres atipicos
df_mod %>%
ggplot(., aes(x=Ventas)) +
geom_boxplot()
# 6 Revisar si la variable y tiene una distribucion aprox 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 coeficientes de correlacion de Person, con mes como x
with(df_mod, cor.test(Mes, Ventas))##
## Pearson's product-moment correlation
##
## data: Mes and Ventas
## t = 0.6024, df = 38, p-value = 0.5505
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.2209448 0.3967476
## sample estimates:
## cor
## 0.097258468 Modelo de regresion
modelo_lineal <-lm(Ventas ~ Mes, data = df_mod)
stargazer(modelo_lineal, type = "text")##
## ===============================================
## Dependent variable:
## ---------------------------
## Ventas
## -----------------------------------------------
## Mes 77.990
## (129.467)
##
## Constant 1,347.159
## (1,019.216)
##
## -----------------------------------------------
## Observations 40
## R2 0.009
## Adjusted R2 -0.017
## Residual Std. Error 2,652.567 (df = 38)
## F Statistic 0.363 (df = 1; 38)
## ===============================================
## Note: *p<0.1; **p<0.05; ***p<0.019 Coeficientes de 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 = 1347.16 + 77.99x"10 Prediccion
#Extender la sere temporal para 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 5168.688 -5826.125 16163.50
## 2 5246.678 -6009.462 16502.82
## 3 5324.669 -6192.834 16842.17
## 4 5402.659 -6376.238 17181.56
## 5 5480.650 -6559.672 17520.97
## 6 5558.640 -6743.135 17860.4111 Juntar datos
# Covertir predicciones a un data frame
df_predicciones <- as.data.frame(predicciones)
colnames(df_predicciones) <- c("Ventas" , "Bajo", "Alto")
# Unir las predicciones y los intervalos de confianza con las fechas
df_futuro <- cbind(df_futuro, df_predicciones) #cbind une 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 4040. 12 NA NA
## 2 2018-01-01 5169. 49 -5826. 16164.
## 3 2018-02-01 5247. 50 -6009. 16503.
## 4 2018-03-01 5325. 51 -6193. 16842.
## 5 2018-04-01 5403. 52 -6376. 17182.
## 6 2018-05-01 5481. 53 -6560. 17521.
## 7 2018-06-01 5559. 54 -6743. 17860.#12 Grafica con valores pasados
#Grafica con variable pasados y prediccion
df_total %>%
ggplot(., aes(x = Fecha, y = Ventas)) +
geom_point(data = df_mod) +
geom_line(data = df_mod) +
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")+
geom_line(data = df_futuro, aes(y = Ventas, color = "red",
linetype = "dashed"))