PRACT TEMA3
Yahir Juarez
2024-10-31
df <- read.csv("~/DAATA/PRACTICAS/TEMA1/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# Nota: la prediccion que vamos a hacer considera valores corrientes
df_mod <- df %>% # Llama la base de datos
filter(State == "Kentucky") %>% #Este el es paso nuevo
select(Order.Date, Sales) %>% # Cambia formato a fecha
mutate(Order.Date = mdy(Order.Date)) %>%
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 4375. 1
## 2 2014-03-01 783. 2
## 3 2014-04-01 1945. 3
## 4 2014-05-01 199. 4
## 5 2014-08-01 25.5 5
## 6 2014-11-01 941. 64 Visualizacion del objetivo
df_mod %>%
ggplot(., aes(x=Mes, y=Ventas)) +
geom_point() +
geom_line() +
geom_smooth(method = "lm", formula = "y ~ x")
5 graficas de caja y bigotes
# Esta grafica me sirve para detectar valores atipicos
df_mod %>%
ggplot(., aes(x=Ventas)) +
geom_boxplot()
# 6
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 = 1.1681, df = 27, p-value = 0.253
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.1600369 0.5422495
## sample estimates:
## cor
## 0.2193337# La correlacion va de -1 a 1
# Valores extremos indican correlacion mas fuerte
# Puede ser positiva (Suben o bajan juantas) 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 39.553
## (33.860)
##
## Constant 668.487
## (581.566)
##
## -----------------------------------------------
## Observations 29
## R2 0.048
## Adjusted R2 0.013
## Residual Std. Error 1,525.585 (df = 27)
## F Statistic 1.365 (df = 1; 27)
## ===============================================
## Note: *p<0.1; **p<0.05; ***p<0.01# El modelo que buscamos estimar es: y = a + bx
# En este caso
# Constante# 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 <- paste("y = ",
round(intercepto, 2),
" + ",
round(pendiente, 2),
"x")
ecuacion## [1] "y = 668.49 + 39.55 x"10 Generacion de predicciones
# Vamos extender la serie temporal 6 meses
data.frame(Fecha = seq.Date(from = max(df_mod$Fecha) + months(1),
by = "month",
length.out = 6))## Fecha
## 1 2018-01-01
## 2 2018-02-01
## 3 2018-03-01
## 4 2018-04-01
## 5 2018-05-01
## 6 2018-06-01