Introducción

La regresión lineal es un modelo que permite analizar la relación lineal entre una variable dependiente y múltiples variables independientes o explicativas. En esta actividad se utilizará para predecir las ventas semanales de Walmart.

Instalar paquetes y llamar librerías

library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.3     ✔ readr     2.1.4
## ✔ forcats   1.0.0     ✔ stringr   1.5.0
## ✔ ggplot2   3.5.0     ✔ tibble    3.2.1
## ✔ lubridate 1.9.2     ✔ tidyr     1.3.0
## ✔ purrr     1.0.2     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

Importar la base de datos

df <- read.csv("/Users/lishdz/Downloads/Walmart_Store_sales.csv")

Entender la base de datos

df$Date <- as.Date(df$Date, format="%d-%m-%Y")

summary(df)
##      Store         Date             Weekly_Sales      Holiday_Flag    
##  Min.   : 1   Min.   :2010-02-05   Min.   : 209986   Min.   :0.00000  
##  1st Qu.:12   1st Qu.:2010-10-08   1st Qu.: 553350   1st Qu.:0.00000  
##  Median :23   Median :2011-06-17   Median : 960746   Median :0.00000  
##  Mean   :23   Mean   :2011-06-17   Mean   :1046965   Mean   :0.06993  
##  3rd Qu.:34   3rd Qu.:2012-02-24   3rd Qu.:1420159   3rd Qu.:0.00000  
##  Max.   :45   Max.   :2012-10-26   Max.   :3818686   Max.   :1.00000  
##   Temperature       Fuel_Price         CPI         Unemployment   
##  Min.   : -2.06   Min.   :2.472   Min.   :126.1   Min.   : 3.879  
##  1st Qu.: 47.46   1st Qu.:2.933   1st Qu.:131.7   1st Qu.: 6.891  
##  Median : 62.67   Median :3.445   Median :182.6   Median : 7.874  
##  Mean   : 60.66   Mean   :3.359   Mean   :171.6   Mean   : 7.999  
##  3rd Qu.: 74.94   3rd Qu.:3.735   3rd Qu.:212.7   3rd Qu.: 8.622  
##  Max.   :100.14   Max.   :4.468   Max.   :227.2   Max.   :14.313
str(df)
## 'data.frame':    6435 obs. of  8 variables:
##  $ Store       : int  1 1 1 1 1 1 1 1 1 1 ...
##  $ Date        : Date, format: "2010-02-05" "2010-02-12" ...
##  $ Weekly_Sales: num  1643691 1641957 1611968 1409728 1554807 ...
##  $ Holiday_Flag: int  0 1 0 0 0 0 0 0 0 0 ...
##  $ Temperature : num  42.3 38.5 39.9 46.6 46.5 ...
##  $ Fuel_Price  : num  2.57 2.55 2.51 2.56 2.62 ...
##  $ CPI         : num  211 211 211 211 211 ...
##  $ Unemployment: num  8.11 8.11 8.11 8.11 8.11 ...
df$Year <- as.integer(format(df$Date, "%Y"))
df$Month <- as.integer(format(df$Date, "%m"))

df$Month <- as.integer(format(df$Date, "%d"))

df$WeekYear <- as.integer(format(df$Date, "%W"))
df$WeekDay <- as.integer(format(df$Date, "%u"))
df$Day <- as.integer(format(df$Date, "%d"))

str(df)
## 'data.frame':    6435 obs. of  13 variables:
##  $ Store       : int  1 1 1 1 1 1 1 1 1 1 ...
##  $ Date        : Date, format: "2010-02-05" "2010-02-12" ...
##  $ Weekly_Sales: num  1643691 1641957 1611968 1409728 1554807 ...
##  $ Holiday_Flag: int  0 1 0 0 0 0 0 0 0 0 ...
##  $ Temperature : num  42.3 38.5 39.9 46.6 46.5 ...
##  $ Fuel_Price  : num  2.57 2.55 2.51 2.56 2.62 ...
##  $ CPI         : num  211 211 211 211 211 ...
##  $ Unemployment: num  8.11 8.11 8.11 8.11 8.11 ...
##  $ Year        : int  2010 2010 2010 2010 2010 2010 2010 2010 2010 2010 ...
##  $ Month       : int  5 12 19 26 5 12 19 26 2 9 ...
##  $ WeekYear    : int  5 6 7 8 9 10 11 12 13 14 ...
##  $ WeekDay     : int  5 5 5 5 5 5 5 5 5 5 ...
##  $ Day         : int  5 12 19 26 5 12 19 26 2 9 ...

Generar regresión lineal

regresion <- lm(Weekly_Sales ~., data=df)
summary(regresion)
## 
## Call:
## lm(formula = Weekly_Sales ~ ., data = df)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -1093737  -382386   -42671   375664  2586331 
## 
## Coefficients: (3 not defined because of singularities)
##                Estimate Std. Error t value Pr(>|t|)    
## (Intercept)   3.998e+08  5.234e+07   7.638 2.53e-14 ***
## Store        -1.538e+04  5.201e+02 -29.576  < 2e-16 ***
## Date          4.621e+02  7.186e+01   6.430 1.37e-10 ***
## Holiday_Flag  4.573e+04  2.626e+04   1.742   0.0816 .  
## Temperature  -1.784e+03  3.903e+02  -4.571 4.95e-06 ***
## Fuel_Price    6.525e+04  2.556e+04   2.553   0.0107 *  
## CPI          -2.103e+03  1.917e+02 -10.972  < 2e-16 ***
## Unemployment -2.225e+04  3.930e+03  -5.662 1.56e-08 ***
## Year         -2.014e+05  2.649e+04  -7.601 3.36e-14 ***
## Month        -1.693e+03  7.464e+02  -2.268   0.0234 *  
## WeekYear             NA         NA      NA       NA    
## WeekDay              NA         NA      NA       NA    
## Day                  NA         NA      NA       NA    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 520800 on 6425 degrees of freedom
## Multiple R-squared:  0.1495, Adjusted R-squared:  0.1483 
## F-statistic: 125.5 on 9 and 6425 DF,  p-value: < 2.2e-16
df_ajustada <- df %>% select(-Store, -Date, -Fuel_Price, -Year:-Day)
regresion_ajustada <- lm(Weekly_Sales ~., data=df_ajustada)
summary(regresion_ajustada)
## 
## Call:
## lm(formula = Weekly_Sales ~ ., data = df_ajustada)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -1020421  -477999  -115859   396128  2800875 
## 
## Coefficients:
##               Estimate Std. Error t value Pr(>|t|)    
## (Intercept)  1687798.2    52515.7  32.139  < 2e-16 ***
## Holiday_Flag   75760.1    27605.3   2.744  0.00608 ** 
## Temperature     -773.1      393.2  -1.966  0.04930 *  
## CPI            -1570.0      189.9  -8.267  < 2e-16 ***
## Unemployment  -41235.7     3942.0 -10.460  < 2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 557300 on 6430 degrees of freedom
## Multiple R-squared:  0.02538,    Adjusted R-squared:  0.02477 
## F-statistic: 41.86 on 4 and 6430 DF,  p-value: < 2.2e-16

Conclusión

Las regresiones lineales son herramientas sencillas que se pueden utilizar para muchos procesos de negocios, como la predicción de ventas.

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