# Importar la base de datos

library(tidyverse)
## Warning: package 'tidyverse' was built under R version 4.3.2
## Warning: package 'ggplot2' was built under R version 4.3.2
## Warning: package 'tibble' was built under R version 4.3.1
## Warning: package 'tidyr' was built under R version 4.3.1
## Warning: package 'readr' was built under R version 4.3.1
## Warning: package 'purrr' was built under R version 4.3.1
## Warning: package 'dplyr' was built under R version 4.3.1
## Warning: package 'stringr' was built under R version 4.3.1
## Warning: package 'forcats' was built under R version 4.3.1
## Warning: package 'lubridate' was built under R version 4.3.1
## ── 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   3.4.4     ✔ 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
df <- read.csv("C:\\Users\\memil\\OneDrive\\Desktop\\aaTecDeMonterrey\\6to Semestre\\Walmart_Store_sales.csv")

Entender la base de datos

summary(df)
##      Store        Date            Weekly_Sales      Holiday_Flag    
##  Min.   : 1   Length:6435        Min.   : 209986   Min.   :0.00000  
##  1st Qu.:12   Class :character   1st Qu.: 553350   1st Qu.:0.00000  
##  Median :23   Mode  :character   Median : 960746   Median :0.00000  
##  Mean   :23                      Mean   :1046965   Mean   :0.06993  
##  3rd Qu.:34                      3rd Qu.:1420159   3rd Qu.:0.00000  
##  Max.   :45                      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

Limpiar 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

Agregar variables a la base de datos

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

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

df$Year <- format(df$Date, "%Y")
df$Year <- as.integer(df$Year)

df$WeekYear <- format(df$Date, "%W") #iniciando el lunes
df$WeekYear <- as.integer(df$WeekYear)

#df$WeekDay <- format(df$Date, "%u") #vemos que las ventas son semanales y se cierran el viernes.
#df$WeekDay <- as.integer(df$WeekDay)

df <- df %>% select(- Store, - Date, -Fuel_Price, -Month, -WeekYear,- Year: -Day)

Generar regresión lineal

options(scipen = 9999)
regresion <- lm(Weekly_Sales ~., data = df)
summary(regresion)
## 
## Call:
## lm(formula = Weekly_Sales ~ ., data = df)
## 
## 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 < 0.0000000000000002 ***
## 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 < 0.0000000000000002 ***
## Unemployment  -41235.7     3942.0 -10.460 < 0.0000000000000002 ***
## ---
## 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: < 0.00000000000000022