Libraries

library(dplyr)
## 
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
## 
##     filter, lag
## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ forcats   1.0.0     ✔ readr     2.1.4
## ✔ ggplot2   3.4.4     ✔ stringr   1.5.0
## ✔ lubridate 1.9.2     ✔ tibble    3.2.1
## ✔ purrr     1.0.2     ✔ tidyr     1.3.0
## ── 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

Import Databases

library(readr)
df <- read_csv("Walmart_Store_sales.csv")
head(df)
## # A tibble: 6 × 8
##   Store Date       Weekly_Sales Holiday_Flag Temperature Fuel_Price   CPI
##   <dbl> <chr>             <dbl>        <dbl>       <dbl>      <dbl> <dbl>
## 1     1 05-02-2010     1643691.            0        42.3       2.57  211.
## 2     1 12-02-2010     1641957.            1        38.5       2.55  211.
## 3     1 19-02-2010     1611968.            0        39.9       2.51  211.
## 4     1 26-02-2010     1409728.            0        46.6       2.56  211.
## 5     1 05-03-2010     1554807.            0        46.5       2.62  211.
## 6     1 12-03-2010     1439542.            0        57.8       2.67  211.
## # ℹ 1 more variable: Unemployment <dbl>

Understand the database

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)
## spc_tbl_ [6,435 × 8] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
##  $ Store       : num [1:6435] 1 1 1 1 1 1 1 1 1 1 ...
##  $ Date        : Date[1:6435], format: "2010-02-05" "2010-02-12" ...
##  $ Weekly_Sales: num [1:6435] 1643691 1641957 1611968 1409728 1554807 ...
##  $ Holiday_Flag: num [1:6435] 0 1 0 0 0 0 0 0 0 0 ...
##  $ Temperature : num [1:6435] 42.3 38.5 39.9 46.6 46.5 ...
##  $ Fuel_Price  : num [1:6435] 2.57 2.55 2.51 2.56 2.62 ...
##  $ CPI         : num [1:6435] 211 211 211 211 211 ...
##  $ Unemployment: num [1:6435] 8.11 8.11 8.11 8.11 8.11 ...
##  - attr(*, "spec")=
##   .. cols(
##   ..   Store = col_double(),
##   ..   Date = col_character(),
##   ..   Weekly_Sales = col_double(),
##   ..   Holiday_Flag = col_double(),
##   ..   Temperature = col_double(),
##   ..   Fuel_Price = col_double(),
##   ..   CPI = col_double(),
##   ..   Unemployment = col_double()
##   .. )
##  - attr(*, "problems")=<externalptr>

Add variables to dataframe

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

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$WeekYear <- format(df$Date, "%w")
# df$WeekYear <- as.integer(df$WeekYear)

# df$WeekDay <- format(df$Date, "%u")
# df$WeekDay <- as.integer(df$WeekDay)

str(df)
## spc_tbl_ [6,435 × 11] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
##  $ Store       : num [1:6435] 1 1 1 1 1 1 1 1 1 1 ...
##  $ Date        : Date[1:6435], format: "2010-02-05" "2010-02-12" ...
##  $ Weekly_Sales: num [1:6435] 1643691 1641957 1611968 1409728 1554807 ...
##  $ Holiday_Flag: num [1:6435] 0 1 0 0 0 0 0 0 0 0 ...
##  $ Temperature : num [1:6435] 42.3 38.5 39.9 46.6 46.5 ...
##  $ Fuel_Price  : num [1:6435] 2.57 2.55 2.51 2.56 2.62 ...
##  $ CPI         : num [1:6435] 211 211 211 211 211 ...
##  $ Unemployment: num [1:6435] 8.11 8.11 8.11 8.11 8.11 ...
##  $ Year        : int [1:6435] 2010 2010 2010 2010 2010 2010 2010 2010 2010 2010 ...
##  $ Month       : int [1:6435] 2 2 2 2 3 3 3 3 4 4 ...
##  $ Day         : int [1:6435] 5 12 19 26 5 12 19 26 2 9 ...
##  - attr(*, "spec")=
##   .. cols(
##   ..   Store = col_double(),
##   ..   Date = col_character(),
##   ..   Weekly_Sales = col_double(),
##   ..   Holiday_Flag = col_double(),
##   ..   Temperature = col_double(),
##   ..   Fuel_Price = col_double(),
##   ..   CPI = col_double(),
##   ..   Unemployment = col_double()
##   .. )
##  - attr(*, "problems")=<externalptr>

Generate Linear Regression

regression <- lm(Weekly_Sales ~.,data=df)
summary(regression)
## 
## Call:
## lm(formula = Weekly_Sales ~ ., data = df)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -1094800  -382464   -42860   375406  2587123 
## 
## Coefficients:
##                Estimate Std. Error t value Pr(>|t|)    
## (Intercept)  -2.384e+09  9.127e+09  -0.261   0.7940    
## Store        -1.538e+04  5.202e+02 -29.576  < 2e-16 ***
## Date         -3.399e+03  1.266e+04  -0.268   0.7883    
## Holiday_Flag  4.773e+04  2.706e+04   1.763   0.0779 .  
## Temperature  -1.817e+03  4.053e+02  -4.484 7.47e-06 ***
## Fuel_Price    6.124e+04  2.876e+04   2.130   0.0332 *  
## CPI          -2.109e+03  1.928e+02 -10.941  < 2e-16 ***
## Unemployment -2.209e+04  3.967e+03  -5.569 2.67e-08 ***
## Year          1.212e+06  4.633e+06   0.262   0.7937    
## Month         1.177e+05  3.858e+05   0.305   0.7604    
## Day           2.171e+03  1.269e+04   0.171   0.8642    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 520900 on 6424 degrees of freedom
## Multiple R-squared:  0.1495, Adjusted R-squared:  0.1482 
## F-statistic:   113 on 10 and 6424 DF,  p-value: < 2.2e-16

Adjusta Regression

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

regression_adjusted <- lm(Weekly_Sales ~., data=df_adjusted)
summary(regression_adjusted)
## 
## Call:
## lm(formula = Weekly_Sales ~ ., data = df_adjusted)
## 
## 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

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