Regresión Lineal
Luis Dávila - A01285521
2025-08-25
# Importar paquetes y llamar librerías
# install.packages("tidyverse")
library(tidyverse)Importar la base de datos
df <- read.csv("C:\\Users\\Adrián\\Downloads\\walmart.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. :3818687 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. :14.313str(df)## 'data.frame': 6435 obs. of 8 variables:
## $ Store : int 1 1 1 1 1 1 1 1 1 1 ...
## $ Date : chr "05-02-2010" "12-02-2010" "19-02-2010" "26-02-2010" ...
## $ 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$Date <- as.Date(df$Date, format="%d-%m-%Y")
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 ...Agregar variables a la base de datos
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$weekYear <- format(df$Date, "%W")
df$weekYear <- as.integer(df$weekYear)
df$weekDay <- format(df$Date, "%u") # 1: Lunes
df$weekDay <- as.integer(df$weekDay)
df$Day <- format(df$Date, "%d")
df$Day <- as.integer(df$Day)
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. :3818687 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
## Year Month weekYear weekDay Day
## Min. :2010 Min. : 1.000 Min. : 1.00 Min. :5 Min. : 1.00
## 1st Qu.:2010 1st Qu.: 4.000 1st Qu.:14.00 1st Qu.:5 1st Qu.: 8.00
## Median :2011 Median : 6.000 Median :26.00 Median :5 Median :16.00
## Mean :2011 Mean : 6.448 Mean :25.82 Mean :5 Mean :15.68
## 3rd Qu.:2012 3rd Qu.: 9.000 3rd Qu.:38.00 3rd Qu.:5 3rd Qu.:23.00
## Max. :2012 Max. :12.000 Max. :52.00 Max. :5 Max. :31.00str(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 2 2 2 2 3 3 3 3 4 4 ...
## $ 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 la regresión
regresion <- lm(Weekly_Sales~.,data=df)
summary(regresion)##
## Call:
## lm(formula = Weekly_Sales ~ ., data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1094800 -382464 -42860 375406 2587123
##
## Coefficients: (2 not defined because of singularities)
## 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
## weekYear NA NA NA NA
## weekDay NA NA NA NA
## 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-16Ajustar la regresión
df_ajustada <- df %>% select(-Date,-Year:-Day,-Fuel_Price)
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
## -1035858 -392195 -40416 371110 2711797
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2031943.1 50654.7 40.114 < 2e-16 ***
## Store -15373.4 521.3 -29.488 < 2e-16 ***
## Holiday_Flag 72218.3 25911.0 2.787 0.00533 **
## Temperature -929.0 369.1 -2.517 0.01186 *
## CPI -2345.9 180.2 -13.019 < 2e-16 ***
## Unemployment -22198.9 3755.9 -5.910 3.59e-09 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 523100 on 6429 degrees of freedom
## Multiple R-squared: 0.1415, Adjusted R-squared: 0.1408
## F-statistic: 211.9 on 5 and 6429 DF, p-value: < 2.2e-16Conclusión
El modelo de regresión ajustado es estadisticamente significativo en todos sus componentes para la predicción de las ventas. Bajo este modelo, factores como la presencia de festividades impactan positivamente las ventas de la tienda, mientras que el aumento de la temperatura, CPI y desempleo son factores que impactan de forma negativa en los resultados de las ventas.
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