Regresión Lineal
Maria Jose Flores
2025-08-31
Instalar paquetes y llamar librerías
#install.package("tidyverse")
library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.5.2 ✔ tibble 3.3.0
## ✔ lubridate 1.9.4 ✔ tidyr 1.3.1
## ✔ purrr 1.1.0
## ── 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 errorsImportar base de datos
df <- read.csv("/Users/mariajoseflores/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. :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. :14.313str(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 ...Entender 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")
df$WeekDay <- as.integer(df$WeekDay) ## 1: Lunes
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
## Year Month WeekYear WeekDay
## Min. :2010 Min. : 1.000 Min. : 1.00 Min. :5
## 1st Qu.:2010 1st Qu.: 4.000 1st Qu.:14.00 1st Qu.:5
## Median :2011 Median : 6.000 Median :26.00 Median :5
## Mean :2011 Mean : 6.448 Mean :25.82 Mean :5
## 3rd Qu.:2012 3rd Qu.: 9.000 3rd Qu.:38.00 3rd Qu.:5
## Max. :2012 Max. :12.000 Max. :52.00 Max. :5str(df)## 'data.frame': 6435 obs. of 12 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 ...head(df)## Store Date Weekly_Sales Holiday_Flag Temperature Fuel_Price CPI
## 1 1 2010-02-05 1643691 0 42.31 2.572 211.0964
## 2 1 2010-02-12 1641957 1 38.51 2.548 211.2422
## 3 1 2010-02-19 1611968 0 39.93 2.514 211.2891
## 4 1 2010-02-26 1409728 0 46.63 2.561 211.3196
## 5 1 2010-03-05 1554807 0 46.50 2.625 211.3501
## 6 1 2010-03-12 1439542 0 57.79 2.667 211.3806
## Unemployment Year Month WeekYear WeekDay
## 1 8.106 2010 2 5 5
## 2 8.106 2010 2 6 5
## 3 8.106 2010 2 7 5
## 4 8.106 2010 2 8 5
## 5 8.106 2010 3 9 5
## 6 8.106 2010 3 10 5Generar la regresión
regresion <- lm(Weekly_Sales~., data=df)
summary(regresion)##
## Call:
## lm(formula = Weekly_Sales ~ ., data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1094109 -382170 -42356 375814 2586732
##
## Coefficients: (2 not defined because of singularities)
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -8.253e+08 5.346e+08 -1.544 0.1227
## Store -1.538e+04 5.201e+02 -29.578 < 2e-16 ***
## Date -1.237e+03 7.416e+02 -1.668 0.0953 .
## Holiday_Flag 4.662e+04 2.627e+04 1.774 0.0761 .
## Temperature -1.799e+03 3.903e+02 -4.608 4.15e-06 ***
## Fuel_Price 6.349e+04 2.556e+04 2.484 0.0130 *
## CPI -2.106e+03 1.916e+02 -10.987 < 2e-16 ***
## Unemployment -2.218e+04 3.930e+03 -5.644 1.74e-08 ***
## Year 4.205e+05 2.714e+05 1.549 0.1213
## Month 5.178e+04 2.269e+04 2.282 0.0225 *
## WeekYear NA NA NA NA
## WeekDay 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: 0.1484
## F-statistic: 125.5 on 9 and 6425 DF, p-value: < 2.2e-16Ajustar la regresión
df_ajustada <- df %>%
dplyr::select(-dplyr::any_of(c("Date","Year","Month","WeekYear","WeekDay")))
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
## -1033609 -393019 -38294 371884 2711539
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1995738.3 75421.7 26.461 < 2e-16 ***
## Store -15388.7 521.9 -29.486 < 2e-16 ***
## Holiday_Flag 73034.5 25942.7 2.815 0.00489 **
## Temperature -975.4 376.0 -2.594 0.00950 **
## Fuel_Price 9596.1 14810.3 0.648 0.51705
## CPI -2319.5 184.8 -12.553 < 2e-16 ***
## Unemployment -21881.2 3788.0 -5.776 7.99e-09 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 523100 on 6428 degrees of freedom
## Multiple R-squared: 0.1416, Adjusted R-squared: 0.1408
## F-statistic: 176.7 on 6 and 6428 DF, p-value: < 2.2e-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