Regresión Lineal
Federico Zorrilla
2025-08-25
Instalar paquetes y llamar librerías
# install.packages("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 la base de datos
df <- read.csv("/Users/fedezorrilla/Downloads/walmart.csv")
head(df)## Store Date Weekly_Sales Holiday_Flag Temperature Fuel_Price CPI
## 1 1 05-02-2010 1643691 0 42.31 2.572 211.0964
## 2 1 12-02-2010 1641957 1 38.51 2.548 211.2422
## 3 1 19-02-2010 1611968 0 39.93 2.514 211.2891
## 4 1 26-02-2010 1409728 0 46.63 2.561 211.3196
## 5 1 05-03-2010 1554807 0 46.50 2.625 211.3501
## 6 1 12-03-2010 1439542 0 57.79 2.667 211.3806
## Unemployment
## 1 8.106
## 2 8.106
## 3 8.106
## 4 8.106
## 5 8.106
## 6 8.106Entender 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 ...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") #1. Lunes
df$Day <- as.integer(df$Day)
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 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 ...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 Regresión
df_ajustada <- df %>% select(-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
## -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-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