Regresión Lineal
Humberto Cortés Saldaña
2025-08-25
Paquetes y librerías
library(tidyverse)Importar la base de datos
df <- read.csv("/Users/humbertocs/Desktop/Tec/Concentración IA/M2_Programacion R IA/Regresion Lineal/walmart.csv")Entender los 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 ...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)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. :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 %>% select(-Date, -Fuel_Price, -Year:-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
## -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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