Regresión Lineal
Avril Lobato - A00833113
2024-02-23
Walmart
Paso 0. Instalar y cargar librerías
#install.packages("tidyverse")
library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.2 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ ggplot2 3.4.2 ✔ tibble 3.2.1
## ✔ lubridate 1.9.2 ✔ tidyr 1.3.0
## ✔ purrr 1.0.1
## ── 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 errorsPaso 1. Importar la base datos
df <- read.csv("Walmart_Store_sales.csv")Paso 2. Entender y limpiar la base de datos
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. :14.313str(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 ...Paso 3. Agregar variables a la base de datos
df$Year <- format(df$Date, "%Y")
df$Year <- as.integer(df$Year)
df$Day <- format(df$Date, "%d")
df$Day <- as.integer(df$Day)
df$Month <- format(df$Date, "%m")
df$Month <- as.integer(df$Month)
df$WeekYear <- format(df$Date, "%W") #Inicia el Lunes
df$WeekYear <- as.integer(df$WeekYear)
df$WeekDay <- format(df$Date, "%u") #Inicia el Lunes
df$WeekDay <- as.integer(df$WeekDay)
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 ...
## $ Day : int 5 12 19 26 5 12 19 26 2 9 ...
## $ 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 ...Paso 4. Generar 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
## Day 2.171e+03 1.269e+04 0.171 0.8642
## Month 1.177e+05 3.858e+05 0.305 0.7604
## 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: 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-16Paso 5. Ajustar regresión lineal
df_ajustada <- df %>% select(-Store, -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
## -1069878 -470146 -117461 403864 2705866
##
## Coefficients: (1 not defined because of singularities)
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1593231.9 54731.5 29.110 < 2e-16 ***
## Holiday_Flag 48020.7 27974.7 1.717 0.086105 .
## Temperature -1467.3 407.1 -3.604 0.000315 ***
## CPI -1496.6 189.6 -7.892 3.47e-15 ***
## Unemployment -39956.8 3938.9 -10.144 < 2e-16 ***
## Month 57686.0 23926.6 2.411 0.015939 *
## WeekYear -9921.3 5490.0 -1.807 0.070783 .
## WeekDay NA NA NA NA
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 555400 on 6428 degrees of freedom
## Multiple R-squared: 0.03231, Adjusted R-squared: 0.03141
## F-statistic: 35.77 on 6 and 6428 DF, p-value: < 2.2e-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