Una empresa con 5 tiendas en el país solicita un análisis de sus ventas de abarrotes entre mayo y noviembre de 2020.
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ forcats 1.0.0 ✔ readr 2.1.4
## ✔ ggplot2 3.4.1 ✔ stringr 1.5.0
## ✔ lubridate 1.9.2 ✔ tibble 3.1.8
## ✔ purrr 1.0.1 ✔ tidyr 1.3.0
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the ]8;;http://conflicted.r-lib.org/conflicted package]8;; to force all conflicts to become errors
library(janitor)
##
## Attaching package: 'janitor'
##
## The following objects are masked from 'package:stats':
##
## chisq.test, fisher.test
library(lubridate)
library(plyr)
## ------------------------------------------------------------------------------
## You have loaded plyr after dplyr - this is likely to cause problems.
## If you need functions from both plyr and dplyr, please load plyr first, then dplyr:
## library(plyr); library(dplyr)
## ------------------------------------------------------------------------------
##
## Attaching package: 'plyr'
##
## The following object is masked from 'package:purrr':
##
## compact
##
## The following objects are masked from 'package:dplyr':
##
## arrange, count, desc, failwith, id, mutate, rename, summarise,
## summarize
library(Matrix)
##
## Attaching package: 'Matrix'
##
## The following objects are masked from 'package:tidyr':
##
## expand, pack, unpack
library(arules)
##
## Attaching package: 'arules'
##
## The following object is masked from 'package:dplyr':
##
## recode
##
## The following objects are masked from 'package:base':
##
## abbreviate, write
library(arulesViz)
library(datasets)
bd = read.csv("C:\\Users\\Silva\\Documents\\CSV\\Semestre 4\\Manipulación de datos\\abarrotes.csv")
Resumen de BD
summary(bd)
## vcClaveTienda DescGiro Codigo.Barras PLU
## Length:200625 Length:200625 Min. :8.347e+05 Min. : 1.00
## Class :character Class :character 1st Qu.:7.501e+12 1st Qu.: 1.00
## Mode :character Mode :character Median :7.501e+12 Median : 1.00
## Mean :5.950e+12 Mean : 2.11
## 3rd Qu.:7.501e+12 3rd Qu.: 1.00
## Max. :1.750e+13 Max. :30.00
## NA's :199188
## Fecha Hora Marca Fabricante
## Length:200625 Length:200625 Length:200625 Length:200625
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
##
## Producto Precio Ult.Costo Unidades
## Length:200625 Min. :-147.00 Min. : 0.38 Min. : 0.200
## Class :character 1st Qu.: 11.00 1st Qu.: 8.46 1st Qu.: 1.000
## Mode :character Median : 16.00 Median : 12.31 Median : 1.000
## Mean : 19.42 Mean : 15.31 Mean : 1.262
## 3rd Qu.: 25.00 3rd Qu.: 19.23 3rd Qu.: 1.000
## Max. :1000.00 Max. :769.23 Max. :96.000
##
## F.Ticket NombreDepartamento NombreFamilia NombreCategoria
## Min. : 1 Length:200625 Length:200625 Length:200625
## 1st Qu.: 33964 Class :character Class :character Class :character
## Median :105993 Mode :character Mode :character Mode :character
## Mean :193990
## 3rd Qu.:383005
## Max. :450040
##
## Estado Mts.2 Tipo.ubicación Giro
## Length:200625 Min. :47.0 Length:200625 Length:200625
## Class :character 1st Qu.:53.0 Class :character Class :character
## Mode :character Median :60.0 Mode :character Mode :character
## Mean :56.6
## 3rd Qu.:60.0
## Max. :62.0
##
## Hora.inicio Hora.cierre
## Length:200625 Length:200625
## Class :character Class :character
## Mode :character Mode :character
##
##
##
##
Analisis de variables cualitativas
#count(bd, vcClaveTienda, sort = TRUE)
#count(bd, DescGiro, sort = TRUE)
#count(bd, Marca, sort = TRUE)
#count(bd, Fabricante, sort = TRUE)
#count(bd, Producto, sort = TRUE)
#count(bd, NombreDepartamento, sort = TRUE)
#count(bd, NombreFamilia, sort = TRUE)
#count(bd, NombreCategoria, sort = TRUE)
#count(bd, Estado, sort = TRUE)
#count(bd, Tipo.ubicación, sort = TRUE)
#count(bd, Giro, sort = TRUE)
Entendimiento general
tibble(bd)
## # A tibble: 200,625 × 22
## vcClaveTienda DescGiro Codig…¹ PLU Fecha Hora Marca Fabri…² Produ…³ Precio
## <chr> <chr> <dbl> <int> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 MX001 Abarrot… 7.50e12 NA 19/0… 08:1… NUTR… MEXILAC Nutri … 16
## 2 MX001 Abarrot… 7.50e12 NA 19/0… 08:2… DAN … DANONE… DANUP … 14
## 3 MX001 Abarrot… 7.50e12 NA 19/0… 08:2… BIMBO GRUPO … Rebana… 5
## 4 MX001 Abarrot… 7.50e12 NA 19/0… 08:2… PEPSI PEPSI-… Pepsi … 8
## 5 MX001 Abarrot… 7.50e12 NA 19/0… 08:2… BLAN… FABRIC… Deterg… 19.5
## 6 MX001 Abarrot… 7.50e12 NA 19/0… 08:1… NUTR… MEXILAC Nutri … 16
## 7 MX001 Abarrot… 7.50e12 NA 19/0… 08:2… DAN … DANONE… DANUP … 14
## 8 MX001 Abarrot… 7.50e12 NA 19/0… 08:2… BIMBO GRUPO … Rebana… 5
## 9 MX001 Abarrot… 7.50e12 NA 19/0… 08:2… PEPSI PEPSI-… Pepsi … 8
## 10 MX001 Abarrot… 7.50e12 NA 19/0… 08:2… BLAN… FABRIC… Deterg… 19.5
## # … with 200,615 more rows, 12 more variables: Ult.Costo <dbl>, Unidades <dbl>,
## # F.Ticket <int>, NombreDepartamento <chr>, NombreFamilia <chr>,
## # NombreCategoria <chr>, Estado <chr>, Mts.2 <int>, Tipo.ubicación <chr>,
## # Giro <chr>, Hora.inicio <chr>, Hora.cierre <chr>, and abbreviated variable
## # names ¹Codigo.Barras, ²Fabricante, ³Producto
head(bd)
## vcClaveTienda DescGiro Codigo.Barras PLU Fecha Hora
## 1 MX001 Abarrotes 7.501021e+12 NA 19/06/2020 08:16:21
## 2 MX001 Abarrotes 7.501032e+12 NA 19/06/2020 08:23:33
## 3 MX001 Abarrotes 7.501000e+12 NA 19/06/2020 08:24:33
## 4 MX001 Abarrotes 7.501031e+12 NA 19/06/2020 08:24:33
## 5 MX001 Abarrotes 7.501026e+12 NA 19/06/2020 08:26:28
## 6 MX001 Abarrotes 7.501021e+12 NA 19/06/2020 08:16:21
## Marca Fabricante
## 1 NUTRI LECHE MEXILAC
## 2 DAN UP DANONE DE MEXICO
## 3 BIMBO GRUPO BIMBO
## 4 PEPSI PEPSI-COLA MEXICANA
## 5 BLANCA NIEVES (DETERGENTE) FABRICA DE JABON LA CORONA
## 6 NUTRI LECHE MEXILAC
## Producto Precio Ult.Costo Unidades F.Ticket
## 1 Nutri Leche 1 Litro 16.0 12.31 1 1
## 2 DANUP STRAWBERRY P/BEBER 350GR NAL 14.0 14.00 1 2
## 3 Rebanadas Bimbo 2Pz 5.0 5.00 1 3
## 4 Pepsi N.R. 400Ml 8.0 8.00 1 3
## 5 Detergente Blanca Nieves 500G 19.5 15.00 1 4
## 6 Nutri Leche 1 Litro 16.0 12.31 1 1
## NombreDepartamento NombreFamilia NombreCategoria
## 1 Abarrotes Lacteos y Refrigerados Leche
## 2 Abarrotes Lacteos y Refrigerados Yogurt
## 3 Abarrotes Pan y Tortilla Pan Dulce Empaquetado
## 4 Abarrotes Bebidas Refrescos Plástico (N.R.)
## 5 Abarrotes Limpieza del Hogar Lavandería
## 6 Abarrotes Lacteos y Refrigerados Leche
## Estado Mts.2 Tipo.ubicación Giro Hora.inicio Hora.cierre
## 1 Nuevo León 60 Esquina Abarrotes 08:00 22:00
## 2 Nuevo León 60 Esquina Abarrotes 08:00 22:00
## 3 Nuevo León 60 Esquina Abarrotes 08:00 22:00
## 4 Nuevo León 60 Esquina Abarrotes 08:00 22:00
## 5 Nuevo León 60 Esquina Abarrotes 08:00 22:00
## 6 Nuevo León 60 Esquina Abarrotes 08:00 22:00
tail(bd)
## vcClaveTienda DescGiro Codigo.Barras PLU Fecha Hora
## 200620 MX005 Depósito 7.62221e+12 NA 12/07/2020 01:08:25
## 200621 MX005 Depósito 7.62221e+12 NA 23/10/2020 22:17:37
## 200622 MX005 Depósito 7.62221e+12 NA 10/10/2020 20:30:20
## 200623 MX005 Depósito 7.62221e+12 NA 10/10/2020 22:40:43
## 200624 MX005 Depósito 7.62221e+12 NA 27/06/2020 22:30:19
## 200625 MX005 Depósito 7.62221e+12 NA 26/06/2020 23:43:34
## Marca Fabricante Producto Precio
## 200620 TRIDENT XTRA CARE CADBURY ADAMS Trident Xtracare Freshmint 16.32G 9
## 200621 TRIDENT XTRA CARE CADBURY ADAMS Trident Xtracare Freshmint 16.32G 9
## 200622 TRIDENT XTRA CARE CADBURY ADAMS Trident Xtracare Freshmint 16.32G 9
## 200623 TRIDENT XTRA CARE CADBURY ADAMS Trident Xtracare Freshmint 16.32G 9
## 200624 TRIDENT XTRA CARE CADBURY ADAMS Trident Xtracare Freshmint 16.32G 9
## 200625 TRIDENT XTRA CARE CADBURY ADAMS Trident Xtracare Freshmint 16.32G 9
## Ult.Costo Unidades F.Ticket NombreDepartamento NombreFamilia
## 200620 6.92 1 103100 Abarrotes Dulcería
## 200621 6.92 1 116598 Abarrotes Dulcería
## 200622 6.92 1 114886 Abarrotes Dulcería
## 200623 6.92 1 114955 Abarrotes Dulcería
## 200624 6.92 1 101121 Abarrotes Dulcería
## 200625 6.92 1 100879 Abarrotes Dulcería
## NombreCategoria Estado Mts.2 Tipo.ubicación Giro Hora.inicio
## 200620 Gomas de Mazcar Quintana Roo 58 Esquina Mini súper 08:00
## 200621 Gomas de Mazcar Quintana Roo 58 Esquina Mini súper 08:00
## 200622 Gomas de Mazcar Quintana Roo 58 Esquina Mini súper 08:00
## 200623 Gomas de Mazcar Quintana Roo 58 Esquina Mini súper 08:00
## 200624 Gomas de Mazcar Quintana Roo 58 Esquina Mini súper 08:00
## 200625 Gomas de Mazcar Quintana Roo 58 Esquina Mini súper 08:00
## Hora.cierre
## 200620 21:00
## 200621 21:00
## 200622 21:00
## 200623 21:00
## 200624 21:00
## 200625 21:00
Hallazgos
Remover valores irrelevantes
#Eliminar columnas
bd1 = bd
bd1 = subset(bd1, select = -c(PLU, Codigo.Barras))
#Eliminar renglones
bd2 = bd1
bd2 = bd2[bd2$Precio >0,]
summary(bd2)
## vcClaveTienda DescGiro Fecha Hora
## Length:200478 Length:200478 Length:200478 Length:200478
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
## Marca Fabricante Producto Precio
## Length:200478 Length:200478 Length:200478 Min. : 0.50
## Class :character Class :character Class :character 1st Qu.: 11.00
## Mode :character Mode :character Mode :character Median : 16.00
## Mean : 19.45
## 3rd Qu.: 25.00
## Max. :1000.00
## Ult.Costo Unidades F.Ticket NombreDepartamento
## Min. : 0.38 Min. : 0.200 Min. : 1 Length:200478
## 1st Qu.: 8.46 1st Qu.: 1.000 1st Qu.: 33977 Class :character
## Median : 12.31 Median : 1.000 Median :106034 Mode :character
## Mean : 15.31 Mean : 1.261 Mean :194096
## 3rd Qu.: 19.23 3rd Qu.: 1.000 3rd Qu.:383062
## Max. :769.23 Max. :96.000 Max. :450040
## NombreFamilia NombreCategoria Estado Mts.2
## Length:200478 Length:200478 Length:200478 Min. :47.0
## Class :character Class :character Class :character 1st Qu.:53.0
## Mode :character Mode :character Mode :character Median :60.0
## Mean :56.6
## 3rd Qu.:60.0
## Max. :62.0
## Tipo.ubicación Giro Hora.inicio Hora.cierre
## Length:200478 Length:200478 Length:200478 Length:200478
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
Remover valores duplicados
# ¿Cuántos renglones duplicados tenemos?
bd2[duplicated(bd2),]
## vcClaveTienda DescGiro Fecha Hora Marca
## 6 MX001 Abarrotes 19/06/2020 08:16:21 NUTRI LECHE
## 7 MX001 Abarrotes 19/06/2020 08:23:33 DAN UP
## 8 MX001 Abarrotes 19/06/2020 08:24:33 BIMBO
## 9 MX001 Abarrotes 19/06/2020 08:24:33 PEPSI
## 10 MX001 Abarrotes 19/06/2020 08:26:28 BLANCA NIEVES (DETERGENTE)
## Fabricante Producto Precio
## 6 MEXILAC Nutri Leche 1 Litro 16.0
## 7 DANONE DE MEXICO DANUP STRAWBERRY P/BEBER 350GR NAL 14.0
## 8 GRUPO BIMBO Rebanadas Bimbo 2Pz 5.0
## 9 PEPSI-COLA MEXICANA Pepsi N.R. 400Ml 8.0
## 10 FABRICA DE JABON LA CORONA Detergente Blanca Nieves 500G 19.5
## Ult.Costo Unidades F.Ticket NombreDepartamento NombreFamilia
## 6 12.31 1 1 Abarrotes Lacteos y Refrigerados
## 7 14.00 1 2 Abarrotes Lacteos y Refrigerados
## 8 5.00 1 3 Abarrotes Pan y Tortilla
## 9 8.00 1 3 Abarrotes Bebidas
## 10 15.00 1 4 Abarrotes Limpieza del Hogar
## NombreCategoria Estado Mts.2 Tipo.ubicación Giro
## 6 Leche Nuevo León 60 Esquina Abarrotes
## 7 Yogurt Nuevo León 60 Esquina Abarrotes
## 8 Pan Dulce Empaquetado Nuevo León 60 Esquina Abarrotes
## 9 Refrescos Plástico (N.R.) Nuevo León 60 Esquina Abarrotes
## 10 Lavandería Nuevo León 60 Esquina Abarrotes
## Hora.inicio Hora.cierre
## 6 08:00 22:00
## 7 08:00 22:00
## 8 08:00 22:00
## 9 08:00 22:00
## 10 08:00 22:00
sum(duplicated(bd2))
## [1] 5
#Eliminar renglones duplicados
bd3 = bd2
bd3 = distinct(bd3)
Resolver errores tipográficos y similares
# Precios en absoluto
bd4 = bd1
bd4$Precio = abs(bd4$Precio)
summary(bd4)
## vcClaveTienda DescGiro Fecha Hora
## Length:200625 Length:200625 Length:200625 Length:200625
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
## Marca Fabricante Producto Precio
## Length:200625 Length:200625 Length:200625 Min. : 0.50
## Class :character Class :character Class :character 1st Qu.: 11.00
## Mode :character Mode :character Mode :character Median : 16.00
## Mean : 19.45
## 3rd Qu.: 25.00
## Max. :1000.00
## Ult.Costo Unidades F.Ticket NombreDepartamento
## Min. : 0.38 Min. : 0.200 Min. : 1 Length:200625
## 1st Qu.: 8.46 1st Qu.: 1.000 1st Qu.: 33964 Class :character
## Median : 12.31 Median : 1.000 Median :105993 Mode :character
## Mean : 15.31 Mean : 1.262 Mean :193990
## 3rd Qu.: 19.23 3rd Qu.: 1.000 3rd Qu.:383005
## Max. :769.23 Max. :96.000 Max. :450040
## NombreFamilia NombreCategoria Estado Mts.2
## Length:200625 Length:200625 Length:200625 Min. :47.0
## Class :character Class :character Class :character 1st Qu.:53.0
## Mode :character Mode :character Mode :character Median :60.0
## Mean :56.6
## 3rd Qu.:60.0
## Max. :62.0
## Tipo.ubicación Giro Hora.inicio Hora.cierre
## Length:200625 Length:200625 Length:200625 Length:200625
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
# Unidades en enteros
bd5 = bd4
bd5$Unidades = ceiling(bd5$Unidades)
summary(bd5)
## vcClaveTienda DescGiro Fecha Hora
## Length:200625 Length:200625 Length:200625 Length:200625
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
## Marca Fabricante Producto Precio
## Length:200625 Length:200625 Length:200625 Min. : 0.50
## Class :character Class :character Class :character 1st Qu.: 11.00
## Mode :character Mode :character Mode :character Median : 16.00
## Mean : 19.45
## 3rd Qu.: 25.00
## Max. :1000.00
## Ult.Costo Unidades F.Ticket NombreDepartamento
## Min. : 0.38 Min. : 1.000 Min. : 1 Length:200625
## 1st Qu.: 8.46 1st Qu.: 1.000 1st Qu.: 33964 Class :character
## Median : 12.31 Median : 1.000 Median :105993 Mode :character
## Mean : 15.31 Mean : 1.262 Mean :193990
## 3rd Qu.: 19.23 3rd Qu.: 1.000 3rd Qu.:383005
## Max. :769.23 Max. :96.000 Max. :450040
## NombreFamilia NombreCategoria Estado Mts.2
## Length:200625 Length:200625 Length:200625 Min. :47.0
## Class :character Class :character Class :character 1st Qu.:53.0
## Mode :character Mode :character Mode :character Median :60.0
## Mean :56.6
## 3rd Qu.:60.0
## Max. :62.0
## Tipo.ubicación Giro Hora.inicio Hora.cierre
## Length:200625 Length:200625 Length:200625 Length:200625
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
Convertir tipos de datos
#Convertir de caracter a fecha
bd6 = bd3
bd6$Fecha = as.Date(bd6$Fecha, format= "%d/%m/%Y")
tibble(bd6)
## # A tibble: 200,473 × 20
## vcCla…¹ DescG…² Fecha Hora Marca Fabri…³ Produ…⁴ Precio Ult.C…⁵ Unida…⁶
## <chr> <chr> <date> <chr> <chr> <chr> <chr> <dbl> <dbl> <dbl>
## 1 MX001 Abarro… 2020-06-19 08:1… NUTR… MEXILAC Nutri … 16 12.3 1
## 2 MX001 Abarro… 2020-06-19 08:2… DAN … DANONE… DANUP … 14 14 1
## 3 MX001 Abarro… 2020-06-19 08:2… BIMBO GRUPO … Rebana… 5 5 1
## 4 MX001 Abarro… 2020-06-19 08:2… PEPSI PEPSI-… Pepsi … 8 8 1
## 5 MX001 Abarro… 2020-06-19 08:2… BLAN… FABRIC… Deterg… 19.5 15 1
## 6 MX001 Abarro… 2020-06-19 08:2… FLASH ALEN Flash … 9.5 7.31 1
## 7 MX001 Abarro… 2020-06-19 08:2… VARI… DANONE… Danone… 11 11 1
## 8 MX001 Abarro… 2020-06-19 08:2… ZOTE FABRIC… Jabon … 9.5 7.31 1
## 9 MX001 Abarro… 2020-06-19 08:2… ALWA… PROCTE… T Feme… 23.5 18.1 1
## 10 MX001 Abarro… 2020-06-19 15:2… JUMEX JUMEX Jugo D… 12 12 1
## # … with 200,463 more rows, 10 more variables: F.Ticket <int>,
## # NombreDepartamento <chr>, NombreFamilia <chr>, NombreCategoria <chr>,
## # Estado <chr>, Mts.2 <int>, Tipo.ubicación <chr>, Giro <chr>,
## # Hora.inicio <chr>, Hora.cierre <chr>, and abbreviated variable names
## # ¹vcClaveTienda, ²DescGiro, ³Fabricante, ⁴Producto, ⁵Ult.Costo, ⁶Unidades
# Convertir de caracter a entero
bd7 = bd6
bd7$Hora = substr(bd7$Hora, start = 1, stop = 2)
tibble(bd7)
## # A tibble: 200,473 × 20
## vcCla…¹ DescG…² Fecha Hora Marca Fabri…³ Produ…⁴ Precio Ult.C…⁵ Unida…⁶
## <chr> <chr> <date> <chr> <chr> <chr> <chr> <dbl> <dbl> <dbl>
## 1 MX001 Abarro… 2020-06-19 08 NUTR… MEXILAC Nutri … 16 12.3 1
## 2 MX001 Abarro… 2020-06-19 08 DAN … DANONE… DANUP … 14 14 1
## 3 MX001 Abarro… 2020-06-19 08 BIMBO GRUPO … Rebana… 5 5 1
## 4 MX001 Abarro… 2020-06-19 08 PEPSI PEPSI-… Pepsi … 8 8 1
## 5 MX001 Abarro… 2020-06-19 08 BLAN… FABRIC… Deterg… 19.5 15 1
## 6 MX001 Abarro… 2020-06-19 08 FLASH ALEN Flash … 9.5 7.31 1
## 7 MX001 Abarro… 2020-06-19 08 VARI… DANONE… Danone… 11 11 1
## 8 MX001 Abarro… 2020-06-19 08 ZOTE FABRIC… Jabon … 9.5 7.31 1
## 9 MX001 Abarro… 2020-06-19 08 ALWA… PROCTE… T Feme… 23.5 18.1 1
## 10 MX001 Abarro… 2020-06-19 15 JUMEX JUMEX Jugo D… 12 12 1
## # … with 200,463 more rows, 10 more variables: F.Ticket <int>,
## # NombreDepartamento <chr>, NombreFamilia <chr>, NombreCategoria <chr>,
## # Estado <chr>, Mts.2 <int>, Tipo.ubicación <chr>, Giro <chr>,
## # Hora.inicio <chr>, Hora.cierre <chr>, and abbreviated variable names
## # ¹vcClaveTienda, ²DescGiro, ³Fabricante, ⁴Producto, ⁵Ult.Costo, ⁶Unidades
bd7$Hora = as.integer(bd7$Hora)
str(bd7)
## 'data.frame': 200473 obs. of 20 variables:
## $ vcClaveTienda : chr "MX001" "MX001" "MX001" "MX001" ...
## $ DescGiro : chr "Abarrotes" "Abarrotes" "Abarrotes" "Abarrotes" ...
## $ Fecha : Date, format: "2020-06-19" "2020-06-19" ...
## $ Hora : int 8 8 8 8 8 8 8 8 8 15 ...
## $ Marca : chr "NUTRI LECHE" "DAN UP" "BIMBO" "PEPSI" ...
## $ Fabricante : chr "MEXILAC" "DANONE DE MEXICO" "GRUPO BIMBO" "PEPSI-COLA MEXICANA" ...
## $ Producto : chr "Nutri Leche 1 Litro" "DANUP STRAWBERRY P/BEBER 350GR NAL" "Rebanadas Bimbo 2Pz" "Pepsi N.R. 400Ml" ...
## $ Precio : num 16 14 5 8 19.5 9.5 11 9.5 23.5 12 ...
## $ Ult.Costo : num 12.3 14 5 8 15 ...
## $ Unidades : num 1 1 1 1 1 1 1 1 1 1 ...
## $ F.Ticket : int 1 2 3 3 4 4 4 4 4 5 ...
## $ NombreDepartamento: chr "Abarrotes" "Abarrotes" "Abarrotes" "Abarrotes" ...
## $ NombreFamilia : chr "Lacteos y Refrigerados" "Lacteos y Refrigerados" "Pan y Tortilla" "Bebidas" ...
## $ NombreCategoria : chr "Leche" "Yogurt" "Pan Dulce Empaquetado" "Refrescos Plástico (N.R.)" ...
## $ Estado : chr "Nuevo León" "Nuevo León" "Nuevo León" "Nuevo León" ...
## $ Mts.2 : int 60 60 60 60 60 60 60 60 60 60 ...
## $ Tipo.ubicación : chr "Esquina" "Esquina" "Esquina" "Esquina" ...
## $ Giro : chr "Abarrotes" "Abarrotes" "Abarrotes" "Abarrotes" ...
## $ Hora.inicio : chr "08:00" "08:00" "08:00" "08:00" ...
## $ Hora.cierre : chr "22:00" "22:00" "22:00" "22:00" ...
Tratar valores faltantes (NA)
# ¿Cuántos Na tengo en la base de datos?
sum(is.na(bd7))
## [1] 0
sum(is.na(bd))
## [1] 199188
# ¿Cuántos NA tengo por variable?
sapply(bd, function(x) sum(is.na(x)))
## vcClaveTienda DescGiro Codigo.Barras PLU
## 0 0 0 199188
## Fecha Hora Marca Fabricante
## 0 0 0 0
## Producto Precio Ult.Costo Unidades
## 0 0 0 0
## F.Ticket NombreDepartamento NombreFamilia NombreCategoria
## 0 0 0 0
## Estado Mts.2 Tipo.ubicación Giro
## 0 0 0 0
## Hora.inicio Hora.cierre
## 0 0
# Borrar todos los registros NA de una tabla
bd8 = bd
bd8 = na.omit(bd8)
summary(bd8)
## vcClaveTienda DescGiro Codigo.Barras PLU
## Length:1437 Length:1437 Min. :6.750e+08 Min. : 1.000
## Class :character Class :character 1st Qu.:6.750e+08 1st Qu.: 1.000
## Mode :character Mode :character Median :6.750e+08 Median : 1.000
## Mean :2.616e+11 Mean : 2.112
## 3rd Qu.:6.750e+08 3rd Qu.: 1.000
## Max. :7.501e+12 Max. :30.000
## Fecha Hora Marca Fabricante
## Length:1437 Length:1437 Length:1437 Length:1437
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
## Producto Precio Ult.Costo Unidades
## Length:1437 Min. :30.00 Min. : 1.00 Min. :1.000
## Class :character 1st Qu.:90.00 1st Qu.:64.62 1st Qu.:1.000
## Mode :character Median :90.00 Median :64.62 Median :1.000
## Mean :87.94 Mean :56.65 Mean :1.124
## 3rd Qu.:90.00 3rd Qu.:64.62 3rd Qu.:1.000
## Max. :90.00 Max. :64.62 Max. :7.000
## F.Ticket NombreDepartamento NombreFamilia NombreCategoria
## Min. : 772 Length:1437 Length:1437 Length:1437
## 1st Qu.: 99955 Class :character Class :character Class :character
## Median :102493 Mode :character Mode :character Mode :character
## Mean :100595
## 3rd Qu.:106546
## Max. :118356
## Estado Mts.2 Tipo.ubicación Giro
## Length:1437 Min. :58.00 Length:1437 Length:1437
## Class :character 1st Qu.:58.00 Class :character Class :character
## Mode :character Median :58.00 Mode :character Mode :character
## Mean :58.07
## 3rd Qu.:58.00
## Max. :60.00
## Hora.inicio Hora.cierre
## Length:1437 Length:1437
## Class :character Class :character
## Mode :character Mode :character
##
##
##
# Reemplazar los NA con CEROS
bd9 = bd
bd9[is.na(bd9)] = 0
summary(bd9)
## vcClaveTienda DescGiro Codigo.Barras PLU
## Length:200625 Length:200625 Min. :8.347e+05 Min. : 0.00000
## Class :character Class :character 1st Qu.:7.501e+12 1st Qu.: 0.00000
## Mode :character Mode :character Median :7.501e+12 Median : 0.00000
## Mean :5.950e+12 Mean : 0.01513
## 3rd Qu.:7.501e+12 3rd Qu.: 0.00000
## Max. :1.750e+13 Max. :30.00000
## Fecha Hora Marca Fabricante
## Length:200625 Length:200625 Length:200625 Length:200625
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
## Producto Precio Ult.Costo Unidades
## Length:200625 Min. :-147.00 Min. : 0.38 Min. : 0.200
## Class :character 1st Qu.: 11.00 1st Qu.: 8.46 1st Qu.: 1.000
## Mode :character Median : 16.00 Median : 12.31 Median : 1.000
## Mean : 19.42 Mean : 15.31 Mean : 1.262
## 3rd Qu.: 25.00 3rd Qu.: 19.23 3rd Qu.: 1.000
## Max. :1000.00 Max. :769.23 Max. :96.000
## F.Ticket NombreDepartamento NombreFamilia NombreCategoria
## Min. : 1 Length:200625 Length:200625 Length:200625
## 1st Qu.: 33964 Class :character Class :character Class :character
## Median :105993 Mode :character Mode :character Mode :character
## Mean :193990
## 3rd Qu.:383005
## Max. :450040
## Estado Mts.2 Tipo.ubicación Giro
## Length:200625 Min. :47.0 Length:200625 Length:200625
## Class :character 1st Qu.:53.0 Class :character Class :character
## Mode :character Median :60.0 Mode :character Mode :character
## Mean :56.6
## 3rd Qu.:60.0
## Max. :62.0
## Hora.inicio Hora.cierre
## Length:200625 Length:200625
## Class :character Class :character
## Mode :character Mode :character
##
##
##
# Reemplazar NA con el PROMEDIO
bd10 = bd
bd10$PLU[is.na(bd10$PLU)] = mean(bd10$PLU, na.rm = TRUE)
summary(bd10)
## vcClaveTienda DescGiro Codigo.Barras PLU
## Length:200625 Length:200625 Min. :8.347e+05 Min. : 1.000
## Class :character Class :character 1st Qu.:7.501e+12 1st Qu.: 2.112
## Mode :character Mode :character Median :7.501e+12 Median : 2.112
## Mean :5.950e+12 Mean : 2.112
## 3rd Qu.:7.501e+12 3rd Qu.: 2.112
## Max. :1.750e+13 Max. :30.000
## Fecha Hora Marca Fabricante
## Length:200625 Length:200625 Length:200625 Length:200625
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
## Producto Precio Ult.Costo Unidades
## Length:200625 Min. :-147.00 Min. : 0.38 Min. : 0.200
## Class :character 1st Qu.: 11.00 1st Qu.: 8.46 1st Qu.: 1.000
## Mode :character Median : 16.00 Median : 12.31 Median : 1.000
## Mean : 19.42 Mean : 15.31 Mean : 1.262
## 3rd Qu.: 25.00 3rd Qu.: 19.23 3rd Qu.: 1.000
## Max. :1000.00 Max. :769.23 Max. :96.000
## F.Ticket NombreDepartamento NombreFamilia NombreCategoria
## Min. : 1 Length:200625 Length:200625 Length:200625
## 1st Qu.: 33964 Class :character Class :character Class :character
## Median :105993 Mode :character Mode :character Mode :character
## Mean :193990
## 3rd Qu.:383005
## Max. :450040
## Estado Mts.2 Tipo.ubicación Giro
## Length:200625 Min. :47.0 Length:200625 Length:200625
## Class :character 1st Qu.:53.0 Class :character Class :character
## Mode :character Median :60.0 Mode :character Mode :character
## Mean :56.6
## 3rd Qu.:60.0
## Max. :62.0
## Hora.inicio Hora.cierre
## Length:200625 Length:200625
## Class :character Class :character
## Mode :character Mode :character
##
##
##
Verificar datos con métofos estadísticos
bd11 = bd7
boxplot(bd11$Precio, horizontal = TRUE)
boxplot(bd11$Unidades, horizontal = TRUE)
bd11$diadelasemana = wday(bd11$Fecha)
summary(bd11)
## vcClaveTienda DescGiro Fecha Hora
## Length:200473 Length:200473 Min. :2020-05-01 Min. : 0.00
## Class :character Class :character 1st Qu.:2020-06-06 1st Qu.:13.00
## Mode :character Mode :character Median :2020-07-11 Median :17.00
## Mean :2020-07-18 Mean :16.23
## 3rd Qu.:2020-08-29 3rd Qu.:20.00
## Max. :2020-11-11 Max. :23.00
## Marca Fabricante Producto Precio
## Length:200473 Length:200473 Length:200473 Min. : 0.50
## Class :character Class :character Class :character 1st Qu.: 11.00
## Mode :character Mode :character Mode :character Median : 16.00
## Mean : 19.45
## 3rd Qu.: 25.00
## Max. :1000.00
## Ult.Costo Unidades F.Ticket NombreDepartamento
## Min. : 0.38 Min. : 0.200 Min. : 1 Length:200473
## 1st Qu.: 8.46 1st Qu.: 1.000 1st Qu.: 33978 Class :character
## Median : 12.31 Median : 1.000 Median :106035 Mode :character
## Mean : 15.31 Mean : 1.261 Mean :194101
## 3rd Qu.: 19.23 3rd Qu.: 1.000 3rd Qu.:383065
## Max. :769.23 Max. :96.000 Max. :450040
## NombreFamilia NombreCategoria Estado Mts.2
## Length:200473 Length:200473 Length:200473 Min. :47.0
## Class :character Class :character Class :character 1st Qu.:53.0
## Mode :character Mode :character Mode :character Median :60.0
## Mean :56.6
## 3rd Qu.:60.0
## Max. :62.0
## Tipo.ubicación Giro Hora.inicio Hora.cierre
## Length:200473 Length:200473 Length:200473 Length:200473
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
## diadelasemana
## Min. :1.000
## 1st Qu.:2.000
## Median :4.000
## Mean :3.911
## 3rd Qu.:6.000
## Max. :7.000
bd11$subtotal = bd11$Precio * bd11$Unidades
summary(bd11)
## vcClaveTienda DescGiro Fecha Hora
## Length:200473 Length:200473 Min. :2020-05-01 Min. : 0.00
## Class :character Class :character 1st Qu.:2020-06-06 1st Qu.:13.00
## Mode :character Mode :character Median :2020-07-11 Median :17.00
## Mean :2020-07-18 Mean :16.23
## 3rd Qu.:2020-08-29 3rd Qu.:20.00
## Max. :2020-11-11 Max. :23.00
## Marca Fabricante Producto Precio
## Length:200473 Length:200473 Length:200473 Min. : 0.50
## Class :character Class :character Class :character 1st Qu.: 11.00
## Mode :character Mode :character Mode :character Median : 16.00
## Mean : 19.45
## 3rd Qu.: 25.00
## Max. :1000.00
## Ult.Costo Unidades F.Ticket NombreDepartamento
## Min. : 0.38 Min. : 0.200 Min. : 1 Length:200473
## 1st Qu.: 8.46 1st Qu.: 1.000 1st Qu.: 33978 Class :character
## Median : 12.31 Median : 1.000 Median :106035 Mode :character
## Mean : 15.31 Mean : 1.261 Mean :194101
## 3rd Qu.: 19.23 3rd Qu.: 1.000 3rd Qu.:383065
## Max. :769.23 Max. :96.000 Max. :450040
## NombreFamilia NombreCategoria Estado Mts.2
## Length:200473 Length:200473 Length:200473 Min. :47.0
## Class :character Class :character Class :character 1st Qu.:53.0
## Mode :character Mode :character Mode :character Median :60.0
## Mean :56.6
## 3rd Qu.:60.0
## Max. :62.0
## Tipo.ubicación Giro Hora.inicio Hora.cierre
## Length:200473 Length:200473 Length:200473 Length:200473
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
## diadelasemana subtotal
## Min. :1.000 Min. : 1.0
## 1st Qu.:2.000 1st Qu.: 12.0
## Median :4.000 Median : 18.0
## Mean :3.911 Mean : 24.3
## 3rd Qu.:6.000 3rd Qu.: 27.0
## Max. :7.000 Max. :2496.0
# Paso 5. Exportar base de datos limpia
bd_limpia = bd11
#write.csv(bd_limpia, file= "abarrotes_bdlimpia.csv", row.names = FALSE)
bd_limpia = read.csv("C:\\Users\\Silva\\Documents\\CSV\\Semestre 4\\Manipulación de datos\\abarrotes_bdlimpia.csv")
# Ordenar de menor a mayor los tickets
bd_limpia = bd_limpia[order(bd_limpia$F.Ticket),]
head(bd_limpia)
## vcClaveTienda DescGiro Fecha Hora Marca
## 1 MX001 Abarrotes 2020-06-19 8 NUTRI LECHE
## 2 MX001 Abarrotes 2020-06-19 8 DAN UP
## 3 MX001 Abarrotes 2020-06-19 8 BIMBO
## 4 MX001 Abarrotes 2020-06-19 8 PEPSI
## 5 MX001 Abarrotes 2020-06-19 8 BLANCA NIEVES (DETERGENTE)
## 6 MX001 Abarrotes 2020-06-19 8 FLASH
## Fabricante Producto Precio
## 1 MEXILAC Nutri Leche 1 Litro 16.0
## 2 DANONE DE MEXICO DANUP STRAWBERRY P/BEBER 350GR NAL 14.0
## 3 GRUPO BIMBO Rebanadas Bimbo 2Pz 5.0
## 4 PEPSI-COLA MEXICANA Pepsi N.R. 400Ml 8.0
## 5 FABRICA DE JABON LA CORONA Detergente Blanca Nieves 500G 19.5
## 6 ALEN Flash Xtra Brisa Marina 500Ml 9.5
## Ult.Costo Unidades F.Ticket NombreDepartamento NombreFamilia
## 1 12.31 1 1 Abarrotes Lacteos y Refrigerados
## 2 14.00 1 2 Abarrotes Lacteos y Refrigerados
## 3 5.00 1 3 Abarrotes Pan y Tortilla
## 4 8.00 1 3 Abarrotes Bebidas
## 5 15.00 1 4 Abarrotes Limpieza del Hogar
## 6 7.31 1 4 Abarrotes Limpieza del Hogar
## NombreCategoria Estado Mts.2 Tipo.ubicación Giro
## 1 Leche Nuevo León 60 Esquina Abarrotes
## 2 Yogurt Nuevo León 60 Esquina Abarrotes
## 3 Pan Dulce Empaquetado Nuevo León 60 Esquina Abarrotes
## 4 Refrescos Plástico (N.R.) Nuevo León 60 Esquina Abarrotes
## 5 Lavandería Nuevo León 60 Esquina Abarrotes
## 6 Limpiadores Líquidos Nuevo León 60 Esquina Abarrotes
## Hora.inicio Hora.cierre diadelasemana subtotal
## 1 08:00 22:00 6 16.0
## 2 08:00 22:00 6 14.0
## 3 08:00 22:00 6 5.0
## 4 08:00 22:00 6 8.0
## 5 08:00 22:00 6 19.5
## 6 08:00 22:00 6 9.5
tail(bd_limpia)
## vcClaveTienda DescGiro Fecha Hora Marca
## 107247 MX004 Carnicería 2020-10-15 11 YEMINA
## 167624 MX004 Carnicería 2020-10-15 11 DEL FUERTE
## 149282 MX004 Carnicería 2020-10-15 11 COCA COLA ZERO
## 168603 MX004 Carnicería 2020-10-15 11 DIAMANTE
## 161046 MX004 Carnicería 2020-10-15 12 PEPSI
## 112823 MX004 Carnicería 2020-10-15 12 COCA COLA
## Fabricante Producto Precio Ult.Costo
## 107247 HERDEZ PASTA SPAGHETTI YEMINA 200G 7 5.38
## 167624 ALIMENTOS DEL FUERTE PURE DE TOMATE DEL FUERTE 345G 12 9.23
## 149282 COCA COLA COCA COLA ZERO 600ML 15 11.54
## 168603 EMPACADOS ARROZ DIAMANTE225G 11 8.46
## 161046 PEPSI-COLA MEXICANA PEPSI N. R. 500ML 10 7.69
## 112823 COCA COLA COCA COLA RETORNABLE 500ML 10 7.69
## Unidades F.Ticket NombreDepartamento NombreFamilia
## 107247 2 450032 Abarrotes Sopas y Pastas
## 167624 1 450032 Abarrotes Salsas y Sazonadores
## 149282 2 450034 Abarrotes Bebidas
## 168603 1 450037 Abarrotes Granos y Semillas
## 161046 1 450039 Abarrotes Bebidas
## 112823 8 450040 Abarrotes Bebidas
## NombreCategoria Estado Mts.2 Tipo.ubicación Giro
## 107247 Fideos, Spaguetti, Tallarines Sinaloa 53 Esquina Abarrotes
## 167624 Salsa para Spaguetti Sinaloa 53 Esquina Abarrotes
## 149282 Refrescos Retornables Sinaloa 53 Esquina Abarrotes
## 168603 Arroz Sinaloa 53 Esquina Abarrotes
## 161046 Refrescos Plástico (N.R.) Sinaloa 53 Esquina Abarrotes
## 112823 Refrescos Retornables Sinaloa 53 Esquina Abarrotes
## Hora.inicio Hora.cierre diadelasemana subtotal
## 107247 07:00 23:00 5 14
## 167624 07:00 23:00 5 12
## 149282 07:00 23:00 5 30
## 168603 07:00 23:00 5 11
## 161046 07:00 23:00 5 10
## 112823 07:00 23:00 5 80
# Extraer productos por ticket
basket = ddply(bd_limpia, c("F.Ticket"), function(bd_limpia)paste(bd_limpia$Marca,collapse = ", "))
# Eliminar número de ticket
basket$F.Ticket = NULL
# Renombrar el nombre de la columna marca
colnames(basket) = c("Marca")
# Exportar basket
#write.csv(basket, "basket.csv", quote = FALSE, row.names =FALSE )
tr = read.transactions("C:\\Users\\Silva\\Documents\\CSV\\Semestre 4\\Manipulación de datos\\basket.csv", format = "basket", sep = ",")
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in scan(text = l, what = "character", sep = sep, quote = quote, : EOF
## within quoted string
## Warning in asMethod(object): removing duplicated items in transactions
reglas_asociacion = apriori(tr, parameter = list(supp = 0.001, conf = 0.2, maxlen = 10))
## Apriori
##
## Parameter specification:
## confidence minval smax arem aval originalSupport maxtime support minlen
## 0.2 0.1 1 none FALSE TRUE 5 0.001 1
## maxlen target ext
## 10 rules TRUE
##
## Algorithmic control:
## filter tree heap memopt load sort verbose
## 0.1 TRUE TRUE FALSE TRUE 2 TRUE
##
## Absolute minimum support count: 115
##
## set item appearances ...[0 item(s)] done [0.00s].
## set transactions ...[604 item(s), 115031 transaction(s)] done [0.07s].
## sorting and recoding items ... [207 item(s)] done [0.00s].
## creating transaction tree ... done [0.06s].
## checking subsets of size 1 2 3 done [0.01s].
## writing ... [11 rule(s)] done [0.00s].
## creating S4 object ... done [0.01s].
#summary(reglas_asociacion)
#inspect(reglas_asociacion)
reglas_asociacion = sort(reglas_asociacion, by ="confidence", decreasing = TRUE)
#inspect(reglas_asociacion)
Top 10 reglas de asociación
top10reglas = head(reglas_asociacion, n= 10, by = "confidence")
plot(top10reglas, method = "graph", engine = "htmlwidget")