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, unionlibrary(tidyverse)## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.1 ──## ✔ ggplot2 3.3.5 ✔ purrr 0.3.4
## ✔ tibble 3.1.8 ✔ stringr 1.4.0
## ✔ tidyr 1.2.0 ✔ forcats 0.5.1
## ✔ readr 2.1.2## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()library(readxl)
library(janitor)##
## Attaching package: 'janitor'## The following objects are masked from 'package:stats':
##
## chisq.test, fisher.testlibrary(lubridate)##
## Attaching package: 'lubridate'## The following objects are masked from 'package:base':
##
## date, intersect, setdiff, unionlibrary(readxl)
Abarrotes_Ventas_2 <- read_excel("Abarrotes_Ventas-2.xlsx")glimpse(Abarrotes_Ventas_2)## Rows: 200,620
## Columns: 22
## $ vcClaveTienda <chr> "MX001", "MX001", "MX001", "MX001", "MX001", "MX001…
## $ DescGiro <chr> "Abarrotes", "Abarrotes", "Abarrotes", "Abarrotes",…
## $ `Codigo Barras` <dbl> 7.501021e+12, 7.501032e+12, 7.501000e+12, 7.501031e…
## $ PLU <lgl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,…
## $ Fecha <dttm> 2020-06-19 08:16:20, 2020-06-19 08:23:32, 2020-06-…
## $ Hora <dttm> 1899-12-31 08:16:21, 1899-12-31 08:23:33, 1899-12-…
## $ Marca <chr> "NUTRI LECHE", "DAN UP", "BIMBO", "PEPSI", "BLANCA …
## $ Fabricante <chr> "MEXILAC", "DANONE DE MEXICO", "GRUPO BIMBO", "PEPS…
## $ Producto <chr> "Nutri Leche 1 Litro", "DANUP STRAWBERRY P/BEBER 35…
## $ Precio <dbl> 16.0, 14.0, 5.0, 8.0, 19.5, 9.5, 11.0, 9.5, 23.5, 1…
## $ Ult.Costo <dbl> 12.31, 14.00, 5.00, 8.00, 15.00, 7.31, 11.00, 7.31,…
## $ Unidades <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, …
## $ F.Ticket <dbl> 1, 2, 3, 3, 4, 4, 4, 4, 4, 5, 5, 6, 7, 9, 9, 9, 10,…
## $ NombreDepartamento <chr> "Abarrotes", "Abarrotes", "Abarrotes", "Abarrotes",…
## $ NombreFamilia <chr> "Lacteos y Refrigerados", "Lacteos y Refrigerados",…
## $ NombreCategoria <chr> "Leche", "Yogurt", "Pan Dulce Empaquetado", "Refres…
## $ Estado <chr> "Nuevo León", "Nuevo León", "Nuevo León", "Nuevo Le…
## $ `Mts 2` <dbl> 60, 60, 60, 60, 60, 60, 60, 60, 60, 60, 60, 60, 60,…
## $ `Tipo ubicación` <chr> "Esquina", "Esquina", "Esquina", "Esquina", "Esquin…
## $ Giro <chr> "Abarrotes", "Abarrotes", "Abarrotes", "Abarrotes",…
## $ `Hora inicio` <dttm> 1899-12-31 08:00:00, 1899-12-31 08:00:00, 1899-12-…
## $ `Hora cierre` <dttm> 1899-12-31 22:00:00, 1899-12-31 22:00:00, 1899-12-…#Contar los valores únicos en cada variable
# Función para contar los valores únicos en cada columna
count_unique_values <- function(Abarrotes_Ventas_2) {
result <- data.frame()
for (col in colnames(Abarrotes_Ventas_2)) {
unique_values <- unique(Abarrotes_Ventas_2[[col]])
num_unique_values <- length(unique_values)
result <- rbind(result, data.frame(Variable = col, NumUniqueValues = num_unique_values))
}
return(result)
}
unique_counts <- count_unique_values(Abarrotes_Ventas_2)
print(unique_counts)## Variable NumUniqueValues
## 1 vcClaveTienda 5
## 2 DescGiro 3
## 3 Codigo Barras 2287
## 4 PLU 2
## 5 Fecha 131933
## 6 Hora 52145
## 7 Marca 540
## 8 Fabricante 241
## 9 Producto 3404
## 10 Precio 206
## 11 Ult.Costo 234
## 12 Unidades 43
## 13 F.Ticket 115110
## 14 NombreDepartamento 9
## 15 NombreFamilia 51
## 16 NombreCategoria 174
## 17 Estado 5
## 18 Mts 2 5
## 19 Tipo ubicación 3
## 20 Giro 2
## 21 Hora inicio 3
## 22 Hora cierre 3view(unique_counts)#Valores unicos en ciertas columnas
#Así podemos ver la lista entera de valores únicos en las columnas: Marca, Fabricante, NombreDepartamento, NombreFamilia, y NombreCategoria
columns_to_explore <- c("Marca", "Fabricante", "NombreDepartamento", "NombreFamilia", "NombreCategoria")
for (col in columns_to_explore) {
unique_values <- unique(Abarrotes_Ventas_2[[col]])
cat("Variable:", col, "\n")
print(unique_values)
cat("\n")
}## Variable: Marca
## [1] "NUTRI LECHE" "DAN UP"
## [3] "BIMBO" "PEPSI"
## [5] "BLANCA NIEVES (DETERGENTE)" "FLASH"
## [7] "VARIOS DANONE" "ZOTE"
## [9] "ALWAYS" "JUMEX"
## [11] "VALLE FRUT" "MARINELA"
## [13] "LALA" "MAMUT"
## [15] "ACE" "ENSUEÑO"
## [17] "CHIMEX" "DEL VALLE"
## [19] "COCA COLA" "SPRITE"
## [21] "FUD" "PERMA SHARP"
## [23] "JOYA" "EL GALLO DE ORO"
## [25] "CLORALEX" "YOPLAIT"
## [27] "SAVILE" "RUFFLES"
## [29] "SABRITAS" "KRAFT"
## [31] "CHEETOS" "COCA COLA LIGHT"
## [33] "COCA COLA ZERO" "MANZANITA SOL"
## [35] "KINDER" "FRUTIMAX"
## [37] "PRINGLES" "CREMAX DE NIEVE"
## [39] "EPURA" "DIAMANTE"
## [41] "DORITOS" "KOLALOKA"
## [43] "TRIDENT" "BONAFONT"
## [45] "CAZO MEXICANO" "GAMESA"
## [47] "ORBIT" "CRUJITOS"
## [49] "TOSTITOS" "POWERADE"
## [51] "EGO" "NUGGET"
## [53] "BUBBA XTREME" "LUCAS"
## [55] "BUBBALOO" "LINK"
## [57] "BEBIN" "DANONINO"
## [59] "PAKETAXO" "DEL MONTE"
## [61] "VELADORA MEXICO" "CONVERMEX"
## [63] "DEL FUERTE" "MARIPOSA"
## [65] "SEVEN UP" "SQUIRT"
## [67] "CIERVO" "MIRINDA"
## [69] "KNORR" "AXION"
## [71] "FOCA" "BOKADOS"
## [73] "TANG" "MONARCA"
## [75] "GIRO" "PRISPAS"
## [77] "BLUE HOUSE" "DANONE"
## [79] "HERSHEYS" "RANCHERITOS"
## [81] "CHICHARRON DE CERDO (SABRITAS)" "BIG COLA"
## [83] "CAMPBELL'S" "TIX TIX"
## [85] "PICOT" "SABRITONES"
## [87] "PAPIRRINGAS" "SUAVITEL"
## [89] "PAPATINAS" "NESTLE"
## [91] "MARLBORO" "MONELI"
## [93] "NEVADA" "BENSON & HEDGES"
## [95] "FRUTSI" "RAID"
## [97] "SUAVELASTIC" "PINOL"
## [99] "ENCANTO" "FABULOSO"
## [101] "SALVO" "ISADORA"
## [103] "1-2-3 (ABARROTES)" "TOPO CHICO"
## [105] "NATURELLA" "FRUTZZO"
## [107] "MAIZENA" "CABALLITO"
## [109] "HELLMANN´S" "TOPITOS (BK2)"
## [111] "LEO" "FANTA"
## [113] "ROMA" "MASECA"
## [115] "INCA" "SALADITAS (GAMESA)"
## [117] "HUNTS" "FRESCA"
## [119] "TECATE" "LA VILLITA"
## [121] "GARNIER NUTRISSE" "JARRITOS"
## [123] "PALL MALL" "EL DORADO"
## [125] "TOSTILEO" "EMPERADOR (SENZO)"
## [127] "FRITOS" "LA COSTEÑA"
## [129] "MAZAPAN AZTECA (BK2)" "NORVER"
## [131] "NORTEÑITA" "BOING"
## [133] "M&M" "CRISTAL"
## [135] "POFFETS" "GILLETTE"
## [137] "NESCAFE" "CHEESE PUFFS (LEO)"
## [139] "PREMIER" "COLGATE"
## [141] "SPEED STICK" "MORELOS"
## [143] "ZUKO" "CLAMATO"
## [145] "GATORADE" "LA BOTANERA"
## [147] "TAJIN" "DE LA VIUDA"
## [149] "LA ANITA" "DEL HOGAR"
## [151] "EL JIMADOR" "CAMELIA"
## [153] "VOLT" "CHURRUMAIS"
## [155] "NIDO" "ELITE"
## [157] "PULPY" "TRES ESTRELLAS"
## [159] "NUTRIOLI" "BIDA"
## [161] "DOÑA MARIA" "HOT NUTS"
## [163] "CARNATION CLAVEL" "HABANERAS"
## [165] "MEDIA CREMA" "LARA"
## [167] "CONSOMATE" "DELICIOSAS (LARA)"
## [169] "LA SIERRA" "KARTAMUS"
## [171] "LA FINA" "TIA ROSA"
## [173] "FLAMA" "BUBU LUBU"
## [175] "RANCH STYLE" "FROOT LOOPS"
## [177] "GERBER" "H24"
## [179] "YOP TEENS" "MARUCHAN"
## [181] "MCCORMICK" "SAN LUIS"
## [183] "FIOR DI PASTA" "NORTEÑO"
## [185] "ELECTROPURA" "PEDIGREE"
## [187] "BOGO´S" "ACT II"
## [189] "PEPSI LIGHT" "RICOLINO (DULCE)"
## [191] "LEO CACHAHUATES" "BE-LIGHT"
## [193] "SIDRAL MUNDET" "5 ESTRELLAS"
## [195] "CONCHITAS" "TOSTADITAS HIDALGO"
## [197] "VERDE VALLE" "VALENTINA"
## [199] "EFICAZ" "MAS"
## [201] "WINIS" "CHIQUITIN"
## [203] "HALLS" "HERDEZ"
## [205] "VIRMAR" "ACTIVIA"
## [207] "ATM" "KLEEN BEBE"
## [209] "ZONA DEL SABOR" "SAVILé"
## [211] "CHOCO MILK" "SANTA CLARA"
## [213] "DOWNY" "SELECTA"
## [215] "VERO" "MAZATUN"
## [217] "VELVET" "CHOKIS"
## [219] "ARIEL" "MASSISO"
## [221] "CHICHARRONES HARINA (BK2)" "CIEL"
## [223] "ARCOIRIS (GAMESA)" "MARIAS"
## [225] "CANADA DRY" "LA LECHERA"
## [227] "ZUCARITAS" "SABA"
## [229] "CLAMATO VUELVE A LA VIDA" "PRODUCTOS CIERVO"
## [231] "REXAL" "NESCAFE DECAF"
## [233] "PEÑAFIEL SABORES" "GOLOS"
## [235] "KLEENEX" "GUTEN"
## [237] "LECHE FORTILECHE" "TRIDENT XTRA CARE"
## [239] "IRIS" "AVANT"
## [241] "AXE" "SOL"
## [243] "PALMOLIVE" "SNICKERS"
## [245] "TUNY" "ELECTROLIT"
## [247] "AJAX" "LA MODERNA"
## [249] "ROGELIO BUENO" "KOTEX"
## [251] "ELTORITO REGIO" "EPIX"
## [253] "MILKY WAY" "YOPI"
## [255] "JALOMA" "DEL PRIMO"
## [257] "DEL CAMPO" "LOL-TUN"
## [259] "BABY" "SULTANA"
## [261] "ENRE-2" "VIVE 100 %"
## [263] "HEAD & SHOULDERS" "PANASONIC"
## [265] "CHOCO KRISPIS" "PEÑAFIEL"
## [267] "RUEDAS" "CROSEE & BLACKWELL"
## [269] "ZEST" "FUZE TEA"
## [271] "CHIP-OTLES" "YEMINA"
## [273] "TIC TAC" "LIMONCHO"
## [275] "BREF" "CALAHUA"
## [277] "MR MUSCULO" "MILPA REAL"
## [279] "CLEMENTE JACQUES" "CORN POPS"
## [281] "OBAO" "CALIFORNIA"
## [283] "LA PERLA" "KELLOGG'S"
## [285] "CAPERUCITA" "FUERTE"
## [287] "ORAL-B" "HUEKOS"
## [289] "QUAKER" "ARIZONA"
## [291] "ANCLA" "ABUELITA"
## [293] "HIDALGO (TOSTADAS)" "MANZANA LIFT"
## [295] "DIPAZOS" "CHEESES PUFFS (ENCANTO)"
## [297] "AVE" "BRILUX"
## [299] "CREMINO" "BRASSO"
## [301] "SULTAN" "MICHE-MIX"
## [303] "MAGGI" "NORDIKO"
## [305] "BLANCA NIEVES" "STARKIS"
## [307] "BARCEL" "KARO"
## [309] "CHUPA CHUPS" "LUBRIDERM"
## [311] "INDIO" "MORELIA"
## [313] "LA GUACAMAYA" "CAPULLO"
## [315] "CORN FLAKES (KELLOGGS)" "VICK"
## [317] "NESQUIK" "WHISKAS"
## [319] "MAX AIR DENTYNE" "SCHICK"
## [321] "EVENFLO" "ABSOR SEC"
## [323] "JANEL" "CLASICOS DE LUJO"
## [325] "INDY" "ROCKALETA"
## [327] "PRONTO" "SANISSIMO"
## [329] "NESTEA" "PELIKAN"
## [331] "SALSA CASERA" "SAN RAFAEL"
## [333] "ALPURA" "CHIPS"
## [335] "CHARRONES" "CAPRICE"
## [337] "BUFALO" "KARAMELADAS POP"
## [339] "BARRILITO (CERV. MODELO)" "K'NOX"
## [341] "CARTA BLANCA" "PANTENE"
## [343] "REYMA" "CREST"
## [345] "HOT CAKES (GAMESA)" "SARAZA"
## [347] "LADY SPEED STICK" "3 EN 1"
## [349] "LA CAMPANA" "CORONA (CERV. MODELO)"
## [351] "BIC" "NUTELLA"
## [353] "COFFEE MATE" "BOOTS"
## [355] "AFFECTIVE" "SKWINKLES"
## [357] "O-DOLEX" "AVANCE"
## [359] "SUPER REBANADITAS" "PALOLA"
## [361] "VEL ROSITA" "HUGGIES"
## [363] "LYS" "PIKAROS"
## [365] "ADORABLE" "DOS EQUIS LAGER"
## [367] "VIGOR" "GIL"
## [369] "LA VIUDA NEGRA" "CHOCO CHISPAS (LARA)"
## [371] "PETIT (COSECHA PURA)" "PLASTIPAK"
## [373] "PLASTI LOKA" "VITACILINA"
## [375] "REGIO" "PHILADELPHIA"
## [377] "SUANDY" "HERBAL ESSENCES"
## [379] "VIUDA DE SANCHEZ" "GUAYMEX"
## [381] "HEINEKEN" "LOS PERICOS"
## [383] "NISSIN" "PASTISETAS (SUANDY)"
## [385] "CANELS" "SCRIBE (GRUPO PAPELERO SCRIBE)"
## [387] "CARLOS V" "ALFRESCO"
## [389] "HARPIC" "FERRERO ROCHER"
## [391] "SPECIAL K" "SUAVEL"
## [393] "ADES" "SANTA ISABEL"
## [395] "MEGA SUPREMA" "ANIMALITOS (LARA)"
## [397] "SEDAL" "VARIOS QUALTIA"
## [399] "REXONA" "LUZ ETERNA"
## [401] "VOGUE" "JOSE CUERVO ESPECIAL"
## [403] "BUCHANAN'S" "PALETA PAYASO"
## [405] "PAU-PAU" "BUD LIGHT (CERV. MODELO)"
## [407] "BIO BALANCE" "SERALON"
## [409] "MODELO (CERV. MODELO)" "TOKAI"
## [411] "NUGS" "VICTORIA (CERV. MODELO)"
## [413] "LAS CANITAS" "COLORFIEL"
## [415] "SUAVICREMAS (MARINELA)" "TAKIS"
## [417] "BON O BON" "RED BULL"
## [419] "PLEDGE" "CAL-C-TOSE"
## [421] "TENDAL" "MISION"
## [423] "NEUTRO BALANCE" "BACARDI"
## [425] "SALMAS" "PIZZAS FUD"
## [427] "JOHSONS" "NEW MIX"
## [429] "BARRILITOS (DEL FRUTO)" "CARIBE COOLER"
## [431] "B:OOST" "NAYAR"
## [433] "GARAÑON" "LUCKY STRIKE"
## [435] "GARNIER" "1-2-3 (LAVANDERíA)"
## [437] "TOSTADAS SAN MIGUEL" "CLORETS"
## [439] "CAMAY" "DOVE"
## [441] "MARIANITAS" "NESCAFE DOLCA"
## [443] "PERSIL" "JAZMIN"
## [445] "LA NUESTRA" "DUVALIN"
## [447] "COORS LIGHT" "MAYA"
## [449] "ALAMO" "LEGAL"
## [451] "LA CARRETA" "JAGUAR"
## [453] "LIRIO (JAB Y DET)" "TOTITO"
## [455] "DART (PLAST DESECH)" "CHOCOLATINES"
## [457] "PETALO" "LIPTON"
## [459] "ESTRELLA" "TARASQUITOS"
## [461] "TOSTADAS MUSIQUERAS" "TORTILLAS REGIAS"
## [463] "BIG MIX" "KODYZ"
## [465] "PEPSI KICK" "NEO-MELUBRINA"
## [467] "SUPER STAR" "LA PEÑITA"
## [469] "GARDUÑO" "PRIMAVERA"
## [471] "CHEN" "SMMTY"
## [473] "MUSIQUERAS" "POLVORONES"
## [475] "EL GUISANDERO" "CAFE OLE"
## [477] "CHICOLASTIC" "ARCOIRIS"
## [479] "DAMY" "JACK DANIEL´S"
## [481] "PURINA" "MONSTER"
## [483] "POLIRIS" "BIG ROLL"
## [485] "CHURRITOS (LEO)" "SENIOR"
## [487] "FIORE" "GELY CREAM"
## [489] "ZUMBA PICA" "DE LA ROSA"
## [491] "STAR VALUE" "DELICADOS"
## [493] "HELLMANNS" "CAMPO AZUL"
## [495] "BOMBIUX" "SCOTCH-BRITE"
## [497] "SAN MARCOS" "CUéTARA"
## [499] "BAYGON" "GLADE"
## [501] "CLORO PATITO" "EASY OFF"
## [503] "CONTAC" "HOLANDA"
## [505] "KIR" "TOP"
## [507] "ALPINO" "PAISA"
## [509] "LA ARDILLA" "CLORTEX"
## [511] "DOLORES" "BACO"
## [513] "LOVENA" "EL PATO"
## [515] "EUCALIPTOL" "TOSTACHOS"
## [517] "MAGITEL" "IBEROMEX"
## [519] "SUATEL" "NIVEA"
## [521] "VIOLETA" "SONRICS"
## [523] "LIRIO" "OSO"
## [525] "SUPREMO" "RATIGUM"
## [527] "VIRREY" "SEIS HERMANOS"
## [529] "DOÑA EMILIA" "EL TORITO REGIO"
## [531] "CHURRITOS (BARCEL)" "PPINTAAZUL"
## [533] "DODY´S" "BARILLA"
## [535] "PROSAZON" "TREPA"
## [537] "HINDS" "MILLER"
## [539] "KARLA" "GUDU POP"
##
## Variable: Fabricante
## [1] "MEXILAC"
## [2] "DANONE DE MEXICO"
## [3] "GRUPO BIMBO"
## [4] "PEPSI-COLA MEXICANA"
## [5] "FABRICA DE JABON LA CORONA"
## [6] "ALEN"
## [7] "PROCTER & GAMBLE COMPANY"
## [8] "JUMEX"
## [9] "JUGOS DEL VALLE S.A. DE C.V."
## [10] "GRUPO INDUSTRIAL LALA"
## [11] "GRUPO GAMESA"
## [12] "SIGMA ALIMENTOS"
## [13] "COCA COLA"
## [14] "GILLETTE MANUFACTURA"
## [15] "TOSTADAS Y BOTANAS PREMIUM"
## [16] "COLGATE PALMOLIVE"
## [17] "SABRITAS"
## [18] "FERRERO"
## [19] "QUALAMEX"
## [20] "EMPACADOS"
## [21] "INDUSTRIAS KOLALOKA"
## [22] "CADBURY ADAMS"
## [23] "LIQUIMEX"
## [24] "MARS"
## [25] "RECKITT BENCHISER"
## [26] "EFEM DE MEXICO"
## [27] "LINK"
## [28] "LAMBI S.A. DE C.V."
## [29] "CONAGRA FOODS MEXICO"
## [30] "VELADORA MEXICO"
## [31] "CONVERTIDORA DE PLASTICOS"
## [32] "ALIMENTOS DEL FUERTE"
## [33] "FABRICA DE JABON LA REINERA"
## [34] "PRODUCTOS CIERVO"
## [35] "UNILEVER DE MEXICO"
## [36] "NACIONAL DE ALIMENTOS Y HELADOS"
## [37] "KRAFT FOODS"
## [38] "COMERCIALIZADORA GOMEZ"
## [39] "HERSHEY MEXICO"
## [40] "AJEMONTERREY"
## [41] "CAMPBELL'S DE MEXICO"
## [42] "SONRICS"
## [43] "BRISTOL-MYERS SQUIBB"
## [44] "BOTANAS LEO, S.A. DE C.V."
## [45] "BARCEL"
## [46] "NESTLE"
## [47] "CIGATAM"
## [48] "LABORATORIO MONELI"
## [49] "NEVADA"
## [50] "S. C. JOHNSON AND SON"
## [51] "KLEEN BEBE"
## [52] "FRITOS ENCANTO DE MONTERREY, S.A. DE C.V"
## [53] "PRODUCTOS VERDE VALLE S.A. DE C.V."
## [54] "CORONA"
## [55] "CIA. TOPO CHICO"
## [56] "MONROE CHEMICAL"
## [57] "MOLINOS AZTECA"
## [58] "ALIMENTOS CAPULLO"
## [59] "CERVECERIA CUAUHTEMOC MOCTEZUMA"
## [60] "FRABEL S.A DE C.V"
## [61] "KURUMBA"
## [62] "PESCADOS INDUSTRIALIZADOS"
## [63] "CONSERVAS LA COSTEÑA"
## [64] "EMPACADORA NORVER"
## [65] "Refrescos Pascual, S.A."
## [66] "ACEITES GRASAS Y DERIVADOS"
## [67] "PRODUCTOS PREMIER"
## [68] "SPEED STICK"
## [69] "ESTHER CAMACHO GARNICA"
## [70] "GOMEZ CUETARA HNOS"
## [71] "BELTICOS"
## [72] "GRUPO PEÑAFIEL"
## [73] "MEGA ALIMENTOS"
## [74] "EMPRESAS TAJIN"
## [75] "CASA CUERVO"
## [76] "LA ANITA CONDIMENTOS"
## [77] "DEL HOGAR"
## [78] "CASA HERRADURA"
## [79] "AJEMEX"
## [80] "ABSORMEX S.A DE C.V"
## [81] "TRES ESTRELLAS"
## [82] "RAGASA INDUSTRIAS"
## [83] "JUGOMEX"
## [84] "HERDEZ"
## [85] "SABORMEX"
## [86] "SALES DEL ISTMO"
## [87] "LA CENTRAL"
## [88] "RICOLINO"
## [89] "KELLOGG DE MEXICO"
## [90] "PRODUCTOS GERBER"
## [91] "INDUSTRIAS H24"
## [92] "MARUCHAN"
## [93] "DETERSOL"
## [94] "PASTAS MOLISABA S.A DE C.V"
## [95] "MASTER FOODS USA"
## [96] "BOTANAS BOGO´S"
## [97] "ACT II"
## [98] "EMPACADORA JIMENEZ"
## [99] "TOSTADAS HIDALGO S.A DE C.V"
## [100] "SALSA TAMAZULA"
## [101] "HENKEL"
## [102] "CONFICORP"
## [103] "LAFONT LAUNAY"
## [104] "KIMBERLY CLARK"
## [105] "IMPORTACIONES HNOS. CANTú S.A. DE C.V."
## [106] "SANTA CLARA PRODUCTOS LACTEOS"
## [107] "MOLINERA DE MEXICO"
## [108] "DULCES VERO"
## [109] "FABRICA DE PAPEL SAN FRANCISCO"
## [110] "SCA CONSUMIDOR"
## [111] "REXAL"
## [112] "LALA"
## [113] "AVANT"
## [114] "MARINDUSTRIAS"
## [115] "LABORATORIOS PISA"
## [116] "PRODUCTOS ALIMENTICIOS LA MODERNA"
## [117] "BUENO ALIMENTOS"
## [118] "GRUPO CHI-SO S DE RLMI"
## [119] "STAR COMPANY S.A"
## [120] "EMPACADORA DEL CAMPO"
## [121] "PRODUCTOS LOL-TUN"
## [122] "LABORATORIOS AVANT"
## [123] "PANASONIC"
## [124] "EMBOTELLADORA DE MARCAS INTERNACIONALES"
## [125] "PROCOPSA DE CV"
## [126] "COSBEL"
## [127] "LA IMPERIAL"
## [128] "LA PERLA"
## [129] "QUALTIA ALIMENTOS"
## [130] "DONATO ELIZONDO CANTU"
## [131] "DRINKARIZONA"
## [132] "Grupo Ancla S.A"
## [133] "TOSTADAS HIDALGO SA DE CV"
## [134] "VELADORAS MISTICAS"
## [135] "NUTRESA"
## [136] "COMPAÑIA ALIMENTICIA DEL NORTE"
## [137] "BLANCA NIEVES"
## [138] "PFIZER"
## [139] "INDUSTRIAS GUACAMAYA"
## [140] "EVEREADY DE MEXICO"
## [141] "EVENFLO MEXICO"
## [142] "JANEL"
## [143] "PRODUCTOS INDY S.A. DE C.V."
## [144] "CON ALIMENTOS"
## [145] "SANISSIMO S.A. DE C.V."
## [146] "PRODUCTOS PELIKAN"
## [147] "GRUPO ALPURA"
## [148] "CERVECERIA MODELO, S.A. DE C.V"
## [149] "PLASTICOS ADHERIBLES DEL BAJIO"
## [150] "ESTILO Y VANIDAD"
## [151] "NO SABE FALLAR"
## [152] "PRODUCTOS INTERNACIONALES MABE"
## [153] "PRODUCTOS PESQUEROS DE MATANCITAS"
## [154] "CANDY POP"
## [155] "Palola Distribuciones S.A. de C.V."
## [156] "HUGGIES"
## [157] "ABASTECIMIENTOS PLáSTICOS Y ELéCTRICOS,"
## [158] "Sanjuana Rodriguez Bustamante"
## [159] "Global Brands SRL"
## [160] "BECTON DICKINSON DE MEXICO"
## [161] "COMPAÑIA INTERNACIONAL DE COMERCIO"
## [162] "SCA CONSUMIDOR MéXICO"
## [163] "Edmundo Sánchez"
## [164] "GRUPO GUAYMEX"
## [165] "COMERCIALIZADORA Y PROCESADORA LOS ALAMO"
## [166] "NISSIN FOODS DE MEXICO S.A DE C.V"
## [167] "ULTRA"
## [168] "GRUPO PAPELERO SCRIBE"
## [169] "ALIMENTOS SANTA ISABEL"
## [170] "LUZ ETERNA"
## [171] "TEQUILA CUERVO"
## [172] "JAMES BUCHANAN & CO."
## [173] "COATS MEXICO"
## [174] "TOKAI"
## [175] "MAZAPAN DE LA ROSA"
## [176] "TEMMY S.A"
## [177] "UNIDAL MEXICO"
## [178] "RED BULL"
## [179] "BRISTOL-MYERS SQUIBB DE MEXICO"
## [180] "ENKAPLAST"
## [181] "PRODUCTOS Y DISTRIBUIDORA AZTECA"
## [182] "BACARDI Y COMPAÑIA"
## [183] "JOHNSON & JOHNSON DE MEXICO"
## [184] "TEQUILA HERRADURA"
## [185] "DEL FRUTO"
## [186] "INDUSTRIAS VINICOLAS PEDRO DOMECQ"
## [187] "GARAÑON"
## [188] "BRITISH AMERICAN TOBACCO MEXICO"
## [189] "TOSTADAS SAN MIGUEL"
## [190] "DISTRIBUIDORA UNIVERSAL DE MERCANCIAS"
## [191] "COORS BREWING CO"
## [192] "Fabrica de Cerillos y Fosforos la Indepe"
## [193] "QUIMICA GONCAL"
## [194] "CENTRAL DE BOLSAS"
## [195] "Sánchez y Martín s.a. de c.v"
## [196] "DART DE MEXICO, S. DE R.L DE C.V"
## [197] "TORTILLAS ESTRELLA DEL NORTE, S.A. DE C."
## [198] "TARASQUITOS"
## [199] "Productos Deshidratados Paga SA de CV"
## [200] "HORTENCIA SALAZAR BORJAS"
## [201] "AVENTIS PHARMA"
## [202] "GARZA ELIZONDO Y CIA."
## [203] "TOSTADAS LA PEÑITA"
## [204] "Bolsas y Vasos Garduño S.A. de C.V."
## [205] "PLASTICOS Y PRODUCTOS DE MONTERREY"
## [206] "PRODUCTOS DESHIDRATADOS PAGA, S.A DE C.V"
## [207] "LA PIARA S.A DE C.V"
## [208] "DETERGENTES Y JABONES SASIL, S.A. DE C.V"
## [209] "MONTES Y CIA"
## [210] "BROWN FORMAN TEQUILA MEXICO"
## [211] "MONSTER BEVERAGE COMPANY"
## [212] "HILOS HIRIS"
## [213] "MULTIDISTRIBUIDORA DE ALIMENTOS"
## [214] "MEGA ALIMENTOS, S.A. DE C.V."
## [215] "PRODUCTOS FINOS DE AGAVE"
## [216] "3M MEXICO"
## [217] "EMPACADORA SAN MARCOS"
## [218] "BAYGON"
## [219] "GRUPO GONHER"
## [220] "GLAXOSMITHKLINE"
## [221] "PRODUCTOS SEBRING"
## [222] "Mexicana de Arroz, S.A. de C.V"
## [223] "MANUEL UGALDE MATA"
## [224] "BACO"
## [225] "Walker Foods Inc"
## [226] "RAUL S. GONZALEZ GONZALEZ"
## [227] "BDF MEXICO"
## [228] "ANALARA, S.A."
## [229] "PRODUCTOS LIRIO"
## [230] "TOSTADORES Y MOLINOS"
## [231] "PES"
## [232] "VIRREY"
## [233] "EMPALMES SEIS HERMANOS"
## [234] "ALIMENTOS DELICIAS DEL NORTE"
## [235] "EL TORITO REGIO"
## [236] "BETONE"
## [237] "BARILLA DE MEXICO"
## [238] "PROSAZON"
## [239] "HINDS"
## [240] "MILLER BREWING COMPANY"
## [241] "DULCES KARLA"
##
## Variable: NombreDepartamento
## [1] "Abarrotes" "Ferretería" "Bebes e Infantiles"
## [4] "Mercería" "Vinos y Licores" "Carnes"
## [7] "Farmacia" "Papelería" "Productos a Eliminar"
##
## Variable: NombreFamilia
## [1] "Lacteos y Refrigerados" "Pan y Tortilla"
## [3] "Bebidas" "Limpieza del Hogar"
## [5] "Cuidado Personal" "Galletas"
## [7] "C. Frías y Salchichonería" "Botanas"
## [9] "Dulcería" "Granos y Semillas"
## [11] "Pegamentos" "Cigarros"
## [13] "Pañales" "Aderezos"
## [15] "Velas y Veladoras" "Desechables"
## [17] "Salsas y Sazonadores" "Especias"
## [19] "Cereales" "Aceite"
## [21] "Te, Chocolate y Café" "Varios"
## [23] "Harinas y Complementos" "Mantecas"
## [25] "Cerveza" "Latería"
## [27] "Sopas y Pastas" "Tequila"
## [29] "Alimentos" "Alimentos para Mascotas"
## [31] "Azúcar y Miel" "Productos Higiénicos"
## [33] "Pollo" "Accesorios"
## [35] "Postres" "Material de Curación"
## [37] "Pilas para uso Doméstico" "Antigripal"
## [39] "Dermatológicos" "Materiales y Accesorios"
## [41] "Alcohol" "Sangría"
## [43] "Cuadernos" "Whisky"
## [45] "Alimentos a Granel" "Productos sin Familia"
## [47] "Ron" "Bebidas Premezcladas"
## [49] "Analgésicos" "Antiácido"
## [51] "Artículos de Escritura"
##
## Variable: NombreCategoria
## [1] "Leche"
## [2] "Yogurt"
## [3] "Pan Dulce Empaquetado"
## [4] "Refrescos Plástico (N.R.)"
## [5] "Lavandería"
## [6] "Limpiadores Líquidos"
## [7] "Postres Refrigerados"
## [8] "Higiene Femenina"
## [9] "Jugos y Néctares"
## [10] "Aguas Saborizadas"
## [11] "Sandwich"
## [12] "Malvavisco"
## [13] "Tocino"
## [14] "Refrescos Retornables"
## [15] "Pastelillos"
## [16] "Quesos"
## [17] "Jamón de Pavo"
## [18] "Rellenas"
## [19] "Afeitado y Depilación"
## [20] "Pan para Hamburguesa, HotDog y Tortas"
## [21] "Pan de Barra Blanco"
## [22] "Tostadas"
## [23] "Blanqueador de Ropa"
## [24] "Cuidado del Cabello"
## [25] "Papas Fritas"
## [26] "Frituras"
## [27] "Chocolates"
## [28] "Concentrados en Polvo"
## [29] "Cremas de Nieve"
## [30] "Aguas"
## [31] "Arroz"
## [32] "Productos sin Categoria"
## [33] "Gomas de Mazcar"
## [34] "Antojitos Mexicanos"
## [35] "Energizantes e Hidratantes"
## [36] "Limpieza de Calzado"
## [37] "Paletas"
## [38] "Cajetilla"
## [39] "Leche Saborizada"
## [40] "Surtido"
## [41] "Catsup"
## [42] "Platos y Vasos"
## [43] "Salsa para Spaguetti"
## [44] "Vinagre"
## [45] "Consome"
## [46] "Lavatrastes"
## [47] "Barras Energéticas"
## [48] "Papel Higiénico"
## [49] "Cacahuates"
## [50] "Chicharrón de Cerdo"
## [51] "Dulce Macizo"
## [52] "Sal Combinada"
## [53] "Chicharrón de Harina"
## [54] "Insecticidas y Venenos"
## [55] "Refrescos en Lata"
## [56] "Semillas"
## [57] "Frijol Bayo"
## [58] "Atoles"
## [59] "Mayonesa"
## [60] "Maíz"
## [61] "Saladas"
## [62] "Tradicionales"
## [63] "Lata"
## [64] "Aromatizantes de Ambiente"
## [65] "Atún"
## [66] "Nachos"
## [67] "Chocolate"
## [68] "Chiles Envasados"
## [69] "Mazapán"
## [70] "Lentejas"
## [71] "Cremas"
## [72] "Palomitas"
## [73] "Café"
## [74] "Pasta Dental"
## [75] "Desodorantes"
## [76] "Mantequilla"
## [77] "Tropicales"
## [78] "Pan de Barra Integral"
## [79] "Fideos, Spaguetti, Tallarines"
## [80] "Pastas de Figuritas"
## [81] "Salsa Picante"
## [82] "Chile Seco"
## [83] "Achiotes"
## [84] "Tortillas de Harina e Integrales"
## [85] "Pan Tostado y Crotones"
## [86] "Leche en Polvo"
## [87] "Mole"
## [88] "Verduras y Vegetales"
## [89] "Avena y Fibra"
## [90] "Leches y Cremas"
## [91] "Populares"
## [92] "Varios"
## [93] "Cepillo Dental"
## [94] "Frijoles en Lata"
## [95] "Sal"
## [96] "Cerillos"
## [97] "Chorizo"
## [98] "Empanizador"
## [99] "Azucarados"
## [100] "Jugos"
## [101] "Salchicha para Asar"
## [102] "Sopas Instantáneas"
## [103] "Mostaza"
## [104] "Salsa Botanera"
## [105] "Papillas"
## [106] "Comida para Perros"
## [107] "Charal"
## [108] "Camarón Seco"
## [109] "Palomitas para Microondas"
## [110] "Azúcar"
## [111] "Puré de Papa"
## [112] "Chiclosos"
## [113] "Pastillas"
## [114] "Sazonadores"
## [115] "Frijol Varios"
## [116] "Salchicha HotDog y Viena"
## [117] "Trigo"
## [118] "Servilletas"
## [119] "Harina para Pastel"
## [120] "Polvos"
## [121] "Polvo para Hornear"
## [122] "Fruta Acidulada"
## [123] "Cuidado de la Piel"
## [124] "Jamón de Cerdo"
## [125] "Maíz Rocero"
## [126] "Té helado"
## [127] "Tamarindos"
## [128] "Frutas Envasadas"
## [129] "Productos del mar Envasados"
## [130] "Cal Hidratada"
## [131] "Margarina"
## [132] "Avena"
## [133] "Mermeladas"
## [134] "Chocolate Macizo"
## [135] "Aderezo para Ensalada"
## [136] "Limpieza de Cocina"
## [137] "Mezclas para Cerveza"
## [138] "Miel"
## [139] "Botella"
## [140] "Hojuelas de Maíz"
## [141] "Saborizante para Leche"
## [142] "Comida para Gatos"
## [143] "Salsas Varias"
## [144] "Extractos"
## [145] "Gomas"
## [146] "Gelatinas en Polvo y Ligth"
## [147] "Salsa Casera"
## [148] "Cosméticos"
## [149] "Hot Cakes"
## [150] "Carne Seca"
## [151] "Artículos de Limpieza"
## [152] "Encendedores"
## [153] "Finas"
## [154] "Light"
## [155] "Te"
## [156] "Sustituto de Crema"
## [157] "Bombónes"
## [158] "Repostería"
## [159] "Fibras"
## [160] "Pistaches"
## [161] "Tendederos y Pinzas"
## [162] "Azúcar Glass"
## [163] "Pizzas"
## [164] "Flan en Polvo"
## [165] "Cucharas, Tenedores y Cuchillos"
## [166] "Tortillas de Maíz"
## [167] "Palillos de Madera"
## [168] "Aluminios y Envolturas"
## [169] "Especias"
## [170] "Pañal para Adulto"
## [171] "Helados"
## [172] "Mortadela"
## [173] "Frutas secas"
## [174] "Bicarbonato de Sodio"#Numero total de variables
#Aqui podemos ver el número total de variables
num_variables <- ncol(Abarrotes_Ventas_2)
view(num_variables)#Clasificación de Variables
#Con esta función clasificamos las variables
classify_variables <- function(Abarrotes_Ventas_2) {
ordinal_qualitative <- character(0)
nominal_qualitative <- character(0)
discrete_quantitative <- character(0)
continuous_quantitative <- character(0)
for (col in colnames(Abarrotes_Ventas_2)) {
col_data <- Abarrotes_Ventas_2[[col]]
if (is.ordered(col_data)) {
ordinal_qualitative <- c(ordinal_qualitative, col)
} else if (is.factor(col_data) || is.character(col_data)) {
nominal_qualitative <- c(nominal_qualitative, col)
} else if (is.numeric(col_data)) {
if (all(col_data %% 1 == 0)) {
discrete_quantitative <- c(discrete_quantitative, col)
} else {
continuous_quantitative <- c(continuous_quantitative, col)
}
}
}
return(list(ordinal_qualitative = ordinal_qualitative,
nominal_qualitative = nominal_qualitative,
discrete_quantitative = discrete_quantitative,
continuous_quantitative = continuous_quantitative))
}
classified_vars <- classify_variables(Abarrotes_Ventas_2)
cat("Ordinal Qualitative Variables:", classified_vars$ordinal_qualitative, "\n")## Ordinal Qualitative Variables:cat("Nominal Qualitative Variables:", classified_vars$nominal_qualitative, "\n")## Nominal Qualitative Variables: vcClaveTienda DescGiro Marca Fabricante Producto NombreDepartamento NombreFamilia NombreCategoria Estado Tipo ubicación Girocat("Discrete Quantitative Variables:", classified_vars$discrete_quantitative, "\n")## Discrete Quantitative Variables: Codigo Barras F.Ticket Mts 2cat("Continuous Quantitative Variables:", classified_vars$continuous_quantitative, "\n")## Continuous Quantitative Variables: Precio Ult.Costo Unidades#Numero total de NAs
#Así podemos ver cuantos NAs hay en la base de datos
num_nas <- sum(is.na(Abarrotes_Ventas_2))
view(num_nas)#Eliminación de NAs
#Así limpiamos la base de datos al quitar todos los NAs
abarrotes_limpio_1 <- na.omit(Abarrotes_Ventas_2)
view(abarrotes_limpio_1)#Base de datos limpia (Sin NAs)
#Como podemos ver, ya se limpiaron los NAs
num_nas_2 <- sum(is.na(abarrotes_limpio_1))
view(num_nas_2)#Reemplazo de NAs en columnas con valor numéricos por el MEAN
#Con esta funcion reemplazamos los NAs en columnas de variables numéricos con el MEAN
replace_nas_with_column_mean <- function(Abarrotes_Ventas_2) {
for (col in colnames(Abarrotes_Ventas_2)) {
col_data <- Abarrotes_Ventas_2[[col]]
if (is.numeric(col_data)) {
col_mean <- mean(col_data, na.rm = TRUE)
Abarrotes_Ventas_2[[col]][is.na(col_data)] <- col_mean
}
}
return(Abarrotes_Ventas_2)
}
abarrotes_limpio_2 <- replace_nas_with_column_mean(Abarrotes_Ventas_2)
view(abarrotes_limpio_2)#Base de datos limpia (Sin NAs EN COLUMNAS CON VALORES NUMERICOS)
#Sin embargo, podemos ver que no existen NAs en columas con variables numéricos
num_nas_3 <- sum(is.na(abarrotes_limpio_2))
view(num_nas_3)#Ver donde se concentran los NAs dentro de la base de datos
#Con esta funcion podemos ver que columnas dentro de la base de datos contienen NAs
columns_with_nas <- function(abarrotes_limpio_2) {
na_columns <- colnames(abarrotes_limpio_2)[colSums(is.na(abarrotes_limpio_2)) > 0]
return(na_columns)
}
columns_with_nas_list <- columns_with_nas(abarrotes_limpio_2)
print(columns_with_nas_list)## [1] "PLU"#Eliminación de columnas “PLU” y “Codigo de Barras”
#Eliminamos por completo la columna de "PLU," en la cual se concentran los NAs
columns_to_delete <- c("PLU", "Codigo Barras")
Abarrotes_Ventas_Limpio <- Abarrotes_Ventas_2[, !(colnames(Abarrotes_Ventas_2) %in% columns_to_delete)]
view(Abarrotes_Ventas_Limpio)#Contar precios de valor negativo
#Conteo de valores negativos dentro de la variable de "Precio"
count_negatives <- function(Abarrotes_Ventas_Limpio, precio) {
column <- Abarrotes_Ventas_Limpio[[precio]]
num_negatives <- sum(column < 0, na.rm = TRUE)
return(num_negatives)
}
precio <- "Precio"
num_negatives <- count_negatives(Abarrotes_Ventas_Limpio, precio)
cat("Cantidad de valores negaticos en", precio, ":", num_negatives, "\n")## Cantidad de valores negaticos en Precio : 147#Eliminación de entradas con valor negativo
data_sin_negativos <- Abarrotes_Ventas_Limpio[Abarrotes_Ventas_Limpio$Precio >= 0, ]
view(data_sin_negativos)#Verificación de que ya no hay valores negativos en la base de datos
count_negatives <- function(data_sin_negativos, precio) {
column <- data_sin_negativos[[precio]]
num_negatives <- sum(column < 0, na.rm = TRUE)
return(num_negatives)
}
precio <- "Precio"
num_negatives <- count_negatives(data_sin_negativos, precio)
cat("Cantidad de valores negaticos en", precio, ":", num_negatives, "\n")## Cantidad de valores negaticos en Precio : 0#Ver base de datos final
#conclusion #La limpieza de bases de datos es super importante para proyectos,trabajos y mas que nada toma dedecisiones ya que garantiza la integridad, precisión y confiabilidad de la información. Al eliminar datos duplicados, inexactos o desactualizados, se mejora la toma de decisiones, se reducen errores y se optimiza la eficiencia en tareas y procesos. Una base de datos limpia ofrece una base sólida para análisis, planificación y ejecución exitosa de proyectos, promoviendo resultados más efectivos y satisfactorios en diversas áreas de la vida.