Ruben Cabrera 2025-10-01
##
## 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## Rank Name Platform Year Genre Publisher NA_Sales
## 1 1 Wii Sports Wii 2006 Sports Nintendo 41.49
## 2 2 Super Mario Bros. NES 1985 Platform Nintendo 29.08
## 3 3 Mario Kart Wii Wii 2008 Racing Nintendo 15.85
## 4 4 Wii Sports Resort Wii 2009 Sports Nintendo 15.75
## 5 5 Pokemon Red/Pokemon Blue GB 1996 Role-Playing Nintendo 11.27
## 6 6 Tetris GB 1989 Puzzle Nintendo 23.20
## EU_Sales JP_Sales Other_Sales Global_Sales
## 1 29.02 3.77 8.46 82.74
## 2 3.58 6.81 0.77 40.24
## 3 12.88 3.79 3.31 35.82
## 4 11.01 3.28 2.96 33.00
## 5 8.89 10.22 1.00 31.37
## 6 2.26 4.22 0.58 30.26## 'data.frame': 16598 obs. of 11 variables:
## $ Rank : int 1 2 3 4 5 6 7 8 9 10 ...
## $ Name : chr "Wii Sports" "Super Mario Bros." "Mario Kart Wii" "Wii Sports Resort" ...
## $ Platform : chr "Wii" "NES" "Wii" "Wii" ...
## $ Year : chr "2006" "1985" "2008" "2009" ...
## $ Genre : chr "Sports" "Platform" "Racing" "Sports" ...
## $ Publisher : chr "Nintendo" "Nintendo" "Nintendo" "Nintendo" ...
## $ NA_Sales : num 41.5 29.1 15.8 15.8 11.3 ...
## $ EU_Sales : num 29.02 3.58 12.88 11.01 8.89 ...
## $ JP_Sales : num 3.77 6.81 3.79 3.28 10.22 ...
## $ Other_Sales : num 8.46 0.77 3.31 2.96 1 0.58 2.9 2.85 2.26 0.47 ...
## $ Global_Sales: num 82.7 40.2 35.8 33 31.4 ...## Rank Name Platform Year
## Min. : 1 Length:16598 Length:16598 Length:16598
## 1st Qu.: 4151 Class :character Class :character Class :character
## Median : 8300 Mode :character Mode :character Mode :character
## Mean : 8301
## 3rd Qu.:12450
## Max. :16600
## Genre Publisher NA_Sales EU_Sales
## Length:16598 Length:16598 Min. : 0.0000 Min. : 0.0000
## Class :character Class :character 1st Qu.: 0.0000 1st Qu.: 0.0000
## Mode :character Mode :character Median : 0.0800 Median : 0.0200
## Mean : 0.2647 Mean : 0.1467
## 3rd Qu.: 0.2400 3rd Qu.: 0.1100
## Max. :41.4900 Max. :29.0200
## JP_Sales Other_Sales Global_Sales
## Min. : 0.00000 Min. : 0.00000 Min. : 0.0100
## 1st Qu.: 0.00000 1st Qu.: 0.00000 1st Qu.: 0.0600
## Median : 0.00000 Median : 0.01000 Median : 0.1700
## Mean : 0.07778 Mean : 0.04806 Mean : 0.5374
## 3rd Qu.: 0.04000 3rd Qu.: 0.04000 3rd Qu.: 0.4700
## Max. :10.22000 Max. :10.57000 Max. :82.7400data.vg <- data.vg.raw
data.vg$Platform <- factor(data.vg$Platform)
data.vg$Year <- as.numeric(data.vg$Year)## Warning: NAs introduced by coercion## Rank Name Platform Year
## Min. : 1 Length:16598 DS :2163 Min. :1980
## 1st Qu.: 4151 Class :character PS2 :2161 1st Qu.:2003
## Median : 8300 Mode :character PS3 :1329 Median :2007
## Mean : 8301 Wii :1325 Mean :2006
## 3rd Qu.:12450 X360 :1265 3rd Qu.:2010
## Max. :16600 PSP :1213 Max. :2020
## (Other):7142 NA's :271
## Genre Publisher NA_Sales EU_Sales
## Length:16598 Length:16598 Min. : 0.0000 Min. : 0.0000
## Class :character Class :character 1st Qu.: 0.0000 1st Qu.: 0.0000
## Mode :character Mode :character Median : 0.0800 Median : 0.0200
## Mean : 0.2647 Mean : 0.1467
## 3rd Qu.: 0.2400 3rd Qu.: 0.1100
## Max. :41.4900 Max. :29.0200
##
## JP_Sales Other_Sales Global_Sales
## Min. : 0.00000 Min. : 0.00000 Min. : 0.0100
## 1st Qu.: 0.00000 1st Qu.: 0.00000 1st Qu.: 0.0600
## Median : 0.00000 Median : 0.01000 Median : 0.1700
## Mean : 0.07778 Mean : 0.04806 Mean : 0.5374
## 3rd Qu.: 0.04000 3rd Qu.: 0.04000 3rd Qu.: 0.4700
## Max. :10.22000 Max. :10.57000 Max. :82.7400
## ## 'data.frame': 16598 obs. of 11 variables:
## $ Rank : int 1 2 3 4 5 6 7 8 9 10 ...
## $ Name : chr "Wii Sports" "Super Mario Bros." "Mario Kart Wii" "Wii Sports Resort" ...
## $ Platform : chr "Wii" "NES" "Wii" "Wii" ...
## $ Year : chr "2006" "1985" "2008" "2009" ...
## $ Genre : chr "Sports" "Platform" "Racing" "Sports" ...
## $ Publisher : chr "Nintendo" "Nintendo" "Nintendo" "Nintendo" ...
## $ NA_Sales : num 41.5 29.1 15.8 15.8 11.3 ...
## $ EU_Sales : num 29.02 3.58 12.88 11.01 8.89 ...
## $ JP_Sales : num 3.77 6.81 3.79 3.28 10.22 ...
## $ Other_Sales : num 8.46 0.77 3.31 2.96 1 0.58 2.9 2.85 2.26 0.47 ...
## $ Global_Sales: num 82.7 40.2 35.8 33 31.4 ...## [1] "2006" "1985" "2008" "2009" "1996" "1989" "1984" "2005" "1999" "2007"
## [11] "2010" "2013" "2004" "1990" "1988" "2002" "2001" "2011" "1998" "2015"
## [21] "2012" "2014" "1992" "1997" "1993" "1994" "1982" "2003" "1986" "2000"
## [31] "N/A" "1995" "2016" "1991" "1981" "1987" "1980" "1983" "2020" "2017"## Rank Name Platform Year Genre
## 1 180 Madden NFL 2004 PS2 N/A Sports
## 2 378 FIFA Soccer 2004 PS2 N/A Sports
## 3 432 LEGO Batman: The Videogame Wii N/A Action
## 4 471 wwe Smackdown vs. Raw 2006 PS2 N/A Fighting
## 5 608 Space Invaders 2600 N/A Shooter
## 6 625 Rock Band X360 N/A Misc
## Publisher NA_Sales EU_Sales JP_Sales Other_Sales
## 1 Electronic Arts 4.26 0.26 0.01 0.71
## 2 Electronic Arts 0.59 2.36 0.04 0.51
## 3 Warner Bros. Interactive Entertainment 1.86 1.02 0.00 0.29
## 4 N/A 1.57 1.02 0.00 0.41
## 5 Atari 2.36 0.14 0.00 0.03
## 6 Electronic Arts 1.93 0.34 0.00 0.21
## Global_Sales
## 1 5.23
## 2 3.49
## 3 3.17
## 4 3.00
## 5 2.53
## 6 2.48## [1] Wii NES GB DS X360 PS3 PS2 SNES GBA 3DS PS4 N64 PS XB PC
## [16] 2600 PSP XOne GC WiiU GEN DC PSV SAT SCD WS NG TG16 3DO GG
## [31] PCFX
## 31 Levels: 2600 3DO 3DS DC DS GB GBA GC GEN GG N64 NES NG PC PCFX PS ... XOne## Rank Name Platform Year Genre Publisher NA_Sales EU_Sales JP_Sales
## 1 125 FIFA 15 PS4 2014 Sports Electronic Arts 0.79 4.29 0.05
## 2 220 FIFA 15 PS3 2014 Sports Electronic Arts 0.57 3.14 0.04
## 3 450 FIFA 15 X360 2014 Sports Electronic Arts 0.78 2.02 0.00
## 4 762 FIFA 15 XOne 2014 Sports Electronic Arts 0.60 1.41 0.00
## 5 2477 FIFA 15 PSV 2014 Sports Electronic Arts 0.13 0.48 0.04
## 6 2718 FIFA 15 Wii 2014 Sports Electronic Arts 0.24 0.46 0.00
## 7 4370 FIFA 15 3DS 2014 Sports Electronic Arts 0.09 0.33 0.00
## 8 5913 FIFA 15 PC 2014 Sports Electronic Arts 0.00 0.27 0.00
## Other_Sales Global_Sales
## 1 1.47 6.59
## 2 1.07 4.82
## 3 0.30 3.11
## 4 0.14 2.15
## 5 0.19 0.84
## 6 0.06 0.76
## 7 0.03 0.45
## 8 0.03 0.30
Calculemos la proporcion de los datos missings Esto nos ayudará a decidir la estrategia (borrar vs. llenar)
## [1] "NA por columna:"## Rank Name Platform Year Genre Publisher
## 0 0 0 271 0 0
## NA_Sales EU_Sales JP_Sales Other_Sales Global_Sales
## 0 0 0 0 0# Porcentaje de NA por columna
porcentaje_na <- colMeans(is.na(data.vg)) * 100
print("Porcentaje de NA por columna:")## [1] "Porcentaje de NA por columna:"## Rank Name Platform Year Genre Publisher
## 0.00 0.00 0.00 1.63 0.00 0.00
## NA_Sales EU_Sales JP_Sales Other_Sales Global_Sales
## 0.00 0.00 0.00 0.00 0.00## [1] "Nintendo" "Microsoft Game Studios"
## [3] "Take-Two Interactive" "Sony Computer Entertainment"
## [5] "Activision" "Ubisoft"## [1] Rank Name Platform Year Genre
## [6] Publisher NA_Sales EU_Sales JP_Sales Other_Sales
## [11] Global_Sales
## <0 rows> (or 0-length row.names)A año le faltan 271 valores (aprox 1,63%). Dado que este porcentajee es muy pequeño, la estrategia más segura y sencilla es eliminar estas filas. Intentar ‘adivinar’ (imputar) el año o la editorial podría generar interferencias y llevar a conclusiones incorrectas. Queremos que nuestro análisis se base en datos completos y precisos. Usaremos .dropna() para eliminar las filas que contienen valores NaN en las columnas especificadas.
## [1] "DataFrame original:"## Rank Name Platform Year Genre Publisher NA_Sales
## 1 1 Wii Sports Wii 2006 Sports Nintendo 41.49
## 2 2 Super Mario Bros. NES 1985 Platform Nintendo 29.08
## 3 3 Mario Kart Wii Wii 2008 Racing Nintendo 15.85
## 4 4 Wii Sports Resort Wii 2009 Sports Nintendo 15.75
## 5 5 Pokemon Red/Pokemon Blue GB 1996 Role-Playing Nintendo 11.27
## 6 6 Tetris GB 1989 Puzzle Nintendo 23.20
## EU_Sales JP_Sales Other_Sales Global_Sales
## 1 29.02 3.77 8.46 82.74
## 2 3.58 6.81 0.77 40.24
## 3 12.88 3.79 3.31 35.82
## 4 11.01 3.28 2.96 33.00
## 5 8.89 10.22 1.00 31.37
## 6 2.26 4.22 0.58 30.26## Filas originales: 16598# Método 1: na.omit() - Elimina filas con cualquier NA
df_sin_na <- na.omit(data.vg)
print("Con na.omit():")## [1] "Con na.omit():"## Rank Name Platform Year Genre Publisher NA_Sales
## 1 1 Wii Sports Wii 2006 Sports Nintendo 41.49
## 2 2 Super Mario Bros. NES 1985 Platform Nintendo 29.08
## 3 3 Mario Kart Wii Wii 2008 Racing Nintendo 15.85
## 4 4 Wii Sports Resort Wii 2009 Sports Nintendo 15.75
## 5 5 Pokemon Red/Pokemon Blue GB 1996 Role-Playing Nintendo 11.27
## 6 6 Tetris GB 1989 Puzzle Nintendo 23.20
## EU_Sales JP_Sales Other_Sales Global_Sales
## 1 29.02 3.77 8.46 82.74
## 2 3.58 6.81 0.77 40.24
## 3 12.88 3.79 3.31 35.82
## 4 11.01 3.28 2.96 33.00
## 5 8.89 10.22 1.00 31.37
## 6 2.26 4.22 0.58 30.26## Filas después de na.omit(): 16327# Método 2: complete.cases() - Más control
df_completo <- data.vg[complete.cases(data.vg), ]
print("Con complete.cases():")## [1] "Con complete.cases():"## Rank Name Platform Year Genre Publisher NA_Sales
## 1 1 Wii Sports Wii 2006 Sports Nintendo 41.49
## 2 2 Super Mario Bros. NES 1985 Platform Nintendo 29.08
## 3 3 Mario Kart Wii Wii 2008 Racing Nintendo 15.85
## 4 4 Wii Sports Resort Wii 2009 Sports Nintendo 15.75
## 5 5 Pokemon Red/Pokemon Blue GB 1996 Role-Playing Nintendo 11.27
## 6 6 Tetris GB 1989 Puzzle Nintendo 23.20
## EU_Sales JP_Sales Other_Sales Global_Sales
## 1 29.02 3.77 8.46 82.74
## 2 3.58 6.81 0.77 40.24
## 3 12.88 3.79 3.31 35.82
## 4 11.01 3.28 2.96 33.00
## 5 8.89 10.22 1.00 31.37
## 6 2.26 4.22 0.58 30.26## Filas después de complete.cases(): 16327## [1] 16327 11## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.0100 0.0600 0.1700 0.5402 0.4800 82.7400
set.seed(13)
N <- dim(data.vg)[1]
indices_muestra <- sample(1:N, 200, replace = TRUE)
data.muestra <- data.vg[indices_muestra,];head(data.muestra)## Rank Name
## 14002 14003 Age of Mythology: The Titans
## 16400 16402 The Technomancer
## 9296 9297 Let's Play Ballerina
## 6079 6080 Penguin no Mondai: Saikyou Penguin Densetsu! A Penguin's Troubles
## 14121 14122 Radiant Silvergun
## 726 727 New Super Luigi U
## Platform Year Genre Publisher NA_Sales EU_Sales
## 14002 PC 2003 Strategy Microsoft Game Studios 0.01 0.02
## 16400 PC 2016 Role-Playing Focus Home Interactive 0.00 0.01
## 9296 DS 2010 Sports Deep Silver 0.13 0.00
## 6079 DS 2008 Adventure Konami Digital Entertainment 0.00 0.00
## 14121 SAT 1998 Shooter ESP 0.00 0.00
## 726 WiiU 2013 Platform Nintendo 1.27 0.62
## JP_Sales Other_Sales Global_Sales
## 14002 0.00 0.00 0.04
## 16400 0.00 0.00 0.01
## 9296 0.00 0.01 0.14
## 6079 0.29 0.00 0.29
## 14121 0.03 0.00 0.03
## 726 0.18 0.16 2.22## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.010 0.070 0.185 0.386 0.365 6.430## [1] Wii NES GB DS X360 PS3 PS2 SNES GBA 3DS PS4 N64 PS XB PC
## [16] 2600 PSP XOne GC WiiU GEN DC PSV SAT SCD WS NG TG16 3DO GG
## [31] PCFX
## 31 Levels: 2600 3DO 3DS DC DS GB GBA GC GEN GG N64 NES NG PC PCFX PS ... XOneGraficos
df <- filter(data.vg,NA_Sales<2.5)
# Histograma agrupado por categoría
ggplot( df , aes(x = NA_Sales)) +
geom_histogram(position = "dodge", alpha = 0.7, bins = 20) +
labs(title = "Histograma Agrupado de Ventas por Año",
x = "Ventas",
y = "Frecuencia") +
theme_minimal()