Importamos los datos
animacion <- read.csv("shows.csv", sep = ";")0.15 Recodificación de variables
colnames(animacion)## [1] "Ranking" "Name" "Year" "Minutes" "genre" "Rating" "Votes"names(animacion) <- c("Puesto","Nombre","Año","Duracion","Género","Puntaje","Votos")
names(animacion)## [1] "Puesto" "Nombre" "Año" "Duracion" "Género" "Puntaje" "Votos" # Eliminamos valores NA o nulos
animacion <- na.omit(animacion)
animacion## Puesto Nombre Año Duracion
## 1 1 Big Mouth (2017– ) 30 min
## 2 2 The Bad Guys -2022 100 min
## 3 3 Chainsaw Man (2022– )
## 4 4 Rick and Morty (2013– ) 23 min
## 6 6 Zootopia+ (2022– )
## 7 7 Star Wars: Tales of the Jedi (2022– ) 15 min
## 8 8 One Piece Film: Red -2022 115 min
## 9 9 Family Guy (1999– ) 22 min
## 10 10 Wendell & Wild -2022 105 min
## 11 11 The Simpsons (1989– ) 22 min
## 12 12 The Dragon Prince (2018– ) 26 min
## 13 13 Attack on Titan (2013–2023) 24 min
## 14 14 Pinocchio (II) (2022) 117 min
## 15 15 One Piece (1999– ) 24 min
## 16 16 Bleach: Thousand-Year Blood War (2022– ) 24 min
## 17 17 Lyle, Lyle, Crocodile -2022 106 min
## 18 18 Miraculous: Tales of Ladybug & Cat Noir (2015– ) 20 min
## 20 20 Sing 2 -2021 110 min
## 21 21 Cyberpunk: Edgerunners (2022– ) 24 min
## 22 22 My Hero Academia (2016– ) 24 min
## 23 23 Super Pets -2022 105 min
## 24 24 BoJack Horseman (2014–2020) 25 min
## 25 25 Arcane (2021– ) 41 min
## 26 26 Bob's Burgers (2011– ) 22 min
## 27 27 Zootropolis -2016 108 min
## 28 28 Enchanted -2007 107 min
## 29 29 South Park (1997– ) 22 min
## 30 30 The Nightmare Before Christmas -1993 76 min
## 31 31 Star Wars: The Clone Wars (2008–2020) 23 min
## 32 32 Demon Slayer: Kimetsu no Yaiba (2019– ) 24 min
## 33 33 Love, Death & Robots (2019– ) 15 min
## 35 35 Encanto -2021 102 min
## 36 36 Avatar: The Last Airbender (2005–2008) 23 min
## 37 37 The Soccer Football Movie -2022 73 min
## 38 38 Batman: The Animated Series (1992–1995) 23 min
## 39 39 Archer (2009– ) 22 min
## 40 40 Mob Psycho 100 (2016– ) 24 min
## 41 41 Minions: The Rise of Gru -2022 87 min
## 42 42 Bleach (2004–2012) 24 min
## 43 43 Coco (I) (2017) 105 min
## 44 44 Sing -2016 108 min
## 45 45 American Dad! (2005– ) 22 min
## 46 46 Futurama (1999–2023) 22 min
## 47 47 Bluey (2018– ) 7 min
## 48 48 The Lion King -1994 88 min
## 49 49 Invincible (2021– ) 50 min
## 50 50 SPY×FAMILY (2022– ) 24 min
## Género Puntaje Votos
## 1 Animation, Comedy, Romance 7.9 79301
## 2 Animation, Adventure, Comedy 6.8 37335
## 3 Animation, Action, Adventure 8.8 10613
## 4 Animation, Adventure, Comedy 9.1 515315
## 6 Animation, Short, Adventure 6.8 1232
## 7 Animation, Short, Action 8.4 15691
## 8 Animation, Action, Adventure 6.9 6269
## 9 Animation, Comedy 8.2 338447
## 10 Animation, Adventure, Comedy 6.5 5759
## 11 Animation, Comedy 8.7 406290
## 12 Animation, Action, Adventure 8.3 23460
## 13 Animation, Action, Adventure 9.0 369274
## 14 Animation, Drama, Family 8.0 539
## 15 Animation, Action, Adventure 8.9 124898
## 16 Animation, Action, Adventure 9.4 8182
## 17 Animation, Adventure, Comedy 6.3 2548
## 18 Animation, Action, Adventure 7.6 11645
## 20 Animation, Adventure, Comedy 7.4 67960
## 21 Animation, Action, Adventure 8.4 41881
## 22 Animation, Action, Adventure 8.4 61931
## 23 Animation, Action, Adventure 7.3 60494
## 24 Animation, Comedy, Drama 8.8 156050
## 25 Animation, Action, Adventure 9.0 203013
## 26 Animation, Comedy 8.2 81343
## 27 Animation, Adventure, Comedy 8.0 497187
## 28 Animation, Adventure, Comedy 7.1 200274
## 29 Animation, Comedy 8.7 368653
## 30 Animation, Family, Fantasy 7.9 339067
## 31 Animation, Action, Adventure 8.4 96880
## 32 Animation, Action, Adventure 8.7 101339
## 33 Animation, Short, Action 8.4 168071
## 35 Animation, Comedy, Family 7.2 218233
## 36 Animation, Action, Adventure 9.3 313079
## 37 Animation, Comedy, Family 3.2 355
## 38 Animation, Action, Adventure 9.0 103990
## 39 Animation, Action, Comedy 8.6 155029
## 40 Animation, Action, Comedy 8.6 31786
## 41 Animation, Adventure, Comedy 6.6 60842
## 42 Animation, Action, Adventure 8.2 55915
## 43 Animation, Adventure, Comedy 8.4 503181
## 44 Animation, Comedy, Family 7.1 170727
## 45 Animation, Comedy 7.4 128206
## 46 Animation, Adventure, Comedy 8.5 237826
## 47 Animation, Family 9.7 10061
## 48 Animation, Adventure, Drama 8.5 1052286
## 49 Animation, Action, Adventure 8.7 135460
## 50 Animation, Action, Comedy 8.6 227960.16 Primera forma: Manual
X: Votos Y: Puntaje
recodificacion de variables: En nuestra base de datos original en la columna votos nos salia los valores con coma, para poder trabjar con esa columna, tendriamos usar el siguiente codigo:
bd <- gsub(","," ", animacion$Votos, fixed = T)
Votos = as.numeric(bd)pero decidimos cambiar los valores de forma manual en el archivo csv de nuestra base de datos
# Relacion lineal entre las variables
plot(animacion)
#coeficiente de correlacion
cor(animacion$Votos, animacion$Puntaje)## [1] 0.2676261prom_x <- mean(animacion$Votos)
prom_x## [1] 161717.3prom_y <- mean(animacion$Puntaje)
prom_y## [1] 8.040426# sum((xi-prom_X)(yi-prom_Y))
numerador <- sum((animacion$Votos-prom_x)*(animacion$Puntaje-prom_y))
numerador## [1] 2685379# sum(xi_prom_x)^2
denominador <- sum((animacion$Votos-prom_x)^2)
denominador## [1] 1.818912e+12# b1
b1 <- numerador/denominador
b1## [1] 1.476366e-06#b0 = prom_y - b1*prom_x
b0 <- prom_y - b1*prom_x
b0## [1] 7.801672# Modelo ajustado
# Modelo: Puntaje = bo + b1*X
# Modelo: Puntaje = 7.801672 + 1.476366e-06*X
puntaje_pred <- b0+b1*animacion$Votos
puntaje_pred## [1] 7.918749 7.856792 7.817340 8.562465 7.803491 7.824837 7.810927 8.301343
## [9] 7.810174 8.401504 7.836307 8.346855 7.802467 7.986067 7.813751 7.805433
## [17] 7.818864 7.902005 7.863503 7.893104 7.890983 8.032059 8.101393 7.921764
## [25] 8.535701 8.097349 8.345938 8.302259 7.944702 7.951285 8.049806 8.123863
## [33] 8.263891 7.802196 7.955199 8.030551 7.848599 7.891497 7.884223 8.544551
## [41] 8.053727 7.990951 8.152790 7.816525 9.355231 8.001660 7.835327# JUntar los predichos con la data original
cbind(animacion, puntaje_pred)## Puesto Nombre Año Duracion
## 1 1 Big Mouth (2017– ) 30 min
## 2 2 The Bad Guys -2022 100 min
## 3 3 Chainsaw Man (2022– )
## 4 4 Rick and Morty (2013– ) 23 min
## 6 6 Zootopia+ (2022– )
## 7 7 Star Wars: Tales of the Jedi (2022– ) 15 min
## 8 8 One Piece Film: Red -2022 115 min
## 9 9 Family Guy (1999– ) 22 min
## 10 10 Wendell & Wild -2022 105 min
## 11 11 The Simpsons (1989– ) 22 min
## 12 12 The Dragon Prince (2018– ) 26 min
## 13 13 Attack on Titan (2013–2023) 24 min
## 14 14 Pinocchio (II) (2022) 117 min
## 15 15 One Piece (1999– ) 24 min
## 16 16 Bleach: Thousand-Year Blood War (2022– ) 24 min
## 17 17 Lyle, Lyle, Crocodile -2022 106 min
## 18 18 Miraculous: Tales of Ladybug & Cat Noir (2015– ) 20 min
## 20 20 Sing 2 -2021 110 min
## 21 21 Cyberpunk: Edgerunners (2022– ) 24 min
## 22 22 My Hero Academia (2016– ) 24 min
## 23 23 Super Pets -2022 105 min
## 24 24 BoJack Horseman (2014–2020) 25 min
## 25 25 Arcane (2021– ) 41 min
## 26 26 Bob's Burgers (2011– ) 22 min
## 27 27 Zootropolis -2016 108 min
## 28 28 Enchanted -2007 107 min
## 29 29 South Park (1997– ) 22 min
## 30 30 The Nightmare Before Christmas -1993 76 min
## 31 31 Star Wars: The Clone Wars (2008–2020) 23 min
## 32 32 Demon Slayer: Kimetsu no Yaiba (2019– ) 24 min
## 33 33 Love, Death & Robots (2019– ) 15 min
## 35 35 Encanto -2021 102 min
## 36 36 Avatar: The Last Airbender (2005–2008) 23 min
## 37 37 The Soccer Football Movie -2022 73 min
## 38 38 Batman: The Animated Series (1992–1995) 23 min
## 39 39 Archer (2009– ) 22 min
## 40 40 Mob Psycho 100 (2016– ) 24 min
## 41 41 Minions: The Rise of Gru -2022 87 min
## 42 42 Bleach (2004–2012) 24 min
## 43 43 Coco (I) (2017) 105 min
## 44 44 Sing -2016 108 min
## 45 45 American Dad! (2005– ) 22 min
## 46 46 Futurama (1999–2023) 22 min
## 47 47 Bluey (2018– ) 7 min
## 48 48 The Lion King -1994 88 min
## 49 49 Invincible (2021– ) 50 min
## 50 50 SPY×FAMILY (2022– ) 24 min
## Género Puntaje Votos puntaje_pred
## 1 Animation, Comedy, Romance 7.9 79301 7.918749
## 2 Animation, Adventure, Comedy 6.8 37335 7.856792
## 3 Animation, Action, Adventure 8.8 10613 7.817340
## 4 Animation, Adventure, Comedy 9.1 515315 8.562465
## 6 Animation, Short, Adventure 6.8 1232 7.803491
## 7 Animation, Short, Action 8.4 15691 7.824837
## 8 Animation, Action, Adventure 6.9 6269 7.810927
## 9 Animation, Comedy 8.2 338447 8.301343
## 10 Animation, Adventure, Comedy 6.5 5759 7.810174
## 11 Animation, Comedy 8.7 406290 8.401504
## 12 Animation, Action, Adventure 8.3 23460 7.836307
## 13 Animation, Action, Adventure 9.0 369274 8.346855
## 14 Animation, Drama, Family 8.0 539 7.802467
## 15 Animation, Action, Adventure 8.9 124898 7.986067
## 16 Animation, Action, Adventure 9.4 8182 7.813751
## 17 Animation, Adventure, Comedy 6.3 2548 7.805433
## 18 Animation, Action, Adventure 7.6 11645 7.818864
## 20 Animation, Adventure, Comedy 7.4 67960 7.902005
## 21 Animation, Action, Adventure 8.4 41881 7.863503
## 22 Animation, Action, Adventure 8.4 61931 7.893104
## 23 Animation, Action, Adventure 7.3 60494 7.890983
## 24 Animation, Comedy, Drama 8.8 156050 8.032059
## 25 Animation, Action, Adventure 9.0 203013 8.101393
## 26 Animation, Comedy 8.2 81343 7.921764
## 27 Animation, Adventure, Comedy 8.0 497187 8.535701
## 28 Animation, Adventure, Comedy 7.1 200274 8.097349
## 29 Animation, Comedy 8.7 368653 8.345938
## 30 Animation, Family, Fantasy 7.9 339067 8.302259
## 31 Animation, Action, Adventure 8.4 96880 7.944702
## 32 Animation, Action, Adventure 8.7 101339 7.951285
## 33 Animation, Short, Action 8.4 168071 8.049806
## 35 Animation, Comedy, Family 7.2 218233 8.123863
## 36 Animation, Action, Adventure 9.3 313079 8.263891
## 37 Animation, Comedy, Family 3.2 355 7.802196
## 38 Animation, Action, Adventure 9.0 103990 7.955199
## 39 Animation, Action, Comedy 8.6 155029 8.030551
## 40 Animation, Action, Comedy 8.6 31786 7.848599
## 41 Animation, Adventure, Comedy 6.6 60842 7.891497
## 42 Animation, Action, Adventure 8.2 55915 7.884223
## 43 Animation, Adventure, Comedy 8.4 503181 8.544551
## 44 Animation, Comedy, Family 7.1 170727 8.053727
## 45 Animation, Comedy 7.4 128206 7.990951
## 46 Animation, Adventure, Comedy 8.5 237826 8.152790
## 47 Animation, Family 9.7 10061 7.816525
## 48 Animation, Adventure, Drama 8.5 1052286 9.355231
## 49 Animation, Action, Adventure 8.7 135460 8.001660
## 50 Animation, Action, Comedy 8.6 22796 7.835327# Residuales
residuales <- animacion$Puntaje-puntaje_pred
residuales## [1] -0.01874894 -1.05679177 0.98265967 0.53753495 -1.00349054 0.57516269
## [7] -0.91092700 -0.10134320 -1.31017405 0.29849572 0.46369280 0.65314487
## [13] 0.19753258 0.91393322 1.58624872 -1.50543344 -0.21886394 -0.50200547
## [19] 0.53649667 0.50689554 -0.59098293 0.76794147 0.89860691 0.27823633
## [25] -0.53570150 -0.99734932 0.35406169 -0.40225855 0.45529803 0.74871492
## [31] 0.35019408 -0.92386338 1.03610924 -4.60219577 1.04480107 0.56944884
## [37] 0.75140058 -1.29149670 0.31577735 -0.14455083 -0.95372715 -0.59095060
## [43] 0.34721019 1.88347463 -0.85523063 0.69833984 0.76467311cbind(animacion, puntaje_pred, residuales)## Puesto Nombre Año Duracion
## 1 1 Big Mouth (2017– ) 30 min
## 2 2 The Bad Guys -2022 100 min
## 3 3 Chainsaw Man (2022– )
## 4 4 Rick and Morty (2013– ) 23 min
## 6 6 Zootopia+ (2022– )
## 7 7 Star Wars: Tales of the Jedi (2022– ) 15 min
## 8 8 One Piece Film: Red -2022 115 min
## 9 9 Family Guy (1999– ) 22 min
## 10 10 Wendell & Wild -2022 105 min
## 11 11 The Simpsons (1989– ) 22 min
## 12 12 The Dragon Prince (2018– ) 26 min
## 13 13 Attack on Titan (2013–2023) 24 min
## 14 14 Pinocchio (II) (2022) 117 min
## 15 15 One Piece (1999– ) 24 min
## 16 16 Bleach: Thousand-Year Blood War (2022– ) 24 min
## 17 17 Lyle, Lyle, Crocodile -2022 106 min
## 18 18 Miraculous: Tales of Ladybug & Cat Noir (2015– ) 20 min
## 20 20 Sing 2 -2021 110 min
## 21 21 Cyberpunk: Edgerunners (2022– ) 24 min
## 22 22 My Hero Academia (2016– ) 24 min
## 23 23 Super Pets -2022 105 min
## 24 24 BoJack Horseman (2014–2020) 25 min
## 25 25 Arcane (2021– ) 41 min
## 26 26 Bob's Burgers (2011– ) 22 min
## 27 27 Zootropolis -2016 108 min
## 28 28 Enchanted -2007 107 min
## 29 29 South Park (1997– ) 22 min
## 30 30 The Nightmare Before Christmas -1993 76 min
## 31 31 Star Wars: The Clone Wars (2008–2020) 23 min
## 32 32 Demon Slayer: Kimetsu no Yaiba (2019– ) 24 min
## 33 33 Love, Death & Robots (2019– ) 15 min
## 35 35 Encanto -2021 102 min
## 36 36 Avatar: The Last Airbender (2005–2008) 23 min
## 37 37 The Soccer Football Movie -2022 73 min
## 38 38 Batman: The Animated Series (1992–1995) 23 min
## 39 39 Archer (2009– ) 22 min
## 40 40 Mob Psycho 100 (2016– ) 24 min
## 41 41 Minions: The Rise of Gru -2022 87 min
## 42 42 Bleach (2004–2012) 24 min
## 43 43 Coco (I) (2017) 105 min
## 44 44 Sing -2016 108 min
## 45 45 American Dad! (2005– ) 22 min
## 46 46 Futurama (1999–2023) 22 min
## 47 47 Bluey (2018– ) 7 min
## 48 48 The Lion King -1994 88 min
## 49 49 Invincible (2021– ) 50 min
## 50 50 SPY×FAMILY (2022– ) 24 min
## Género Puntaje Votos puntaje_pred residuales
## 1 Animation, Comedy, Romance 7.9 79301 7.918749 -0.01874894
## 2 Animation, Adventure, Comedy 6.8 37335 7.856792 -1.05679177
## 3 Animation, Action, Adventure 8.8 10613 7.817340 0.98265967
## 4 Animation, Adventure, Comedy 9.1 515315 8.562465 0.53753495
## 6 Animation, Short, Adventure 6.8 1232 7.803491 -1.00349054
## 7 Animation, Short, Action 8.4 15691 7.824837 0.57516269
## 8 Animation, Action, Adventure 6.9 6269 7.810927 -0.91092700
## 9 Animation, Comedy 8.2 338447 8.301343 -0.10134320
## 10 Animation, Adventure, Comedy 6.5 5759 7.810174 -1.31017405
## 11 Animation, Comedy 8.7 406290 8.401504 0.29849572
## 12 Animation, Action, Adventure 8.3 23460 7.836307 0.46369280
## 13 Animation, Action, Adventure 9.0 369274 8.346855 0.65314487
## 14 Animation, Drama, Family 8.0 539 7.802467 0.19753258
## 15 Animation, Action, Adventure 8.9 124898 7.986067 0.91393322
## 16 Animation, Action, Adventure 9.4 8182 7.813751 1.58624872
## 17 Animation, Adventure, Comedy 6.3 2548 7.805433 -1.50543344
## 18 Animation, Action, Adventure 7.6 11645 7.818864 -0.21886394
## 20 Animation, Adventure, Comedy 7.4 67960 7.902005 -0.50200547
## 21 Animation, Action, Adventure 8.4 41881 7.863503 0.53649667
## 22 Animation, Action, Adventure 8.4 61931 7.893104 0.50689554
## 23 Animation, Action, Adventure 7.3 60494 7.890983 -0.59098293
## 24 Animation, Comedy, Drama 8.8 156050 8.032059 0.76794147
## 25 Animation, Action, Adventure 9.0 203013 8.101393 0.89860691
## 26 Animation, Comedy 8.2 81343 7.921764 0.27823633
## 27 Animation, Adventure, Comedy 8.0 497187 8.535701 -0.53570150
## 28 Animation, Adventure, Comedy 7.1 200274 8.097349 -0.99734932
## 29 Animation, Comedy 8.7 368653 8.345938 0.35406169
## 30 Animation, Family, Fantasy 7.9 339067 8.302259 -0.40225855
## 31 Animation, Action, Adventure 8.4 96880 7.944702 0.45529803
## 32 Animation, Action, Adventure 8.7 101339 7.951285 0.74871492
## 33 Animation, Short, Action 8.4 168071 8.049806 0.35019408
## 35 Animation, Comedy, Family 7.2 218233 8.123863 -0.92386338
## 36 Animation, Action, Adventure 9.3 313079 8.263891 1.03610924
## 37 Animation, Comedy, Family 3.2 355 7.802196 -4.60219577
## 38 Animation, Action, Adventure 9.0 103990 7.955199 1.04480107
## 39 Animation, Action, Comedy 8.6 155029 8.030551 0.56944884
## 40 Animation, Action, Comedy 8.6 31786 7.848599 0.75140058
## 41 Animation, Adventure, Comedy 6.6 60842 7.891497 -1.29149670
## 42 Animation, Action, Adventure 8.2 55915 7.884223 0.31577735
## 43 Animation, Adventure, Comedy 8.4 503181 8.544551 -0.14455083
## 44 Animation, Comedy, Family 7.1 170727 8.053727 -0.95372715
## 45 Animation, Comedy 7.4 128206 7.990951 -0.59095060
## 46 Animation, Adventure, Comedy 8.5 237826 8.152790 0.34721019
## 47 Animation, Family 9.7 10061 7.816525 1.88347463
## 48 Animation, Adventure, Drama 8.5 1052286 9.355231 -0.85523063
## 49 Animation, Action, Adventure 8.7 135460 8.001660 0.69833984
## 50 Animation, Action, Comedy 8.6 22796 7.835327 0.76467311# Supuestos
plot(residuales, animacion$Puntaje)
# Normalidad
hist(residuales)
## Pueba de normalidad
# H0: La variable en estudio tiene (se aproxima) un comportamiento normal
# H1: La variable en estudio no tiene (no se aproxima) un comportamiento normal
shapiro.test(residuales)##
## Shapiro-Wilk normality test
##
## data: residuales
## W = 0.86259, p-value = 5.63e-05