Nube de datos: factor

Mostrando entradas con la etiqueta factor. Mostrar todas las entradas

2019-12-28

How to convert a continuous variable to discrete in R?

Problem

We want to convert continuous variable to discrete in R:

'Create a new qualitative variable, called Elite, by binning the Top10perc variable. We are going to divide universities into two groups based on whether or not the proportion of students coming from the top 10% of their high school classes exceeds 50%'.

library(ISLR)
library(tidyverse)
glimpse(College)

Observations: 777
Variables: 18
$ Private      Yes, Yes, Yes, Yes, Yes, Yes, Yes, Yes, Yes, Yes, Yes, Ye...
$ Apps         1660, 2186, 1428, 417, 193, 587, 353, 1899, 1038, 582, 17...
$ Accept       1232, 1924, 1097, 349, 146, 479, 340, 1720, 839, 498, 142...
$ Enroll       721, 512, 336, 137, 55, 158, 103, 489, 227, 172, 472, 484...
$ Top10perc    23, 16, 22, 60, 16, 38, 17, 37, 30, 21, 37, 44, 38, 44, 2...
$ Top25perc    52, 29, 50, 89, 44, 62, 45, 68, 63, 44, 75, 77, 64, 73, 4...
$ F.Undergrad  2885, 2683, 1036, 510, 249, 678, 416, 1594, 973, 799, 183...
$ P.Undergrad  537, 1227, 99, 63, 869, 41, 230, 32, 306, 78, 110, 44, 63...
$ Outstate     7440, 12280, 11250, 12960, 7560, 13500, 13290, 13868, 155...
$ Room.Board   3300, 6450, 3750, 5450, 4120, 3335, 5720, 4826, 4400, 338...
$ Books        450, 750, 400, 450, 800, 500, 500, 450, 300, 660, 500, 40...
$ Personal     2200, 1500, 1165, 875, 1500, 675, 1500, 850, 500, 1800, 6...
$ PhD          70, 29, 53, 92, 76, 67, 90, 89, 79, 40, 82, 73, 60, 79, 3...
$ Terminal     78, 30, 66, 97, 72, 73, 93, 100, 84, 41, 88, 91, 84, 87, ...
$ S.F.Ratio    18.1, 12.2, 12.9, 7.7, 11.9, 9.4, 11.5, 13.7, 11.3, 11.5,...
$ perc.alumni  12, 16, 30, 37, 2, 11, 26, 37, 23, 15, 31, 41, 21, 32, 26...
$ Expend       7041, 10527, 8735, 19016, 10922, 9727, 8861, 11487, 11644...
$ Grad.Rate    60, 56, 54, 59, 15, 55, 63, 73, 80, 52, 73, 76, 74, 68, 5...

Solution

Option 1: form ISLR's book.

Elite = rep("No", nrow(College))
Elite[College$Top10perc > 50] = "Yes"
Elite <- as.factor(Elite)
college <- data.frame(College,  Elite)
summary(college[, c("Top10perc", "Elite")])

  Top10perc     Elite    
 Min.   : 1.00   No :699  
 1st Qu.:15.00   Yes: 78  
 Median :23.00            
 Mean   :27.56            
 3rd Qu.:35.00            
 Max.   :96.00

Option 2: ifelse from base package and dplyr

# base 
College$Elite <- factor(ifelse(College$Top10perc > 50, "Yes", "No"))
# dplyr
library(dplyr)
College <-
  college %>%
  mutate(Elite = factor(ifelse(College$Top10perc > 50, "Yes", "No")))

Option 3: creating a logical vector.

There are multiple options. I show two examples.

college$Elite <- transform(College, Elite = Top10perc > 50)
College$Elite <- College$Top10perc > 50

References

An Introduction to Statistical Learning - Page 54.

From 'An Introduction to Statistical Learning' (ISLR), page 54.

2019-05-03

Drop unused levels from a factor in R

Problem

If we filter a data frame containing a factor and then perform any operation, such as creating a contingency table, R will still show the unused levels. Subsetting does not in general drop unused levels.

df <- data.frame(name = c("a", "a", "a", "b", "b", "c", "c", "c", "c"), x = 1:9)
library(dplyr)
aa <-  df %>%
  group_by(name) %>%
  filter(n() < 4) %>% 
  droplevels()
table(aa$name)

In our example, the level c is still included in the results. We'd like to remove it and display only the used levels a and b.

# Resultado
a b c 
3 2 0
# Resultado deseado
a b 
3 2

Solution

There are two alternatives, the function droplevels or factor.

table(droplevels(aa$name))
table(factor(aa$name))

If we are using dplyr and the pipe operator:

aa <-  df %>%
  group_by(name) %>%
  filter(n() < 4) %>% 
  droplevels()
table(aa$name)

# Better still
df %>%
  group_by(name) %>%
  filter(n() < 4) %>% 
  droplevels() %>% 
  {table(.$name)}

Spanish version

References

2018-12-08

Discretización de variables en R

Problema

Deseamos discretizar una variable, es decir, convertir una variable continua en discreta. Utilizamos el conjunto de datos College del paquete ISLR. Crearemos una nueva variable cualitativa llamada Elite, discretizando la variable Top10perc. Vamos a dividir las universidades en dos grupos basados en si la proporción de nuevos estudiantes provienen de entre el 10% de los mejores alumnos de sus institutos excede o no el 50%.

library(ISLR)
library(tidyverse)
glimpse(College)

Observations: 777
Variables: 18
$ Private      Yes, Yes, Yes, Yes, Yes, Yes, Yes, Yes, Yes, Yes, Yes, Ye...
$ Apps         1660, 2186, 1428, 417, 193, 587, 353, 1899, 1038, 582, 17...
$ Accept       1232, 1924, 1097, 349, 146, 479, 340, 1720, 839, 498, 142...
$ Enroll       721, 512, 336, 137, 55, 158, 103, 489, 227, 172, 472, 484...
$ Top10perc    23, 16, 22, 60, 16, 38, 17, 37, 30, 21, 37, 44, 38, 44, 2...
$ Top25perc    52, 29, 50, 89, 44, 62, 45, 68, 63, 44, 75, 77, 64, 73, 4...
$ F.Undergrad  2885, 2683, 1036, 510, 249, 678, 416, 1594, 973, 799, 183...
$ P.Undergrad  537, 1227, 99, 63, 869, 41, 230, 32, 306, 78, 110, 44, 63...
$ Outstate     7440, 12280, 11250, 12960, 7560, 13500, 13290, 13868, 155...
$ Room.Board   3300, 6450, 3750, 5450, 4120, 3335, 5720, 4826, 4400, 338...
$ Books        450, 750, 400, 450, 800, 500, 500, 450, 300, 660, 500, 40...
$ Personal     2200, 1500, 1165, 875, 1500, 675, 1500, 850, 500, 1800, 6...
$ PhD          70, 29, 53, 92, 76, 67, 90, 89, 79, 40, 82, 73, 60, 79, 3...
$ Terminal     78, 30, 66, 97, 72, 73, 93, 100, 84, 41, 88, 91, 84, 87, ...
$ S.F.Ratio    18.1, 12.2, 12.9, 7.7, 11.9, 9.4, 11.5, 13.7, 11.3, 11.5,...
$ perc.alumni  12, 16, 30, 37, 2, 11, 26, 37, 23, 15, 31, 41, 21, 32, 26...
$ Expend       7041, 10527, 8735, 19016, 10922, 9727, 8861, 11487, 11644...
$ Grad.Rate    60, 56, 54, 59, 15, 55, 63, 73, 80, 52, 73, 76, 74, 68, 5...

Solución

Opción 1:Propuesta en el libro ISLR.

Elite = rep("No", nrow(College))
Elite[College$Top10perc > 50] = "Yes"
Elite <- as.factor(Elite)
college <- data.frame(College,  Elite)
summary(college[, c("Top10perc", "Elite")])

  Top10perc     Elite    
 Min.   : 1.00   No :699  
 1st Qu.:15.00   Yes: 78  
 Median :23.00            
 Mean   :27.56            
 3rd Qu.:35.00            
 Max.   :96.00

Opción 2: ifelse con paquete base y dplyr

# base 
College$Elite <- factor(ifelse(College$Top10perc > 50, "Yes", "No"))
# dplyr
library(dplyr)
College <-
  college %>%
  mutate(Elite = factor(ifelse(College$Top10perc > 50, "Yes", "No")))

Opción 3: vector lógico.

Hay múltiples opciones. Presento dos ejemplos.

college$Elite <- transform(College, Elite = Top10perc > 50)
College$Elite <- College$Top10perc > 50

Entradas relacionadas

2017-11-26

Diagrama de barras en ggplot - Preservar orden del data frame

Title

Problema

Cuando creamos un diagrama de barras, ggplot2 ordena por defecto el eje x alfabéticamente, de manera que en el gráfico aparecen desordenadas las categorías.

library("ggplot2") 
ggplot(df, aes(x = palabra, y= contar, fill = categoria)) + geom_bar(stat = "identity")

Datos

 palabras contar categoria palabra
1       BI  67452    Defect      BI
2       Bu  47279    Defect      Bu
3       Re  38530    Defect      Re
4      dvd   2554    Defect     dvd
5    Techn  34044  Digitaal   Techn
6   Retour  12190  Digitaal  Retour
7  Digital  22102  Digitaal Digital
8     Kobo   1234  Digitaal    Kobo

# Data frame
df <- structure(list(palabras = structure(c(1L, 2L, 6L, 4L, 8L, 7L, 
3L, 5L), .Label = c("BI", "Bu", "Digital", "dvd", "Kobo", "Re", 
"Retour", "Techn"), class = "factor"), contar = c(67452, 47279, 
38530, 2554, 34044, 12190, 22102, 1234), categoria = structure(c(1L, 
1L, 1L, 1L, 2L, 2L, 2L, 2L), .Label = c("Defect", "Digitaal"), class = "factor")), .Names = c("palabras", 
"contar", "categoria"), row.names = c(NA, -8L), class = "data.frame")

Solución

Ordenamos el factor palabra conforme al orden en el que aparecen en el data frame.

df$palabra <- factor(df$palabra, levels = df$palabra)
ggplot(df, aes(x = palabra, y= contar, fill = categoria)) + geom_bar(stat = "identity")

Referencias

2017-08-31

Eliminar los niveles no usados de un factor en R

Problema

Cuando filtramos un data frame que contiene un factor, y creamos por ejemplo una tabla de contingencia, R nos muestra también aquellos niveles del factor no usados.

df <- data.frame(name = c("a", "a", "a", "b", "b", "c", "c", "c", "c"), x = 1:9)
library(dplyr)
aa <-  df %>%
  group_by(name) %>%
  filter(n() < 4) %>% 
  droplevels()
table(aa$name)

En este ejemplo muestra c, cuando queremos que muestre solamente a y b.

# Resultado
a b c 
3 2 0
# Resultado deseado
a b 
3 2

Solución

Usamos la función droplevels o factor.

table(droplevels(aa$name))
table(factor(aa$name))

O como estamos empleando el paquete dplyr.

aa <-  df %>%
  group_by(name) %>%
  filter(n() < 4) %>% 
  droplevels()
table(aa$name)

# Mejor aún:
df %>%
  group_by(name) %>%
  filter(n() < 4) %>% 
  droplevels() %>% 
  {table(.$name)}

Entradas relacionadas

Versión en inglés

Nube de datos

2019-12-28

How to convert a continuous variable to discrete in R?

Problem

Solution

References

Related posts

2019-05-03

Drop unused levels from a factor in R

Problem

Solution

Related posts

References

2018-12-08

Discretización de variables en R

Problema

Solución

Entradas relacionadas

2017-11-26

Diagrama de barras en ggplot - Preservar orden del data frame

Problema

Solución

Referencias

2017-08-31

Eliminar los niveles no usados de un factor en R

Problema

Solución

Entradas relacionadas

Referencias