tidyverse : Converting character columns to factor using mutate_if and mutate_each_

library(readr)
adult <- read_csv("adultincome.csv")

## Parsed with column specification:
## cols(
##   age = col_double(),
##   workclass = col_character(),
##   fnlwgt = col_double(),
##   education = col_character(),
##   education.num = col_double(),
##   marital.status = col_character(),
##   occupation = col_character(),
##   relationship = col_character(),
##   race = col_character(),
##   sex = col_character(),
##   capital.gain = col_double(),
##   capital.loss = col_double(),
##   hours.per.week = col_double(),
##   native.country = col_character(),
##   income = col_character()
## )

str(adult)

## Classes 'spec_tbl_df', 'tbl_df', 'tbl' and 'data.frame': 32561 obs. of  15 variables:
##  $ age           : num  90 82 66 54 41 34 38 74 68 41 ...
##  $ workclass     : chr  "?" "Private" "?" "Private" ...
##  $ fnlwgt        : num  77053 132870 186061 140359 264663 ...
##  $ education     : chr  "HS-grad" "HS-grad" "Some-college" "7th-8th" ...
##  $ education.num : num  9 9 10 4 10 9 6 16 9 10 ...
##  $ marital.status: chr  "Widowed" "Widowed" "Widowed" "Divorced" ...
##  $ occupation    : chr  "?" "Exec-managerial" "?" "Machine-op-inspct" ...
##  $ relationship  : chr  "Not-in-family" "Not-in-family" "Unmarried" "Unmarried" ...
##  $ race          : chr  "White" "White" "Black" "White" ...
##  $ sex           : chr  "Female" "Female" "Female" "Female" ...
##  $ capital.gain  : num  0 0 0 0 0 0 0 0 0 0 ...
##  $ capital.loss  : num  4356 4356 4356 3900 3900 ...
##  $ hours.per.week: num  40 18 40 40 40 45 40 20 40 60 ...
##  $ native.country: chr  "United-States" "United-States" "United-States" "United-States" ...
##  $ income        : chr  "<=50K" "<=50K" "<=50K" "<=50K" ...
##  - attr(*, "spec")=
##   .. cols(
##   ..   age = col_double(),
##   ..   workclass = col_character(),
##   ..   fnlwgt = col_double(),
##   ..   education = col_character(),
##   ..   education.num = col_double(),
##   ..   marital.status = col_character(),
##   ..   occupation = col_character(),
##   ..   relationship = col_character(),
##   ..   race = col_character(),
##   ..   sex = col_character(),
##   ..   capital.gain = col_double(),
##   ..   capital.loss = col_double(),
##   ..   hours.per.week = col_double(),
##   ..   native.country = col_character(),
##   ..   income = col_character()
##   .. )

library(tidyverse)

1. Method 1: Using mutate_if

adult1 <- adult %>%
  mutate_if(is.character,as.factor)

str(adult1)

## Classes 'spec_tbl_df', 'tbl_df', 'tbl' and 'data.frame': 32561 obs. of  15 variables:
##  $ age           : num  90 82 66 54 41 34 38 74 68 41 ...
##  $ workclass     : Factor w/ 9 levels "?","Federal-gov",..: 1 5 1 5 5 5 5 8 2 5 ...
##  $ fnlwgt        : num  77053 132870 186061 140359 264663 ...
##  $ education     : Factor w/ 16 levels "10th","11th",..: 12 12 16 6 16 12 1 11 12 16 ...
##  $ education.num : num  9 9 10 4 10 9 6 16 9 10 ...
##  $ marital.status: Factor w/ 7 levels "Divorced","Married-AF-spouse",..: 7 7 7 1 6 1 6 5 1 5 ...
##  $ occupation    : Factor w/ 15 levels "?","Adm-clerical",..: 1 5 1 8 11 9 2 11 11 4 ...
##  $ relationship  : Factor w/ 6 levels "Husband","Not-in-family",..: 2 2 5 5 4 5 5 3 2 5 ...
##  $ race          : Factor w/ 5 levels "Amer-Indian-Eskimo",..: 5 5 3 5 5 5 5 5 5 5 ...
##  $ sex           : Factor w/ 2 levels "Female","Male": 1 1 1 1 1 1 2 1 1 2 ...
##  $ capital.gain  : num  0 0 0 0 0 0 0 0 0 0 ...
##  $ capital.loss  : num  4356 4356 4356 3900 3900 ...
##  $ hours.per.week: num  40 18 40 40 40 45 40 20 40 60 ...
##  $ native.country: Factor w/ 42 levels "?","Cambodia",..: 40 40 40 40 40 40 40 40 40 1 ...
##  $ income        : Factor w/ 2 levels "<=50K",">50K": 1 1 1 1 1 1 1 2 1 2 ...

2. Method 2: Using mutate_each_

cols <- c("workclass", "education", "marital.status", "occupation","relationship", 
          "race","sex", "native.country","income")
adult2 <- adult %>% 
  mutate_each_(funs(factor(.)),cols)

## Warning: mutate_each() is deprecated
## Please use mutate_if(), mutate_at(), or mutate_all() instead: 
## 
##   - To map `funs` over all variables, use mutate_all()
##   - To map `funs` over a selection of variables, use mutate_at()
## This warning is displayed once per session.

## Warning: funs() is soft deprecated as of dplyr 0.8.0
## Please use a list of either functions or lambdas: 
## 
##   # Simple named list: 
##   list(mean = mean, median = median)
## 
##   # Auto named with `tibble::lst()`: 
##   tibble::lst(mean, median)
## 
##   # Using lambdas
##   list(~ mean(., trim = .2), ~ median(., na.rm = TRUE))
## This warning is displayed once per session.

str(adult2)

## Classes 'spec_tbl_df', 'tbl_df', 'tbl' and 'data.frame': 32561 obs. of  15 variables:
##  $ age           : num  90 82 66 54 41 34 38 74 68 41 ...
##  $ workclass     : Factor w/ 9 levels "?","Federal-gov",..: 1 5 1 5 5 5 5 8 2 5 ...
##  $ fnlwgt        : num  77053 132870 186061 140359 264663 ...
##  $ education     : Factor w/ 16 levels "10th","11th",..: 12 12 16 6 16 12 1 11 12 16 ...
##  $ education.num : num  9 9 10 4 10 9 6 16 9 10 ...
##  $ marital.status: Factor w/ 7 levels "Divorced","Married-AF-spouse",..: 7 7 7 1 6 1 6 5 1 5 ...
##  $ occupation    : Factor w/ 15 levels "?","Adm-clerical",..: 1 5 1 8 11 9 2 11 11 4 ...
##  $ relationship  : Factor w/ 6 levels "Husband","Not-in-family",..: 2 2 5 5 4 5 5 3 2 5 ...
##  $ race          : Factor w/ 5 levels "Amer-Indian-Eskimo",..: 5 5 3 5 5 5 5 5 5 5 ...
##  $ sex           : Factor w/ 2 levels "Female","Male": 1 1 1 1 1 1 2 1 1 2 ...
##  $ capital.gain  : num  0 0 0 0 0 0 0 0 0 0 ...
##  $ capital.loss  : num  4356 4356 4356 3900 3900 ...
##  $ hours.per.week: num  40 18 40 40 40 45 40 20 40 60 ...
##  $ native.country: Factor w/ 42 levels "?","Cambodia",..: 40 40 40 40 40 40 40 40 40 1 ...
##  $ income        : Factor w/ 2 levels "<=50K",">50K": 1 1 1 1 1 1 1 2 1 2 ...

Method 3: Using lappy function

adult3 <- adult

adult3[cols] <- lapply(adult3[cols], factor)

str(adult3)

## Classes 'spec_tbl_df', 'tbl_df', 'tbl' and 'data.frame': 32561 obs. of  15 variables:
##  $ age           : num  90 82 66 54 41 34 38 74 68 41 ...
##  $ workclass     : Factor w/ 9 levels "?","Federal-gov",..: 1 5 1 5 5 5 5 8 2 5 ...
##  $ fnlwgt        : num  77053 132870 186061 140359 264663 ...
##  $ education     : Factor w/ 16 levels "10th","11th",..: 12 12 16 6 16 12 1 11 12 16 ...
##  $ education.num : num  9 9 10 4 10 9 6 16 9 10 ...
##  $ marital.status: Factor w/ 7 levels "Divorced","Married-AF-spouse",..: 7 7 7 1 6 1 6 5 1 5 ...
##  $ occupation    : Factor w/ 15 levels "?","Adm-clerical",..: 1 5 1 8 11 9 2 11 11 4 ...
##  $ relationship  : Factor w/ 6 levels "Husband","Not-in-family",..: 2 2 5 5 4 5 5 3 2 5 ...
##  $ race          : Factor w/ 5 levels "Amer-Indian-Eskimo",..: 5 5 3 5 5 5 5 5 5 5 ...
##  $ sex           : Factor w/ 2 levels "Female","Male": 1 1 1 1 1 1 2 1 1 2 ...
##  $ capital.gain  : num  0 0 0 0 0 0 0 0 0 0 ...
##  $ capital.loss  : num  4356 4356 4356 3900 3900 ...
##  $ hours.per.week: num  40 18 40 40 40 45 40 20 40 60 ...
##  $ native.country: Factor w/ 42 levels "?","Cambodia",..: 40 40 40 40 40 40 40 40 40 1 ...
##  $ income        : Factor w/ 2 levels "<=50K",">50K": 1 1 1 1 1 1 1 2 1 2 ...
##  - attr(*, "spec")=
##   .. cols(
##   ..   age = col_double(),
##   ..   workclass = col_character(),
##   ..   fnlwgt = col_double(),
##   ..   education = col_character(),
##   ..   education.num = col_double(),
##   ..   marital.status = col_character(),
##   ..   occupation = col_character(),
##   ..   relationship = col_character(),
##   ..   race = col_character(),
##   ..   sex = col_character(),
##   ..   capital.gain = col_double(),
##   ..   capital.loss = col_double(),
##   ..   hours.per.week = col_double(),
##   ..   native.country = col_character(),
##   ..   income = col_character()
##   .. )