lares (version 5.2.13)

ohse: One Hot Smart Encoding (Dummy Variables)

Description

This function lets the user automatically transform a dataframe with categorical columns into numerical by one hot encoding technic.

Usage

ohse(
  df,
  redundant = FALSE,
  drop = TRUE,
  ignore = NULL,
  dates = FALSE,
  holidays = FALSE,
  country = "Venezuela",
  currency_pair = NA,
  trim = 0,
  limit = 10,
  variance = 0.9,
  other_label = "OTHER",
  sep = "_",
  quiet = FALSE,
  ...
)

Value

data.frame on which all features are numerical by nature or transformed with one hot encoding.

Arguments

df

Dataframe

redundant

Boolean. Should we keep redundant columns? i.e. If the column only has two different values, should we keep both new columns? Is set to NULL, only binary variables will dump redundant columns.

drop

Boolean. Drop automatically some useless features?

ignore

Vector or character. Which column should be ignored?

dates

Boolean. Do you want the function to create more features out of the date/time columns?

holidays

Boolean. Include holidays as new columns?

country

Character or vector. For which countries should the holidays be included?

currency_pair

Character. Which currency exchange do you wish to get the history from? i.e, USD/COP, EUR/USD...

trim

Integer. Trim names until the nth character

limit

Integer. Limit one hot encoding to the n most frequent values of each column. Set to NA to ignore argument.

variance

Numeric. Drop columns with more than n variance. Range: 0-1. For example: if a variable contains 91 unique different values out of 100 observations, this column will be suppressed if value is set to 0.9

other_label

Character. With which text do you wish to replace the filtered values with?

sep

Character. Separator's string

quiet

Boolean. Quiet all messages and summaries?

...

Additional parameters.

See Also

Other Data Wrangling: balance_data(), categ_reducer(), cleanText(), date_cuts(), date_feats(), file_name(), formatHTML(), holidays(), impute(), left(), normalize(), num_abbr(), ohe_commas(), quants(), removenacols(), replaceall(), replacefactor(), textFeats(), textTokenizer(), vector2text(), year_month(), zerovar()

Other Feature Engineering: date_feats(), holidays()

Other One Hot Encoding: date_feats(), holidays(), ohe_commas()

Examples

data(dft)
dft <- dft[, c(2, 3, 5, 9, 11)]

ohse(dft, limit = 3) %>% head(3)
ohse(dft, limit = 3, redundant = NULL) %>% head(3)

# Getting rid of columns with no (or too much) variance
dft$no_variance1 <- 0
dft$no_variance2 <- c("A", rep("B", nrow(dft) - 1))
dft$no_variance3 <- as.character(rnorm(nrow(dft)))
dft$no_variance4 <- c(rep("A", 20), round(rnorm(nrow(dft) - 20), 4))
ohse(dft, limit = 3) %>% head(3)