fill_NA_N: 'fill_NA_N' function for the multiple imputations purpose

View source: R/fill_NA_N.R

fill_NA_NR Documentation

fill_NA_N function for the multiple imputations purpose

Description

Multiple imputations to fill the missing data. Non missing independent variables are used to approximate a missing observations for a dependent variable. Quantitative models were built under Rcpp packages and the C++ library Armadillo.

Usage

fill_NA_N(
  x,
  model,
  posit_y,
  posit_x,
  w = NULL,
  logreg = FALSE,
  k = 10,
  ridge = 1e-06
)

## S3 method for class 'data.frame'
fill_NA_N(
  x,
  model,
  posit_y,
  posit_x,
  w = NULL,
  logreg = FALSE,
  k = 10,
  ridge = 1e-06
)

## S3 method for class 'data.table'
fill_NA_N(
  x,
  model,
  posit_y,
  posit_x,
  w = NULL,
  logreg = FALSE,
  k = 10,
  ridge = 1e-06
)

## S3 method for class 'matrix'
fill_NA_N(
  x,
  model,
  posit_y,
  posit_x,
  w = NULL,
  logreg = FALSE,
  k = 10,
  ridge = 1e-06
)

Arguments

x

a numeric matrix or data.frame/data.table (factor/character/numeric/logical) - variables

model

a character - posibble options ("lm_bayes","lm_noise","pmm")

posit_y

an integer/character - a position/name of dependent variable

posit_x

an integer/character vector - positions/names of independent variables

w

a numeric vector - a weighting variable - only positive values, Default: NULL

logreg

a boolean - if dependent variable has log-normal distribution (numeric). If TRUE log-regression is evaluated and then returned exponential of results., Default: FALSE

k

an integer - a number of multiple imputations or for pmm a number of closest points from which a one random value is taken, Default:10

ridge

a numeric - a value added to diagonal elements of the x'x matrix, Default:1e-5

Value

load imputations in a numeric/character/factor (similar to the input type) vector format

Methods (by class)

  • fill_NA_N(data.frame): s3 method for data.frame

  • fill_NA_N(data.table): S3 method for data.table

  • fill_NA_N(matrix): S3 method for matrix

Note

There is assumed that users add the intercept by their own. The miceFast module provides the most efficient environment, the second recommended option is to use data.table and the numeric matrix data type. The lda model is assessed only if there are more than 15 complete observations and for the lms models if number of variables is smaller than number of observations.

See Also

fill_NA VIF

Examples

library(miceFast)
library(dplyr)
library(data.table)
### Data
# airquality dataset with additional variables
data(air_miss)
### Intro: dplyr
# IMPUTATIONS
air_miss <- air_miss %>%
  # Imputations with a grouping option (models are separately assessed for each group)
  # taking into account provided weights
  group_by(groups) %>%
  do(mutate(., Solar_R_imp = fill_NA(
    x = .,
    model = "lm_pred",
    posit_y = "Solar.R",
    posit_x = c("Wind", "Temp", "Intercept"),
    w = .[["weights"]]
  ))) %>%
  ungroup() %>%
  # Imputations - discrete variable
  mutate(x_character_imp = fill_NA(
    x = .,
    model = "lda",
    posit_y = "x_character",
    posit_x = c("Wind", "Temp")
  )) %>%
  # logreg was used because almost log-normal distribution of Ozone
  # imputations around mean
  mutate(Ozone_imp1 = fill_NA(
    x = .,
    model = "lm_bayes",
    posit_y = "Ozone",
    posit_x = c("Intercept"),
    logreg = TRUE
  )) %>%
  # imputations using positions - Intercept, Temp
  mutate(Ozone_imp2 = fill_NA(
    x = .,
    model = "lm_bayes",
    posit_y = 1,
    posit_x = c(4, 6),
    logreg = TRUE
  )) %>%
  # multiple imputations (average of x30 imputations)
  # with a factor independent variable, weights and logreg options
  mutate(Ozone_imp3 = fill_NA_N(
    x = .,
    model = "lm_noise",
    posit_y = "Ozone",
    posit_x = c("Intercept", "x_character_imp", "Wind", "Temp"),
    w = .[["weights"]],
    logreg = TRUE,
    k = 30
  )) %>%
  mutate(Ozone_imp4 = fill_NA_N(
    x = .,
    model = "lm_bayes",
    posit_y = "Ozone",
    posit_x = c("Intercept", "x_character_imp", "Wind", "Temp"),
    w = .[["weights"]],
    logreg = TRUE,
    k = 30
  )) %>%
  group_by(groups) %>%
  do(mutate(., Ozone_imp5 = fill_NA(
    x = .,
    model = "lm_pred",
    posit_y = "Ozone",
    posit_x = c("Intercept", "x_character_imp", "Wind", "Temp"),
    w = .[["weights"]],
    logreg = TRUE
  ))) %>%
  do(mutate(., Ozone_imp6 = fill_NA_N(
    x = .,
    model = "pmm",
    posit_y = "Ozone",
    posit_x = c("Intercept", "x_character_imp", "Wind", "Temp"),
    w = .[["weights"]],
    logreg = TRUE,
    k = 20
  ))) %>%
  ungroup() %>%
  # Average of a few methods
  mutate(Ozone_imp_mix = rowMeans(select(., starts_with("Ozone_imp")))) %>%
  # Protecting against collinearity or low number of observations - across small groups
  # Be carful when using a grouping option
  # because of lack of protection against collinearity or low number of observations.
  # There could be used a tryCatch(fill_NA(...),error=function(e) return(...))
  group_by(groups) %>%
  do(mutate(., Ozone_chac_imp = tryCatch(
    fill_NA(
      x = .,
      model = "lda",
      posit_y = "Ozone_chac",
      posit_x = c(
        "Intercept",
        "Month",
        "Day",
        "Temp",
        "x_character_imp"
      ),
      w = .[["weights"]]
    ),
    error = function(e) .[["Ozone_chac"]]
  ))) %>%
  ungroup()

# Sample of results
air_miss[which(is.na(air_miss[, 1]))[1:5], ]

### Intro: data.table
# IMPUTATIONS
# Imputations with a grouping option (models are separately assessed for each group)
# taking into account provided weights
data(air_miss)
setDT(air_miss)
air_miss[, Solar_R_imp := fill_NA_N(
  x = .SD,
  model = "lm_bayes",
  posit_y = "Solar.R",
  posit_x = c("Wind", "Temp", "Intercept"),
  w = .SD[["weights"]],
  k = 100
), by = .(groups)] %>%
  # Imputations - discrete variable
  .[, x_character_imp := fill_NA(
    x = .SD,
    model = "lda",
    posit_y = "x_character",
    posit_x = c("Wind", "Temp", "groups")
  )] %>%
  # logreg was used because almost log-normal distribution of Ozone
  # imputations around mean
  .[, Ozone_imp1 := fill_NA(
    x = .SD,
    model = "lm_bayes",
    posit_y = "Ozone",
    posit_x = c("Intercept"),
    logreg = TRUE
  )] %>%
  # imputations using positions - Intercept, Temp
  .[, Ozone_imp2 := fill_NA(
    x = .SD,
    model = "lm_bayes",
    posit_y = 1,
    posit_x = c(4, 6),
    logreg = TRUE
  )] %>%
  # model with a factor independent variable
  # multiple imputations (average of x30 imputations)
  # with a factor independent variable, weights and logreg options
  .[, Ozone_imp3 := fill_NA_N(
    x = .SD,
    model = "lm_noise",
    posit_y = "Ozone",
    posit_x = c("Intercept", "x_character_imp", "Wind", "Temp"),
    w = .SD[["weights"]],
    logreg = TRUE,
    k = 30
  )] %>%
  .[, Ozone_imp4 := fill_NA_N(
    x = .SD,
    model = "lm_bayes",
    posit_y = "Ozone",
    posit_x = c("Intercept", "x_character_imp", "Wind", "Temp"),
    w = .SD[["weights"]],
    logreg = TRUE,
    k = 30
  )] %>%
  .[, Ozone_imp5 := fill_NA(
    x = .SD,
    model = "lm_pred",
    posit_y = "Ozone",
    posit_x = c("Intercept", "x_character_imp", "Wind", "Temp"),
    w = .SD[["weights"]],
    logreg = TRUE
  ), .(groups)] %>%
  .[, Ozone_imp6 := fill_NA_N(
    x = .SD,
    model = "pmm",
    posit_y = "Ozone",
    posit_x = c("Intercept", "x_character_imp", "Wind", "Temp"),
    w = .SD[["weights"]],
    logreg = TRUE,
    k = 10
  ), .(groups)] %>%
  # Average of a few methods
  .[, Ozone_imp_mix := apply(.SD, 1, mean), .SDcols = Ozone_imp1:Ozone_imp6] %>%
  # Protecting against collinearity or low number of observations - across small groups
  # Be carful when using a data.table grouping option
  # because of lack of protection against collinearity or low number of observations.
  # There could be used a tryCatch(fill_NA(...),error=function(e) return(...))

  .[, Ozone_chac_imp := tryCatch(
    fill_NA(
      x = .SD,
      model = "lda",
      posit_y = "Ozone_chac",
      posit_x = c(
        "Intercept",
        "Month",
        "Day",
        "Temp",
        "x_character_imp"
      ),
      w = .SD[["weights"]]
    ),
    error = function(e) .SD[["Ozone_chac"]]
  ), .(groups)]

# Sample of results
air_miss[which(is.na(air_miss[, 1]))[1:5], ]


miceFast documentation built on Nov. 18, 2022, 1:07 a.m.