Minimum redundancy, maximum relevance feature selection for tidyfit

Selects features for continuous or (ordered) factor data using MRMR on a 'tidyFit' R6 class. The function can be used with regress and classify.

Usage

.model.mrmr(self, data = NULL)

Arguments

self: a 'tidyFit' R6 class.
data: a data frame, data frame extension (e.g. a tibble), or a lazy data frame (e.g. from dbplyr or dtplyr).

Value

A fitted 'tidyFit' class model.

Details

Hyperparameters:

None. Cross validation not applicable.

Important method arguments (passed to m)

feature_count (number of features to select)
solution_count (ensemble size)

The MRMR algorithm is estimated using the mRMRe::mRMR.ensemble function. See ?mRMR.ensemble for more details.

Implementation

Use with regress for regression problems and with classify for classification problems. The selected features can be obtained using coef.

The MRMR objects have no predict and related methods.

References

De Jay N, Papillon-Cavanagh S, Olsen C, Bontempi G and Haibe-Kains B (2012). mRMRe: an R package for parallelized mRMR ensemble feature selection.

Author

Johann Pfitzinger

Examples

# Load data
data <- tidyfit::Factor_Industry_Returns

# Stand-alone function
fit <- m("mrmr", Return ~ ., data, feature_count = 3)
coef(fit)
#> # A tibble: 3 × 3
#>   term          estimate model_info      
#>   <chr>            <dbl> <list>          
#> 1 IndustryTelcm        1 <tibble [1 × 0]>
#> 2 Mkt-RF               1 <tibble [1 × 0]>
#> 3 SMB                  1 <tibble [1 × 0]>

# Within 'regress' function
fit <- regress(data, Return ~ ., m("mrmr", feature_count = 3),
               .mask = c("Date", "Industry"))
coef(fit)
#> # A tibble: 3 × 4
#> # Groups:   model [1]
#>   model term   estimate model_info      
#>   <chr> <chr>     <dbl> <list>          
#> 1 mrmr  Mkt-RF        1 <tibble [1 × 0]>
#> 2 mrmr  SMB           1 <tibble [1 × 0]>
#> 3 mrmr  RF            1 <tibble [1 × 0]>

Minimum redundancy, maximum relevance feature selection for `tidyfit`