Learn R Programming

recipes (version 1.1.0)

Preprocessing and Feature Engineering Steps for Modeling

Description

A recipe prepares your data for modeling. We provide an extensible framework for pipeable sequences of feature engineering steps provides preprocessing tools to be applied to data. Statistical parameters for the steps can be estimated from an initial data set and then applied to other data sets. The resulting processed output can then be used as inputs for statistical or machine learning models.

Copy Link

Version

Install

install.packages('recipes')

Monthly Downloads

173,696

Version

1.1.0

License

MIT + file LICENSE

Issues

Pull Requests

Stars

Forks

Repository

https://github.com/tidymodels/recipes

Homepage

https://recipes.tidymodels.org/

Maintainer

Last Published

July 4th, 2024

Functions in recipes (1.1.0)

Discretize Numeric Variables

Helper Functions for Profile Data Sets

Detect if a particular step or check is used in a recipe

Create a formula from a prepared recipe

Check to see if a recipe is trained/prepared

.get_data_types

Get types for use in recipes

Check range consistency

Helpers for printing step functions

developer_functions

Developer functions for creating recipes steps

Quantitatively check on variables

Extract transformed training set

Estimate a preprocessing recipe

Objects exported from other packages

recipes_eval_select

Evaluate a selection with tidyselect semantics specific to recipes

Create a recipe for preprocessing data

Wrapper function for preparing recipes within resampling

Internal Functions

get_keep_original_cols

Get the keep_original_cols value of a recipe step

recipes_extension_check

Checks that steps have all S3 methods

remove_original_cols

Removes original columns if options apply

recipes-role-indicator

Role indicators

recipes: A package for computing and preprocessing design matrices.

recipes_pkg_check

Update packages

Make a random identification field for steps

Prototype of recipe object

Methods for selecting variables in step functions

Sort rows using dplyr

B-spline basis functions

step_bin2factor

Create a factors from A dummy variable

Box-Cox transformation for non-negative data

recipes_remove_cols

Removes columns if options apply

recipes_ptype_validate

Validate prototype of recipe object

Impute via bagged trees

step sets the class of the step and check is for checks.

step_YeoJohnson

Yeo-Johnson transformation

Manually alter roles

required_pkgs.step_classdist_shrunken

S3 methods for tracking which additional packages are needed for steps.

Distances to class centroids

Centering numeric data

Date feature generator

Create counts of patterns using regular expressions

Cut a numeric variable into a factor

High correlation filter

step_classdist_shrunken

Compute shrunken centroid distances for classification models

Create traditional dummy variables

step_discretize

Discretize Numeric Variables

step_filter_missing

Missing value column filter

step_factor2string

Convert factors to strings

Holiday feature generator

Add sin and cos terms for harmonic analysis

step_hyperbolic

Hyperbolic transformations

step_dummy_extract

Extract patterns from nominal data

step_dummy_multi_choice

Handle levels in multiple predictors together

Filter rows using dplyr

Distance between two locations

ICA signal extraction

step_indicate_na

Create missing data column indicators

step_impute_median

Impute numeric data using the median

step_impute_linear

Impute numeric variables via a linear model

step_impute_mode

Impute nominal data using the most common value

step_impute_lower

Impute numeric data below the threshold of measurement

step_impute_roll

Impute numeric data using a rolling window statistic

step_impute_mean

Impute numeric data using the mean

step_impute_bag

Impute via bagged trees

step_impute_knn

Impute via k-nearest neighbors

Convert values to predefined integers

Radial basis function kernel PCA signal extraction

Create interaction variables

Inverse transformation

Create a lagged predictor

Add intercept (or constant) column

Kernel PCA signal extraction

Polynomial kernel PCA signal extraction

Isomap embedding

Inverse logit transformation

Impute via k-nearest neighbors

Logit transformation

Add new variables using dplyr

step_modeimpute

Impute nominal data using the most common value

Linear combination filter

Logarithmic transformation

Remove observations with missing values

step_lowerimpute

Impute numeric data below the threshold of measurement

Mutate multiple columns using dplyr

step_meanimpute

Impute numeric data using the mean

step_medianimpute

Impute numeric data using the median

Natural spline basis functions

step_ordinalscore

Convert ordinal factors to numeric scores

step_num2factor

Convert numbers to factors

Collapse infrequent categorical levels

Simple value assignments for novel factor levels

Non-negative matrix factorization signal extraction

Center and scale numeric data

PCA signal extraction

step_nnmf_sparse

Non-negative matrix factorization signal extraction with lasso penalization

Near-zero variance filter

Orthogonal polynomial basis functions

Create a profiling version of a data set

step_poly_bernstein

Generalized bernstein polynomial basis

Relevel factors to a desired level

Ratio variable creation

Detect a regular expression

Apply (smoothed) rectified linear transformation

Scaling numeric data to a specific range

step_percentile

Percentile transformation

Partial least squares feature extraction

General variable filter

step_spatialsign

Spatial sign preprocessing

Select variables using dplyr

step_rollimpute

Impute numeric data using a rolling window statistic

Rename variables by name using dplyr

Sample rows using dplyr

Shuffle variables

Rename multiple columns using dplyr

Scaling numeric data

Filter rows by position using dplyr

Assign missing categories to "unknown"

step_spline_convex

step_spline_monotone

Monotone splines

step_string2factor

Convert strings to factors

step_spline_nonnegative

Non-negative splines

Time feature generator

step_spline_natural

Natural splines

Square root transformation

Convert ordered factors to unordered factors

Summarize a recipe

Moving window functions

Zero variance filter

Select terms in a step function.

update_role_requirements

Update role specific requirements

Update a recipe step

tidy.step_BoxCox

Tidy the result of a recipe

Using case weights with recipes

Check variable class

Add a New Operation to the Current Recipe

check that newly created variable names don't overlap

Check if all columns are present

Apply a trained preprocessing recipe

case-weight-helpers

Helpers for steps with case weights

check_new_values

Check for new values

Check for missing values

Check for required column at bake-time