Learn R Programming

⚠️There's a newer version (1.2.1) of this package.Take me there.

recipes (version 1.0.1)

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

158,337

Version

1.0.1

License

MIT + file LICENSE

Issues

Pull Requests

Stars

Forks

Repository

https://github.com/tidymodels/recipes

Homepage

https://recipes.tidymodels.org/

Maintainer

Max Kuhn

Last Published

July 7th, 2022

Functions in recipes (1.0.1)

Check for required column at bake-time

Check if all Columns are Present

Check Variable Class

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

Internal Functions

Discretize Numeric Variables

Create a recipe for preprocessing data

Using case weights with recipes

case-weight-helpers

Helpers for steps with case weights

Helper Functions for Profile Data Sets

Helpers for printing step functions

recipes: A package for computing and preprocessing design matrices.

Estimate a preprocessing recipe

get_keep_original_cols

Get the keep_original_cols value of a recipe step

Wrapper function for preparing recipes within resampling

recipes_pkg_check

Update packages

Create Counts of Patterns using Regular Expressions

check_new_values

Check for New Values

Create a Formula from a Prepared Recipe

Date Feature Generator

Manually Alter Roles

Make a random identification field for steps

Check to see if a recipe is trained/prepared

Objects exported from other packages

Methods for selecting variables in step functions

Holiday Feature Generator

Cut a numeric variable into a factor

Add sin and cos terms for harmonic analysis

required_pkgs.step_depth

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

Distance between two locations

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

step_filter_missing

Missing Value Column Filter

step_impute_linear

Impute numeric variables via a linear model

step_indicate_na

Create Missing Data Column Indicators

Logarithmic Transformation

Convert values to predefined integers

Logit Transformation

step_impute_lower

Impute numeric data below the threshold of measurement

Linear Combination Filter

Create a lagged predictor

recipes_eval_select

Evaluate a selection with tidyselect semantics specific to recipes

High Correlation Filter

Distances to Class Centroids

step_dummy_extract

Extract patterns from nominal data

Apply (Smoothed) Rectified Linear Transformation

Relevel factors to a desired level

Natural Spline Basis Functions

step_dummy_multi_choice

Handle levels in multiple predictors together

step_num2factor

Convert Numbers to Factors

Polynomial Kernel PCA Signal Extraction

Create a Profiling Version of a Data Set

Radial Basis Function Kernel PCA Signal Extraction

Box-Cox Transformation for Non-Negative Data

step_impute_mode

Impute nominal data using the most common value

Ratio Variable Creation

Scaling Numeric Data

Select variables using dplyr

Update a recipe step

Near-Zero Variance Filter

step_spatialsign

Spatial Sign Preprocessing

step_impute_median

Impute numeric data using the median

step_impute_mean

Impute numeric data using the mean

Inverse Transformation

step_string2factor

Convert Strings to Factors

Scaling Numeric Data to a Specific Range

update_role_requirements

Update role specific requirements

Time Feature Generator

Simple Value Assignments for Novel Factor Levels

Check Range Consistency

PCA Signal Extraction

Create traditional dummy variables

Quantitatively check on variables

step_ordinalscore

Convert Ordinal Factors to Numeric Scores

Extract transformed training set

Non-Negative Matrix Factorization Signal Extraction

Inverse Logit Transformation

Remove observations with missing values

Create Interaction Variables

step_percentile

Percentile Transformation

Sort rows using dplyr

step_bin2factor

Create a Factors from A Dummy Variable

step_discretize

Discretize Numeric Variables

step_YeoJohnson

Yeo-Johnson Transformation

step_hyperbolic

Hyperbolic Transformations

B-Spline Basis Functions

step_impute_roll

Impute numeric data using a rolling window statistic

Isomap Embedding

Centering numeric data

ICA Signal Extraction

step_nnmf_sparse

Non-Negative Matrix Factorization Signal Extraction with lasso Penalization

Filter rows using dplyr

step_factor2string

Convert Factors to Strings

step_impute_bag

Impute via bagged trees

Add new variables using dplyr

step_impute_knn

Impute via k-nearest neighbors

tidy.step_BoxCox

Tidy the Result of a Recipe

Square Root Transformation

Convert Ordered Factors to Unordered Factors

General Variable Filter

Collapse Some Categorical Levels

Select Terms in a Step Function.

Assign missing categories to "unknown"

Sample rows using dplyr

Summarize a recipe

Shuffle Variables

Detect a regular expression

Kernel PCA Signal Extraction

Center and scale numeric data

Orthogonal Polynomial Basis Functions

Filter rows by position using dplyr

Partial Least Squares Feature Extraction

Add intercept (or constant) column

Mutate multiple columns using dplyr

Rename multiple columns using dplyr

Rename variables by name using dplyr

Zero Variance Filter

Moving Window Functions

Apply a trained preprocessing recipe

Add a New Operation to the Current Recipe

Check for Missing Values

check that newly created variable names don't overlap