Introduction | The tidyclust workflow | K-means example | 1. Create a specification | 2. Fit to data | 3. Extract results | 4. Evaluate | Hierarchical clustering example | Tidymodels integration | Next steps

Tuning Parameters | Parameter Objects | Numeric Parameters | Discrete Parameters | Creating Novel Parameters | Unknown Values | Parameter Sets | Parameter Grids

The problem | The solution | Batched summation | Example | Supported models | Output behavior | When to use | Good candidates for separate_trees = TRUE | When to stick with the default | Tradeoffs | Benchmarking recommendation

Supported models | Recipes steps | tailor adjustments

tidypredict_ functions | Supported objectives | Regression objectives (identity transform) | Binary classification (sigmoid transform) | Multiclass classification | Binary classification example | Multiclass classification example | Categorical features | With parsnip/bonsai (recommended) | With raw CatBoost | Parse model spec | Limitations

tidypredict_ functions | Parse model spec | Limitations

The issue | Which models are affected? | Example | What tidypredict does | Pros and cons | Recommendations

tidypredict_ functions | Supported objectives | Regression objectives (identity transform) | Regression objectives (exp transform) | Binary classification (sigmoid transform) | Multiclass classification | Binary classification example | Categorical features | parsnip | Parse model spec | Limitations

tidypredict_ functions | parsnip | Parse model spec

Nested vs flat case_when | Flat case_when (old approach) | Nested case_when (current approach) | Why nested is better | Parsed model versions

How it works | Under the hood | Classification | parsnip | Categorical predictors | Surrogate splits

Example | Metrics

How lime explains stuff | How to permute an observation | Calculating similarities with permutations | Selecting the features to use | Fitting a model to the permuted and feature-reduced data | An example - Tabular Data | An example - text data | Interactive text model explanations | Session Info

Motivation | Placeholders for Parameters | Specifying Arguments | Process

How it works | Under the hood | parsnip

How it works | Under the hood | parsnip

tidypredict_ functions | parsnip | Parse model spec

Highlights & Limitations | How it works | Prediction intervals | Under the hood | How it performs | parsnip

Pre-processing | Model Fitting | Post-processing

Score class objects | A scoring example — random forest | Hyperparameter tuning | Seamless argument support | A scoring example — conditional random forest | An scoring example — oblique random forest | Available objects and engines

A scoring example | Filtering and ranking | A filtering exmple for score singular | A filtering example for scores plural | Available score objects and filter methods

Introduction | 1-Sample t-Test | 2-Sample t-Test

Generalized estimator equations (GEE) | Generalized least squares | Linear mixed effects via lme | Models using lmer, glmer, and stan_glmer | Using tidymodels workflows | Other tips

Introduction | Example

Introduction | Hypothesis tests | One numerical variable (mean) | One numerical variable (standardized mean $t$) | One numerical variable (median) | One numerical variable (paired) | One categorical (one proportion) | One categorical variable (standardized proportion $z$) | Two categorical (2 level) variables | Two categorical (2 level) variables (z) | One categorical (>2 level) - GoF | Two categorical (>2 level): Chi-squared test of independence | One numerical variable, one categorical (2 levels) (diff in means) | One numerical variable, one categorical (2 levels) (t) | One numerical variable, one categorical (2 levels) (diff in medians) | One numerical, one categorical (>2 levels) - ANOVA | Two numerical vars - SLR | Two numerical vars - correlation | Two numerical vars - SLR (t) | Multiple explanatory variables | Confidence intervals | One numerical (one mean) | One numerical (one mean - standardized) | Two categorical variables (diff in proportions) | Two categorical variables (z) | Two numerical vars - t

Introduction | specify(): Specifying Response (and Explanatory) Variables | hypothesize(): Declaring the Null Hypothesis | generate(): Generating the Null Distribution | calculate(): Calculating Summary Statistics | Other Utilities | Theoretical Methods | Multiple regression | Conclusion

Introduction | Test of Independence | Goodness of Fit

Introduction

broom: let's tidy up a bit | Tidying functions | Other Examples | Generalized linear and non-linear models | Hypothesis testing | Conventions | All functions | tidy functions | augment functions | glance functions

Defining candidate ensemble members | Putting together a stack

Define candidate ensemble members | Putting together a stack | Fit the stack

Group-awareness | Groupwise metrics

Introduction | Macro averaging | Micro averaging | Specialized multiclass implementations

Creating Dummy Variables | Interactions with Dummy Variables | Warning! | Getting All of the Indicator Variables | Novel Levels | Other Steps Related to Dummy Variables

An Example | An Initial Recipe | Preprocessing Steps | Checks

Example: Class Imbalance Sampling and Skipping Steps | Other Examples | How To Skip Steps | Be Careful!

The Formula Method | The Non-Formula Interface | Role Inheritance

Counting select words | Removing words in addition to the stop words list | Letter distributions | TF-IDF of ngrams of stemmed tokens

tokens attribute | lemma and pos attributes

Only using step_tokenize() | Using step_tokenize() and step_ngram()

Random Resampling | Initial Splits | V-Fold Cross-Validation | Monte-Carlo Cross-Validation | Bootstrap Resampling | Validation Set | Stratified Resampling | Grouped Resampling | Time-Based Resampling

Terminology | rset Objects Contain Many Resamples | Individual Resamples are rsplit Objects

Introduction | Model Assessment | Using the Bootstrap to Make Comparisons | Bootstrap Estimates of Model Coefficients | Keeping Tidy

Introduction | What's Our Model? | Model Fitting | Model Constructor | Model Fitting Implementation | Model Fitting Bridge | User Facing Fitting Function | Adding an Intercept Option | Model Prediction | Prediction Implementation | Prediction Bridge | User Facing Prediction Function | Final Testing

Introduction | Connection with mold() | Outcomes | Validation | Column existence | Column types | Lossless conversion | Recipes and forge() | A note on recipes

Introduction | A First Example | blueprints | Formulas | Intercepts | Dummy variables | Multivariate outcomes | XY | Vector outcomes | Recipe

Intro | Example setup | Model inside the database | Categorical variables | Multiple linear regression | Interactions | Full example

Example setup | Model preparation | Scenario 1 - Update scores | Scenario 2- Append new scores

Highlights & Limitations | How it works | Under the hood | How it performs

tidypredict_ functions | GLM models | parsnip | Parse model spec

Intro | Example setup | Running Kmeans clustering | Under the hood | Safeguards for long running jobs

Recap

Introduction | Fitting models with the 'h2o' engine

python example | Read in R | tidypredict | broom

Parse model | Saving the model | Re-load the model | broom

Transforming a variable | Handling levels in categorical data | Dummy variables | Recommended preprocessing outline

Why a correlation data frame? | API | Other Resources

An example | sparklyr | Limitations

Tidying k-means clustering