Julia Silge

The newest monthly release of Positron has a revamp of the integration between GitHub Copilot and Positron Assistant.

The newest monthly release of Positron delivers some fresh new features for the Data Explorer.

See how you can use Positron, a new, next-generation data science IDE, for R package development tasks and releasing a new version of an R package.

Get to know Positron, a new, next-generation data science IDE, using this week’s Tidy Tuesday data on encounters with orcas.

Let’s walk through the ML lifecycle from EDA to model development to deployment, using tidymodels, vetiver, and Posit Team.

Let’s use summarization and visualization to explore how the numbers of polling places have changed in the United States.

Which writers of Doctor Who episodes are rated the most highly?

Today is Election Day in the United States, so let’s use logistic regression modeling to explore vote share in US House elections.

Learn how to fit and interpret an unsupervised text model for all of Taylor Swift’s ERAS.

Use tidy log odds to compare which US states are more likely to have haunted cemeteries or haunted schools.

He’s here, he’s there, he’s every f*cking where, and we’re finding bootstrap confidence intervals.

Use workflowsets to evaluate multiple possible models to predict whether email is spam.

Learn about different kinds of metrics for evaluating classification models, and how to compute, compare, and visualize them.

Let’s use byte pair encoding tokenization along with Poisson regression to understand which tokens are more more often (or less often) in US place names.

How well can we predict the magnitude of tornadoes in the US?

Can we predict childcare costs in the US using an xgboost model?

Learn how to train and deploy a model with R and vetiver on AWS SageMaker infrastructure.

High quality text embeddings are becoming more available from companies like OpenAI.

Artists who are women are underrepresented in art history textbooks, and we can use resampling to robustly understand more about this imbalance.

Will squirrels will come eat from your bird feeder?

Learn how to handle predictors with high cardinality using tidymodels for accreditation data on UK museums.

Worried about how a certain social media platform is going and want to start removing yourself?

New functionality in tidytext supports identifying high FREX and high lift words from topic modeling results.

Learn how to use vetiver to set up different types of prediction endpoints for your deployed model.

After you train a model, you can use vetiver to prepare a Dockerfile and deploy your model in a flexible way.

The slider package provides support for flexible sliding window aggregation, and we can use these kinds of sliding windows to analyze rents over time.

Use summarization, a single linear model, and bootstrapping to understand what economic activities involve a larger pay gap for women.

The spatialsample package is gaining many new methods this summer, and we can use spatially aware resampling to understand how drought is related to other quantities across Texas.

Will a book be on the NYT bestseller list a long time, or a short time?

Understand how much money colleges spend on sports using linear modeling and bootstrap intervals.

The tidymodels framework provides extension packages for specialized tasks such as Poisson regression.

The infer package is part of tidymodels and provides an expressive statistical grammar.

Use custom feature engineering for board game categories, tune an xgboost model with racing methods, and use explainability methods for deeper understanding.

Get started with feature engineering for text data, transforming text to be used in machine learning algorithms.

Learn how to train, explore, and understand an unsupervised topic model for text data.

Using a tidymodels workflow can make many modeling tasks more convenient, but sometimes you want more flexibility and control of how to handle your modeling objects.

Use spatial resampling to more accurately estimate model performance for geographic data.

Get started with tidymodels workflowsets to handle and evaluate multiple preprocessing and modeling approaches simultaneously, using pumpkin competitions.

Tune and evaluate a multiclass model with lasso regulariztion for economics working papers.

Songs on the Billboard Top 100 have many audio features.

In this screencast, focus on some tidymodels basics such as how to put together feature engineering and a model algorithm, and how to fit and predict.

Learn how to evaluate multiple feature engineering and modeling approaches with workflowsets, predicting whether a person or the computer spoke a line on Star Trek.

More xgboost with tidymodels!

Our new book in the Chapman & Hall/CRC Data Science Series is now complete and available for preorder!

Early stopping can keep an xgboost model from overfitting.

Models like xgboost have many tuning hyperparameters, but racing methods can help identify parameter combinations that are not performing well.

Which Scooby Doo monsters are REAL?!

Predict prices for Airbnb listings in NYC with a data set from a recent episode of SLICED, with a focus on two specific aspects of this model analysis: creating a custom metric to evaluate the model and combining both tabular and unstructured text data in…

Handling class imbalance in modeling affects classification metrics in different ways.

Tune a decision tree model to predict whether a Mario Kart world record used a shortcut, and explore partial dependence profiles for the world record times.