Machine learning models have biases using small data, and some industries such as health care and manufaturing lack labled data. In light of this, a good approach is to select robust features to build models.

 

Read more...

This accelerator shows how you can use Visual AI on geospatial data. Instead of deriving numeric features from the georeferenced data, you look at the geospatial data as images. For example, if you have a map of population distribution, instead of extracting the population that corresponds to each row of the main table you can pass the region of the map that corresponds to that row. 

 

Read more...

This notebook serves as a comprehensive guide to the intricate world of insurance pricing, leveraging historical claims data for modeling and analysis. The primary objective of this notebook is to enable insurance professionals and data scientists to predict insurance pricing accurately and efficiently with DataRobot platform.

 

Read more...

This accelerator shows how users can apply Local Interpretable Model-agnostic Explanations (LIME) to models built and deployed with DataRobot. LIME serves as another method in your toolbox to explain model predictions, complementing the built-in DataRobot capabilities of XEMP and SHAP prediction explanations.

Read more...

There are a wide variety of open source models. For example, there has been a lot of interest in LLama and variations such as Alpaca or Vicuna, Falcon, Mistral etc. Hosting these is a challenge as they require GPUs which are expensive so often customers want to compare cloud providers to find the best hosting option to meet their own needs. In this example we will work with Google Cloud Platform.

 
 
 
Read more...

This notebook presents an example workflow to create one-way and two-way partial dependence plots (PDP), and Individual Conditional Expectations (ICE) insights using DataRobot

 

This notebook has two parts:

  1. Where we score data against a deployment, and join the predictions back with the full dataset, and
  2. Where we use the scored dataset to gain insights by generation PDP and ICE plots
Read more...

Modern machine learning techniques are now capable of assisting manufacturers streamline their product development in numerous ways. In this notebook, we are going to focus on detecting and classifying product defects using state of the art computer vision systems. Utilizing machine learning brings immense value to manufacturers, transforming their production processes and giving them an overall competitive edge. By leveraging these advanced methods, manufacturers can streamline product development, enhance defect detection accuracy, optimize operational efficiency, reduce costs, and ultimately deliver higher-quality products to meet the ever-growing demands of the market.

Read more...

This note book provides a user with a method of changing the output of User Activity Monitor to allow the user to drop an entire column of output or change the contents of that column in a way to preserve the anonymity of the column but maintain consistency for reporting.

Read more...

This notebook is intended for a GraphQL developer who wants to integrate with DataRobot.

In this is example implementation, a GraphQL server is connecting to the DataRobot OpenAPI specification using GraphQL Mesh, the currently maintained option.

Read more...

DataRobot Visual AI  allows you to train deep learning models intended for the Computer Vision projects that are demanded by the different industries. The object detection (binary and multiclass classification) applied to image and video processing is one of the tasks that can be easily and efficiently implemented with the DataRobot Visual AI. You can also bring your own Computer Vision model and deploy it in DataRobot via Custom Model Workshop .

Read more...

An AI model can't just be an experiment. AI Predictions need to be in the hands of real users interactive with customers, products, or users. This accelerator demonstrates how to incorporate DataRobot predictions into a mobile app.

Read more...

This accelerator shows an app to create synthetic training data

Read more...

This notebook presents an example workflow for carrying out statistical tests, notify stakeholders of any issues via Slack, and generate automated compliance documentation with the test results.

Read more...

In this notebook, we implement a very simple model based on the Q-learning algorithm. This notebook is intend to show a basic form of Reinforcement Learning that doesn't require a deep understanding of neural networks or advanced mathematics and how one might deploy such a model in DataRobot.

Read more...

This accelerator demonstrates the use of DataRobot custom models functionality to deploy a speech recognition capability to DataRobot based on the OpenAI Whisper models (currently uses the "base" model). This allows the capability to leverage the DataRobot environment and resources, on cloud or on prem.

Read more...

There are a wide variety of open source models. For example, there has been a lot of interest in LLama and variations such as Alpaca or Vicuna, Falcon, Mistral etc. Hosting these is a challenge as they require GPUs which are expensive so often customers want to compare cloud providers to find the best hosting option to meet their own needs. In this example we will work with Google Cloud Platform.

Read more...

Conjoint analysis is widely used tool used in marketing research for new product development testing. It's usually executed as an online survey format with a few survey respondents will make 1 choice out of a set of different alternatives. The output allows researches to accurately identify what product features and combination works best before developing them.

Read more...

This AI Accelerator demonstrates how to reconcile (e.g., post-processing to sum appropriately) independent time series forecasts with a hierarchical structure. Reconciling, also known as making "coherent" forecasts , is often a requirement when submitting hierarchical forecasts to stakeholders. This notebook leverages the increasingly popular HierarchicalForecast  python library to do the reconciliation on forecasts generated from DataRobot time series deployments. 

Read more...

The use case provided in this notebook takes the latest update of an RSS feed from CNN, downloads the article as text, embeds the text into a vector database, uses Google Bison to summarize the text, and provides a summary of the article in a streamlit app.

Read more...

The use case provided in this notebook creates synthetic training data sets for use in DataRobot models. This notebook outlines how to create a synthetic training data set in a csv file, with name, address, phone number, company, account number, and credit score.

Read more...

This AI Accelerator demonstrates various ways for generating prediction intervals for any DataRobot model. The methods presented here are rooted in the area of conformal inference  (also known as conformal prediction ). These types of approaches have become increasingly popular for uncertainty quantification because they do not require strict distributional assumptions to be met in order to achieve proper coverage (i.e., they only require that the testing data is exchangeable with the training data).

Read more...

This tutorial introduces a workflow utilizing OpenAI's Whisper model, a cutting-edge speech recognition system. Whisper excels in transcribing a diverse range of audio types, even with varying accents, converting spoken language into precise written text efficiently.

Read more...

This notebook presents some examples for taking a datarobot project and exporting its model insights as both machine readable files and plots in various file formats.

Read more...

t-SNE (t-Distributed Stochastic Neighbor Embedding) is a powerful technique for dimensionality reduction that can effectively visualize high-dimensional data in a lower-dimensional space. Dimensionality reduction can improve machine learning results by reducing computational complexity of the algorithms, preventing overfitting, and focusing on the most relevant features in the dataset.

Read more...

This accelerator shows how to call a Flask app to easily annotate image data for an ML model.

 

Read more...

The notebook demonstrates how to leverage DataRobot MLOps functionality to predict if a machine learning model is likely to degrade within a specific time period and if infrastructure failures may occur.

Read more...

Predictive AI models are a powerful tool for uncovering subtle predictive relationships between observed variables. But sometimes, you need to draw conclusions about the causal relationship between two variables, not just the observed association. To achieve this "Causal AI", you can use the DataRobot platform and a quasi-experimental technique called "Inverse Propensity of Treatment Weighting". This notebook will apply this technique to data on diabetes hospital patient readmission.

Read more...

This notebook illustrates an end-to-end demand FP&A workflow in DataRobot. Time series forecasting in DataRobot has a huge suite of tools and approaches to handle highly complex multiseries problems.

Read more...

This accelerator outlines how to create, deploy, and monitor a custom inference model with DataRobot's Python client. You can use the Custom Model Workshop to upload a model artifact to create, test, and deploy custom inference models to DataRobot’s centralized deployment hub.

Read more...

Retrieval Augmented Generation (RAG) has become an industry standard method for interfacing with large language models by making them 'context aware'. However, there are a number of situations where a text generation problem is not solved by interacting with large vector database containing many documents. These problems require context but where the context is not known before query time and is often unrelated to existing vector stores. Usually, they are questions about single documents where desirable behavior is to allow the document to be specified at runtime.

Read more...

This accelerator aims to assist DataRobot trial users by providing a guided walkthough of the trial experience. DataRobot suggests that you complete the Flight Delays sample use case in the graphical user interface first, and then return to this accelerator.

Read more...

Deep dive into the utilization of zero-shot text classification for error analysis in machine learning models.

Read more...

This accelerator aims to illustrate how businesses can use DataRobot to effectively and holistically monitor generative AI solutions, using the metrics relevant to them.

Read more...

This accelerator shows how users can quickly and seamlessly enable LLMOPs or Observability in their existing Generative AI Solutions without the need of code refactoring.

Read more...

In this accelerator, we will illustrate how to use Generative AI models to cater to Level 1 requests, allowing support teams to focus on more pressing and high visibility requests. Learning from historical communications, Generative AI Agents can maintain the same standard of support communication that the customers are used to. 

Read more...

Understand all of your models in one place and more easily share your findings

Read more...

A repeatable framework for a production pipeline from multiple tables. 

Read more...

This accelerator is developed for use with Databricks to help users leverage the power of DataRobot for time-series modeling within their Databricks ecosystem.

Read more...

Level up your end-to-end ML lifecycle on the Data Cloud  by integrating DataRobot and Snowflake.

Read more...

This accelerator aims to provide instructions on how to build this type of system using DataRobot's generative AI solution framework. The accelerator shows how you can build a pipeline to create a knowledge base with only trusted research papers, and build a conversational agent that can answer questions from medical professionals.

Read more...

Source data from S3 or Athena, build and evaluate ML models using DataRobot, send predictions back to S3.

Read more...

Leverage popular python packages as well as DataRobot's python client  to recreate and augment lift chart visualizations.

Read more...

Leverage DataRobot's python client to extract predictions and compute custom metrics.

Read more...

How data stored in Azure can be used to train a collection of models.

Read more...

Import data, build and evaluate models, and deploy a model into production to make new predictions with Snowflake.

Read more...

Integrate DataRobot API, Papermill, and MLFlow to automate machine learning making it easier, robust, and easy to share.

Read more...

Build and refine ML models within DataRobot and deploy them to run within AWS SageMaker.

Read more...

Integrate directly into your GCP environment to accelerate your use of machine learning across all of the GCP services.

Read more...

Pair the power of DataRobot with the Spark-backed notebook environment provided by Databricks.

Read more...

Access, understand, and tune blueprints for both preprocessing and model hyperparameters.

Read more...

About AI Accelerators
Discover code-first, modular building blocks for efficient model development and deployment that provide a template for kick-starting a project with DataRobot.

Check out GitHub to learn how to get started.