Code samples

Published

November 20, 2024

Our code samples, based on Jupyter Notebooks, showcase the capabilities and features of the ValidMind Library, while also providing you with useful examples that you can build on and adapt for your own use cases.

Try Notebooks on JupyterHub

Download Notebooks & Datasets

Access Notebooks on GitHub

QuickStart for Customer Churn Model Documentation — Full Suite

Learn how to use dataset and model documentation function on a simple customer churn model. The easiest way to try the QuickStart is on JupyterHub or Google Colaboratory:

JupyterHub
A a web-based platform when you can interact with Jupyter Notebook instances on a shared server. It is commonly used as a collaborative and interactive computing environment for data analysis, scientific research, and programming.
Try it on JupyterHub:

JupyterHub logo

Google Colaboratory (Colab)
A free Jupyter Notebook environment that runs in the cloud. There, you can work with our Jupyter Notebooks by saving your own copy, write and execute code, share your work to collaborate with others in real-time.
Try it on Colab:

Google Colaboratory logo

Code samples for your use case

Automate news summarization using LLMs
9 min
Document a LLM-based text summarization model of news using the CNN DailyMail sample dataset from HuggingFace with the ValidMind Library.
Customize test outputs using output templates
16 min
Run individual tests and tests for experimentation and when exploring and building output templates to create custom results.
Document a California Housing Price Prediction regression model
7 min
Use the California Housing Price Prediction sample dataset from Sklearn to train a simple regression model and document that model with the ValidMind Library.
Document a time series forecasting model
11 min
Use the FRED sample dataset to train a simple time series model and document that model with the ValidMind Library.
Document a time series forecasting model
10 min
Use the FRED sample dataset to train a simple time series model and document that model with the ValidMind Library.
Document an Credit Risk Model
10 min
Build and document an application scorecard model with the ValidMind Library by using Kaggle’s Lending Club sample dataset to build a simple application scorecard.
Document an application scorecard model
16 min
Build and document an application scorecard model with the ValidMind Library by using Kaggle’s Lending Club sample dataset to build a simple application scorecard.
Implement custom tests
15 min
Custom tests extend the functionality of ValidMind, allowing you to document any model or use case with added flexibility.
Integrate external test providers
14 min
Register a custom test provider with the ValidMind Library to run your own tests.
Prompt validation for large language models (LLMs)
8 min
Run and document prompt validation tests for a large language model (LLM) specialized in sentiment analysis for financial news.
Quickstart for ongoing monitoring of models with ValidMind
11 min
Welcome! In this quickstart guide, you’ll learn how to seamlessly monitor your production models using the ValidMind platform.
RAG Model Documentation Demo
22 min
In this notebook, we are going to implement a simple RAG Model for automating the process of answering RFP questions using GenAI. We will see how we can initialize an embedding model, a retrieval model and a generator model with LangChain…
Sentiment analysis of financial data using Hugging Face NLP models
5 min
Document a natural language processing (NLP) model using the ValidMind Library after performing a sentiment analysis of financial news data using several different Hugging Face transformers.
Sentiment analysis of financial data using a large language model (LLM)
5 min
Document a large language model (LLM) specialized in sentiment analysis for financial news using the ValidMind Library.
Summarization of financial data using Hugging Face NLP models
5 min
Document a natural language processing (NLP) model using ValidMind to summarize financial news, based on a dataset of just over 300,000 unique news articles written by journalists at CNN and the Daily Mail.
Summarization of financial data using a large language model (LLM)
4 min
Document a large language model (LLM) using the ValidMind Library. The use case is a summarization of financial news based on a dataset containing just over 300k unique news articles as written by journalists at CNN and the Daily Mail.
No matching items