Instructive and educational notebooks
Top Notebooks
-
Analyze audio recordings
This notebook provides an example of how to prompt Gemini Flash using an audio file. In this case, you'll use a sound recording of President John F. Kennedy’s 1961 State of the Union address.
See notebook -
Exploratory Data Analysis with Python
Exploratory Data Analysis or (EDA) is understanding the data sets by summarizing their main characteristics and, usually, plotting them visually.
See notebook -
Get started with Video generation using Veo
Learn how to use Veo to generate videos from text prompts and images. Control lighting, camera, audio, dialog, and more!
See notebook
Gemini API
-
Create a marketing campaign
This notebook contains a code example of using the Gemini API to analyze a a product sketch (in this case, a drawing of a Jet Backpack), create a marketing campaign for it, and output taglines in JSON format.
See notebook -
Analyze audio recordings
This notebook provides an example of how to prompt Gemini Flash using an audio file. In this case, you'll use a sound recording of President John F. Kennedy’s 1961 State of the Union address.
See notebook -
Use system instructions in chat
System instructions allow you to steer the behavior of the model. By setting the system instruction, you are giving the model additional context to understand the task, provide more customized responses, and adhere to guidelines over the user interaction. Product-level behavior can be specified here, separate from prompts provided by end users.
See notebook -
Function calling
Using function calling allows you to control how the Gemini API acts when tools have been specified
See notebook -
Prompting with a text file
This notebook provides a quick example of how to prompt Gemini using a text file. In this case, you'll use a 400 page transcript from Apollo 11.
See notebook -
Compare Gemini and ChatGPT responses
Use Google's latest model release, Gemini, to teach you what you want to know and compare those with ChatGPT's responses. The models are specifically prompted not to generate extra text to make it easier to compare any differences.
See notebook
AI & Machine Learning
-
Inspect Rich Documents with Gemini Multimodality and Multimodal RAG
Use this self paced lab from Google Cloud to inspect rich documents with Gemini.
See notebook -
Music Transcriptions with Transformers
This notebook is an interactive demo of a few music transcription models created by Google's Magenta team. You can upload audio and have one of our models automatically transcribe it.
See notebook -
Generating Music with Transformers
This Colab notebook lets you play with pretrained Transformer models for piano music generation, based on the music Transformer model introduced by Huang et al. in 2018.
See notebook -
Text Classification with Movie Reviews
This notebook classifies movie reviews as positive or negative using the text of the review. This is an example of binary—or two-class—classification, an important and widely applicable kind of machine learning problem.
See notebook -
Create and train a Custom RL Agent
This colab demonstrates how to create a variant of a provided agent (Example 1) and how to create a new agent from scratch (Example 2).
See notebook -
Visualize RL Agent Training on TensorBoard
This colab allows you to easily view the trained baselines with Tensorboard (even if you don't have Tensorboard on your local machine!). Simply specify the game you would like to visualize and then run the cells in order.
See notebook -
Hyperparameter Tuning with TensorBoard
The HParams dashboard in TensorBoard provides several tools to help with this process of identifying the best experiment or most promising set of hyperparameters.
See notebook
Data & Analytics
-
10 Minutes to RAPIDS cuDF's pandas accelerator mode
cuDF is a Python GPU DataFrame library for loading, joining, aggregating, filtering, and otherwise manipulating tabular data using a DataFrame style API in the style of pandas.
See notebook -
Working with time series in Python
This notebook introduces how to work with timestamps, time intervals, periods, time deltas, and durations.
See notebook -
Exploratory Data Analysis Intro
Getting started with data analysis on colab using python.
See notebook -
Advanced Business Analytics and Mathematics
Programmatic Google Colab Notebook Series (2018-2023)
See on GitHub -
Twitter Pulse Checker
This is a quick and dirty way to get a sense of what's trending on Twitter related to a particular Topic. For my use case, I am focusing on the city of Seattle but you can easily apply this to any topic.
See notebook
Cloud Computing
-
Colab + BigQuery - Perfect Together
The goal of this Colab notebook is to highlight some benefits of using Google BigQuery and Colab together to perform some common data science tasks.
See notebook -
Online prediction with BigQuery ML
In this tutorial, you learn how to train and deploy a churn prediction model for real-time inference, with the data in BigQuery and model trained using BigQuer registered to Vertex AI Model Registry, and deployed to an...
See notebook -
Serving PyTorch image models with prebuilt containers on Vertex Al
In this tutorial containers on Vertex Al package and deploy a PyTorch image classification model using a prebuilt Vertex Al container with TorchServe for serving online and batch predictions
See notebook -
AutoML training tabular binary classification model for batch explanation
In this tutorial, you learn to use AutoML to create a tabular binary classification model from a Python script, and then learn to use Vertex Al Batch Prediction to make predictions with explanations
See notebook
Data Visualization
-
Explore Patent Database with ML
Patent landscaping is an analytical approach commonly used by corporations, patent offices, and academics to better understand the potential technical coverage of a large number of patents where manual review (i.e., actually readin..
Read blog post -
-
Visualize Chemical Structures in a Notebook
Molecules can be represented as strings with SMILES. Simplified molecular-input line-entry system (SMILES) is a string based representation of a molecule.
See notebook -
Exploratory Data Analysis with Python
Exploratory Data Analysis or (EDA) is understanding the data sets by summarizing their main characteristics and, usually, plotting them visually.
See notebook
Education
-
-
-
Advanced Python Tutorial
In this tutorial, we will be exploring some advanced Python concepts and techniques using Google Colab
See notebook
Fun
-
Fast Style Transfer for Arbitrary Styles
Based on the model code in magenta and the publication: Exploring the structure of a real-time, arbitrary neural artistic stylization network.
See notebook -
Brax - Physics Environments for Simulations
Brax simulates physical systems made up of rigid bodies, joints, and actutators.
See notebook -
Predict Shakespeare with Keras+CloudTPU
This example uses tf.keras to build a language model and train it on a Cloud TPU. This language model predicts the next character of text given the text so far. The trained model can generate new snippets of text that read in a similar style to th...
See notebook -
Binary Classification of Rice
Examine a rice dataset and create a binary classifier to sort grains of rice into two species. Then evaluate the performance of the model.
See notebook
Science
-
AlphaFold
This Colab notebook allows you to easily predict the structure of a protein using a slightly simplified version of AlphaFold v2.3.2.
See notebook -
AlphaTensor
This Colab shows how to load the provided .npz file with rank- 49 factorizations of Y4 in standard arithmetic, and how to compute the invariants IZ and :IC in order to demonstrate that these factorizations are mutually...
See notebook -
Molecular Dynamics Simulations
Notebook for running Molecular Dynamics (MD) simulations using OpenMM engine and AMBER force field for PROTEIN systems. This notebook is a supplementary material of the paper Making it rain: Cloud-based molecular simulation...
See notebook -
Google Earth API
This notebook demonstrates how to setup the Earth Engine Python API in Colab and provides several examples of how to print and visualize Earth Engine processed data.
See notebook