twinLab - Probabilistic Machine Learning for Engineers
twinLab is a tool for augmenting engineering workflows with Probabilistic Machine Learning. It enables users to quickly and easily build real-time emulators of their simulations, experimental set-ups, or sensor networks. Then they can make predictions, make recommendations, perform optimisations, and calibrate physics parameters from data.
twinLab comes with built-in uncertainty quantification (UQ), which means that even with sparse or noisy data, users can maximise their understanding of the design space and surrogate model with confidence.
For help, or to arrange a trial, please email: twinlab@digilab.co.uk or fill in the contact form here.
Getting Started
Step 1: Install the Python Interface
pip install twinlab
Step 2: Configure your user details
If you don't yet have one, you'll need to request a trial. Please email twinlab@digilab.co.uk or fill in the contact form here.
Method 1: Use tl.set_user and tl.set_api_key within a script. Be careful not to publicly expose your API key if sharing files.
import twinlab as tl
tl.set_user("<your_username>")
tl.set_api_key("<your_api_key>")
Method 2: Create a .env file containing TWINLAB_USER and TWINLAB_API_KEY in your working directory. You can then import twinlab as tl in your Python script / notebook as normal. The API key will be read from .env automatically.
echo "TWINLAB_USER=<your_username>" >> .env
echo "TWINLAB_API_KEY=<your_api_key>" >> .env
Step 3: Run an Example
Here’s an example script to get you started:
import pandas as pd
import twinlab as tl
# Load an example dataset and upload to twinLab
dataset = tl.Dataset("quickstart")
df = tl.load_example_dataset("quickstart")
dataset.upload(df)
# Train a machine-learning emulator for the data
emulator = tl.Emulator("test-emulator")
emulator.train(dataset, ["x"], ["y"])
# Evaluate the emulator on some unseen data
sample_points = pd.DataFrame({"x": [0.25, 0.5, 0.75]})
predict_mean, predict_std = emulator.predict(sample_points)
# Explore the results
print(predict_mean)
print(predict_std)
Documentation
Find more examples, tutorials, and the full reference guide for our Python Interface in our documentation.
Speak to an Expert
Our Solution Engineers are here to provide technical support and help you maximise the value of twinLab. Please email twinlab@digilab.co.uk or fill in the contact form here.
4 maintainers
Metadata
4 maintainers
Release files for twinlab 2.21.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| twinlab-2.21.0.tar.gz | 51.3 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| twinlab-2.21.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 110.1 kB
Release files / twinlab-2.21.0.tar.gz
| Download URL | twinlab-2.21.0.tar.gz |
|---|---|
| Size | 51.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
c55fdce01d4bdbe984d32a7734c50c4f01882d15b3e58e808d16b881a565bc11
|
|
BLAKE2b-256 checksum How to use checksums |
610e96302c41a40ec1d223518040ac1c2b2f87ca98fc9ceb4cfc9eed0e2e9fdc
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/2.0.1 CPython/3.13.2 Darwin/24.3.0
|
Release files / twinlab-2.21.0-py3-none-any.whl
| Download URL | twinlab-2.21.0-py3-none-any.whl |
|---|---|
| Size | 58.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
5f707c43a012f6b4a6dc413e8447b00f6f20302d720b8ca4649915a90aa054a2
|
|
BLAKE2b-256 checksum How to use checksums |
ff8a01b4f451ccb8d517f96c931196c32ad3d59d3a2e1047c0aa1100410c9455
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/2.0.1 CPython/3.13.2 Darwin/24.3.0
|
