https://github.com/numaproj/numalogic
Collection of operational time series ML models and tools
https://github.com/numaproj/numalogic
autoencoders deep-learning hacktoberfest machine-learning outlier-detection python time-series unsupervised-learning variational-autoencoder
Last synced: 8 months ago
JSON representation
Collection of operational time series ML models and tools
- Host: GitHub
- URL: https://github.com/numaproj/numalogic
- Owner: numaproj
- License: apache-2.0
- Created: 2022-07-12T23:48:54.000Z (over 3 years ago)
- Default Branch: main
- Last Pushed: 2024-10-15T22:18:19.000Z (about 1 year ago)
- Last Synced: 2025-05-15T23:02:50.178Z (8 months ago)
- Topics: autoencoders, deep-learning, hacktoberfest, machine-learning, outlier-detection, python, time-series, unsupervised-learning, variational-autoencoder
- Language: Python
- Homepage: https://numalogic.numaproj.io/
- Size: 46.3 MB
- Stars: 169
- Watchers: 7
- Forks: 31
- Open Issues: 52
-
Metadata Files:
- Readme: README.md
- Changelog: CHANGELOG.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
- Code of conduct: CODE_OF_CONDUCT.md
- Codeowners: .github/CODEOWNERS
Awesome Lists containing this project
README
# numalogic
[](https://github.com/numaproj/numalogic/actions/workflows/ci.yml)
[](https://codecov.io/gh/numaproj/numalogic)
[](https://github.com/ambv/black)
[](LICENSE)
[](https://join.slack.com/t/numaproj/shared_invite/zt-19svuv47m-YKHhsQ~~KK9mBv1E7pNzfg)
[](https://github.com/numaproj/numalogic/releases/latest)
## Background
Numalogic is a collection of ML models and algorithms for operation data analytics and AIOps.
At Intuit, we use Numalogic at scale for continuous real-time data enrichment including
anomaly scoring. We assign an anomaly score (ML inference) to any time-series
datum/event/message we receive on our streaming platform (say, Kafka). 95% of our
data sets are time-series, and we have a complex flowchart to execute ML inference on
our high throughput sources. We run multiple models on the same datum, say a model that is
sensitive towards +ve sentiments, another more tuned towards -ve sentiments, and another
optimized for neutral sentiments. We also have a couple of ML models trained for the same
data source to provide more accurate scores based on the data density in our model store.
An ensemble of models is required because some composite keys in the data tend to be less
dense than others, e.g., forgot-password interaction is less frequent than a status check
interaction. At runtime, for each datum that arrives, models are picked based on a conditional
forwarding filter set on the data density. ML engineers need to worry about only their
inference container; they do not have to worry about data movement and quality assurance.
## Numalogic realtime training
For an always-on ML platform, the key requirement is the ability to train or retrain models
automatically based on the incoming messages. The composite key built at per message runtime
looks for a matching model, and if the model turns out to be stale or missing, an automatic
retriggering is applied. The conditional forwarding feature of the platform improves the
development velocity of the ML developer when they have to make a decision whether to forward
the result further or drop it after a trigger request.
## Key Features
1. Ease of use: simple and efficient tools for predictive data analytics
2. Reusability: all the functionalities can be re-used in various contexts
3. Model selection: easy to compare, validate, fine-tune and choose the model that works best with each data set
4. Data processing: readily available feature extraction, scaling, transforming and normalization tools
5. Extensibility: adding your own functions or extending over the existing capabilities
6. Model Storage: out-of-the-box support for MLFlow and support for other model ML lifecycle management tools
## Use Cases
1. Deployment failure detection
2. System failure detection for node failures or crashes
3. Fraud detection
4. Network intrusion detection
5. Forecasting on time series data
## Getting Started
For set-up information and running your first pipeline using numalogic, please see our [getting started guide](./quick-start.md).
## Installation
Numalogic requires Python 3.8 or higher.
### Prerequisites
Numalogic needs [PyTorch](https://pytorch.org/) and
[PyTorch Lightning](https://pytorch-lightning.readthedocs.io/en/stable/) to work.
But since these packages are platform dependendent,
they are not included in the numalogic package itself. Kindly install them first.
Numalogic supports pytorch versions `2.0.0` and above.
numalogic can be installed using pip.
```shell
pip install numalogic
```
If using mlflow for model registry, install using:
```shell
pip install numalogic[mlflow]
```
### Build locally
1. Install [Poetry](https://python-poetry.org/docs/):
```
curl -sSL https://install.python-poetry.org | python3 -
```
2. To activate virtual env:
```
poetry shell
```
3. To install dependencies:
```
poetry install --with dev,torch
```
If extra dependencies are needed:
```
poetry install --all-extras
```
4. To run unit tests:
```
make test
```
5. To format code style using black and ruff:
```
make lint
```
6. Setup [pre-commit](https://pre-commit.com/) hooks:
```bash
pre-commit install
```
## Contributing
We would love contributions in the numalogic project in one of the following (but not limited to) areas:
- Adding new time series anomaly detection models
- Making it easier to add user's custom models
- Support for additional model registry frameworks
For contribution guildelines please refer [here](https://github.com/numaproj/numaproj/blob/main/CONTRIBUTING.md).
## Resources
- [QUICK_START](docs/quick-start.md)
- [EXAMPLES](examples)
- [CONTRIBUTING](https://github.com/numaproj/numaproj/blob/main/CONTRIBUTING.md)