Ambrosia
Ambrosia is a Python library for A/B tests design, split and effect measurement. It provides rich set of methods for conducting full A/B test pipeline.
An experiment design stage is performed using metrics historical data which could be processed in both forms of pandas and spark dataframes with either theoretical or empirical approach.
Group split methods support different strategies and multi-group split, which allows to quickly create control and test groups of interest.
Final effect measurement stage is conducted via testing tools that are able to return relative and absolute effects and construct corresponding confidence intervalsfor continious and binary variables. Testing tools as well as design ones support significant number of statistical criteria, like t-test, non-parametric, and bootstrap.
For additional A/B tests support library provides features and tools for data preproccesing and experiment acceleration.
Key functionality
Pilots design ✈
Multi-group split 🎳
Matching of new control group to the existing pilot 🎏
Getting the experiments result evaluation as p-value, point estimate of effect and confidence interval 🎞
Experiments acceleration 🎢
Documentation
For more details, see the Documentation and Tutorials.
Installation
Stable version is released on every tag to main branch.
pip install ambroziaAmbrosia requires Python 3.7+
Usage
Designer
from ambrozia.designer import Designer
designer = Designer(dataframe=df, effects=1.2, metrics='portfel_clc') # 20% effect, and loaded data frame df
designer.run('size')Splitter
from ambrozia.splitter import Splitter
splitter = Splitter(dataframe=df, id_column='id') # loaded data frame df with column with id - 'id'
splitter.run(groups_size=500, method='simple')Tester
from ambrozia.tester import Tester
tester = Tester(dataframe=df, column_groups='group') # loaded data frame df with groups info 'group'
tester.run(metrics='retention', method='theory', criterion='ttest')Development
To install all requirements run
make installYou must have python3 and poetry installed.
For autoformatting run
make autoformatFor linters check run
make lintFor tests run
make testFor coverage run
make coverageTo remove virtual environment run
make cleanCommunication
Developers and evangelists:
1 maintainer
Metadata
1 maintainer
Release files for ambrozia 0.1.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| Ambrozia-0.1.2.tar.gz | 74.7 kB | Without provenance | Details for Ambrozia-0.1.2.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| Ambrozia-0.1.2-py3-none-any.whl | Python 3 | none | any | Details for Ambrozia-0.1.2-py3-none-any.whl |
Total release size: 179.4 kB
Release files / Ambrozia-0.1.2.tar.gz
| Download URL | Ambrozia-0.1.2.tar.gz |
|---|---|
| Size | 74.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
11d564b52251cd44e8e1489f476f9913696d70f647fe9a0a6b5de3360cb80c92
|
|
BLAKE2b-256 checksum How to use checksums |
570bd9759911f6b543473d51d2f92e619910aa66b67c1edc9f0d1519b1070c3a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/1.1.15 CPython/3.8.14 Linux/5.15.0-1022-azure
|
Release files / Ambrozia-0.1.2-py3-none-any.whl
| Download URL | Ambrozia-0.1.2-py3-none-any.whl |
|---|---|
| Size | 104.6 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
658b00b28e3ab09cde16ef2850d24a3a98af785e74a063ce892dc5ed1d6eac4a
|
|
BLAKE2b-256 checksum How to use checksums |
645c13181d3b4df36c7712e154d5b992a14f7d03bfa9c7ce42ed1d46bf557b37
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/1.1.15 CPython/3.8.14 Linux/5.15.0-1022-azure
|
Security for ambrozia 0.1.2
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
