Skip to main content

Библиотека для расчета минимального определяемого эффекта (MDE) в A/B тестах.

Project description

medoed

medoed

Библиотека для расчета минимального определяемого эффекта (MDE) в A/B тестах.

Установка

pip install medoed

Пример использования

from medoed import MDECalculator

mde_calculator = MDECalculator(
    pre_experiment_data=pre_experiment_data,
    date_field='install_date',
    metrics=['revenue', 'retention'],
    historical_data=historical_data,
    strata=['geo', 'os'],
    alpha=0.05,
    power=0.8,
    outliers_handling_method='replace_threshold',
    outliers_threshold_quantile=0.995,
    outlier_type='upper',
    test_days=30,
    sample_size=10000
)

df_mde = mde_calculator.calculate(n_processes=8)
fig = mde_calculator.create_mde_plot(df_mde)
fig.show()

Требования

  • Python 3.8+
  • pandas 1.3+
  • numpy 1.20+
  • scipy 1.7+
  • statsmodels 0.13+
  • otvertka 0.1.6+
  • tqdm 4.65+

Лицензия

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

medoed-0.1.6.tar.gz (269.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

medoed-0.1.6-py3-none-any.whl (8.1 kB view details)

Uploaded Python 3

File details

Details for the file medoed-0.1.6.tar.gz.

File metadata

  • Download URL: medoed-0.1.6.tar.gz
  • Upload date:
  • Size: 269.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.0.1 CPython/3.13.0

File hashes

Hashes for medoed-0.1.6.tar.gz
Algorithm Hash digest
SHA256 cf7a92429c42006e9efde2191d411c9f57a5380c2eb1c5de7639866f14107809
MD5 d8aa21a1dbbe6e77598614d000af9fe4
BLAKE2b-256 59dce4baa67180f9e2569acddfdb5f619bb979249717d9ea6978ae9c4ff58645

See more details on using hashes here.

File details

Details for the file medoed-0.1.6-py3-none-any.whl.

File metadata

  • Download URL: medoed-0.1.6-py3-none-any.whl
  • Upload date:
  • Size: 8.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.0.1 CPython/3.13.0

File hashes

Hashes for medoed-0.1.6-py3-none-any.whl
Algorithm Hash digest
SHA256 641135bf8c88315dd46c753b771580f8bc95bc0b4d5b7d83066269b739ad7d67
MD5 ec2bfcd5f104c26df8fe1e9386efc6f9
BLAKE2b-256 0b580877bb44fe6167ed293cde535dd706b7de5b4dd5745d959e0f3dbee5443b

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page