Skip to main content

Finding optimal threshold based on ROC CURVE.

Project description

Installation

pip install threshold-finder

Usage

Folowing display an usage example.

>>> from threshold_finder.finder import OptimalThresholdFinder, ThresholdFinder, YoudenThresholdFinder
>>> # Example data
>>> true_label = pd.Series([1,1,1,0,0,0])
>>> predicted_proba = pd.Series([0.9, 0.8, 0.7, 0.72, 0.6, 0.5])

>>> # Use a specific finder directly ...
>>> finder = YoudenThresholdFinder()
>>> optimal_threshold = finder.optimal_threshold(true_label, predicted_proba)
>>> print(optimal_threshold)
0.7

>>> # ... Or use the factory
>>> factory = ThresholdFinder()
>>> finder = factory.get_finder(method="youden_statistic")
>>> optimal_threshold = finder.optimal_threshold(true_label, predicted_proba)
>>> print(optimal_threshold)
0.7

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

threshold-finder-0.1.4.tar.gz (1.9 kB view details)

Uploaded Source

Built Distribution

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

threshold_finder-0.1.4-py3-none-any.whl (2.2 kB view details)

Uploaded Python 3

File details

Details for the file threshold-finder-0.1.4.tar.gz.

File metadata

  • Download URL: threshold-finder-0.1.4.tar.gz
  • Upload date:
  • Size: 1.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.1.13 CPython/3.8.10 Linux/5.13.0-1021-azure

File hashes

Hashes for threshold-finder-0.1.4.tar.gz
Algorithm Hash digest
SHA256 94aad3133dd57bca8d8acd5759d6d3172d0c5cfc4831c884698d7427f58a052e
MD5 b4524addcd76f1f0e93a2dac0f9bdca0
BLAKE2b-256 2b29a2dde6925aae38a1d4e90e81c7b64cdbeae78fa08dbd625bce728a0dc6eb

See more details on using hashes here.

File details

Details for the file threshold_finder-0.1.4-py3-none-any.whl.

File metadata

  • Download URL: threshold_finder-0.1.4-py3-none-any.whl
  • Upload date:
  • Size: 2.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.1.13 CPython/3.8.10 Linux/5.13.0-1021-azure

File hashes

Hashes for threshold_finder-0.1.4-py3-none-any.whl
Algorithm Hash digest
SHA256 ef363552324e2e2cb0b0e55e30054978c344abdc8dc834bde01a7a1de962421a
MD5 49d82da42bf1fbd8a981b750e888b4fd
BLAKE2b-256 020eacfb1d5073e74309ea7969d532257140a0801301bfa9be3f50faab626813

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