Skip to main content

A supervised learning tool for estimating task duration.

Project description

Estimator

Pipeline Status PyPI Status

A Python script for automatically estimating work hours in Jira using supervised learning.

Installation

Install the Python 3 package:

pip install estimator

Usage

Fill out the login credentials in your config.yaml. A sample file to pull data from Jira would look like:

source: jira
server: https://myname.atlassian.net
username: myusername
password: mypassword
projects: MYPROJECTKEY
regressor:
    cls: KernelRidge
    stop_words: ''
    ngram_range: [1, 6]
    analyzer: char
    min_df: 0.0
minimum_estimate_minutes: 15
hour_update_fields:
-   Story Points

Retrieve training data:

estimator config.yaml retrieve

Generate all possible algorithm and setting combinations:

estimator config.yaml generation-combinations

Test all combinations to find which algorithm works best:

estimator config.yaml test-combinations

Fill in the regressor settings in your config.yaml, then train your final regressor:

estimator config.yaml train

Find the algorithm's accuracy:

estimator config.yaml test

Dryrun the application of the regressor to unestimated tickets:

estimator config.yaml apply

Save these estimates with:

estimator config.yaml apply --save

To combine the above retrieve, train and apply steps into a single command, just add --retrain to the apply command:

estimator config.yaml apply --save --retrain

Development

Run tests locally with:

tox

To run tests for a specific environment (e.g. Python 3.7):

tox -e py37

To run a specific test:

export TESTNAME=.test_learning; tox -e py37

Project details


Download files

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

Files for task-estimator, version 0.9.2
Filename, size File type Python version Upload date Hashes
Filename, size task-estimator-0.9.2.tar.gz (12.3 kB) File type Source Python version None Upload date Hashes View

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Huawei Huawei PSF Sponsor Microsoft Microsoft PSF Sponsor NVIDIA NVIDIA PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page