Skip to main content

metriks is a Python package of commonly used metrics for evaluating information retrieval models.

Project description

logo/metriks-logo.svg

Python Version build coverage


metriks is a Python package of commonly used metrics for evaluating information retrieval models.

Available Metrics

Python API Description
metriks.recall_at_k(y_true, y_prob, k) Calculates recall at k for binary classification ranking problems.
metriks.precision_at_k(y_true, y_prob, k) Calculates precision at k for binary classification ranking problems.
metriks.mean_reciprocal_rank(y_true, y_prob) Gets a positional score on how well you did at rank 1, rank 2, etc.
metriks.ndcg(y_true, y_prob, k) A score for measuring the quality of a set of ranked results.
label_mean_reciprocal_rank(y_true, y_prob) Determines the average rank each label was placed across samples. Only labels that are relevant in the true data set are considered in the calculation.
metriks.confusion_matrix_at_k(y_true, y_prob, k) Generates binary predictions from probabilities by evaluating the top k items (in ranked order by y_prob) as true.

Installation

Install using pip

pip install metriks

Alternatively, specific distributions can be downloaded from the github release page. Once downloaded, install the .tar.gz file directly:

pip install metriks-\*.tar.gz

Development

1. (Optional) If you have virtualenv and virtualenvwrapper create a new virtual environment:

mkvirtualenv metriks

This isolates your specific project dependencies to avoid conflicts with other projects.

2. Clone and install the repository:

git clone git@github.com:intuit/metriks.git
cd metriks
pip install -e .

This will install a version to an isolated environment in editable mode. As you update the code in the repository, the new code will immediately be available to run within the environment (without the need to pip install it again)

3. Run the tests using tox:

pip install tox
tox

Tox will run all of the tests in isolated environments

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 metriks, version 0.0.2
Filename, size File type Python version Upload date Hashes
Filename, size metriks-0.0.2-py3-none-any.whl (7.4 kB) File type Wheel Python version py3 Upload date Hashes View hashes
Filename, size metriks-0.0.2.tar.gz (13.9 kB) File type Source Python version None Upload date Hashes View hashes

Supported by

Elastic Elastic Search Pingdom Pingdom Monitoring Google Google BigQuery Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN SignalFx SignalFx Supporter DigiCert DigiCert EV certificate StatusPage StatusPage Status page