The most common information retrieval (IR) metrics
Project description
A set of the most common metrics in used in information retrieval.
Usage
The metrics are designed to work for array-like structures and integers:
>>> from irmetrics.topk import rr
>>> y_true = "apple"
>>> y_pred = ["banana", "apple", "grapes"]
>>> rr(y_true, y_pred)
0.5The same function works also for the matrix-like structures:
>>> import numpy as np
>>> from irmetrics.topk import rr
>>> y_trues = np.repeat(y_true, 128)
>>> y_preds = np.repeat([y_pred], 128, axis=0)
>>> # Calculate the Mean Reciprocal Rank
>>> rr(y_trues, y_preds).mean()
0.5
>>> # Calculate the standard deviation for Reciprocal Ranks
>>> rr(y_trues, y_preds).std()
0.0Check the docs for more examples.
Installation
To install with pip, run:
pip install ir-metricsRelease history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
ir-metrics-0.1.6.tar.gz
(16.4 kB
view hashes)
Built Distribution
Close
Hashes for ir_metrics-0.1.6-py3-none-any.whl
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 83b165a9b08620f1ca9fa712fb5a56791bb0ebbc78d17572996f29fc3416f558 |
|
| MD5 | 7cff4b299919c77458cd6f06e4285149 |
|
| BLAKE2b-256 | a9b3f503bc548b8f820641bc52c0684aa230c22f9539e47240550026508667e5 |
