MRR#

class ignite.metrics.rec_sys.MRR(top_k, ignore_zero_hits=True, relevance_threshold=1.0, output_transform=<function MRR.<lambda>>, device=device(type='cpu'), skip_unrolling=False)[source]#

Calculates the Mean Reciprocal Rank (MRR) at k for Recommendation Systems.

MRR measures the average of the reciprocal of the rank of the first relevant item in the predicted list. It is widely used in retrieval systems, recommendation systems, and RAG pipelines.

\text{MRR}@K = \frac{1}{N} \sum_{i=1}^{N} \frac{1}{\text{rank}_i}

where $\text{rank}_i$ is the rank (1-indexed) of the first relevant item in the top-K predictions for user $i$ . If no relevant item is found in the top-K, the reciprocal rank for that user is 0.

update must receive output of the form (y_pred, y).
y_pred is expected to be raw logits or probability score for each item in the catalog.
y is expected to be binary (only 0s and 1s) values where 1 indicates relevant item. Graded relevance labels are also supported via relevance_threshold.
y_pred and y are only allowed shape $(batch, num\_items)$ .
returns a list of MRR ordered by the sorted values of top_k.

Parameters:

top_k (list[int]) – a list of sorted positive integers that specifies k for calculating MRR@top-k.
ignore_zero_hits (bool) – if True, users with no relevant items (ground truth tensor being all zeros) are ignored in computation of MRR. If set False, such users are counted as having reciprocal rank of 0. By default, True.
relevance_threshold (float) – minimum label value to be considered relevant. Defaults to 1, which handles standard binary labels and graded relevance scales (e.g. TREC-style 0-4) by treating any label >= 1 as relevant.
output_transform (Callable) – a callable that is used to transform the Engine’s process_function’s output into the form expected by the metric. The output is expected to be a tuple (prediction, target) where prediction and target are tensors of shape (batch, num_items).
device (str | device) – specifies which device updates are accumulated on. Setting the metric’s device to be the same as your update arguments ensures the update method is non-blocking. By default, CPU.
skip_unrolling (bool) – specifies whether input should be unrolled or not before being processed. Should be true for multi-output models..

Examples

To use with Engine and process_function, simply attach the metric instance to the engine. The output of the engine’s process_function needs to be in the format of (y_pred, y). If not, output_tranform can be added to the metric to transform the output into the form expected by the metric.

For more information on how metric works with Engine, visit Attach Engine API.

from collections import OrderedDict

import torch
from torch import nn, optim

from ignite.engine import *
from ignite.handlers import *
from ignite.metrics import *
from ignite.metrics.clustering import *
from ignite.metrics.fairness import *
from ignite.metrics.rec_sys import *
from ignite.metrics.regression import *
from ignite.utils import *

# create default evaluator for doctests

def eval_step(engine, batch):
    return batch

default_evaluator = Engine(eval_step)

# create default optimizer for doctests

param_tensor = torch.zeros([1], requires_grad=True)
default_optimizer = torch.optim.SGD([param_tensor], lr=0.1)

# create default trainer for doctests
# as handlers could be attached to the trainer,
# each test must define his own trainer using `.. testsetup:`

def get_default_trainer():

    def train_step(engine, batch):
        return batch

    return Engine(train_step)

# create default model for doctests

default_model = nn.Sequential(OrderedDict([
    ('base', nn.Linear(4, 2)),
    ('fc', nn.Linear(2, 1))
]))

manual_seed(666)

ignore_zero_hits=True case

metric = MRR(top_k=[1, 2, 3, 4])
metric.attach(default_evaluator,"mrr")
y_pred=torch.Tensor([
    [4.0, 2.0, 3.0, 1.0],
    [1.0, 2.0, 3.0, 4.0]
])
y_true=torch.Tensor([
    [0.0, 0.0, 1.0, 1.0],
    [0.0, 0.0, 0.0, 0.0]
])
state = default_evaluator.run([(y_pred, y_true)])
print(state.metrics["mrr"])

[0.0, 0.5, 0.5, 0.5]

ignore_zero_hits=False case

metric = MRR(top_k=[1, 2, 3, 4], ignore_zero_hits=False)
metric.attach(default_evaluator,"mrr")
y_pred=torch.Tensor([
    [4.0, 2.0, 3.0, 1.0],
    [1.0, 2.0, 3.0, 4.0]
])
y_true=torch.Tensor([
    [0.0, 0.0, 1.0, 1.0],
    [0.0, 0.0, 0.0, 0.0]
])
state = default_evaluator.run([(y_pred, y_true)])
print(state.metrics["mrr"])

[0.0, 0.25, 0.25, 0.25]

New in version 0.6.0.

Methods

`compute`	Computes the metric based on its accumulated state.
`reset`	Resets the metric to its initial state.
`update`	Updates the metric's state using the passed batch output.

compute()[source]#

Computes the metric based on its accumulated state.

By default, this is called at the end of each epoch.

Returns:

the actual quantity of interest. However, if a Mapping is returned, it will be (shallow) flattened into engine.state.metrics when completed() is called.

Return type:

Any

Raises:

NotComputableError – raised when the metric cannot be computed.

reset()[source]#

Resets the metric to its initial state.

By default, this is called at the start of each epoch.

Return type:: None

update(output)[source]#

Updates the metric’s state using the passed batch output.

By default, this is called once for each batch.

Parameters:: output (tuple[torch.Tensor, torch.Tensor]) – the is the output from the engine’s process function.
Return type:: None

MRR#

Search Docs