PrecisionRecallCurve

class ignite.metrics.PrecisionRecallCurve(output_transform=<function PrecisionRecallCurve.<lambda>>, check_compute_fn=False, device=device(type='cpu'), skip_unrolling=False)

Compute precision-recall pairs for different probability thresholds for binary classification task by accumulating predictions and the ground-truth during an epoch and applying sklearn.metrics.precision_recall_curve .

Parameters

• output_transform (Callable) – a callable that is used to transform the Engine’s process_function’s output into the form expected by the metric. This can be useful if, for example, you have a multi-output model and you want to compute the metric with respect to one of the outputs.

• check_compute_fn (bool) – Default False. If True, precision_recall_curve is run on the first batch of data to ensure there are no issues. User will be warned in case there are any issues computing the function.

• skip_unrolling (bool) – specifies whether output should be unrolled before being fed to update method. Should be true for multi-output model, for example, if y_pred contains multi-ouput as (y_pred_a, y_pred_b) Alternatively, output_transform can be used to handle this.

• device (Union[str, device]) –

Note

PrecisionRecallCurve expects y to be comprised of 0’s and 1’s. y_pred must either be probability estimates or confidence values. To apply an activation to y_pred, use output_transform as shown below:

def sigmoid_output_transform(output):
    y_pred, y = output
    y_pred = torch.sigmoid(y_pred)
    return y_pred, y
avg_precision = PrecisionRecallCurve(sigmoid_output_transform)

Examples

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.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)

y_pred = torch.tensor([0.0474, 0.5987, 0.7109, 0.9997])
y_true = torch.tensor([0, 0, 1, 1])
prec_recall_curve = PrecisionRecallCurve()
prec_recall_curve.attach(default_evaluator, 'prec_recall_curve')
state = default_evaluator.run([[y_pred, y_true]])

print("Precision", [round(i, 4) for i in state.metrics['prec_recall_curve'][0].tolist()])
print("Recall", [round(i, 4) for i in state.metrics['prec_recall_curve'][1].tolist()])
print("Thresholds", [round(i, 4) for i in state.metrics['prec_recall_curve'][2].tolist()])

Precision [0.5, 0.6667, 1.0, 1.0, 1.0]
Recall [1.0, 1.0, 1.0, 0.5, 0.0]
Thresholds [0.0474, 0.5987, 0.7109, 0.9997]

Changed in version 0.5.1: skip_unrolling argument is added.

Methods

compute

Computes the metric based on its accumulated state.

compute()

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.