o .wi?#@sddlmZddlmZddlmZmZmZddlZddl m Z ddlm Z ddl m Z ddlmZdd lmZdd lmZmZdd lmZesKd gZ ddededej fddZGdddeZdS))Sequencedeepcopy)AnyOptionalUnionN)apply_to_collection)Tensor) ModuleList)Metric)_MATPLOTLIB_AVAILABLE)_AX_TYPE_PLOT_OUT_TYPE) WrapperMetricBootStrapper.plotpoissonsizesampling_strategyreturncCs^|dkrtjd}||f}t|j|ddS|dkr+tjt||ddSt d) zResample a tensor along its first dimension with replacement. Args: size: number of samples sampling_strategy: the strategy to use for sampling, either ``'poisson'`` or ``'multinomial'`` Returns: resampled tensor rrdim multinomialT) num_samples replacementzUnknown sampling strategy) torch distributionsPoissonsamplearangerepeat_interleavelongrones ValueError)rrpnr&`/home/ubuntu/sommelier/.venv/lib/python3.10/site-packages/torchmetrics/wrappers/bootstrapping.py_bootstrap_sampler s  r(cseZdZUdZdZeeed<      d ded e d ed ed ee e e fd ede deddffdd ZdededdfddZdee e ffddZdededeffdd Zd!fdd Z d"dee e ee fdeedefddZZS)# BootStrapperaUsing `Turn a Metric into a Bootstrapped`_. That can automate the process of getting confidence intervals for metric values. This wrapper class basically keeps multiple copies of the same base metric in memory and whenever ``update`` or ``forward`` is called, all input tensors are resampled (with replacement) along the first dimension. Args: base_metric: base metric class to wrap num_bootstraps: number of copies to make of the base metric for bootstrapping mean: if ``True`` return the mean of the bootstraps std: if ``True`` return the standard deviation of the bootstraps quantile: if given, returns the quantile of the bootstraps. Can only be used with pytorch version 1.6 or higher raw: if ``True``, return all bootstrapped values sampling_strategy: Determines how to produce bootstrapped samplings. Either ``'poisson'`` or ``multinomial``. If ``'possion'`` is chosen, the number of times each sample will be included in the bootstrap will be given by :math:`n\sim Poisson(\lambda=1)`, which approximates the true bootstrap distribution when the number of samples is large. If ``'multinomial'`` is chosen, we will apply true bootstrapping at the batch level to approximate bootstrapping over the hole dataset. kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info. Example:: >>> from pprint import pprint >>> from torch import randint >>> from torchmetrics.wrappers import BootStrapper >>> from torchmetrics.classification import MulticlassAccuracy >>> base_metric = MulticlassAccuracy(num_classes=5, average='micro') >>> bootstrap = BootStrapper(base_metric, num_bootstraps=20) >>> bootstrap.update(randint(5, (20,)), randint(5, (20,))) >>> output = bootstrap.compute() >>> pprint(output) {'mean': tensor(0.2089), 'std': tensor(0.0772)} Tfull_state_update NFr base_metricnum_bootstrapsmeanstdquantilerawrkwargsrc  stjdi|ttstdtfddt|D|_||_||_ ||_ ||_ ||_ d} || vrBtd| d|||_ dS)NzKExpected base metric to be an instance of torchmetrics.Metric but received csg|]}tqSr&r).0_r,r&r' nz)BootStrapper.__init__..)rrz5Expected argument ``sampling_strategy`` to be one of z but received r&)super__init__ isinstancer r#r rangemetricsr-r.r/r0r1r) selfr,r-r.r/r0r1rr2allowed_sampling __class__r5r'r9]s&  zBootStrapper.__init__argsc Ost|tjt}t|tjt}t|dkr|d}nt|dkr(tt|}ntdt|j D]5}t ||j d |j }|dkrEq1t|tjtjd|d}t|tjtjd|d} |j|j|i| q1dS)ztUpdate the state of the base metric. Any tensor passed in will be bootstrapped along dimension 0. rzMNone of the input contained tensors, so could not determine the sampling size)r)rindexN)rrr lennextitervaluesr#r;r-r(rtodevicenumel index_selectr<update) r=rAr2 args_sizes kwargs_sizesridx sample_idxnew_args new_kwargsr&r&r'rK~s    zBootStrapper.updatecCsxtjdd|jDdd}i}|jr|jdd|d<|jr%|jdd|d<|jdur3t||j|d<|jr:||d <|S) zCompute the bootstrapped metric values. Always returns a dict of tensors, which can contain the following keys: ``mean``, ``std``, ``quantile`` and ``raw`` depending on how the class was initialized. cSsg|]}|qSr&)compute)r3mr&r&r'r6r7z(BootStrapper.compute..rrr.r/Nr0r1)rstackr<r.r/r0r1)r= computed_vals output_dictr&r&r'rRs zBootStrapper.computecstt|j|i|S)z9Use the original forward method of the base metric class.)r8rforward)r=rAr2r?r&r'rWszBootStrapper.forwardcs"|jD]}|qtdS)z#Reset the state of the base metric.N)r<resetr8)r=rSr?r&r'rXs  zBootStrapper.resetvalaxcCs |||S)aPlot a single or multiple values from the metric. Args: val: Either a single result from calling `metric.forward` or `metric.compute` or a list of these results. If no value is provided, will automatically call `metric.compute` and plot that result. ax: An matplotlib axis object. If provided will add plot to that axis Returns: Figure and Axes object Raises: ModuleNotFoundError: If `matplotlib` is not installed .. plot:: :scale: 75 >>> # Example plotting a single value >>> import torch >>> from torchmetrics.wrappers import BootStrapper >>> from torchmetrics.regression import MeanSquaredError >>> metric = BootStrapper(MeanSquaredError(), num_bootstraps=20) >>> metric.update(torch.randn(100,), torch.randn(100,)) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> # Example plotting multiple values >>> import torch >>> from torchmetrics.wrappers import BootStrapper >>> from torchmetrics.regression import MeanSquaredError >>> metric = BootStrapper(MeanSquaredError(), num_bootstraps=20) >>> values = [ ] >>> for _ in range(3): ... values.append(metric(torch.randn(100,), torch.randn(100,))) >>> fig_, ax_ = metric.plot(values) )_plot)r=rYrZr&r&r'plots *r)r+TTNFr)rN)NN)__name__ __module__ __qualname____doc__r*rbool__annotations__r intrfloatr strrr9rKdictrRrWrXrr rr\ __classcell__r&r&r?r'r)7sP #  !r))r)collections.abcrcopyrtypingrrrrlightning_utilitiesrr torch.nnr torchmetrics.metricr torchmetrics.utilities.importsr torchmetrics.utilities.plotr rtorchmetrics.wrappers.abstractr__doctest_skip__rcrer(r)r&r&r&r's,