Fix typos and docstring issues across botorch (meta-pytorch#3211)

Summary:
Pull Request resolved: meta-pytorch#3211

Fix typos, docstring errors, and a copy-paste bug across botorch (excluding acquisition/).

**models/**
- pairwise_gp.py: "occured" → "occurred", "creteria" → "criteria" (x2), "substition" → "substitution", "the the" → "the", "will filters" → "will be filtered"
- map_saas.py: "distrbution" → "distribution", "MixtureGaussiaPosterior" → "GaussianMixturePosterior", "callling" → "calling", "outcome transforms" → "outcome transform"
- fully_bayesian.py: "the a" → "a"
- transforms/outcome.py: "transfomred" → "transformed" (x4), "currenlty" → "currently", "min_stddv" → "min_stdv" in docstring
- transforms/input.py: "acqusition" → "acquisition", added missing `almost_zero` param docs
- kernels/linear_truncated_fidelity.py: "parmeters" → "parameters", "the the determistic" → "the deterministic"
- gpytorch.py: "its is" → "it is" (x2), "in in" → "in", "which can overwritten" → "which can be overwritten"
- higher_order_gp.py: "its is" → "it is", "min_stddv" → "min_stdv" in docstring
- model.py: "constitutent" → "constituent", "singe-model" → "single-model"
- relevance_pursuit.py: "exluding" → "excluding", copy-paste "expanded" → "contracted" in support_contraction docstring
- kernels/contextual_lcea.py: "unbserverable" → "unobservable", "indictor" → "indicator", "contruct" → "construct"
- kernels/contextual_sac.py: "oberseving" → "observing", "compponent" → "component"
- contextual_multioutput.py: "contruct" → "construct"

**optim/**
- initializers.py: "dimesional" → "dimensional" (x2), "Intutively" → "Intuitively" (x3), "initital" → "initial", "acquisiton" → "acquisition", swapped class name qHVKG → qKG in docstring, "using to the" → "using the"
- optimize.py: "sequentually" → "sequentially", "optmizers" → "optimizers", "occurences" → "occurrences"
- parameter_constraints.py: "inptus" → "inputs"

**utils/**
- sampling.py: "A a" → "A"
- multi_objective/hypervolume.py: "acqusition" → "acquisition", removed duplicate "have points that have"
- context_managers.py: "orginal" → "original" (x2)
- probability/lin_ess.py: "multivariante" → "multivariate"
- probability/mvnxpb.py: "G. Tring" → "G. Trinh" (author name)

**test_functions/**
- synthetic.py: "synthtetic" → "synthetic" (x2), "mininimum" → "minimum", "aproximate" → "approximate", "unreacheable" → "unreachable", "proble problem" → "problem"
- sensitivity_analysis.py: "dgsm_gradient_bas" → "dgsm_gradient_abs", **BUG FIX**: gradient_measure used dx_1 for all 3 entries instead of dx_1, dx_2, dx_3
- multi_objective.py: "inputsto" → "inputs to"
- multi_fidelity.py: "ther" → "there"
- base.py: "ouf" → "of"

**exceptions/**
- warnings.py: removed phantom `logei_name` param from docstring

Reviewed By: dme65

Differential Revision: D94993014

fbshipit-source-id: 2324a2b0b665103b1a680b01014c30d08c524651

Author: saitcakmak

botorch/exceptions/warnings.py

@@ -72,7 +72,6 @@ def legacy_ei_numerics_warning(legacy_name: str) -> None:
 
     Args:
         legacy_name: The name of the legacy EI acquisition function.
-        logei_name: The name of the associated LogEI acquisition function.
     """
     legacy_to_logei = {
         "ExpectedImprovement": "LogExpectedImprovement",

botorch/models/contextual_multioutput.py

@@ -142,7 +142,7 @@ def __init__(
             (len(context_cat_feature[:, i].unique()), embs_dim_list[i])
             for i in range(context_cat_feature.size(1))
         ]
-        # contruct embedding layer: need to handle multiple categorical features
+        # construct embedding layer: need to handle multiple categorical features
         self.emb_layers = ModuleList(
             [
                 torch.nn.Embedding(num_embeddings=x, embedding_dim=y, max_norm=1.0)

botorch/models/fully_bayesian.py

@@ -381,7 +381,7 @@ def sample_observations(
 
 
 class MaternPyroModel(PyroModel):
-    r"""Implementation of the a fully Bayesian model with a dimension-scaling prior.
+    r"""Implementation of a fully Bayesian model with a dimension-scaling prior.
 
     ``MaternPyroModel`` is not a standard BoTorch model; instead, it is used as
     an input to ``FullyBayesianSingleTaskGP``.

botorch/models/gpytorch.py

@@ -223,7 +223,7 @@ def condition_on_observations(
                 ``batch_shape'`` is the batch shape of the observations.
                 ``batch_shape'`` must be broadcastable to ``batch_shape`` using
                 standard broadcasting semantics. If ``Y`` has fewer batch dimensions
-                than ``X``, its is assumed that the missing batch dimensions are
+                than ``X``, it is assumed that the missing batch dimensions are
                 the same for all ``Y``.
             noise: If not ``None``, a tensor of the same shape as ``Y`` representing
                 the associated noise variance.
@@ -625,7 +625,7 @@ def condition_on_observations(
                 ``batch_shape'`` is the batch shape of the observations.
                 ``batch_shape'`` must be broadcastable to ``batch_shape`` using
                 standard broadcasting semantics. If ``Y`` has fewer batch dimensions
-                than ``X``, its is assumed that the missing batch dimensions are
+                than ``X``, it is assumed that the missing batch dimensions are
                 the same for all ``Y``.
 
         Returns:
@@ -1034,8 +1034,8 @@ def posterior(
                 of points considered jointly. The ``+ 1`` dimension is the optional
                 task feature / index. If given, the model produces the outputs for
                 the given task indices. If omitted, the model produces outputs for
-                tasks in in ``self._output_tasks`` (specified as ``output_tasks``
-                while constructing the model), which can overwritten using
+                tasks in ``self._output_tasks`` (specified as ``output_tasks``
+                while constructing the model), which can be overwritten using
                 ``output_indices``.
             output_indices: A list of task values over which to compute the posterior.
                 Only used if ``X`` does not include the task feature. If omitted,

botorch/models/higher_order_gp.py

@@ -71,7 +71,7 @@ def __init__(
         Args:
             output_shape: A ``n x output_shape``-dim tensor of training targets.
             batch_shape: The batch_shape of the training targets.
-            min_stddv: The minimum standard deviation for which to perform
+            min_stdv: The minimum standard deviation for which to perform
                 standardization (if lower, only de-mean the data).
         """
         if batch_shape is None:
@@ -417,7 +417,7 @@ def condition_on_observations(
                 ``batch_shape'`` is the batch shape of the observations.
                 ``batch_shape'`` must be broadcastable to ``batch_shape`` using
                 standard broadcasting semantics. If ``Y`` has fewer batch dimensions
-                than ``X``, its is assumed that the missing batch dimensions are
+                than ``X``, it is assumed that the missing batch dimensions are
                 the same for all ``Y``.
             noise: If not None, a tensor of the same shape as ``Y`` representing
                 the noise variance associated with each observation.

botorch/models/kernels/contextual_lcea.py

@@ -87,7 +87,7 @@ class LCEAKernel(Kernel):
     r"""The Latent Context Embedding Additive (LCE-A) Kernel.
 
     This kernel is similar to the SACKernel, and is used when context breakdowns are
-    unbserverable. It assumes the same additive structure and a spatial kernel shared
+    unobservable. It assumes the same additive structure and a spatial kernel shared
     across contexts. Rather than assuming independence, LCEAKernel models the
     correlation in the latent functions for each context through learning context
     embeddings.
@@ -111,7 +111,7 @@ def __init__(
             batch_shape: Batch shape as usual for gpytorch kernels. Model does not
                 support batch training. When batch_shape is non-empty, it is used for
                 loading hyper-parameter values generated from MCMC sampling.
-            train_embedding: A boolean indictor of whether to learn context embeddings.
+            train_embedding: A boolean indicator of whether to learn context embeddings.
             cat_feature_dict: Keys are context names and values are list of categorical
                 features i.e. {"context_name" : [cat_0, ..., cat_k]}. k equals the
                 number of categorical variables. If None, uses context names in the
@@ -154,7 +154,7 @@ def __init__(
             embs_feature_dict=embs_feature_dict,
             embs_dim_list=embs_dim_list,
         )
-        # contruct embedding layer
+        # construct embedding layer
         if train_embedding:
             self._set_emb_layers()
         # task covariance matrix

botorch/models/kernels/contextual_sac.py

@@ -19,13 +19,13 @@
 class SACKernel(Kernel):
     r"""The structural additive contextual(SAC) kernel.
 
-    The kernel is used for contextual BO without oberseving context breakdowns.
+    The kernel is used for contextual BO without observing context breakdowns.
     There are d parameters and M contexts. In total, the dimension of parameter space
     is d*M and input x can be written as
     x=[x_11, ..., x_1d, x_21, ..., x_2d, ...,  x_M1, ..., x_Md].
 
     The kernel uses the parameter decomposition and assumes an additive structure
-    across contexts. Each context compponent is assumed to be independent.
+    across contexts. Each context component is assumed to be independent.
 
     .. math::
        \begin{equation*}

botorch/models/kernels/linear_truncated_fidelity.py

@@ -22,7 +22,7 @@ class LinearTruncatedFidelityKernel(Kernel):
     r"""GPyTorch Linear Truncated Fidelity Kernel.
 
     Computes a covariance matrix based on the Linear truncated kernel between
-    inputs ``x_1`` and ``x_2`` for up to two fidelity parmeters:
+    inputs ``x_1`` and ``x_2`` for up to two fidelity parameters:
 
         K(x_1, x_2) = k_0 + c_1(x_1, x_2)k_1 + c_2(x_1,x_2)k_2 + c_3(x_1,x_2)k_3
 
@@ -31,7 +31,7 @@ class LinearTruncatedFidelityKernel(Kernel):
     - ``k_i(i=0,1,2,3)`` are Matern kernels calculated between non-fidelity
         parameters of ``x_1`` and ``x_2`` with different priors.
     - ``c_1=(1 - x_1[f_1])(1 - x_2[f_1]))(1 + x_1[f_1] x_2[f_1])^p`` is the kernel
-        of the the bias term, which can be decomposed into a determistic part
+        of the bias term, which can be decomposed into a deterministic part
         and a polynomial kernel. Here ``f_1`` is the first fidelity dimension and
         ``p`` is the order of the polynomial kernel.
     - ``c_3`` is the same as ``c_1`` but is calculated for the second fidelity

botorch/models/map_saas.py

@@ -211,7 +211,7 @@ def get_map_saas_model(
         train_Yvar: Optional tensor of shape ``n x 1`` with observed noise,
             inferred if None.
         input_transform: An optional input transform.
-        outcome_transform: An optional outcome transforms.
+        outcome_transform: An optional outcome transform.
         tau: Fixed value of the global shrinkage tau. If None, the model
             places a HC(0.1) prior on tau and infers it.
 
@@ -319,7 +319,7 @@ def get_additive_map_saas_covar_module(
 
     The constructed kernel is an additive kernel with ``num_taus`` terms. Each term is a
     scaled Matern kernel with a SAAS prior and a tau sampled from a HalfCauchy(0, 1)
-    distrbution.
+    distribution.
 
     Args:
         ard_num_dims: The number of inputs dimensions.
@@ -425,8 +425,8 @@ def __init__(
             num_taus=num_taus,
             batch_shape=self._aug_batch_shape,
             # Need to pass dtype and device at initialization of the covar_module
-            # because its priors contain tensors, and prior are currently not moved
-            # to the correct device/dtype when callling ``to`` on the model.
+            # because its priors contain tensors, and priors are currently not moved
+            # to the correct device/dtype when calling ``to`` on the model.
             dtype=train_X.dtype,
             device=train_X.device,
         )
@@ -465,7 +465,7 @@ def __init__(
         The model is intended to be trained with ``ExactMarginalLogLikelihood`` and
         ``fit_gpytorch_mll``. Under the hood, the model is equivalent to a
         multi-output ``BatchedMultiOutputGPyTorchModel``, but it produces a
-        ``MixtureGaussiaPosterior``, which leads to ensembling of the model outputs.
+        ``GaussianMixturePosterior``, which leads to ensembling of the model outputs.
 
         Args:
             train_X: An ``n x d`` tensor of training features.

botorch/models/model.py

@@ -541,9 +541,9 @@ def subset_output(self, idcs: list[int]) -> Model:
             the outputs subset to the indices in ``idcs``.
 
         Internally, this drops (if single-output) or subsets (if multi-output)
-        the constitutent models and returns them as a ``ModelList``. If the
+        the constituent models and returns them as a ``ModelList``. If the
         result is a single (possibly subset) model from the list, returns this
-        model (instead of forming a degenerate singe-model ``ModelList``).
+        model (instead of forming a degenerate single-model ``ModelList``).
         For instance, if ``m = ModelList(m1, m2)`` with ``m1`` a two-output model
         and ``m2`` a single-output model, then ``m.subset_output([1]) `` will return
         the model ``m1`` subset to its second output.