[Doc] Update with Mono font to keep doc string consistent. (#5213)

* part1

* more

* more

* spmatrix

* code
Co-authored-by: Steve <ubuntu@ip-172-31-34-29.ap-northeast-1.compute.internal>

python/dgl/sparse/diag_matrix.py

@@ -181,7 +181,7 @@ class DiagMatrix:
 
         >>> val = torch.ones(2)
         >>> D = dglsp.diag(val)
-        >>> D.to(device='cuda:0', dtype=torch.int32)
+        >>> D.to(device="cuda:0", dtype=torch.int32)
         DiagMatrix(values=tensor([1, 1], device='cuda:0', dtype=torch.int32),
                    shape=(2, 2))
         """
@@ -198,7 +198,7 @@ class DiagMatrix:
     def cuda(self):
         """Moves the matrix to GPU. If the matrix is already on GPU, the
         original matrix will be returned. If multiple GPU devices exist,
-        'cuda:0' will be selected.
+        ``cuda:0`` will be selected.
 
         Returns
         -------
@@ -383,7 +383,7 @@ def identity(
         Shape of the matrix.
     d : int, optional
         If None, the diagonal entries will be scaler 1. Otherwise, the diagonal
-        entries will be a 1-valued tensor of shape (d).
+        entries will be a 1-valued tensor of shape ``(d)``.
     dtype : torch.dtype, optional
         The data type of the matrix
     device : torch.device, optional
@@ -399,9 +399,11 @@ def identity(
 
     Case1: 3-by-3 matrix with scaler diagonal values
 
-    [[1, 0, 0],
-     [0, 1, 0],
-     [0, 0, 1]]
+    .. code::
+
+        [[1, 0, 0],
+         [0, 1, 0],
+         [0, 0, 1]]
 
     >>> dglsp.identity(shape=(3, 3))
     DiagMatrix(val=tensor([1., 1., 1.]),
@@ -409,9 +411,11 @@ def identity(
 
     Case2: 3-by-5 matrix with scaler diagonal values
 
-    [[1, 0, 0, 0, 0],
-     [0, 1, 0, 0, 0],
-     [0, 0, 1, 0, 0]]
+    .. code::
+
+        [[1, 0, 0, 0, 0],
+         [0, 1, 0, 0, 0],
+         [0, 0, 1, 0, 0]]
 
     >>> dglsp.identity(shape=(3, 5))
     DiagMatrix(val=tensor([1., 1., 1.]),

python/dgl/sparse/matmul.py

@@ -254,10 +254,9 @@ def matmul(
 
     * The operator supports batched sparse-dense matrix multiplication. In \
         this case, the sparse or diagonal matrix :attr:`A` should have shape \
-        :math:`(L, M)`, where the non-zero values have a batch dimension \
-        :math:`K`. The dense matrix :attr:`B` should have shape \
-        :math:`(M, N, K)`. The output is a dense matrix of shape \
-        :math:`(L, N, K)`.
+        ``(L, M)``, where the non-zero values have a batch dimension ``K``. \
+        The dense matrix :attr:`B` should have shape ``(M, N, K)``. The output \
+        is a dense matrix of shape ``(L, N, K)``.
 
     * Sparse-sparse matrix multiplication does not support batched computation.
 

python/dgl/sparse/reduction.py

@@ -9,8 +9,8 @@ from .sparse_matrix import SparseMatrix
 
 
 def reduce(input: SparseMatrix, dim: Optional[int] = None, rtype: str = "sum"):
-    """Computes the reduction of non-zero values of the ``input`` sparse matrix
-    along the given dimension :attr:`dim`.
+    """Computes the reduction of non-zero values of the :attr:`input` sparse
+    matrix along the given dimension :attr:`dim`.
 
     The reduction does not count zero elements. If the row or column to be
     reduced does not have any non-zero elements, the result will be 0.
@@ -83,8 +83,8 @@ def reduce(input: SparseMatrix, dim: Optional[int] = None, rtype: str = "sum"):
 
 
 def sum(input: SparseMatrix, dim: Optional[int] = None):
-    """Computes the sum of non-zero values of the ``input`` sparse matrix along
-    the given dimension :attr:`dim`.
+    """Computes the sum of non-zero values of the :attr:`input` sparse matrix
+    along the given dimension :attr:`dim`.
 
     Parameters
     ----------
@@ -137,8 +137,8 @@ def sum(input: SparseMatrix, dim: Optional[int] = None):
 
 
 def smax(input: SparseMatrix, dim: Optional[int] = None):
-    """Computes the maximum of non-zero values of the ``input`` sparse matrix
-    along the given dimension :attr:`dim`.
+    """Computes the maximum of non-zero values of the :attr:`input` sparse
+    matrix along the given dimension :attr:`dim`.
 
     The reduction does not count zero values. If the row or column to be
     reduced does not have any non-zero value, the result will be 0.
@@ -195,8 +195,8 @@ def smax(input: SparseMatrix, dim: Optional[int] = None):
 
 
 def smin(input: SparseMatrix, dim: Optional[int] = None):
-    """Computes the minimum of non-zero values of the ``input`` sparse matrix
-    along the given dimension :attr:`dim`.
+    """Computes the minimum of non-zero values of the :attr:`input` sparse
+    matrix along the given dimension :attr:`dim`.
 
     The reduction does not count zero values. If the row or column to be reduced
     does not have any non-zero value, the result will be 0.
@@ -257,8 +257,8 @@ def smin(input: SparseMatrix, dim: Optional[int] = None):
 
 
 def smean(input: SparseMatrix, dim: Optional[int] = None):
-    """Computes the mean of non-zero values of the ``input`` sparse matrix along
-    the given dimension :attr:`dim`.
+    """Computes the mean of non-zero values of the :attr:`input` sparse matrix
+    along the given dimension :attr:`dim`.
 
     The reduction does not count zero values. If the row or column to be reduced
     does not have any non-zero value, the result will be 0.
@@ -319,8 +319,8 @@ def smean(input: SparseMatrix, dim: Optional[int] = None):
 
 
 def sprod(input: SparseMatrix, dim: Optional[int] = None):
-    """Computes the product of non-zero values of the ``input`` sparse matrix
-    along the given dimension :attr:`dim`.
+    """Computes the product of non-zero values of the :attr:`input` sparse
+    matrix along the given dimension :attr:`dim`.
 
     The reduction does not count zero values. If the row or column to be reduced
     does not have any non-zero value, the result will be 0.

python/dgl/sparse/softmax.py

@@ -14,7 +14,7 @@ def softmax(input: SparseMatrix) -> SparseMatrix:
     Equivalently, applies softmax to the non-zero elements of the sparse
     matrix along the column (``dim=1``) dimension.
 
-    If :attr:`input.val` takes shape :attr:`(nnz, D)`, then the output matrix
+    If :attr:`input.val` takes shape ``(nnz, D)``, then the output matrix
     :attr:`output` and :attr:`output.val` take the same shape as :attr:`input`
     and :attr:`input.val`. :attr:`output.val[:, i]` is calculated based on
     :attr:`input.val[:, i]`.

python/dgl/sparse/sparse_matrix.py

@@ -246,7 +246,7 @@ class SparseMatrix:
 
         >>> indices = torch.tensor([[1, 1, 2], [1, 2, 0]])
         >>> A = dglsp.spmatrix(indices, shape=(3, 4))
-        >>> A.to(device='cuda:0', dtype=torch.int32)
+        >>> A.to(device="cuda:0", dtype=torch.int32)
         SparseMatrix(indices=tensor([[1, 1, 2],
                                      [1, 2, 0]], device='cuda:0'),
                      values=tensor([1, 1, 1], device='cuda:0',
@@ -274,7 +274,7 @@ class SparseMatrix:
     def cuda(self):
         """Moves the matrix to GPU. If the matrix is already on GPU, the
         original matrix will be returned. If multiple GPU devices exist,
-        'cuda:0' will be selected.
+        ``cuda:0`` will be selected.
 
         Returns
         -------
@@ -308,6 +308,7 @@ class SparseMatrix:
 
         >>> indices = torch.tensor([[1, 1, 2], [1, 2, 0]]).to("cuda")
         >>> A = dglsp.spmatrix(indices, shape=(3, 4))
+
         >>> A.cpu()
         SparseMatrix(indices=tensor([[1, 1, 2],
                                      [1, 2, 0]]),
@@ -466,12 +467,12 @@ def spmatrix(
         which should have shape of ``(2, N)`` where the first row is the row
         indices and the second row is the column indices of non-zero elements.
     val : tensor.Tensor, optional
-        The values of shape (nnz) or (nnz, D). If None, it will be a tensor of
-        shape (nnz) filled by 1.
+        The values of shape ``(nnz)`` or ``(nnz, D)``. If None, it will be a
+        tensor of shape ``(nnz)`` filled by 1.
     shape : tuple[int, int], optional
         If not specified, it will be inferred from :attr:`row` and :attr:`col`,
-        i.e., (row.max() + 1, col.max() + 1). Otherwise, :attr:`shape` should
-        be no smaller than this.
+        i.e., ``(row.max() + 1, col.max() + 1)``. Otherwise, :attr:`shape`
+        should be no smaller than this.
 
     Returns
     -------
@@ -540,16 +541,16 @@ def from_coo(
     Parameters
     ----------
     row : torch.Tensor
-        The row indices of shape (nnz)
+        The row indices of shape ``(nnz)``
     col : torch.Tensor
-        The column indices of shape (nnz)
+        The column indices of shape ``(nnz)``
     val : torch.Tensor, optional
-        The values of shape (nnz) or (nnz, D). If None, it will be a tensor of
-        shape (nnz) filled by 1.
+        The values of shape ``(nnz)`` or ``(nnz, D)``. If None, it will be a
+        tensor of shape ``(nnz)`` filled by 1.
     shape : tuple[int, int], optional
         If not specified, it will be inferred from :attr:`row` and :attr:`col`,
-        i.e., (row.max() + 1, col.max() + 1). Otherwise, :attr:`shape` should
-        be no smaller than this.
+        i.e., ``(row.max() + 1, col.max() + 1)``. Otherwise, :attr:`shape`
+        should be no smaller than this.
 
     Returns
     -------
@@ -630,17 +631,17 @@ def from_csr(
     Parameters
     ----------
     indptr : torch.Tensor
-        Pointer to the column indices of shape (N + 1), where N is the number
-        of rows
+        Pointer to the column indices of shape ``(N + 1)``, where ``N`` is the
+        number of rows
     indices : torch.Tensor
-        The column indices of shape (nnz)
+        The column indices of shape ``(nnz)``
     val : torch.Tensor, optional
-        The values of shape (nnz) or (nnz, D). If None, it will be a tensor of
-        shape (nnz) filled by 1.
+        The values of shape ``(nnz)`` or ``(nnz, D)``. If None, it will be a
+        tensor of shape ``(nnz)`` filled by 1.
     shape : tuple[int, int], optional
         If not specified, it will be inferred from :attr:`indptr` and
-        :attr:`indices`, i.e., (len(indptr) - 1, indices.max() + 1). Otherwise,
-        :attr:`shape` should be no smaller than this.
+        :attr:`indices`, i.e., ``(len(indptr) - 1, indices.max() + 1)``.
+        Otherwise, :attr:`shape` should be no smaller than this.
 
     Returns
     -------
@@ -652,9 +653,11 @@ def from_csr(
 
     Case1: Sparse matrix without values
 
-    [[0, 1, 0],
-     [0, 0, 1],
-     [1, 1, 1]]
+    .. code::
+
+        [[0, 1, 0],
+         [0, 0, 1],
+         [1, 1, 1]]
 
     >>> indptr = torch.tensor([0, 1, 2, 5])
     >>> indices = torch.tensor([1, 2, 0, 1, 2])
@@ -725,12 +728,12 @@ def from_csc(
     indices : torch.Tensor
         The row indices of shape nnz
     val : torch.Tensor, optional
-        The values of shape (nnz) or (nnz, D). If None, it will be a tensor of
-        shape (nnz) filled by 1.
+        The values of shape ``(nnz)`` or ``(nnz, D)``. If None, it will be a
+        tensor of shape ``(nnz)`` filled by 1.
     shape : tuple[int, int], optional
         If not specified, it will be inferred from :attr:`indptr` and
-        :attr:`indices`, i.e., (indices.max() + 1, len(indptr) - 1). Otherwise,
-        :attr:`shape` should be no smaller than this.
+        :attr:`indices`, i.e., ``(indices.max() + 1, len(indptr) - 1)``.
+        Otherwise, :attr:`shape` should be no smaller than this.
 
     Returns
     -------
@@ -742,9 +745,11 @@ def from_csc(
 
     Case1: Sparse matrix without values
 
-    [[0, 1, 0],
-     [0, 0, 1],
-     [1, 1, 1]]
+    .. code::
+
+        [[0, 1, 0],
+         [0, 0, 1],
+         [1, 1, 1]]
 
     >>> indptr = torch.tensor([0, 1, 3, 5])
     >>> indices = torch.tensor([2, 0, 2, 1, 2])
@@ -801,7 +806,8 @@ def val_like(mat: SparseMatrix, val: torch.Tensor) -> SparseMatrix:
     mat : SparseMatrix
         An existing sparse matrix with non-zero values
     val : torch.Tensor
-        The new values of the non-zero elements, a tensor of shape (nnz) or (nnz, D)
+        The new values of the non-zero elements, a tensor of shape ``(nnz)`` or
+        ``(nnz, D)``
 
     Returns
     -------