Fix small typos (#235)

Author: aurorarossi

docs/src/gnngraph.md

@@ -221,7 +221,7 @@ using Flux: gpu
 g_gpu = g |> gpu
 ```
 
-## Integraton with Graphs.jl integration
+## Integration with Graphs.jl
 
 Since `GNNGraph <: Graphs.AbstractGraph`, we can use any functionality from [Graphs.jl](https://github.com/JuliaGraphs/Graphs.jl) for querying and analyzing the graph structure. 
 Moreover, a `GNNGraph` can be easily constructed from a `Graphs.Graph` or a `Graphs.DiGraph`:

perf/perf.jl

@@ -49,8 +49,8 @@ end
         layers = [GCNConv, GraphConv, GATConv]
         )
 
-Benchmark GNN layers on Erdos-Renyi ranomd graphs 
-with average degree `c`. Benchmarks are perfomed for each graph size in the list `Ns`.
+Benchmark GNN layers on Erdos-Renyi random graphs 
+with average degree `c`. Benchmarks are performed for each graph size in the list `Ns`.
 `D` is the number of node features.
 """
 function run_benchmarks(; 

src/GNNGraphs/generate.jl

@@ -102,7 +102,7 @@ to its `k` closest `points`.
 
 - `points`: A num_features × num_nodes matrix storing the Euclidean positions of the nodes.
 - `k`: The number of neighbors considered in the kNN algorithm.
-- `graph_indicator`: Either nothing or a vector containing the graph assigment of each node, 
+- `graph_indicator`: Either nothing or a vector containing the graph assignment of each node, 
                      in which case the returned graph will be a batch of graphs. 
 - `self_loops`: If `true`, consider the node itself among its `k` nearest neighbors, in which
                 case the graph will contain self-loops. 
@@ -184,7 +184,7 @@ to its neighbors within a given distance `r`.
 
 - `points`: A num_features × num_nodes matrix storing the Euclidean positions of the nodes.
 - `r`: The radius.
-- `graph_indicator`: Either nothing or a vector containing the graph assigment of each node, 
+- `graph_indicator`: Either nothing or a vector containing the graph assignment of each node, 
                      in which case the returned graph will be a batch of graphs. 
 - `self_loops`: If `true`, consider the node itself among its neighbors, in which
                 case the graph will contain self-loops. 

src/GNNGraphs/gnngraph.jl

@@ -60,7 +60,7 @@ functionality from that library.
 - `dir`: The assumed edge direction when given adjacency matrix or adjacency list input data `g`. 
         Possible values are `:out` and `:in`. Default `:out`.
 - `num_nodes`: The number of nodes. If not specified, inferred from `g`. Default `nothing`.
-- `graph_indicator`: For batched graphs, a vector containing the graph assigment of each node. Default `nothing`.  
+- `graph_indicator`: For batched graphs, a vector containing the graph assignment of each node. Default `nothing`.  
 - `ndata`: Node features. An array or named tuple of arrays whose last dimension has size `num_nodes`.
 - `edata`: Edge features. An array or named tuple of arrays whose last dimension has size `num_edges`.
 - `gdata`: Graph features. An array or named tuple of arrays whose last dimension has size `num_graphs`. 

src/GNNGraphs/gnnheterograph.jl

@@ -6,15 +6,15 @@ const NDict{T} = Dict{Symbol, T}
 """
     GNNHeteroGraph(data; ndata, edata, gdata, num_nodes, graph_indicator, dir])
     
-A type representing a heterogeneus graph structure.
+A type representing a heterogeneous graph structure.
 it is similar [`GNNGraph`](@ref) but node and edges are of different types.
 
 # Arguments
 
 - `data`: A dictionary or an iterable object that maps (source_type, edge_type, target_type) 
     triples to (source, target) index vectors.
 - `num_nodes`: The number of nodes for each type. If not specified, inferred from `g`. Default `nothing`.
-- `graph_indicator`: For batched graphs, a dictionary of vectors containing the graph assigment of each node. Default `nothing`.  
+- `graph_indicator`: For batched graphs, a dictionary of vectors containing the graph assignment of each node. Default `nothing`.  
 - `ndata`: Node features. A dictionary of arrays or named tuple of arrays. 
            The size of the last dimension of each array must be given by `g.num_nodes`.
 - `edata`: Edge features. A dictionary of arrays or named tuple of arrays.

src/GNNGraphs/query.jl

@@ -140,7 +140,7 @@ If `dir=:in` instead, `A[i,j] > 0` denotes the presence of an edge from node `j`
 
 User may specify the eltype `T` of the returned matrix. 
 
-If `weighted=true`, the `A` will contain the edge weigths if any, otherwise the elements of `A` will be either 0 or 1.
+If `weighted=true`, the `A` will contain the edge weights if any, otherwise the elements of `A` will be either 0 or 1.
 """
 function Graphs.adjacency_matrix(g::GNNGraph{<:COO_T}, T::DataType=eltype(g); dir=:out, weighted=true)
     if g.graph[1] isa CuVector

src/msgpass.jl

@@ -277,7 +277,7 @@ end
 
 
 # function propagate(::typeof(copy_xj), g::GNNGraph, ::typeof(mean), xi, xj::AbstractMatrix, e)
-#     A = adjacency_matrix(g, weigthed=false)
+#     A = adjacency_matrix(g, weighted=false)
 #     D = compute_degree(A)
 #     return xj * A * D
 # end