Merge pull request #81 from yuehhua/pickle

Use Pickle in favor of PyCall

.github/workflows/UnitTest.yml

@@ -16,7 +16,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        julia-version: ['1.0', '1', 'nightly']
+        julia-version: ['1.3', '1', 'nightly']
         os: [ubuntu-latest, windows-latest, macOS-latest]
     env:
       PYTHON: ""

Project.toml

@@ -11,8 +11,9 @@ FixedPointNumbers = "53c48c17-4a7d-5ca2-90c5-79b7896eea93"
 GZip = "92fee26a-97fe-5a0c-ad85-20a5f3185b63"
 JSON3 = "0f8b85d8-7281-11e9-16c2-39a750bddbf1"
 MAT = "23992714-dd62-5051-b70f-ba57cb901cac"
-PyCall = "438e738f-606a-5dbb-bf0a-cddfbfd45ab0"
+Pickle = "fbb45041-c46e-462f-888f-7c521cafbc2c"
 Requires = "ae029012-a4dd-5104-9daa-d747884805df"
+SparseArrays = "2f01184e-e22b-5df5-ae63-d93ebab69eaf"
 
 [compat]
 BinDeps = "1"
@@ -23,9 +24,9 @@ GZip = "0.5"
 ImageCore = "0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8"
 JSON3 = "1"
 MAT = "0.7, 0.8, 0.9, 0.10"
-PyCall = "1"
+Pickle = "0.2"
 Requires = "1"
-julia = "1"
+julia = "1.3"
 
 [extras]
 ImageCore = "a09fc81d-aa75-5fe9-8630-4744c3626534"

src/CiteSeer/CiteSeer.jl

@@ -25,8 +25,6 @@ using DataDeps
 using ..MLDatasets: datafile, read_planetoid_data
 using DelimitedFiles: readdlm
 
-using PyCall
-
 const DEPNAME = "CiteSeer"
 const LINK = "https://github.com/kimiyoung/planetoid/raw/master/data"
 const DOCS = "https://github.com/kimiyoung/planetoid"

src/Cora/Cora.jl

@@ -39,8 +39,6 @@ using DataDeps
 using ..MLDatasets: datafile, read_planetoid_data
 using DelimitedFiles: readdlm
 
-using PyCall
-
 const DEPNAME = "Cora"
 # LINK = "https://github.com/shchur/gnn-benchmark/raw/master/data/npz"
 # LINK = "https://github.com/abojchevski/graph2gauss/raw/master/data/"

src/MLDatasets.jl

@@ -5,7 +5,8 @@ using ColorTypes: length
 using Requires
 using DelimitedFiles: readdlm
 using FixedPointNumbers, ColorTypes
-using PyCall
+using Pickle
+using SparseArrays
 
 # Julia 1.0 compatibility
 if !isdefined(Base, :isnothing)
@@ -67,20 +68,6 @@ function __init__()
         global __images_supported__ = true
     end
 
-    # install scipy if not already there
-    pyimport_conda("scipy", "scipy")
-
-    py"""
-    import pickle
-
-    def pyread_planetoid_file(path, name):
-        out = pickle.load(open(path, "rb"), encoding="latin1")
-        if name == 'graph':
-            return out
-        out = out.todense() if hasattr(out, 'todense') else out
-        return out
-    """
-
     __init__tudataset()
 end
 

src/PubMed/PubMed.jl

@@ -25,8 +25,6 @@ using DataDeps
 using ..MLDatasets: datafile, read_planetoid_data
 using DelimitedFiles: readdlm
 
-using PyCall
-
 const DEPNAME = "PubMed"
 const LINK = "https://github.com/kimiyoung/planetoid/raw/master/data"
 const DOCS = "https://github.com/kimiyoung/planetoid"

src/TUDataset/TUDataset.jl

@@ -17,7 +17,7 @@ function __init__tudataset()
         Website: $LINK)
         """,
         "$LINK/$DATA",
-        # "81de017067dc045ebdb8ffd5c0e69a209973ffdb1fe2d5b434e94d3614f3f5c7",  # if checksum omitted, will be generated by DataDeps
+        "2da8de15284b88edabca2888ce5444d62f364ed41159260977088c4e53d4d848",  # if checksum omitted, will be generated by DataDeps
         post_fetch_method = unpack
     ))
 end

src/planetoid.jl

@@ -69,12 +69,23 @@ function read_planetoid_data(DEPNAME; dir=nothing, reverse_edges=true)
               directed = reverse_edges != true)
 end
 
+function read_pickle_file(filename, name)
+    out = Pickle.npyload(filename)
+    if name == "graph"
+        return out
+    end
+    if out isa SparseMatrixCSC
+        return Matrix(out)
+    end
+    return out
+end
+
 function read_planetoid_file(DEPNAME, name, dir)
     filename = datafile(DEPNAME, name, dir)
     if endswith(name, "test.index")
         out = 1 .+ vec(readdlm(filename, Int))
     else
-        out = py"pyread_planetoid_file"(filename, name)
+        out = read_pickle_file(filename, name)
         if out isa Matrix
             out = collect(out')
         end