Implement geodb.jl

.gitignore

@@ -9,3 +9,6 @@ notebooks
 .idea
 *.lp
 Manifest.toml
+data
+build
+benchmark

Project.toml

@@ -4,6 +4,7 @@ authors = ["Alinson S Xavier <axavier@anl.gov>"]
 version = "0.5.0"
 
 [deps]
+CRC = "44b605c4-b955-5f2b-9b6d-d2bd01d3d205"
 CSV = "336ed68f-0bac-5ca0-87d4-7b16caf5d00b"
 Cbc = "9961bab8-2fa3-5c5a-9d89-47fab24efd76"
 Clp = "e2554f3b-3117-50c0-817c-e040a3ddf72d"
@@ -19,10 +20,13 @@ MathOptInterface = "b8f27783-ece8-5eb3-8dc8-9495eed66fee"
 PackageCompiler = "9b87118b-4619-50d2-8e1e-99f35a4d4d9d"
 Printf = "de0858da-6303-5e67-8744-51eddeeeb8d7"
 ProgressBars = "49802e3a-d2f1-5c88-81d8-b72133a6f568"
+Shapefile = "8e980c4a-a4fe-5da2-b3a7-4b4b0353a2f4"
 Statistics = "10745b16-79ce-11e8-11f9-7d13ad32a3b2"
 Test = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
+ZipFile = "a5390f91-8eb1-5f08-bee0-b1d1ffed6cea"
 
 [compat]
+CRC = "4"
 CSV = "0.7"
 Cbc = "0.6"
 Clp = "0.8"
@@ -36,4 +40,6 @@ JuMP = "0.21"
 MathOptInterface = "0.9"
 PackageCompiler = "1"
 ProgressBars = "0.6"
+Shapefile = "0.7"
+ZipFile = "0.9"
 julia = "1"

src/RELOG.jl

@@ -11,6 +11,7 @@ include("graph/structs.jl")
 include("graph/build.jl")
 include("graph/csv.jl")
 include("instance/compress.jl")
+include("instance/geodb.jl")
 include("instance/parse.jl")
 include("instance/validate.jl")
 include("model/build.jl")

src/instance/geodb.jl

@@ -0,0 +1,92 @@
+# RELOG: Reverse Logistics Optimization
+# Copyright (C) 2020, UChicago Argonne, LLC. All rights reserved.
+# Released under the modified BSD license. See COPYING.md for more details.
+
+using CRC
+using CSV
+using DataFrames
+using Shapefile
+using Statistics
+using ZipFile
+
+crc32 = crc(CRC_32)
+
+struct GeoPoint
+    lat::Float64
+    lon::Float64
+end
+
+DB_CACHE = Dict{String,Dict{String,GeoPoint}}()
+
+function centroid(geom::Shapefile.Polygon)::GeoPoint
+    x_max, x_min, y_max, y_min = -Inf, Inf, -Inf, Inf
+    for p in geom.points
+        x_max = max(x_max, p.x)
+        x_min = min(x_min, p.x)
+        y_max = max(y_max, p.y)
+        y_min = min(y_min, p.y)
+    end
+    x_center = (x_max + x_min) / 2.0
+    y_center = (y_max + y_min) / 2.0
+    return GeoPoint(round(y_center, digits = 5), round(x_center, digits = 5))
+end
+
+function download_census_gov(url, outputdir, expected_crc32)::Nothing
+    if isdir(outputdir)
+        return
+    end
+    mkpath(outputdir)
+    @info "Downloading: $url"
+    zip_filename = download(url)
+    actual_crc32 = open(crc32, zip_filename)
+    expected_crc32 == actual_crc32 || error("CRC32 mismatch")
+    open(zip_filename) do zip_file
+        zr = ZipFile.Reader(zip_file)
+        for file in zr.files
+            open(joinpath(outputdir, file.name), "w") do output_file
+                write(output_file, read(file))
+            end
+        end
+    end
+    return
+end
+
+function load_2018_us_county()::Dict{String,GeoPoint}
+    db_name = "2018-us-county"
+    basedir = joinpath(dirname(@__FILE__), "..", "..", "data", db_name)
+    csv_filename = "$basedir/locations.csv"
+    if !isfile(csv_filename)
+        download_census_gov(
+            "https://www2.census.gov/geo/tiger/GENZ2018/shp/cb_2018_us_county_500k.zip",
+            basedir,
+            0x83eaec6d,
+        )
+        table = Shapefile.Table("$basedir/cb_2018_us_county_500k.shp")
+        geoms = Shapefile.shapes(table)
+        df = DataFrame(id = String[], latitude = Float64[], longitude = Float64[])
+        for (i, geom) in enumerate(geoms)
+            c = centroid(geom)
+            id = table.STATEFP[i] * table.COUNTYFP[i]
+            push!(df, [id, c.lat, c.lon])
+        end
+        sort!(df)
+        @info "Writing: $csv_filename"
+        CSV.write(csv_filename, df)
+    end
+    if db_name ∉ keys(DB_CACHE)
+        csv = CSV.File(csv_filename; types = [String, Float64, Float64])
+        DB_CACHE[db_name] =
+            Dict(row.id => GeoPoint(row.latitude, row.longitude) for row in csv)
+    end
+    return DB_CACHE[db_name]
+end
+
+function load_latlon_database(db_name)
+    db_name == "2018-us-county" && return load_2018_us_county()
+    error("Unknown database: $db_name")
+end
+
+function geodb_query(name)
+    db_name, id = split(name, ":")
+    return load_latlon_database(db_name)[id]
+end

src/reports/write.jl

@@ -4,6 +4,7 @@
 
 using DataFrames
 using CSV
+import Base: write
 
 function write(solution::AbstractDict, filename::AbstractString)
     @info "Writing solution: $filename"

test/instance/geodb_test.jl

@@ -0,0 +1,11 @@
+# RELOG: Reverse Logistics Optimization
+# Copyright (C) 2020, UChicago Argonne, LLC. All rights reserved.
+# Released under the modified BSD license. See COPYING.md for more details.
+
+using RELOG
+
+@testset "geodb_query (2018-us-county)" begin
+    point = RELOG.geodb_query("2018-us-county:17043")
+    @test point.lat == 41.83956
+    @test point.lon == -88.08857
+end

test/runtests.jl

@@ -6,6 +6,7 @@ using Test
 @testset "RELOG" begin
     @testset "Instance" begin
         include("instance/compress_test.jl")
+        include("instance/geodb_test.jl")
         include("instance/parse_test.jl")
     end
     @testset "Graph" begin