added docstring, added test cases, changed load function to use GeoDa…

…taFrames instead of Shapefile package.

Project.toml

@@ -7,10 +7,10 @@ version = "0.0.1"
 DataFrames = "a93c6f00-e57d-5684-b7b6-d8193f3e46c0"
 Downloads = "f43a241f-c20a-4ad4-852c-f6b1247861c6"
 EzXML = "8f5d6c58-4d21-5cfd-889c-e3ad7ee6a615"
+GeoDataFrames = "62cb38b5-d8d2-4862-a48e-6a340996859f"
 HTTP = "cd3eb016-35fb-5094-929b-558a96fad6f3"
 JSON3 = "0f8b85d8-7281-11e9-16c2-39a750bddbf1"
 OpenAPI = "d5e62ea6-ddf3-4d43-8e4c-ad5e6c8bfd7d"
-Shapefile = "8e980c4a-a4fe-5da2-b3a7-4b4b0353a2f4"
 
 [compat]
 DataFrames = "1.4"

src/IPUMS.jl

@@ -6,8 +6,8 @@ module IPUMS
         download as dl
     import OpenAPI.Clients: 
         Client
-    import Shapefile:
-        Table
+    import GeoDataFrames:
+        read
     using DataFrames: 
         DataFrames, 
         DataFrame, 
@@ -66,5 +66,6 @@ module IPUMS
     export parse_ddi
     export extract_download
     export load_ipums_extract
+    export load_ipums_nhgis
 
 end

src/parsers/nhgis_parser.jl

@@ -1,9 +1,35 @@
 
 
-function load_nhgis_extract(fname::String)
-
+"""
+    load_ipums_nhgis(filepath::String)
+
+    This function will take in the filename for an NHGIS Shapefile, and will 
+        return a GeoDataFrame object containing the shapefile data.
+
+### Arguments
+
+- `filepath::String` - The directory path to an IPUMS NHGIS extracted shapefile. 
+
+### Returns
+
+    This function outputs a Julia GeoDataframe that contains all of the data from 
+    the IPUMS NHGIS extract file. Further, the metadata fields of the Dataframe 
+    contain the metadata parsed from the Shapefile. 
+
+# Examples
+
+Let's assume we have an extract NHGIS file named `US_state_1790.shp` in a folder
+that contains the other shapefile files. The user can open this Shapefile using 
+the following code. 
+
+```julia-repl
+julia> gdf = load_ipums_nhgis("test/testdata/nhgis0001_shapefile/US_state_1790.shp");
+```
+
+"""
+function load_ipums_nhgis(filepath::String)
 
-    gdf = DataFrame(Table(fname))
+    gdf = read(fname)
 
     return gdf
 

test/runtests.jl

@@ -22,3 +22,10 @@ end
     @test isa(metadata(df), Dict)
     @test isa(colmetadata(df, :YEAR), Dict)
 end
+
+@testset "NHGIS Parser" begin
+    datafile = "testdata/nhgis0001_shapefile/US_state_1790.shp"
+    df = load_ipums_nhgis(datafile)
+    @test size(df) == (16, 8)
+
+end

test/testdata/nhgis0001_shapefile/US_state_1790.prj

@@ -0,0 +1 @@
+PROJCS["USA_Contiguous_Albers_Equal_Area_Conic",GEOGCS["GCS_North_American_1983",DATUM["D_North_American_1983",SPHEROID["GRS_1980",6378137.0,298.257222101]],PRIMEM["Greenwich",0.0],UNIT["Degree",0.0174532925199433]],PROJECTION["Albers"],PARAMETER["False_Easting",0.0],PARAMETER["False_Northing",0.0],PARAMETER["Central_Meridian",-96.0],PARAMETER["Standard_Parallel_1",29.5],PARAMETER["Standard_Parallel_2",45.5],PARAMETER["Latitude_Of_Origin",37.5],UNIT["Meter",1.0]]