Merge pull request #28 from IBM/ColumnProjection

bump version; add test

Project.toml

@@ -1,7 +1,7 @@
 name = "Lale"
 uuid = "25676c37-aa2f-4f14-ad5b-b63670ababff"
 authors = ["Paulito Palmes <[email protected]>", "Martin Hirzel", "Avraham Shinnar", "Kiran Kate"]
-version = "0.1.5"
+version = "0.1.6"
 
 [deps]
 AMLPipelineBase = "e3c3008a-8869-4d53-9f34-c96f99c8a2b6"
@@ -14,7 +14,7 @@ Test = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
 
 [compat]
 AMLPipelineBase = "0.1"
-DataFrames = "0.17, 0.18, 0.19, 0.20, 0.21, 0.22, 1.0"
+DataFrames = "0.17, 0.18, 0.19, 0.20, 0.21, 0.22, 1.0, 1.1"
 Pandas = "1.1, 1.2, 1.3, 1.4"
 PyCall = "1.90, 1.91, 1.92"
 julia = "1"

demo/demo-lale-project.jl

@@ -20,7 +20,7 @@ X = df[:,2:end]
 train_X,train_y,test_X,test_y = Lale.train_test_split(X, y,testprop=0.20)
 
 prep_to_numbers = 
- ((stringprj >> OneHotEncoder(handle_unknown = "ignore")) & numericprj )>> ConcatFeatures
+ ((strfeat >> OneHotEncoder(handle_unknown = "ignore")) & numfeat)>> ConcatFeatures
 planned_orig = prep_to_numbers >> ( Tree | KNN)
 lopt = LalePipeOptimizer(planned_orig,max_evals = 10,cv = 3)
 laletrained = fit(lopt,train_X,train_y)

test/test_project.jl

@@ -0,0 +1,45 @@
+module TestProject
+
+using DataFrames
+using CSV
+using Lale
+using Test
+
+function proj_test()
+
+   strfeat= laleoperator("Project","lale")(columns=Dict("type"=>"string"))
+   numfeat = laleoperator("Project","lale")(columns=Dict("type"=>"number"))
+
+   OneHotEncoder = laleoperator("OneHotEncoder")
+   ConcatFeatures = laleoperator("ConcatFeatures","lale")
+   Tree = laleoperator("DecisionTreeClassifier")
+   KNN = laleoperator("KNeighborsClassifier")
+   RF =  laleoperator("RandomForestClassifier")
+   PCA = laleoperator("PCA")
+   Hyperopt = laleoperator("Hyperopt","lale")
+
+   df = CSV.read("./demo/old/credit.csv",DataFrame) 
+   y = df[!,"class"] |> collect
+   X = df[:,2:end]
+
+   train_X,train_y,test_X,test_y = Lale.train_test_split(X, y,testprop=0.20)
+
+   prep_to_numbers = 
+   ((strfeat >> OneHotEncoder(handle_unknown = "ignore")) & numfeat )>> ConcatFeatures
+   planned_orig = prep_to_numbers >> ( Tree | KNN)
+   lopt = LalePipeOptimizer(planned_orig,max_evals = 3,cv = 3)
+   laletrained = fit(lopt,train_X,train_y)
+   lalepred  = Lale.transform(laletrained,test_X)
+   @test score(:accuracy,lalepred,test_y) > 0.50
+
+   pca_tree_planned = prep_to_numbers >> PCA >> RF
+   lopt = LalePipeOptimizer(pca_tree_planned,max_evals = 3,cv = 3)
+   laletrained = fit(lopt,train_X,train_y)
+   lalepred  = Lale.transform(laletrained,test_X)
+   @test score(:accuracy,lalepred,test_y) > 0.50
+end
+@testset "Lale Projection" begin
+   proj_test()
+end
+
+end