Consistent column names

JuliaStats · Apr 9, 2015 · 7be4d66 · 7be4d66
1 parent 59d4e94
commit 7be4d66
Show file tree

Hide file tree

Showing 20 changed files with 14 additions and 5 deletions.
diff --git a/data/Ecdat/Klein.csv.gz b/data/Ecdat/Klein.csv.gz
diff --git a/data/ISLR/Auto.rda b/data/ISLR/Auto.rda
diff --git a/data/ISLR/College.rda b/data/ISLR/College.rda
diff --git a/data/ISLR/Default.rda b/data/ISLR/Default.rda
diff --git a/data/ISLR/Wage.rda b/data/ISLR/Wage.rda
diff --git a/data/MASS/abbey.csv.gz b/data/MASS/abbey.csv.gz
diff --git a/data/MASS/chem.csv.gz b/data/MASS/chem.csv.gz
diff --git a/data/MASS/galaxies.csv.gz b/data/MASS/galaxies.csv.gz
diff --git a/data/MASS/newcomb.csv.gz b/data/MASS/newcomb.csv.gz
diff --git a/data/car/Bfox.csv.gz b/data/car/Bfox.csv.gz
diff --git a/data/cluster/votes.repub.csv.gz b/data/cluster/votes.repub.csv.gz
diff --git a/data/datasets/USPersonalExpenditure.csv.gz b/data/datasets/USPersonalExpenditure.csv.gz
diff --git a/data/datasets/precip.csv.gz b/data/datasets/precip.csv.gz
diff --git a/data/datasets/rivers.csv.gz b/data/datasets/rivers.csv.gz
diff --git a/data/robustbase/cushny.csv.gz b/data/robustbase/cushny.csv.gz
diff --git a/data/robustbase/wagnerGrowth.rda b/data/robustbase/wagnerGrowth.rda
diff --git a/data/rpart/solder.rda b/data/rpart/solder.rda
diff --git a/data/vcd/Hospital.csv.gz b/data/vcd/Hospital.csv.gz
diff --git a/doc/datasets.csv b/doc/datasets.csv
@@ -188,7 +188,7 @@
 "ISLR","Auto","Auto Data Set",392,9
 "ISLR","Caravan","The Insurance Company (TIC) Benchmark",5822,86
 "ISLR","Carseats","Sales of Child Car Seats",400,11
-"ISLR","College","U.S. News and World Report's College Data",777,18
+"ISLR","College","U.S. News and World Report's College Data",777,19
 "ISLR","Default","Credit Card Default Data",10000,4
 "ISLR","Hitters","Baseball Data",322,20
 "ISLR","OJ","Orange Juice Data",1070,18

diff --git a/test/dataset.jl b/test/dataset.jl
@@ -2,10 +2,7 @@ module TestDataset
     using Base.Test
     using RDatasets
 
-    function badname(sym)
-        n = string(sym)
-        ismatch(r"^[a-z]", n) || contains(n, ".")
-    end
+    goodname(sym) = ismatch(r"^([_xA-Z]|pH|pK)", string(sym))
 
     package_directory = joinpath(dirname(@__FILE__), "..", "data")
 
@@ -21,5 +18,17 @@ module TestDataset
             println("Package: $pkg Dataset: $ds -")
             @test size(df) == recorded_size
         end
+
+        if !all(map(goodname, names(df)))
+
+            println("Package: $pkg Dataset: $ds -")
+            println("Names: ", names(df))
+            throw(ErrorException("""
+
+                Column names should be match what 'readtable' would produce,
+                except words should be 'UpperCamelCase' (acronyms uppercase), &
+                '_' used only where two acronyms or two numbers would be concatenated.
+            """))
+        end
     end
 end