[BREAKING] Refactor unstack

src/abstractdataframe/reshape.jl

@@ -207,8 +207,10 @@ end
 
 Unstack data frame `df`, i.e. convert it from long to wide format.
 
-Row keys and values from value column will be ordered in the order produced
-by `groupby`.
+Row and column keys will be ordered in the order of their first appearance except
+when they are stored in an `AbstractVector` which supports `DataAPI.refpool`
+(two most common cases are `CategoricalVector` and `PooledVector`),
+in which case the odrer follows the order of values in this pool.
 
 # Positional arguments
 - `df` : the AbstractDataFrame to be unstacked
@@ -369,15 +371,16 @@ function find_group_row(gdf::GroupedDataFrame)
 
     filled = 0
     i = 1
+    groups = gdf.groups
     while filled < length(gdf)
-        group = gdf.groups[i]
+        group = groups[i]
         if rows[group] == 0
             rows[group] = i
             filled += 1
         end
         i += 1
     end
-    return rows # return row index of first occurence of each group in gdf
+    return rows # return row index of first occurrence of each group in gdf
 end
 
 function _unstack(df::AbstractDataFrame, rowkeys::AbstractVector{Int},

test/reshape.jl

@@ -498,7 +498,7 @@ end
     @test unstack(df, [:id, :id2], :var, :val) == unstack(df, :var, :val) ==
           DataFrame(id=1:3, id2=1:3, a=1:3:7, b=2:3:8, c=3:3:9)
 
-    # an exertice on current unstack invariants
+    # an exercise on current unstack invariants
     Random.seed!(1234)
     for i in 1:16
         df = df[Random.shuffle(1:9), :]