Merge pull request #121 from davidanthoff/simple-map-syntax

Add a..b syntax

docs/src/querycommands.md

@@ -283,6 +283,37 @@ println(x)
 │ 2   │ 2   │ 2     │
 ```
 
+## Split-Apply-Combine (a.k.a. `dplyr`)
+
+`Query.jl` provides special syntax to summarise data in a `Query.Grouping` as above. *Summarising* here is synonymous to *aggregating* or *collapsing* the dataset over a certain grouping variable. Summarising thus requires an aggregating function like `mean`, `maximum`, or any other function that takes a vector and returns a scalar. The special syntax is `@select new_var = agg_fun(g..var)`, where `agg_fun` is your aggregation function (e.g. `mean`), `g` is your grouping, and `var` is the relevant column that you want to summarise.
+
+#### Example
+
+```jldoctest
+using Query, DataFrames
+
+df = DataFrame(name=repeat(["John", "Sally", "Kirk"],inner=[1],outer=[2]), 
+     age=vcat([10., 20., 30.],[10., 20., 30.].+3), 
+     children=repeat([3,2,2],inner=[1],outer=[2]),state=[:a,:a,:a,:b,:b,:b])
+
+x = @from i in df begin
+    @group i by i.state into g
+    @select {group=g.key,mage=mean(g..age), oldest=maximum(g..age), youngest=minimum(g..age)}
+    @collect DataFrame
+end
+
+println(x)
+
+# Output
+
+2×4 DataFrames.DataFrame
+│ Row │ group │ mage │ oldest │ youngest │
+├─────┼───────┼──────┼────────┼──────────┤
+│ 1   │ a     │ 20.0 │ 30.0   │ 10.0     │
+│ 2   │ b     │ 23.0 │ 33.0   │ 13.0     │
+
+```
+
 ## Range variables
 
 The `@let` statement introduces new range variables in a query expression. The syntax for the range statement is `@let <range variable> = <value selector>`. `<range variable>` specifies the name of the new range variable and `<value selector>` is any julia expression that returns the value that should be assigned to the new range variable.

example/25-ab-syntax.jl

@@ -0,0 +1,14 @@
+using Query
+using DataFrames
+
+df = DataFrame(name=repeat(["John", "Sally", "Kirk"],inner=[1],outer=[2]), 
+     age=vcat([10., 20., 30.],[10., 20., 30.].+3), 
+     children=repeat([3,2,2],inner=[1],outer=[2]),state=[:a,:a,:a,:b,:b,:b])
+
+x = @from i in df begin
+    @group i by i.state into g
+    @select {group=g.key,mage=mean(g..age), oldest=maximum(g..age), youngest=minimum(g..age)}
+    @collect DataFrame
+end
+
+println(x)

src/Query.jl

@@ -5,7 +5,7 @@ using NamedTuples
 using DataStructures
 using IterableTables
 using DataValues
-import MacroTools
+using MacroTools: postwalk
 
 import Base.start
 import Base.next

src/query_translation.jl

@@ -1,5 +1,5 @@
 function helper_namedtuples_replacement(ex)
-	return MacroTools.postwalk(ex) do x
+	return postwalk(ex) do x
 		if x isa Expr && x.head==:cell1d
 			new_ex = Expr(:macrocall, Symbol("@NT"), x.args...)
 
@@ -24,7 +24,7 @@ end
 function helper_replace_anon_func_syntax(ex)
 	if !(isa(ex, Expr) && ex.head==:->)
 		new_symb = gensym()
-		new_ex = MacroTools.postwalk(ex) do x
+		new_ex = postwalk(ex) do x
 			if isa(x, Symbol) && x==:_
 				return new_symb
 			else
@@ -52,6 +52,16 @@ function query_expression_translation_phase_A(qe)
 		end
 		i+=1
 	end
+
+	for i in 1:length(qe)
+		qe[i] = postwalk(qe[i]) do x
+			if x isa Expr && x.head==:call && x.args[1]==:(..)
+				return :(map(i->i.$(x.args[3]),$(x.args[2])))
+			else
+				return x
+			end
+		end
+	end
 end
 
 function query_expression_translation_phase_B(qe)

test/runtests.jl

@@ -550,6 +550,7 @@ q = collect(Query.@select(source_df, i->get(i.children)))
 
 include("test_indexedtables.jl")
 include("test_pipesyntax.jl")
+include("test_dplyr-syntax.jl")
 
 end
 
@@ -576,7 +577,8 @@ end
         "../example/21-nulls.jl",
         "../example/22-datastreams-sink.jl",
         "../example/23-dict-sink.jl",
-        "../example/24-DataTable.jl"]
+        "../example/24-DataTable.jl",
+        "../example/25-ab-syntax.jl"]
 
     color = Base.have_color ? "--color=yes" : "--color=no"
     compilecache = "--compilecache=" * (Bool(Base.JLOptions().use_compilecache) ? "yes" : "no")

test/test_dplyr-syntax.jl

@@ -0,0 +1,27 @@
+using Query
+using DataFrames
+using Base.Test
+
+
+
+@testset "a..b Syntax (dplyr API)" begin
+
+    df = DataFrame(name=repeat(["John", "Sally", "Kirk"],inner=[1],outer=[2]), 
+                   age=vcat([10., 20., 30.],[10., 20., 30.].+3), 
+                   children=repeat([3,2,2],inner=[1],outer=[2]),state=[:a,:a,:a,:b,:b,:b])
+
+    x = @from i in df begin
+        @group i by i.state into g
+        @select {group=g.key,mage=mean(g..age), oldest=maximum(g..age), youngest=minimum(g..age)}
+        @collect DataFrame
+    end
+
+    @test x isa DataFrame
+    @test size(x) == (2,4)
+    @test x[1,:mage] == 20
+    @test x[2,:mage] == 23
+    @test x[1,:oldest] == 30
+    @test x[2,:oldest] == 33
+    @test x[1,:youngest] == 10
+    @test x[2,:youngest] == 13
+end