Merge pull request #3 from JuliaRecsys/persa2p0

Fixing to julia 1.0 and the new persa's interface

Author: filipebraida

.travis.yml

@@ -2,9 +2,9 @@
 language: julia
 os:
   - linux
-  - osx
 julia:
-  - 0.6
+  - 1.0
+  - nightly
 notifications:
   email: false
 # uncomment the following lines to override the default test script

README.md

@@ -17,7 +17,9 @@ julia> dataset = DatasetsCF.MovieLens();
 
 julia> using Persa
 
-julia> μ = Persa.mean(dataset)
+julia> using Statistic
+
+julia> μ = mean(dataset)
 3.52986
 ```
 

REQUIRE

@@ -1,5 +1,6 @@
-julia 0.6
+julia 1.0
 Persa
 MLBase
 DataFrames
 BinDeps
+CSV

appveyor.yml

@@ -1,9 +1,9 @@
 environment:
   matrix:
-  - JULIAVERSION: "julialang/bin/winnt/x86/0.6/julia-0.5-latest-win32.exe"
-  - JULIAVERSION: "julialang/bin/winnt/x64/0.6/julia-0.5-latest-win64.exe"
-  - JULIAVERSION: "julianightlies/bin/winnt/x86/julia-latest-win32.exe"
-  - JULIAVERSION: "julianightlies/bin/winnt/x64/julia-latest-win64.exe"
+  - julia_version: 0.6
+  - julia_version: 0.7
+  - julia_version: 1.0
+  - julia_version: latest
 
 branches:
   only:
@@ -17,18 +17,12 @@ notifications:
     on_build_status_changed: false
 
 install:
-# Download most recent Julia Windows binary
-  - ps: (new-object net.webclient).DownloadFile(
-        $("http://s3.amazonaws.com/"+$env:JULIAVERSION),
-        "C:\projects\julia-binary.exe")
-# Run installer silently, output to C:\projects\julia
-  - C:\projects\julia-binary.exe /S /D=C:\projects\julia
+  - ps: iex ((new-object net.webclient).DownloadString("https://raw.githubusercontent.com/JuliaCI/Appveyor.jl/version-1/bin/install.ps1"))
 
 build_script:
-# Need to convert from shallow to complete for Pkg.clone to work
-  - IF EXIST .git\shallow (git fetch --unshallow)
-  - C:\projects\julia\bin\julia -e "versioninfo();
-      Pkg.clone(pwd(), \"DatasetsCF\"); Pkg.build(\"DatasetsCF\")"
+  - echo "%JL_BUILD_SCRIPT%"
+  - C:\julia\bin\julia -e "%JL_BUILD_SCRIPT%"
 
 test_script:
-  - C:\projects\julia\bin\julia -e "Pkg.test(\"DatasetsCF\")"
+  - echo "%JL_TEST_SCRIPT%"
+- C:\julia\bin\julia -e "%JL_TEST_SCRIPT%"

src/DatasetsCF.jl

@@ -2,11 +2,12 @@ module DatasetsCF
 
 # package code goes here
 using Persa
-using MLBase
+using MLBase: labelencode, labelmap
 using DataFrames
 using BinDeps
+using CSV
 
 include("movielens.jl")
-include("others.jl")
+#include("others.jl")
 
 end # module

src/movielens.jl

@@ -1,57 +1,55 @@
 const defdir = joinpath(dirname(@__FILE__), "..", "datasets")
 
 function getmovielensdata(dir)
-    mkpath(dir)
-    path = download("http://files.grouplens.org/datasets/movielens/ml-100k.zip")
-    run(unpack_cmd(path,dir,".zip", ""))
+	mkpath(dir)
+	path = download("http://files.grouplens.org/datasets/movielens/ml-100k.zip")
+	run(unpack_cmd(path,dir,".zip", ""))
 end
 
 function getmovielensdata1m(dir)
-    mkpath(dir)
-    path = download("http://files.grouplens.org/datasets/movielens/ml-1m.zip")
-    run(unpack_cmd(path,dir,".zip", ""))
+	mkpath(dir)
+	path = download("http://files.grouplens.org/datasets/movielens/ml-1m.zip")
+	run(unpack_cmd(path,dir,".zip", ""))
 end
 
 """
-    MovieLens()::Persa.TimeCFDataset
+    MovieLens()::Persa.Dataset
 
 Return MovieLens 100k dataset.
 """
-function MovieLens()::Persa.TimeCFDataset
-  file = "$(defdir)/ml-100k/u.data"
+function MovieLens()::Persa.Dataset
+	filename = "$(defdir)/ml-100k/u.data"
 
-  isfile(file) || getmovielensdata(defdir)
+	isfile(filename) || getmovielensdata(defdir)
 
-  file = readtable(file, separator = ' ', header = false)
+	file = CSV.read(filename, delim = '	',
+	                      header = [:user, :item, :rating, :timestamp],
+	                      allowmissing = :none)
 
-  df = DataFrame()
-
-  df[:user] = file[:,1]
-  df[:item] = file[:,2]
-  df[:rating] = file[:,3]
-  df[:timestamp] = file[:,4]
-
-  return Persa.Dataset(df)
+	return Persa.Dataset(file)
 end
 
 """
-    MovieLens1M()::Persa.TimeCFDataset
+    MovieLens1M()::Persa.Dataset
 
 Return MovieLens 1M dataset.
 """
-function MovieLens1M()::Persa.TimeCFDataset
-  file = "$(defdir)/ml-1m/ratings.dat"
+function MovieLens1M()::Persa.Dataset
+    filename = "$(defdir)/ml-1m/ratings.dat"
 
-  isfile(file) || getmovielensdata1m(defdir)
+    isfile(filename) || getmovielensdata1m(defdir)
 
-  file = readtable(file, separator = ':', header = false)
+    file = CSV.read(filename, delim = "::",
+							header = [:user, :item, :rating, :timestamp],
+							allowmissing = :all)
 
-  df = DataFrame()
+    df = DataFrame()
 
-  df[:user] = file[:,1]
-  df[:item] = labelencode(labelmap(file[:,3]), file[:,3])
-  df[:rating] = file[:,5]
-  df[:timestamp] = file[:,7]
+	df[:user] = convert(Array{Int}, file[:user])
+	df[:item] = convert(Array{Int}, file[:item])
+	df[:item] = labelencode(labelmap(df[:item]), df[:item])
+	df[:rating] = convert(Array{Int}, file[:rating])
+	df[:timestamp] = convert(Array{Int}, file[:timestamp])
 
-  return Persa.Dataset(df)
+    return Persa.Dataset(df)
 end

test/runtests.jl

@@ -1,17 +1,18 @@
+using Persa
 using DatasetsCF
-using Base.Test
+using Test
 
 # write your own tests here
 ds = DatasetsCF.MovieLens()
-@test ds.users == 943
-@test ds.items == 1682
-@test length(ds.preferences.possibles) == 5
-@test ds.preferences.min == 1
-@test ds.preferences.max == 5
+@test Persa.users(ds) == 943
+@test Persa.items(ds) == 1682
+@test Persa.size(ds.preference) == 5
+@test Persa.minimum(ds.preference) == 1
+@test Persa.maximum(ds.preference) == 5
 
 ds = DatasetsCF.MovieLens1M()
-@test ds.users == 6040
-@test ds.items == 3706
-@test length(ds.preferences.possibles) == 5
-@test ds.preferences.min == 1
-@test ds.preferences.max == 5
+@test Persa.users(ds) == 6040
+@test Persa.items(ds) == 3706
+@test Persa.size(ds.preference) == 5
+@test Persa.minimum(ds.preference) == 1
+@test Persa.maximum(ds.preference) == 5