diff --git a/REQUIRE b/REQUIRE index d124b931..ea9cd5e7 100644 --- a/REQUIRE +++ b/REQUIRE @@ -5,3 +5,4 @@ MacroTools 0.3.3 NNlib ForwardDiff Requires +ZipFile diff --git a/src/data/Data.jl b/src/data/Data.jl index ffea729c..631e45e5 100644 --- a/src/data/Data.jl +++ b/src/data/Data.jl @@ -11,4 +11,7 @@ end include("cmudict.jl") using .CMUDict +include("sentiment.jl") +using .Sentiment + end diff --git a/src/data/sentiment.jl b/src/data/sentiment.jl new file mode 100644 index 00000000..7917f302 --- /dev/null +++ b/src/data/sentiment.jl @@ -0,0 +1,21 @@ +module Sentiment + +using ..Data: deps + +function load() + isfile(deps("stanfordSentimentTreebank.zip")) || + download("http://nlp.stanford.edu/~socherr/stanfordSentimentTreebank.zip", + deps("stanfordSentimentTreebank.zip")) + return +end + +getfile(r, name) = r.files[findfirst(x -> x.name == name, r.files)] + +function loadtext() + r = ZipFile.Reader(deps("stanfordSentimentTreebank.zip")) + sentences = readstring(getfile(r, "stanfordSentimentTreebank/datasetSentences.txt")) + close(r) + return sentences +end + +end