Merge pull request #234 from JuliaText/as/textmodels

Split project, separate TextModels
JuliaText · Nov 1, 2020 · 1cb2fd7 · 1cb2fd7 · aviks · Nov 1, 2020
2 parents 67434f7 + bdd76e6
commit 1cb2fd7
Show file tree

Hide file tree

Showing 48 changed files with 75 additions and 311,215 deletions.
diff --git a/.gitignore b/.gitignore
@@ -1,2 +1,3 @@
 .DS_Store
 docs/build
+Manifest.toml
diff --git a/.travis.yml b/.travis.yml
@@ -1,25 +1,24 @@
 language: julia
 os:
   - linux
-env:
-  - DATADEPS_ALWAYS_ACCEPT=true
+  - osx
+  - windows
 julia:
-  - 1.0
   - 1.3
+  - 1
+  - nightly
+matrix:
+  allow_failures:
+    - julia: nightly
+  exclude:
+    - os: osx
+      julia: 1.3
+    - os: windows
+      julia: 1.3
+    - os: osx
+      julia: nightly
+    - os: windows
+      julia: nightly
+  fast_finish: true
 notifications:
   email: false
-before_script: julia -e 'VERSION < v"1.3" && rm("Manifest.toml"; force = true)'
-jobs:
-  include:
-    - stage: "Documentation"
-      julia: 1.0
-      os: linux
-      script:
-        - julia --project=docs/ -e 'using Pkg;
-                                    Pkg.develop(PackageSpec(path=pwd()));
-                                    Pkg.instantiate();
-                                    Pkg.build();'
-        - julia --project=docs/ docs/make.jl
-      after_success: skip
-after_success:
-- julia -e 'cd(Pkg.dir("TextAnalysis")); Pkg.add("Coverage"); using Coverage; Coveralls.submit(Coveralls.process_folder())';
diff --git a/NEWS.md b/NEWS.md
diff --git a/Project.toml b/Project.toml
@@ -5,30 +5,29 @@ desc = "Julia package for text analysis"
 version = "0.7.0"
 
 [deps]
-BSON = "fbb218c0-5317-5bc6-957e-2ee96dd4b1f0"
-BinaryProvider = "b99e7846-7c00-51b0-8f62-c81ae34c0232"
-DataDeps = "124859b0-ceae-595e-8997-d05f6a7a8dfe"
 DataFrames = "a93c6f00-e57d-5684-b7b6-d8193f3e46c0"
 DataStructures = "864edb3b-99cc-5e75-8d2d-829cb0a9cfe8"
 DelimitedFiles = "8bb1440f-4735-579b-a4ab-409b98df4dab"
-Flux = "587475ba-b771-5e3f-ad9e-33799f191a9c"
 JSON = "682c06a0-de6a-54ab-a142-c8b1cf79cde6"
 Languages = "8ef0a80b-9436-5d2c-a485-80b904378c43"
-Libdl = "8f399da3-3557-5675-b5ff-fb832c97cbdb"
 LinearAlgebra = "37e2e46d-f89d-539d-b4ee-838fcccc9c8e"
-NNlib = "872c559c-99b0-510c-b3b7-b6c96a88d5cd"
 Printf = "de0858da-6303-5e67-8744-51eddeeeb8d7"
 Random = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c"
+Snowball = "fb8f903a-0164-4e73-9ffe-431110250c3b"
 SparseArrays = "2f01184e-e22b-5df5-ae63-d93ebab69eaf"
 Statistics = "10745b16-79ce-11e8-11f9-7d13ad32a3b2"
 StatsBase = "2913bbd2-ae8a-5f71-8c99-4fb6c76f3a91"
-Tracker = "9f7883ad-71c0-57eb-9f7f-b5c9e6d3789c"
 WordTokenizers = "796a5d58-b03d-544a-977e-18100b691f6e"
 
 [compat]
-BSON = ">= 0.2.5"
-Flux = "< 0.10"
-julia = "1"
+DataFrames = "0.21"
+DataStructures = "0.17, 0.18"
+JSON = "0.21"
+Languages = "0.4"
+Snowball = "0.1"
+StatsBase = "0.33"
+WordTokenizers = "0.5"
+julia = "1.3"
 
 [extras]
 Test = "8dfed614-e22c-5e08-85e1-65c5234f0b40"

diff --git a/README.md b/README.md
@@ -4,29 +4,38 @@ A Julia package for working with text.
 
 [![Travis](https://travis-ci.org/JuliaText/TextAnalysis.jl.svg?branch=master)](https://travis-ci.org/JuliaText/TextAnalysis.jl)
 [![Appveyor](https://ci.appveyor.com/api/projects/status/aviks/textanalysis-jl?svg=true)](https://ci.appveyor.com/project/aviks/textanalysis-jl)
-<!--[![](https://img.shields.io/badge/docs-stable-blue.svg)](https://juliatext.github.io/TextAnalysis.jl/stable) -->
-[![](https://img.shields.io/badge/docs-dev-blue.svg)](https://juliatext.github.io/TextAnalysis.jl/dev)
-[![](https://img.shields.io/badge/docs-latest-blue.svg)](https://juliatext.github.io/TextAnalysis.jl/latest)
+[![version](https://juliahub.com/docs/TextAnalysis/version.svg)](https://juliahub.com/ui/Packages/TextAnalysis/5Mwet)
+[![](https://img.shields.io/badge/docs-stable-blue.svg)](https://juliahub.com/docs/TextAnalysis/5Mwet) 
 
-Please see the detailed `manual` and `API Documentation` for the linked above. The package also comes with a set of `docstrings` for offline documentation access.
+
+Please see the detailed `example` and `API Documentation`  linked above. The package also comes with a set of `docstrings` for offline documentation access.
 
 ## Introduction
 
-TextAnalysis provides support for standard tools and models for working with textual data and natural languages in the Julia langauges. Please see the [documentation](https://juliatext.github.io/TextAnalysis.jl/latest) for more.
+TextAnalysis provides support for standard tools and models for working with textual data and natural languages in the Julia langauges. Please see the [documentation](https://juliahub.com/docs/TextAnalysis/5Mwett) for more.
 
-- **Features** : Refer to NEWS.md for the latest features.
 - **License** : [MIT License](https://github.com/JuliaText/TextAnalysis.jl/blob/master/LICENSE.md)
 
-## Installation
+## Features
 
-```julia
-pkg> add TextAnalysis
-```
+* Containers for Document and Corpus
+* DocumentTermMatrix and TF/IDF
+* LSA/LDA
+* Vocabulary and Language Model
+* Co-occurance matrix
+* NaiveBayes classifier
+* ROUGE evaluation metrics
 
-You may want to work on the master branch for the latest features (as mentioned in NEWS.md).
+This package also incorporates features from the [Languages](https://juliahub.com/ui/Packages/Languages/w1H1r) and [WordTokenizers](https://juliahub.com/ui/Packages/WordTokenizers/wKkKC) packages within the [JuliaText](https://github.com/JuliaText) ecosystem. 
+
+## TextModels
+
+The [TextModels](https://github.com/JuliaText/TextModels.jl) package enhances this library with the additon of practical neural network based models. Some of that code used to live in this package, but was moved to simplify installation and dependencies. 
+
+## Installation
 
 ```julia
-pkg> add TextAnalysis#master
+pkg> add TextAnalysis
 ```
 
 ## Contributing and Reporting Bugs

diff --git a/appveyor.yml b/appveyor.yml
diff --git a/deps/.gitignore b/deps/.gitignore
diff --git a/deps/build.jl b/deps/build.jl
diff --git a/docs/make.jl b/docs/make.jl
@@ -4,10 +4,7 @@ makedocs(
     modules = [TextAnalysis],
     sitename = "TextAnalysis",
     format = Documenter.HTML(
-        canonical = "https://juliatext.github.io/TextAnalysis.jl/stable/",
-        #prettyurls = false,
     ),
-    assets = ["assets/custom.css", "assets/custom.js", "assets/favicon.ico"],
     pages = [
         "Home" => "index.md",
         "Documents" => "documents.md",
@@ -17,12 +14,8 @@ makedocs(
         "Classifier" => "classify.md",
         "Extended Example" => "example.md",
         "Evaluation Metrics" => "evaluation_metrics.md",
-        "Conditional Random Fields" => "crf.md",
-        "Named Entity Recognition" => "ner.md",
-        "ULMFiT" => "ULMFiT.md",
         "Statistical Language Model" => "LM.md",
         "API References" => "APIReference.md"
     ],
 )
 
-deploydocs(repo = "github.com/JuliaText/TextAnalysis.jl.git")