Add r-doc2vec package from CRAN

recipes/r-doc2vec/bld.bat

@@ -0,0 +1,2 @@
+"%R%" CMD INSTALL --build . %R_ARGS%
+IF %ERRORLEVEL% NEQ 0 exit /B 1

recipes/r-doc2vec/build.sh

@@ -0,0 +1,3 @@
+#!/bin/bash
+export DISABLE_AUTOBREW=1
+${R} CMD INSTALL --build . ${R_ARGS}

recipes/r-doc2vec/meta.yaml

@@ -0,0 +1,74 @@
+{% set version = '0.2.0' %}
+{% set posix = 'm2-' if win else '' %}
+{% set native = 'm2w64-' if win else '' %}
+
+package:
+  name: r-doc2vec
+  version: {{ version|replace("-", "_") }}
+
+source:
+  url:
+    - {{ cran_mirror }}/src/contrib/doc2vec_{{ version }}.tar.gz
+    - {{ cran_mirror }}/src/contrib/Archive/doc2vec/doc2vec_{{ version }}.tar.gz
+  sha256: db3853685072554402434ea699d703e01ac7818044cf47a2ee7d0e1040858908
+
+build:
+  merge_build_host: True  # [win]
+  number: 0
+  rpaths:
+    - lib/R/lib/
+    - lib/
+
+requirements:
+  build:
+    - {{ compiler('c') }}          # [not win]
+    - {{ compiler('m2w64_c') }}    # [win]
+    - {{ compiler('cxx') }}        # [not win]
+    - {{ compiler('m2w64_cxx') }}  # [win]
+    - {{ posix }}filesystem        # [win]
+    - {{ posix }}make
+    - {{ posix }}sed               # [win]
+    - {{ posix }}coreutils         # [win]
+    - {{ posix }}zip               # [win]
+    - cross-r-base {{ r_base }}    # [build_platform != target_platform]
+  host:
+    - r-base
+    - r-rcpp >=0.11.5
+  run:
+    - r-base
+    - {{ native }}gcc-libs         # [win]
+    - r-rcpp >=0.11.5
+
+test:
+  commands:
+    - $R -e "library('doc2vec')"           # [not win]
+    - "\"%R%\" -e \"library('doc2vec')\""  # [win]
+
+about:
+  home: https://github.com/bnosac/doc2vec
+  license: MIT
+  summary: 'Learn vector representations of sentences, paragraphs or documents by using the ''Paragraph
+    Vector'' algorithms, namely the distributed bag of words (''PV-DBOW'') and the distributed
+    memory (''PV-DM'') model. The techniques in the package are detailed in the paper
+    "Distributed Representations of Sentences and Documents" by Mikolov et al. (2014),
+    available at <arXiv:1405.4053>. The package also provides an implementation to cluster
+    documents based on these embedding using a technique called top2vec. Top2vec finds
+    clusters in text documents by combining techniques to embed documents and words
+    and density-based clustering. It does this by embedding documents in the semantic
+    space as defined by the ''doc2vec'' algorithm. Next it maps these document embeddings
+    to a lower-dimensional space using the ''Uniform Manifold Approximation and Projection''
+    (UMAP) clustering algorithm and finds dense areas in that space using a ''Hierarchical
+    Density-Based Clustering'' technique (HDBSCAN). These dense areas are the topic
+    clusters which can be represented by the corresponding topic vector which is an
+    aggregate of the document embeddings of the documents which are part of that topic
+    cluster. In the same semantic space similar words can be found which are representative
+    of the topic. More details can be found in the paper ''Top2Vec: Distributed Representations
+    of Topics'' by D. Angelov available at <arXiv:2008.09470>.'
+  license_family: MIT
+  license_file:
+    - '{{ environ["PREFIX"] }}/lib/R/share/licenses/MIT'
+    - LICENSE
+
+extra:
+  recipe-maintainers:
+    - conda-forge/r