New port: textproc/py-gensim: Python framework for fast Vector Space Modelling

5 files changed, 52 insertions, 0 deletions

diff --git a/textproc/Makefile b/textproc/Makefile
index a3197a1d515d..56347ba6a3b9 100644
--- a/textproc/Makefile
+++ b/textproc/Makefile
@@ -1307,6 +1307,7 @@
     SUBDIR += py-feedparser
     SUBDIR += py-gambit-elasticsearch
     SUBDIR += py-genshi
+    SUBDIR += py-gensim
     SUBDIR += py-gfm
     SUBDIR += py-guess-language
     SUBDIR += py-hexdump
diff --git a/textproc/py-gensim/Makefile b/textproc/py-gensim/Makefile
new file mode 100644
index 000000000000..b5d1c56f80c2
--- /dev/null
+++ b/textproc/py-gensim/Makefile
@@ -0,0 +1,24 @@
+# $FreeBSD$
+
+PORTNAME=	gensim
+DISTVERSION=	3.4.0
+CATEGORIES=	textproc python
+MASTER_SITES=	CHEESESHOP
+PKGNAMEPREFIX=	${PYTHON_PKGNAMEPREFIX}
+
+MAINTAINER=	yuri@FreeBSD.org
+COMMENT=	Python framework for fast Vector Space Modelling
+
+LICENSE=	LGPL21
+LICENSE_FILE=	${WRKSRC}/COPYING
+
+BUILD_DEPENDS=	${PYNUMPY}
+RUN_DEPENDS=	${PYNUMPY} \
+		${PYTHON_PKGNAMEPREFIX}scipy>=0.18.1:science/py-scipy@${FLAVOR} \
+		${PYTHON_PKGNAMEPREFIX}six>=1.5.0:devel/py-six@${FLAVOR} \
+		${PYTHON_PKGNAMEPREFIX}smart_open>=1.2.1:net/py-smart_open@${FLAVOR}
+
+USES=		python
+USE_PYTHON=	distutils autoplist
+
+.include <bsd.port.mk>
diff --git a/textproc/py-gensim/distinfo b/textproc/py-gensim/distinfo
new file mode 100644
index 000000000000..d6b8ccf0fbb2
--- /dev/null
+++ b/textproc/py-gensim/distinfo
@@ -0,0 +1,3 @@
+TIMESTAMP = 1529032423
+SHA256 (gensim-3.4.0.tar.gz) = 05844c82c7c176449218fd3fc31e55e5d8b3fae460f261b11231f4c8ef2ed5e0
+SIZE (gensim-3.4.0.tar.gz) = 22175027
diff --git a/textproc/py-gensim/pkg-descr b/textproc/py-gensim/pkg-descr
new file mode 100644
index 000000000000..dbdd5b4fab4f
--- /dev/null
+++ b/textproc/py-gensim/pkg-descr
@@ -0,0 +1,21 @@
+Gensim is a Python library for topic modelling, document indexing and similarity
+retrieval with large corpora. Target audience is the natural language processing
+(NLP) and information retrieval (IR) community.
+
+Features:
+* All algorithms are memory-independent w.r.t. the corpus size (can process
+  input larger than RAM, streamed, out-of-core),
+* Intuitive interfaces
+  * easy to plug in your own input corpus/datastream (trivial streaming API)
+  * easy to extend with other Vector Space algorithms (trivial transformation
+    API)
+* Efficient multicore implementations of popular algorithms, such as online
+  Latent Semantic Analysis (LSA/LSI/SVD), Latent Dirichlet Allocation (LDA),
+  Random Projections (RP), Hierarchical Dirichlet Process (HDP) or word2vec deep
+  learning.
+* Distributed computing: can run Latent Semantic Analysis and Latent Dirichlet
+  Allocation on a cluster of computers.
+* Extensive documentation and Jupyter Notebook tutorials.
+
+
+WWW: https://radimrehurek.com/gensim/
diff --git a/textproc/py-gensim/pkg-message b/textproc/py-gensim/pkg-message
new file mode 100644
index 000000000000..811be242c950
--- /dev/null
+++ b/textproc/py-gensim/pkg-message
@@ -0,0 +1,3 @@
+If you are using the Python v3.x version and a non-Unicode locale you'll get a runtime error when mkdocs is executed..
+
+In that case please set the locale to a Unicode locale first, e.g. en_US.UTF-8 or similar, before starting mkdocs.