made some more PatternModelOptions available to the Python binding

proycon · Apr 9, 2020 · 317537b · 317537b
1 parent c260d65
commit 317537b
Show file tree

Hide file tree

Showing 5 changed files with 21 additions and 3 deletions.
diff --git a/codemeta.json b/codemeta.json
@@ -6,7 +6,7 @@
     "@type": "SoftwareSourceCode",
     "identifier": "colibricore",
     "name": "Colibri Core",
-    "version": "2.5.2",
+    "version": "2.5.3",
     "description": "Colibri core is an NLP tool as well as a C++ and Python library for working with basic linguistic constructions such as n-grams and skipgrams (i.e patterns with one or more gaps, either of fixed or dynamic size) in a quick and memory-efficient way. ",
     "license": "https://spdx.org/licenses/GPL-3.0",
 	"url": "https://proycon.github.io/colibri-core",

diff --git a/colibricore_classes.in.pxd b/colibricore_classes.in.pxd
@@ -315,11 +315,13 @@ cdef extern from "patternmodel.h":
     cdef cppclass PatternModelOptions:
         int MINTOKENS
         int MINTOKENS_UNIGRAMS
+        int MINTOKENS_SKIPGRAMS
         int MINLENGTH
         int MAXLENGTH
         bool DOSKIPGRAMS
         bool DOSKIPGRAMS_EXHAUSTIVE
         int MINSKIPTYPES
+        int MAXSKIPS
         bool DOREVERSEINDEX
         bool DEBUG
         bool QUIET
@@ -328,6 +330,7 @@ cdef extern from "patternmodel.h":
         bool DOREMOVESKIPGRAMS
         bool DOREMOVEFLEXGRAMS
         bool DORESET
+        int PRUNENONSUBSUMED
 
     cdef cppclass IndexedDataHandler:
         unsigned int count(IndexedData &)

diff --git a/colibricore_wrapper.in.pyx b/colibricore_wrapper.in.pyx
@@ -890,13 +890,16 @@ cdef class PatternModelOptions:
     * DOSKIPGRAMS - Compute skipgrams?
     * DOSKIPGRAMS_EXHAUSTIVE - Compute skipgrams exhaustively?
     * MINSKIPTYPES - Minimum amount of different skip content types
+    * MAXSKIPS - The maximum amount of skips in a skipgram
     * DOREVERSEINDEX - Build reverse index? (default: True)
     * DOPATTERNPERLINE - Assume each line holds one single pattern.
     * MINTOKENS_UNIGRAMS - Word occurrence threshold (secondary threshold): only count patterns in which the words/unigrams occur at least this many times, only effective when the      primary
+    * MINTOKENS_SKIPGRAMS - The occurrence threshold for skipgrams, minimum amount of occurrences for a pattern to be included in a model. Defaults to the same value as MINTOKENS. Only used if DOSKIPGRAMS or DO_SKIPGRAMS_EXHAUSTIVE is set to true
     * DOREMOVENGRAMS - Remove n-grams from the model
     * DOREMOVESKIPGRAMS - Remove skipgrams from the model
     * DOREMOVEFLEXGRAMS - Remove flexgrams from the model
     * DORESET - Reset all counts before training
+    * PRUNENONSUBSUMED - Prune all n-grams up to this length that are not subsumed by higher-order ngrams
     * DEBUG
     * QUIET (default: False)
 
@@ -923,8 +926,12 @@ cdef class PatternModelOptions:
             self.coptions.DOSKIPGRAMS_EXHAUSTIVE = value
         elif key == 'MINTOKENS_UNIGRAMS':
             self.coptions.MINTOKENS_UNIGRAMS = value
+        elif key == 'MINTOKENS_SKIPGRAMS':
+            self.coptions.MINTOKENS_SKIPGRAMS = value
         elif key == 'MINSKIPTYPES':
             self.coptions.MINSKIPTYPES = value
+        elif key == 'MAXSKIPS':
+            self.coptions.MAXSKIPS = value
         elif key == 'DOREVERSEINDEX':
             self.coptions.DOREVERSEINDEX = value
         elif key == 'DOPATTERNPERLINE':
@@ -941,6 +948,8 @@ cdef class PatternModelOptions:
             self.coptions.DEBUG = value
         elif key == 'QUIET':
             self.coptions.QUIET = value
+        elif key == 'PRUNENONSUBSUMED':
+            self.coptions.PRUNENONSUBSUMED = value
         else:
             raise KeyError
 
@@ -957,8 +966,12 @@ cdef class PatternModelOptions:
             return self.coptions.DOSKIPGRAMS_EXHAUSTIVE
         elif key == 'MINTOKENS_UNIGRAMS':
             return self.coptions.MINTOKENS_UNIGRAMS
+        elif key == 'MINTOKENS_SKIPGRAMS':
+            return self.coptions.MINTOKENS_SKIPGRAMS
         elif key == 'MINSKIPTYPES':
             return self.coptions.MINSKIPTYPES
+        elif key == 'MAXSKIPS':
+            return self.coptions.MAXSKIPS
         elif key == 'DOREVERSEINDEX':
             return self.coptions.DOREVERSEINDEX
         elif key == 'DOPATTERNPERLINE':
@@ -975,6 +988,8 @@ cdef class PatternModelOptions:
             return self.coptions.DEBUG
         elif key == 'QUIET':
             return self.coptions.QUIET
+        elif key == 'PRUNENONSUBSUMED':
+            return self.coptions.PRUNENONSUBSUMED
         else:
             raise KeyError
 

diff --git a/configure.ac b/configure.ac
@@ -4,7 +4,7 @@
 # $URL: https://ilk.uvt.nl/svn/sources/ucto/trunk/configure.ac $
 
 AC_PREREQ([2.67])
-AC_INIT([colibri-core],[2.5.2],[[email protected]])
+AC_INIT([colibri-core],[2.5.3],[[email protected]])
 AC_CONFIG_SRCDIR([configure.ac])
 AC_CONFIG_MACRO_DIR([m4])
 AC_CONFIG_HEADER([config.h])

diff --git a/setup.py b/setup.py
@@ -183,7 +183,7 @@ def read(fname):
     license = "GPL",
     keywords = "nlp computational_linguistics frequency ngram skipgram pmi cooccurrence linguistics",
     long_description=read('README.rst'),
-    version = '2.5.2',
+    version = '2.5.3',
     ext_modules = extensions,
     cmdclass = {'build_ext': build_ext},
     classifiers=[