[python] Fork of the suffix-array extractor with surface improvements

Available as the cdec.sa module, with commande-line helpers:
python -m cdec.sa.compile -f ... -e ... -a ... -o sa-out/ -c extract.ini
python -m cdec.sa.extract -c extract.ini -g grammars-out/ < input.txt > input.sgml

+ renamed cdec.scfg -> cdec.sa
+ Python README

1 files changed, 0 insertions, 62 deletions

diff --git a/python/cdec/scfg/features.py b/python/cdec/scfg/features.py
deleted file mode 100644
index 6419cdd8..00000000
--- a/python/cdec/scfg/features.py
+++ /dev/null
@@ -1,62 +0,0 @@
-from __future__ import division
-import math
-import sym
-
-def contextless(feature):
-    feature.compute_contextless_score = feature
-    return feature
-
-MAXSCORE = 99
-
-def EgivenF(fphrase, ephrase, paircount, fcount, fsample_count): # p(e|f)
-    return -math.log10(paircount/fcount)
-
-def CountEF(fphrase, ephrase, paircount, fcount, fsample_count):
-    return math.log10(1 + paircount)
-
-def SampleCountF(fphrase, ephrase, paircount, fcount, fsample_count):
-    return math.log10(1 + fsample_count)
-
-def EgivenFCoherent(fphrase, ephrase, paircount, fcount, fsample_count):
-    prob = paircount/fsample_count
-    return -math.log10(prob) if prob > 0 else MAXSCORE
-
-def CoherenceProb(fphrase, ephrase, paircount, fcount, fsample_count):
-    return -math.log10(fcount/fsample_count)
-
-def MaxLexEgivenF(ttable):
-    def feature(fphrase, ephrase, paircount, fcount, fsample_count):
-        fwords = [sym.tostring(w) for w in fphrase if not sym.isvar(w)] + ['NULL']
-        ewords = (sym.tostring(w) for w in ephrase if not sym.isvar(w))
-        def score():
-            for e in ewords:
-              maxScore = max(ttable.get_score(f, e, 0) for f in fwords)
-              yield -math.log10(maxScore) if maxScore > 0 else MAXSCORE
-        return sum(score())
-    return feature
-
-def MaxLexFgivenE(ttable):
-    def feature(fphrase, ephrase, paircount, fcount, fsample_count):
-        fwords = (sym.tostring(w) for w in fphrase if not sym.isvar(w))
-        ewords = [sym.tostring(w) for w in ephrase if not sym.isvar(w)] + ['NULL']
-        def score():
-            for f in fwords:
-              maxScore = max(ttable.get_score(f, e, 1) for e in ewords)
-              yield -math.log10(maxScore) if maxScore > 0 else MAXSCORE
-        return sum(score())
-    return feature
-
-def IsSingletonF(fphrase, ephrase, paircount, fcount, fsample_count):
-    return (fcount == 1)
-
-def IsSingletonFE(fphrase, ephrase, paircount, fcount, fsample_count):
-    return (paircount == 1)
-
-def IsNotSingletonF(fphrase, ephrase, paircount, fcount, fsample_count):
-    return (fcount > 1)
-
-def IsNotSingletonFE(fphrase, ephrase, paircount, fcount, fsample_count):
-    return (paircount > 1)
-
-def IsFEGreaterThanZero(fphrase, ephrase, paircount, fcount, fsample_count):
-    return (paircount > 0.01)