Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' of github.com:spacy-io/spaCy

This commit is contained in:
Henning Peters 2016-03-24 11:19:47 +01:00
parent a7d7ea3afa a862edc0e6
commit 963570aa49
4 changed files with 11 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
bin/init_model.py
View File

@ -129,7 +129,7 @@ def _read_freqs(loc, max_length=100, min_doc_freq=0, min_freq=200):
word = key
smooth_count = counts.smoother(int(freq))
log_smooth_count = math.log(smooth_count)
probs[word] = math.log(smooth_count) - log_total
probs[word] = log_smooth_count - log_total
oov_prob = math.log(counts.smoother(0)) - log_total
return probs, oov_prob

2
examples/pos_tag.py
View File

@ -54,7 +54,7 @@ def represent_word(word):
# Only do this if the lower-cased form is more probable.
if text.istitle() \
and is_sent_begin(word) \
and word.prob < word.vocab[text.lower()].prob:
and word.prob < word.doc.vocab[text.lower()].prob:
text = text.lower()
return text + '|' + word.tag_

2
spacy/tokenizer.pxd
View File

@ -25,7 +25,7 @@ cdef class Tokenizer:
cdef int _try_cache(self, hash_t key, Doc tokens) except -1
cdef int _tokenize(self, Doc tokens, unicode span, hash_t key) except -1
cdef unicode _split_affixes(self, unicode string, vector[LexemeC*] *prefixes,
cdef unicode _split_affixes(self, Pool mem, unicode string, vector[LexemeC*] *prefixes,
vector[LexemeC*] *suffixes)
cdef int _attach_tokens(self, Doc tokens, unicode string,
vector[LexemeC*] *prefixes, vector[LexemeC*] *suffixes) except -1

16
spacy/tokenizer.pyx
View File

@ -155,11 +155,11 @@ cdef class Tokenizer:
cdef vector[LexemeC*] suffixes
cdef int orig_size
orig_size = tokens.length
span = self._split_affixes(span, &prefixes, &suffixes)
span = self._split_affixes(tokens.mem, span, &prefixes, &suffixes)
self._attach_tokens(tokens, span, &prefixes, &suffixes)
self._save_cached(&tokens.c[orig_size], orig_key, tokens.length - orig_size)
cdef unicode _split_affixes(self, unicode string, vector[const LexemeC*] *prefixes,
cdef unicode _split_affixes(self, Pool mem, unicode string, vector[const LexemeC*] *prefixes,
vector[const LexemeC*] *suffixes):
cdef size_t i
cdef unicode prefix
@ -176,7 +176,7 @@ cdef class Tokenizer:
# Check whether we've hit a special-case
if minus_pre and self._specials.get(hash_string(minus_pre)) != NULL:
string = minus_pre
prefixes.push_back(self.vocab.get(self.vocab.mem, prefix))
prefixes.push_back(self.vocab.get(mem, prefix))
break
suf_len = self.find_suffix(string)
if suf_len != 0:
@ -185,18 +185,18 @@ cdef class Tokenizer:
# Check whether we've hit a special-case
if minus_suf and (self._specials.get(hash_string(minus_suf)) != NULL):
string = minus_suf
suffixes.push_back(self.vocab.get(self.vocab.mem, suffix))
suffixes.push_back(self.vocab.get(mem, suffix))
break
if pre_len and suf_len and (pre_len + suf_len) <= len(string):
string = string[pre_len:-suf_len]
prefixes.push_back(self.vocab.get(self.vocab.mem, prefix))
suffixes.push_back(self.vocab.get(self.vocab.mem, suffix))
prefixes.push_back(self.vocab.get(mem, prefix))
suffixes.push_back(self.vocab.get(mem, suffix))
elif pre_len:
string = minus_pre
prefixes.push_back(self.vocab.get(self.vocab.mem, prefix))
prefixes.push_back(self.vocab.get(mem, prefix))
elif suf_len:
string = minus_suf
suffixes.push_back(self.vocab.get(self.vocab.mem, suffix))
suffixes.push_back(self.vocab.get(mem, suffix))
if string and (self._specials.get(hash_string(string)) != NULL):
break
return string