| /dports/science/py-scikit-learn/scikit-learn-1.0.2/sklearn/feature_extraction/ |
| H A D | text.py | 84 stop_words=None, argument
117 if stop_words is not None:
235 if stop_words is not None:
388 for w in stop_words or ():
455 stop_words=stop_words,
738 stop_words=None, argument
757 self.stop_words = stop_words
1100 stop_words=None, argument
1120 self.stop_words = stop_words
1928 stop_words=None, argument
[all …]
|
| /dports/www/moodle310/moodle/lib/ |
| H A D | tokeniserlib.php | 154 * @param array $stop_words array of utf-8 words than can be ignored in
165 function tokenise_text($text, $stop_words = array(), $overlap_cjk = false, $join_numbers = false) { argument
238 $words = tokenise_split($value, $stop_words, $overlap_cjk, $join_numbers);
288 function tokenise_split($text, $stop_words, $overlap_cjk, $join_numbers) { argument
302 if (is_array($stop_words) && !empty($stop_words)) {
304 …$simp_stop_words = explode(' ', tokenise_simplify(implode(' ', $stop_words), $overlap_cjk, $join_n…
|
| /dports/www/moodle311/moodle/lib/ |
| H A D | tokeniserlib.php | 154 * @param array $stop_words array of utf-8 words than can be ignored in
165 function tokenise_text($text, $stop_words = array(), $overlap_cjk = false, $join_numbers = false) { argument
238 $words = tokenise_split($value, $stop_words, $overlap_cjk, $join_numbers);
288 function tokenise_split($text, $stop_words, $overlap_cjk, $join_numbers) { argument
302 if (is_array($stop_words) && !empty($stop_words)) {
304 …$simp_stop_words = explode(' ', tokenise_simplify(implode(' ', $stop_words), $overlap_cjk, $join_n…
|
| /dports/www/moodle39/moodle/lib/ |
| H A D | tokeniserlib.php | 154 * @param array $stop_words array of utf-8 words than can be ignored in
165 function tokenise_text($text, $stop_words = array(), $overlap_cjk = false, $join_numbers = false) { argument
238 $words = tokenise_split($value, $stop_words, $overlap_cjk, $join_numbers);
288 function tokenise_split($text, $stop_words, $overlap_cjk, $join_numbers) { argument
302 if (is_array($stop_words) && !empty($stop_words)) {
304 …$simp_stop_words = explode(' ', tokenise_simplify(implode(' ', $stop_words), $overlap_cjk, $join_n…
|
| /dports/www/zola/zola-0.15.2/cargo-crates/jieba-rs-0.6.6/src/keywords/ |
| H A D | tfidf.rs | 39 stop_words: BTreeSet<String>, field
48 stop_words: STOP_WORDS.clone(), in new_with_jieba()
86 self.stop_words.insert(word) in add_stop_word()
91 self.stop_words.remove(word) in remove_stop_word()
95 pub fn set_stop_words(&mut self, stop_words: BTreeSet<String>) { in set_stop_words()
96 self.stop_words = stop_words in set_stop_words()
105 if self.stop_words.contains(&s.to_lowercase()) { in filter()
|
| H A D | textrank.rs | 79 stop_words: BTreeSet<String>, field
87 stop_words: STOP_WORDS.clone(), in new_with_jieba()
93 self.stop_words.insert(word) in add_stop_word()
98 self.stop_words.remove(word) in remove_stop_word()
102 pub fn set_stop_words(&mut self, stop_words: BTreeSet<String>) { in set_stop_words()
103 self.stop_words = stop_words in set_stop_words()
112 if self.stop_words.contains(&s.to_lowercase()) { in filter()
|
| /dports/textproc/py-awesome-slugify/awesome-slugify-1.6.5/slugify/ |
| H A D | main.py | 74 def __init__(self, pretranslate=None, translate=unidecode, safe_chars='', stop_words=(), argument
81 self.stop_words = stop_words
133 def set_stop_words(self, stop_words): argument
134 self._stop_words = tuple(stop_words)
137 stop_words = property(fset=set_stop_words) variable in Slugify
145 …_and_words_re = re.compile(unwanted_chars_and_words_re, re.IGNORECASE, stop_words=self._stop_words)
|
| /dports/sysutils/tracker3/tracker-3.1.2/src/libtracker-common/ |
| H A D | tracker-language.c | 37 GHashTable *stop_words; member
132 priv->stop_words = g_hash_table_new_full (g_str_hash, in tracker_language_init()
160 if (priv->stop_words) { in language_finalize()
161 g_hash_table_unref (priv->stop_words); in language_finalize()
184 g_value_set_boxed (value, priv->stop_words); in language_get_property()
272 g_hash_table_insert (priv->stop_words, in language_add_stopwords()
392 return priv->stop_words; in tracker_language_get_stop_words()
416 return g_hash_table_lookup (priv->stop_words, word) != NULL; in tracker_language_is_stop_word()
|
| /dports/sysutils/tracker/tracker-2.3.4/src/libtracker-common/ |
| H A D | tracker-language.c | 38 GHashTable *stop_words; member
133 priv->stop_words = g_hash_table_new_full (g_str_hash, in tracker_language_init()
161 if (priv->stop_words) { in language_finalize()
162 g_hash_table_unref (priv->stop_words); in language_finalize()
185 g_value_set_boxed (value, priv->stop_words); in language_get_property()
273 g_hash_table_insert (priv->stop_words, in language_add_stopwords()
393 return priv->stop_words; in tracker_language_get_stop_words()
417 return g_hash_table_lookup (priv->stop_words, word) != NULL; in tracker_language_is_stop_word()
|
| /dports/textproc/p5-Perl-Critic/Perl-Critic-1.140/lib/Perl/Critic/Policy/Documentation/ |
| H A D | PodSpelling.pm | 164 my ( $self, $stop_words ) = @_;
166 $self->{_stop_words} = $stop_words;
238 my %stop_words = %{ $self->_get_stop_words() };
247 $stop_words{$word} = 1;
253 $self->_set_stop_words(\%stop_words);
|
| /dports/databases/xapian-core12/xapian-core-1.2.25/include/xapian/ |
| H A D | queryparser.h | 57 std::set<std::string> stop_words; variable
74 SimpleStopper(Iterator begin, Iterator end) : stop_words(begin, end) { } in SimpleStopper()
80 while (begin != end) stop_words.insert(*begin++); in SimpleStopper()
85 void add(const std::string & word) { stop_words.insert(word); } in add()
88 return stop_words.find(term) != stop_words.end(); in operator()
|
| /dports/mail/rspamd/rspamd-3.1/src/libmime/ |
| H A D | lang_detection.c | 86 guint stop_words; member
345 const ucl_object_t *stop_words) in rspamd_language_detector_read_file() argument
462 if (stop_words) { in rspamd_language_detector_read_file()
489 nelt->stop_words ++; in rspamd_language_detector_read_file()
684 skipped, loaded, nelt->stop_words, in rspamd_language_detector_read_file()
786 ucl_object_t *stop_words; in rspamd_language_detector_init() local
818 stop_words = NULL; in rspamd_language_detector_init()
863 stop_words); in rspamd_language_detector_init()
894 if (stop_words) { in rspamd_language_detector_init()
895 ucl_object_unref (stop_words); in rspamd_language_detector_init()
[all …]
|
| /dports/mail/rspamd-devel/rspamd-93430bb/src/libmime/ |
| H A D | lang_detection.c | 86 guint stop_words; member
345 const ucl_object_t *stop_words) in rspamd_language_detector_read_file() argument
462 if (stop_words) { in rspamd_language_detector_read_file()
489 nelt->stop_words ++; in rspamd_language_detector_read_file()
684 skipped, loaded, nelt->stop_words, in rspamd_language_detector_read_file()
786 ucl_object_t *stop_words; in rspamd_language_detector_init() local
818 stop_words = NULL; in rspamd_language_detector_init()
863 stop_words); in rspamd_language_detector_init()
894 if (stop_words) { in rspamd_language_detector_init()
895 ucl_object_unref (stop_words); in rspamd_language_detector_init()
[all …]
|
| /dports/biology/ncbi-entrez-direct/ncbi-entrez-direct-14.9.20210423/ |
| H A D | filter-stop-words | 6 stop_words="#a#about#above#abs#accordingly#across#after#afterwards#again#\
40 if [[ $stop_words != *"#$line#"* ]]
|
| /dports/www/chromium-legacy/chromium-88.0.4324.182/components/autofill/content/renderer/ |
| H A D | form_autofill_util.cc | 295 [&stop_words](base::char16 c) { return !base::Contains(stop_words, c); }); in IsLabelValid()
373 if (IsLabelValid(inferred_label, stop_words)) { in InferLabelFromSibling()
803 if (IsLabelValid(inferred_label, stop_words)) { in InferLabelForElement()
811 if (IsLabelValid(inferred_label, stop_words)) { in InferLabelForElement()
837 if (!IsLabelValid(inferred_label, stop_words)) in InferLabelForElement()
849 if (IsLabelValid(inferred_label, stop_words)) { in InferLabelForElement()
858 if (IsLabelValid(inferred_label, stop_words)) { in InferLabelForElement()
1414 std::vector<base::char16> stop_words; in FormOrFieldsetsToFormData() local
1415 stop_words.push_back(static_cast<base::char16>(' ')); in FormOrFieldsetsToFormData()
1416 stop_words.push_back(static_cast<base::char16>('*')); in FormOrFieldsetsToFormData()
[all …]
|
| /dports/www/qt5-webengine/qtwebengine-everywhere-src-5.15.2/src/3rdparty/chromium/components/autofill/content/renderer/ |
| H A D | form_autofill_util.cc | 298 [&stop_words](base::char16 c) { return !base::Contains(stop_words, c); }); in IsLabelValid()
376 if (IsLabelValid(inferred_label, stop_words)) { in InferLabelFromSibling()
806 if (IsLabelValid(inferred_label, stop_words)) { in InferLabelForElement()
814 if (IsLabelValid(inferred_label, stop_words)) { in InferLabelForElement()
840 if (!IsLabelValid(inferred_label, stop_words)) in InferLabelForElement()
852 if (IsLabelValid(inferred_label, stop_words)) { in InferLabelForElement()
861 if (IsLabelValid(inferred_label, stop_words)) { in InferLabelForElement()
1411 std::vector<base::char16> stop_words; in FormOrFieldsetsToFormData() local
1412 stop_words.push_back(static_cast<base::char16>(' ')); in FormOrFieldsetsToFormData()
1413 stop_words.push_back(static_cast<base::char16>('*')); in FormOrFieldsetsToFormData()
[all …]
|
| /dports/databases/xapian-core12/xapian-core-1.2.25/queryparser/ |
| H A D | queryparser.cc | 49 for (i = stop_words.begin(); i != stop_words.end(); ++i) { in get_description()
50 if (i != stop_words.begin()) desc += ' '; in get_description()
|
| /dports/science/py-scikit-learn/scikit-learn-1.0.2/examples/text/ |
| H A D | plot_document_clustering.py | 169 stop_words="english",
177 stop_words="english",
186 stop_words="english",
|
| /dports/databases/xapian-core/xapian-core-1.4.18/queryparser/ |
| H A D | queryparser.cc | 51 for (i = stop_words.begin(); i != stop_words.end(); ++i) { in get_description()
52 if (i != stop_words.begin()) desc += ' '; in get_description()
|
| /dports/science/py-scikit-learn/scikit-learn-1.0.2/sklearn/feature_extraction/tests/ |
| H A D | test_text.py | 366 cv.set_params(stop_words="english")
368 cv.set_params(stop_words="_bad_str_stop_")
371 cv.set_params(stop_words="_bad_unicode_stop_")
375 cv.set_params(stop_words=stoplist)
385 v = CountVectorizer(max_df=1.0, stop_words="english")
1380 stop_words = estimator.get_stop_words()
1395 vec.set_params(stop_words=["you've", "you", "you'll", "AND"])
1409 vec.set_params(stop_words=["you've", "you", "you'll", "blah", "AND"])
1459 vec = CustomEstimator(stop_words=["and"])
1599 stop_words, argument
[all …]
|
| /dports/databases/xapian-core/xapian-core-1.4.18/include/xapian/ |
| H A D | queryparser.h | 97 std::set<std::string> stop_words; variable
113 SimpleStopper(Iterator begin, Iterator end) : stop_words(begin, end) { } in SimpleStopper()
116 void add(const std::string & word) { stop_words.insert(word); } in add()
119 return stop_words.find(term) != stop_words.end(); in operator()
|
| /dports/math/vtk9/VTK-9.1.0/Utilities/Doxygen/ |
| H A D | doc_index.pl | 139 my %stop_words;
143 $stop_words{$stop_word} = 1;
147 print " => ", scalar keys %stop_words, " stop-word(s) read.\n";
231 exists $stop_words{lc($word)}) { # found in stop-words
|
| /dports/math/vtk6/VTK-6.2.0/Utilities/Doxygen/ |
| H A D | doc_index.pl | 139 my %stop_words;
143 $stop_words{$stop_word} = 1;
147 print " => ", scalar keys %stop_words, " stop-word(s) read.\n";
231 exists $stop_words{lc($word)}) { # found in stop-words
|
| /dports/math/vtk8/VTK-8.2.0/Utilities/Doxygen/ |
| H A D | doc_index.pl | 139 my %stop_words;
143 $stop_words{$stop_word} = 1;
147 print " => ", scalar keys %stop_words, " stop-word(s) read.\n";
231 exists $stop_words{lc($word)}) { # found in stop-words
|
| /dports/science/py-scikit-learn/scikit-learn-1.0.2/examples/applications/ |
| H A D | plot_topics_extraction_with_nmf_lda.py | 82 max_df=0.95, min_df=2, max_features=n_features, stop_words="english"
91 max_df=0.95, min_df=2, max_features=n_features, stop_words="english"
|