if result is not None and len(result.dictionary) == 0:
self.Warning.no_token_left()
result = None
self.send(Output.PP_CORPUS, result)
self.progressBarFinished(None)
def set_minimal_width(self):
max_width = 250
for widget in self.stages:
if widget.enabled:
max_width = max(max_width, widget.sizeHint().width())
self.scroll.setMinimumWidth(max_width + 20)
@pyqtSlot()
def settings_invalidated(self):
self.set_minimal_width()
self.commit()
def send_report(self):
self.report_items('Preprocessor', self.preprocessor.report())
if __name__ == '__main__':
app = QApplication([])
widget = OWPreprocess()
widget.show()
corpus = Corpus.from_file('bookexcerpts')
widget.set_data(corpus)
app.exec()
widget.saveSettings()
self.is_preprocessed = ''
self.is_pos_tagged = ''
self.ngram_range = ''
def commit(self):
if self.corpus is not None:
matched = self.corpus[self.output_mask]
output_mask = set(self.output_mask)
unmatched_mask = [
i for i in range(len(self.corpus)) if i not in output_mask
]
unmatched = self.corpus[unmatched_mask]
self.Outputs.matching_docs.send(matched)
self.Outputs.other_docs.send(unmatched)
else:
self.Outputs.matching_docs.send(None)
self.Outputs.other_docs.send(None)
if __name__ == '__main__':
from orangecontrib.text.tag import pos_tagger
app = QApplication([])
widget = OWCorpusViewer()
widget.show()
corpus = Corpus.from_file('book-excerpts')
corpus = corpus[:3]
corpus = pos_tagger.tag_corpus(corpus)
corpus.ngram_range = (1, 2)
widget.set_data(corpus)
app.exec()
output_mask = set(self.output_mask)
unmatched_mask = [
i for i in range(len(self.corpus)) if i not in output_mask
]
unmatched = self.corpus[unmatched_mask]
self.Outputs.matching_docs.send(matched)
self.Outputs.other_docs.send(unmatched)
else:
self.Outputs.matching_docs.send(None)
self.Outputs.other_docs.send(None)
def send_report(self):
self.report_items((
("Query", self.regexp_filter),
("Matching documents", self.n_matching),
))
if __name__ == '__main__':
from orangecontrib.text.tag.pos import AveragedPerceptronTagger
app = QApplication([])
widget = OWCorpusViewer()
widget.show()
corpus = Corpus.from_file('book-excerpts')
corpus = corpus[:3]
tagger = AveragedPerceptronTagger()
tagged_corpus = tagger.tag_corpus(corpus)
tagged_corpus.ngram_range = (1, 2)
widget.set_data(tagged_corpus)
app.exec()