def create_words_table(words: List) -> Table:
words_var = StringVariable("Words")
words_var.attributes = {"type": "words"}
domain = Domain([], metas=[words_var])
data = [[w] for w in words]
words = Table.from_list(domain, data)
words.name = "Words"
return words
def commit(self):
selection = self._get_selected_words_indices()
self.selected_words = set(np.array(self.words_model)[selection])
words, selected_words = None, None
if self.words_model:
words_var = StringVariable("Words")
words_var.attributes = {"type": "words"}
domain = Domain([], metas=[words_var])
_words = Table.from_list(domain, [[w] for w in self.words_model])
_words.name = "Words"
if selection:
selected_words = _words[selection]
words = create_annotated_table(_words, selection)
self.Outputs.words.send(words)
self.Outputs.selected_words.send(selected_words)
def commit(self):
if not self.sig_words:
self.Outputs.words.send(None)
# retrieve the data except the header
tree = np.array(self.tree_to_table(), dtype=object)[1:]
words_var = StringVariable("Words")
words_var.attributes = {"type": "words"}
attrs = [ContinuousVariable("p-values"),
ContinuousVariable("FDR values")]
domain = Domain(attrs, metas=[words_var])
X = tree.take([1, 2], axis=1).astype(float)
metas = tree.take([0], axis=1)
words = Table.from_numpy(domain, X=X, metas=metas)
words.name = "Words"
self.Outputs.words.send(words)
def commit(self):
words = None
if self.selected_words:
words_var = StringVariable(WORDS_COLUMN_NAME)
words_var.attributes = {"type": "words"}
model = self.model
attrs = [
ContinuousVariable(model.headerData(i + 1, Qt.Horizontal))
for i in range(len(self.selected_scoring_methods))
]
domain = Domain(attrs, metas=[words_var])
sort_column, reverse = self.sort_column_order
data = sorted(model, key=lambda a: a[sort_column], reverse=reverse)
data = [s[1:] + s[:1] for s in data if s[0] in self.selected_words]
words = Table.from_list(domain, data)
words.name = "Words"
self.Outputs.words.send(words)
sort_column, reverse = self.sort_column_order
data = sorted(model, key=lambda a: a[sort_column], reverse=reverse)
data = [s[1:] + s[:1] for s in data if s[0] in self.selected_words]
words = Table.from_list(domain, data)
words.name = "Words"
self.Outputs.words.send(words)
def send_report(self):
if not self.corpus:
return
self.report_data("Corpus", self.corpus)
if self.words is not None:
self.report_paragraph("Words", ", ".join(self.words))
self.report_table("Keywords", self.view, num_format="{:.3f}")
if __name__ == "__main__":
# pylint: disable=ungrouped-imports
from Orange.widgets.utils.widgetpreview import WidgetPreview
words_var_ = StringVariable(WORDS_COLUMN_NAME)
words_var_.attributes = {"type": "words"}
lists = [[w] for w in ["human", "graph", "minors", "trees"]]
words_ = Table.from_list(Domain([], metas=[words_var_]), lists)
words_.name = "Words"
WidgetPreview(OWKeywords).run(
set_corpus=Corpus.from_file("deerwester"), # deerwester book-excerpts
# set_words=words_
)