def check_data(self):
self.Error.clear()
if isinstance(self.data, Table) and \
isinstance(self.selected_data, Table):
if len(self.selected_data) == 0:
self.Error.empty_selection()
self.clear()
return
# keep only BoW features
bow_domain = self.get_bow_domain()
if len(bow_domain.attributes) == 0:
self.Error.no_bow_features()
self.clear()
return
self.data = Corpus.from_table(bow_domain, self.data)
self.selected_data_transformed = Corpus.from_table(
bow_domain, self.selected_data)
if np_sp_sum(self.selected_data_transformed.X) == 0:
self.Error.no_words_overlap()
self.clear()
elif len(self.data) == len(self.selected_data):
self.Error.all_selected()
self.clear()
else:
self.apply()
else:
self.clear()
def filter_and_display(self):
self.spin_p.setEnabled(self.filter_by_p)
self.spin_fdr.setEnabled(self.filter_by_fdr)
self.sig_words.clear()
if self.selected_data_transformed is None: # do nothing when no Data
return
count = 0
if self.words:
for word, pval, fval in zip(self.words, self.p_values,
self.fdr_values):
if (not self.filter_by_p or pval <= self.filter_p_value) and \
(not self.filter_by_fdr or fval <= self.filter_fdr_value):
it = EATreeWidgetItem(word, pval, fval, self.sig_words)
self.sig_words.addTopLevelItem(it)
count += 1
for i in range(len(self.cols)):
self.sig_words.resizeColumnToContents(i)
self.info_all.setText('Cluster words: {}'.format(
len(self.selected_data_transformed.domain.attributes)))
self.info_sel.setText('Selected words: {}'.format(
np.count_nonzero(
np_sp_sum(self.selected_data_transformed.X, axis=0))))
if not self.filter_by_p and not self.filter_by_fdr:
self.info_fil.setText('After filtering:')
self.info_fil.setEnabled(False)
else:
self.info_fil.setEnabled(True)
self.info_fil.setText('After filtering: {}'.format(count))
def check_data(self):
self.Error.clear()
if isinstance(self.data, Table) and \
isinstance(self.selected_data, Table):
if len(self.selected_data) == 0:
self.Error.empty_selection()
self.clear()
return
# keep only BoW features
bow_domain = self.get_bow_domain()
if len(bow_domain.attributes) == 0:
self.Error.no_bow_features()
self.clear()
return
self.data = Corpus.from_table(bow_domain, self.data)
self.selected_data_transformed = Corpus.from_table(bow_domain, self.selected_data)
if np_sp_sum(self.selected_data_transformed.X) == 0:
self.Error.no_words_overlap()
self.clear()
elif len(self.data) == len(self.selected_data):
self.Error.all_selected()
self.clear()
else:
self.apply()
else:
self.clear()
def filter_and_display(self):
self.spin_p.setEnabled(self.filter_by_p)
self.spin_fdr.setEnabled(self.filter_by_fdr)
self.sig_words.clear()
if self.selected_data_transformed is None: # do nothing when no Data
return
count = 0
if self.words:
for word, pval, fval in zip(self.words, self.p_values, self.fdr_values):
if (not self.filter_by_p or pval <= self.filter_p_value) and \
(not self.filter_by_fdr or fval <= self.filter_fdr_value):
it = EATreeWidgetItem(word, pval, fval, self.sig_words)
self.sig_words.addTopLevelItem(it)
count += 1
for i in range(len(self.cols)):
self.sig_words.resizeColumnToContents(i)
self.info_all.setText('Cluster words: {}'.format(len(self.selected_data_transformed.domain.attributes)))
self.info_sel.setText('Selected words: {}'.format(np.count_nonzero(np_sp_sum(self.selected_data_transformed.X, axis=0))))
if not self.filter_by_p and not self.filter_by_fdr:
self.info_fil.setText('After filtering:')
self.info_fil.setEnabled(False)
else:
self.info_fil.setEnabled(True)
self.info_fil.setText('After filtering: {}'.format(count))
def set_input_info(self) -> None:
cluster_words = len(self.selected_data_transformed.domain.attributes)
selected_words = np.count_nonzero(
np_sp_sum(self.selected_data_transformed.X, axis=0))
self.info.set_input_summary(
f"{cluster_words}|{selected_words}",
f"Total words: {cluster_words}\n"
f"Words in subset: {selected_words}")
def check_data(self):
self.Error.clear()
if isinstance(self.data, Table) and \
isinstance(self.selected_data, Table):
if len(self.selected_data) == 0:
self.Error.empty_selection()
self.clear()
return
self.selected_data_transformed = Table.from_table(
self.data.domain, self.selected_data)
if np_sp_sum(self.selected_data_transformed.X) == 0:
self.Error.no_words_overlap()
self.clear()
elif len(self.data) == len(self.selected_data):
self.Error.all_selected()
self.clear()
else:
self.apply()
else:
self.clear()
def check_data(self):
self.Error.clear()
if isinstance(self.data, Table) and \
isinstance(self.selected_data, Table):
if len(self.selected_data) == 0:
self.Error.empty_selection()
self.clear()
return
self.selected_data_transformed = Table.from_table(
self.data.domain, self.selected_data)
sum_X = np_sp_sum(self.selected_data_transformed.X)
if sum_X == 0 or math.isnan(sum_X):
self.Error.no_words_overlap()
self.clear()
elif len(self.data) == len(self.selected_data):
self.Error.all_selected()
self.clear()
else:
self.apply()
else:
self.clear()
def test_np_sp_sum(self):
for data in [np.eye(10), sp.csr_matrix(np.eye(10))]:
self.assertEqual(np_sp_sum(data), 10)
np.testing.assert_equal(np_sp_sum(data, axis=1), np.ones(10))
np.testing.assert_equal(np_sp_sum(data, axis=0), np.ones(10))
def test_np_sp_sum(self):
for data in [np.eye(10), sp.csr_matrix(np.eye(10))]:
self.assertEqual(np_sp_sum(data), 10)
np.testing.assert_equal(np_sp_sum(data, axis=1), np.ones(10))
np.testing.assert_equal(np_sp_sum(data, axis=0), np.ones(10))
