def apply(self):
self.topic_desc.clear()
self.refresh_gui()
if self.corpus:
self.commit.setEnabled(False)
self.enabled(False)
with self.progressBar(len(self.corpus)) as bar:
self.lda = LDA(self.corpus.tokens,
num_topics=self.num_topics,
callback=bar.advance)
table = self.lda.insert_topics_into_corpus(self.corpus)
self.update_topics()
self.send(Output.DATA, table)
self.send_topic_by_id(0)
self.enabled(True)
else:
self.send(Output.DATA, None)
self.send(Output.TOPICS, None)
def apply(self):
self.topic_desc.clear()
self.refresh_gui()
if self.corpus:
self.commit.setEnabled(False)
self.enabled(False)
preprocessed = self.preprocessor(self.corpus.documents)
self.progressBarInit()
self.lda = LDA(preprocessed,
num_topics=self.num_topics,
callback=self.progress)
table = self.lda.insert_topics_into_corpus(self.corpus)
self.update_topics()
self.progressBarFinished()
self.send(Output.DATA, table)
self.send_topic_by_id(0)
self.enabled(True)
else:
self.send(Output.DATA, None)
self.send(Output.TOPICS, None)
def apply(self):
self.topic_desc.clear()
self.refresh_gui()
if self.corpus:
self.commit.setEnabled(False)
self.enabled(False)
with self.progressBar(len(self.corpus)) as bar:
self.lda = LDA(self.corpus.tokens, num_topics=self.num_topics,
callback=bar.advance)
table = self.lda.insert_topics_into_corpus(self.corpus)
self.update_topics()
self.send(Output.DATA, table)
self.send_topic_by_id(0)
self.enabled(True)
else:
self.send(Output.DATA, None)
self.send(Output.TOPICS, None)
def apply(self):
self.topic_desc.clear()
self.refresh_gui()
if self.corpus:
self.commit.setEnabled(False)
self.enabled(False)
preprocessed = self.preprocessor(self.corpus.documents)
self.progressBarInit()
self.lda = LDA(preprocessed, num_topics=self.num_topics, callback=self.progress)
table = self.lda.insert_topics_into_corpus(self.corpus)
self.update_topics()
self.progressBarFinished()
self.send(Output.DATA, table)
self.send_topic_by_id(0)
self.enabled(True)
else:
self.send(Output.DATA, None)
self.send(Output.TOPICS, None)
class LDATests(unittest.TestCase):
corp = Corpus.from_file('deerwester')
text = [d.split() for d in corp.documents]
model = LDA(text, num_topics=5)
def test_insert_topic_into_corpus(self):
corp_topics = self.model.insert_topics_into_corpus(self.corp)
self.assertEqual(len(corp_topics), len(self.corp))
self.assertEqual(len(corp_topics.domain.attributes), 5)
self.assertEqual(corp_topics.X.shape, (len(self.corp), 5))
def test_get_topic_table_by_id(self):
topic1 = self.model.get_topics_table_by_id(1)
self.assertEqual(len(topic1), 45)
self.assertEqual(topic1.metas.shape, (45, 2))
def test_top_words_by_topic(self):
words = self.model.get_top_words_by_id(1)
self.assertEqual(len(words), 10)
def test_too_large_id(self):
with self.assertRaises(ValueError):
self.model.get_topics_table_by_id(6)
class OWLDA(OWWidget):
# Basic widget info
name = "Topic Discovery"
description = "Latent Dirichlet Allocation topic model."
icon = "icons/LDA.svg"
priority = 50
settingsHandler = DomainContextHandler()
# Input/output
inputs = [("Corpus", Corpus, "set_data"),
("Preprocessor", Preprocessor, "set_preprocessor")]
outputs = [(Output.DATA, Table), (Output.TOPICS, Topics)]
want_main_area = True
# Settings
num_topics = Setting(5)
def __init__(self):
super().__init__()
self.lda = None
self.corpus = None
self.preprocessor = Preprocessor()
# Info.
info_box = gui.widgetBox(self.controlArea, "Info")
self.info_label = gui.label(info_box, self, '')
# Settings.
topic_box = gui.widgetBox(self.controlArea, "Settings")
hbox = gui.widgetBox(topic_box, orientation=0)
self.topics_label = gui.label(hbox, self, 'Number of topics: ')
self.topics_label.setMaximumSize(self.topics_label.sizeHint())
self.topics_input = gui.spin(hbox,
self,
"num_topics",
minv=1,
maxv=2**31 - 1,
callback=self.num_topics_changed)
# Commit button
self.commit = gui.button(self.controlArea,
self,
"&Apply",
callback=self.apply,
default=True)
self.commit.setEnabled(False)
gui.rubber(self.controlArea)
# Topics description
self.cols = ['Topic', 'Topic keywords']
self.topic_desc = QtGui.QTreeWidget()
self.topic_desc.setColumnCount(len(self.cols))
self.topic_desc.setHeaderLabels(self.cols)
#self.topic_desc.setSelectionMode(QtGui.QTreeView.ExtendedSelection)
self.topic_desc.itemSelectionChanged.connect(
self.selected_topic_changed)
for i in range(len(self.cols)):
self.topic_desc.resizeColumnToContents(i)
self.mainArea.layout().addWidget(self.topic_desc)
self.refresh_gui()
def set_preprocessor(self, data):
if data is None:
self.preprocessor = Preprocessor()
else:
self.preprocessor = data
self.apply()
def set_data(self, data=None):
self.corpus = data
self.apply()
def refresh_gui(self):
got_corpus = self.corpus is not None
ndoc = len(self.corpus) if got_corpus else "(None)"
self.info_label.setText("Input text entries: {}".format(ndoc))
def update_topics(self):
self.topic_desc.clear()
for i in range(self.lda.num_topics):
words = self.lda.get_top_words_by_id(i)
it = LDATreeWidgetItem(i, words, self.topic_desc)
self.topic_desc.addTopLevelItem(it)
for i in range(2):
self.topic_desc.resizeColumnToContents(i)
def num_topics_changed(self):
if self.corpus is None or \
(self.lda is not None and self.lda.num_topics == self.num_topics):
self.commit.setEnabled(False)
else:
self.commit.setEnabled(True)
def selected_topic_changed(self):
selected = self.topic_desc.selectedItems()
if selected:
self.send_topic_by_id(selected[0].topic_id)
def send_topic_by_id(self, topic_id):
self.topic_desc.setCurrentItem(self.topic_desc.topLevelItem(topic_id))
self.send(Output.TOPICS, self.lda.get_topics_table_by_id(topic_id))
def enabled(self, bool):
self.topics_input.setEnabled(bool)
def progress(self, p):
self.progressBarSet(p)
def apply(self):
self.topic_desc.clear()
self.refresh_gui()
if self.corpus:
self.commit.setEnabled(False)
self.enabled(False)
preprocessed = self.preprocessor(self.corpus.documents)
self.progressBarInit()
self.lda = LDA(preprocessed,
num_topics=self.num_topics,
callback=self.progress)
table = self.lda.insert_topics_into_corpus(self.corpus)
self.update_topics()
self.progressBarFinished()
self.send(Output.DATA, table)
self.send_topic_by_id(0)
self.enabled(True)
else:
self.send(Output.DATA, None)
self.send(Output.TOPICS, None)
class OWLDA(OWWidget):
# Basic widget info
name = "Topic Modelling"
description = "Topic modelling with Latent Dirichlet Allocation."
icon = "icons/LDA.svg"
priority = 50
settingsHandler = DomainContextHandler()
# Input/output
inputs = [("Corpus", Corpus, "set_data"),
("Preprocessor", Preprocessor, "set_preprocessor")]
outputs = [(Output.DATA, Table),
(Output.TOPICS, Topics)]
want_main_area = True
# Settings
num_topics = Setting(5)
def __init__(self):
super().__init__()
self.lda = None
self.corpus = None
self.preprocessor = Preprocessor()
# Info.
info_box = gui.widgetBox(self.controlArea, "Info")
self.info_label = gui.label(info_box, self, '')
# Settings.
topic_box = gui.widgetBox(self.controlArea, "Settings")
hbox = gui.widgetBox(topic_box, orientation=0)
self.topics_label = gui.label(hbox, self, 'Number of topics: ')
self.topics_label.setMaximumSize(self.topics_label.sizeHint())
self.topics_input = gui.spin(hbox, self, "num_topics",
minv=1, maxv=2 ** 31 - 1,
callback=self.num_topics_changed)
# Commit button
self.commit = gui.button(self.controlArea, self, "&Apply",
callback=self.apply, default=True)
self.commit.setEnabled(False)
gui.rubber(self.controlArea)
# Topics description
self.cols = ['Topic', 'Topic keywords']
self.topic_desc = QtGui.QTreeWidget()
self.topic_desc.setColumnCount(len(self.cols))
self.topic_desc.setHeaderLabels(self.cols)
#self.topic_desc.setSelectionMode(QtGui.QTreeView.ExtendedSelection)
self.topic_desc.itemSelectionChanged.connect(self.selected_topic_changed)
for i in range(len(self.cols)):
self.topic_desc.resizeColumnToContents(i)
self.mainArea.layout().addWidget(self.topic_desc)
self.refresh_gui()
def set_preprocessor(self, data):
if data is None:
self.preprocessor = Preprocessor()
else:
self.preprocessor = data
self.apply()
def set_data(self, data=None):
self.corpus = data
self.apply()
def refresh_gui(self):
got_corpus = self.corpus is not None
ndoc = len(self.corpus) if got_corpus else "(None)"
self.info_label.setText("Input text entries: {}".format(ndoc))
def update_topics(self):
self.topic_desc.clear()
for i in range(self.lda.num_topics):
words = self.lda.get_top_words_by_id(i)
it = LDATreeWidgetItem(i, words, self.topic_desc)
self.topic_desc.addTopLevelItem(it)
for i in range(2):
self.topic_desc.resizeColumnToContents(i)
def num_topics_changed(self):
if self.corpus is None or \
(self.lda is not None and self.lda.num_topics == self.num_topics):
self.commit.setEnabled(False)
else:
self.commit.setEnabled(True)
def selected_topic_changed(self):
selected = self.topic_desc.selectedItems()
if selected:
self.send_topic_by_id(selected[0].topic_id)
def send_topic_by_id(self, topic_id):
self.topic_desc.setCurrentItem(self.topic_desc.topLevelItem(topic_id))
self.send(Output.TOPICS, self.lda.get_topics_table_by_id(topic_id))
def enabled(self, bool):
self.topics_input.setEnabled(bool)
def progress(self, p):
self.progressBarSet(p)
def apply(self):
self.topic_desc.clear()
self.refresh_gui()
if self.corpus:
self.commit.setEnabled(False)
self.enabled(False)
preprocessed = self.preprocessor(self.corpus.documents)
self.progressBarInit()
self.lda = LDA(preprocessed, num_topics=self.num_topics, callback=self.progress)
table = self.lda.insert_topics_into_corpus(self.corpus)
self.update_topics()
self.progressBarFinished()
self.send(Output.DATA, table)
self.send_topic_by_id(0)
self.enabled(True)
else:
self.send(Output.DATA, None)
self.send(Output.TOPICS, None)
