Python Corpus.from_table方法代码示例

# 需要导入模块: from orangecontrib.text.corpus import Corpus [as 别名]
# 或者: from orangecontrib.text.corpus.Corpus import from_table [as 别名]
    def open_file(self, path=None, data=None):
        self.closeContext()
        self.Error.clear()
        self.unused_attrs_model[:] = []
        self.used_attrs_model[:] = []
        if data:
            self.corpus = Corpus.from_table(data.domain, data)
        elif path:
            try:
                self.corpus = Corpus.from_file(path)
                self.corpus.name = os.path.splitext(os.path.basename(path))[0]
            except BaseException as err:
                self.Error.read_file(path, str(err))
        else:
            return

        self.update_info()
        self.used_attrs = list(self.corpus.text_features)
        if not self.corpus.text_features:
            self.Error.corpus_without_text_features()
            self.Outputs.corpus.send(None)
            return
        self.openContext(self.corpus)
        self.used_attrs_model.extend(self.used_attrs)
        self.unused_attrs_model.extend(
            [f for f in self.corpus.domain.metas
             if f.is_string and f not in self.used_attrs_model])

# 需要导入模块: from orangecontrib.text.corpus import Corpus [as 别名]
# 或者: from orangecontrib.text.corpus.Corpus import from_table [as 别名]
 def set_data(self, data=None):
     self.reset_widget()
     self.corpus = data
     if data is not None:
         if not isinstance(data, Corpus):
             self.corpus = Corpus.from_table(data.domain, data)
         self.load_features()
         self.regenerate_docs()
     self.commit()

# 需要导入模块: from orangecontrib.text.corpus import Corpus [as 别名]
# 或者: from orangecontrib.text.corpus.Corpus import from_table [as 别名]
    def test_from_table(self):
        t = Table.from_file('brown-selected')
        self.assertIsInstance(t, Table)

        c = Corpus.from_table(t.domain, t)
        self.assertIsInstance(c, Corpus)
        self.assertEqual(len(t), len(c))
        np.testing.assert_equal(t.metas, c.metas)
        self.assertEqual(c.text_features, [t.domain.metas[0]])

# 需要导入模块: from orangecontrib.text.corpus import Corpus [as 别名]
# 或者: from orangecontrib.text.corpus.Corpus import from_table [as 别名]
    def test_compute_values(self):
        corpus = Corpus.from_file('deerwester')
        vect = BowVectorizer()

        bow = vect.transform(corpus)
        computed = Corpus.from_table(bow.domain, corpus)

        self.assertEqual(bow.domain, computed.domain)
        self.assertEqual((bow.X != computed.X).nnz, 0)

# 需要导入模块: from orangecontrib.text.corpus import Corpus [as 别名]
# 或者: from orangecontrib.text.corpus.Corpus import from_table [as 别名]
 def on_data(self, data):
     if data and not isinstance(data, Corpus):
         data = Corpus.from_table(data.domain, data)
     self.data = data
     self._repopulate_attr_combo(data)
     if not data:
         self.region_selected('')
         QTimer.singleShot(0, lambda: self.webview.evalJS('DATA = {}; renderMap();'))
     else:
         QTimer.singleShot(0, self.on_attr_change)

# 需要导入模块: from orangecontrib.text.corpus import Corpus [as 别名]
# 或者: from orangecontrib.text.corpus.Corpus import from_table [as 别名]
 def set_data(self, data=None):
     self.reset_widget()  # Clear any old data.
     if data is not None:
         self.corpus = data
         if isinstance(data, Table):
             self.corpus = Corpus.from_table(data.domain, data)
         self.load_features()
         self.regenerate_documents()
         # Send the corpus to output.
         self.send(Output.CORPUS, self.corpus)

# 需要导入模块: from orangecontrib.text.corpus import Corpus [as 别名]
# 或者: from orangecontrib.text.corpus.Corpus import from_table [as 别名]
    def test_documents_from_sparse_features(self):
        t = Table.from_file('brown-selected')
        c = Corpus.from_table(t.domain, t)
        c.X = csr_matrix(c.X)

        # docs from X, Y and metas
        docs = c.documents_from_features([t.domain.attributes[0], t.domain.class_var, t.domain.metas[0]])
        self.assertEqual(len(docs), len(t))
        for first_attr, class_val, meta_attr, d in zip(t.X[:, 0], c.Y, c.metas[:, 0], docs):
            first_attr = c.domain.attributes[0].str_val(first_attr)
            class_val = c.domain.class_var.str_val(class_val)
            meta_attr = c.domain.metas[0].str_val(meta_attr)
            self.assertIn(class_val, d)
            self.assertIn(first_attr, d)
            self.assertIn(meta_attr, d)

        # docs only from sparse X
        docs = c.documents_from_features([t.domain.attributes[0]])
        self.assertEqual(len(docs), len(t))
        for first_attr, d in zip(t.X[:, 0], docs):
            first_attr = c.domain.attributes[0].str_val(first_attr)
            self.assertIn(first_attr, d)

# 需要导入模块: from orangecontrib.text.corpus import Corpus [as 别名]
# 或者: from orangecontrib.text.corpus.Corpus import from_table [as 别名]
 def commit(self):
     if self.output_mask is not None:
         output_corpus = Corpus.from_table(self.corpus.domain, self.corpus,
                                           row_indices=self.output_mask)
         self.send(Output.CORPUS, output_corpus)

# 需要导入模块: from orangecontrib.text.corpus import Corpus [as 别名]
# 或者: from orangecontrib.text.corpus.Corpus import from_table [as 别名]
    def test_compute_values(self):
        sentiment = self.method.transform(self.corpus)
        computed = Corpus.from_table(sentiment.domain, self.corpus)

        self.assertEqual(sentiment.domain, computed.domain)
        self.assertTrue((sentiment.X == computed.X).all())