DBSCAN moved from Prototypes

Orange/widgets/unsupervised/owdbscan.py

@@ -0,0 +1,153 @@
+import numpy as np
+
+from AnyQt.QtWidgets import QLayout
+from AnyQt.QtCore import Qt
+
+from Orange.widgets import widget, gui
+from Orange.widgets.settings import Setting
+from Orange.data import Table, Domain, DiscreteVariable
+from Orange.clustering import DBSCAN
+from Orange import distance
+from Orange.widgets.utils.annotated_data import ANNOTATED_DATA_SIGNAL_NAME
+from Orange.widgets.utils.signals import Input, Output
+from Orange.widgets.widget import Msg
+
+
+class OWDBSCAN(widget.OWWidget):
+    name = "DBSCAN"
+    description = "Density-based spatial clustering."
+    icon = "icons/DBSCAN.svg"
+    priority = 2150
+
+    class Inputs:
+        data = Input("Data", Table)
+
+    class Outputs:
+        annotated_data = Output(ANNOTATED_DATA_SIGNAL_NAME, Table)
+
+    class Error(widget.OWWidget.Error):
+        not_enough_instances = Msg("Not enough unique data instances. "
+                                   "At least two are required.")
+
+    METRICS = [
+        ("Euclidean", "euclidean"),
+        ("Manhattan", "manhattan"),
+        ("Cosine", distance.Cosine),
+        ("Jaccard", distance.Jaccard),
+        # ("Spearman", distance.SpearmanR),
+        # ("Spearman absolute", distance.SpearmanRAbsolute),
+        # ("Pearson", distance.PearsonR),
+        # ("Pearson absolute", distance.PearsonRAbsolute),
+    ]
+
+    min_samples = Setting(5)
+    eps = Setting(0.5)
+    metric_idx = Setting(0)
+    auto_commit = Setting(True)
+
+    want_main_area = False
+
+    def __init__(self):
+        super().__init__()
+
+        self.data = None
+        self.db = None
+        self.model = None
+
+        box = gui.widgetBox(self.controlArea, "Parameters")
+        gui.spin(box, self, "min_samples", 1, 100, 1, callback=self._invalidate,
+                 label="Core point neighbors")
+        gui.doubleSpin(box, self, "eps", 0.1, 10, 0.01,
+                       callback=self._invalidate,
+                       label="Neighborhood distance")
+
+        box = gui.widgetBox(self.controlArea, self.tr("Distance Metric"))
+        gui.comboBox(box, self, "metric_idx",
+                     items=list(zip(*self.METRICS))[0],
+                     callback=self._invalidate)
+
+        gui.auto_commit(self.controlArea, self, "auto_commit", "Apply",
+                        orientation=Qt.Horizontal)
+        gui.rubber(self.controlArea)
+
+        self.controlArea.setMinimumWidth(self.controlArea.sizeHint().width())
+        self.layout().setSizeConstraint(QLayout.SetFixedSize)
+
+    def adjustSize(self):
+        self.ensurePolished()
+        self.resize(self.controlArea.sizeHint())
+
+    def check_data_size(self):
+        if len(self.data) < 2:
+            self.Error.not_enough_instances()
+            return False
+        return True
+
+    def commit(self):
+        self.cluster()
+
+    def cluster(self):
+        if not self.check_data_size():
+            return
+        self.model = DBSCAN(
+            eps=self.eps,
+            min_samples=self.min_samples,
+            metric=self.METRICS[self.metric_idx][1]
+        ).get_model(self.data)
+        self.send_data()
+
+    def send_data(self):
+        model = self.model
+
+        clusters = [c if c >= 0 else np.nan for c in model.labels]
+        k = len(set(clusters) - {np.nan})
+        clusters = np.array(clusters).reshape(len(self.data), 1)
+        core_samples = set(model.projector.core_sample_indices_)
+        in_core = np.array([1 if (i in core_samples) else 0
+                            for i in range(len(self.data))])
+        in_core = in_core.reshape(len(self.data), 1)
+
+        clust_var = DiscreteVariable(
+            "Cluster", values=["C%d" % (x + 1) for x in range(k)])
+        in_core_var = DiscreteVariable("DBSCAN Core", values=["0", "1"])
+
+        domain = self.data.domain
+        attributes, classes = domain.attributes, domain.class_vars
+        meta_attrs = domain.metas
+        x, y, metas = self.data.X, self.data.Y, self.data.metas
+
+        meta_attrs += (clust_var, )
+        metas = np.hstack((metas, clusters))
+        meta_attrs += (in_core_var, )
+        metas = np.hstack((metas, in_core))
+
+        domain = Domain(attributes, classes, meta_attrs)
+        new_table = Table(domain, x, y, metas, self.data.W)
+
+        self.Outputs.annotated_data.send(new_table)
+
+    @Inputs.data
+    def set_data(self, data):
+        self.data = data
+        if self.data is None:
+            self.Outputs.annotated_data.send(None)
+        self.Error.clear()
+        if self.data is None:
+            return
+        self.unconditional_commit()
+
+    def _invalidate(self):
+        self.commit()
+
+
+if __name__ == "__main__":
+    import sys
+    from AnyQt.QtWidgets import QApplication
+
+    a = QApplication(sys.argv)
+    ow = OWDBSCAN()
+    d = Table("iris.tab")
+    ow.set_data(d)
+    ow.show()
+    a.exec()
+    ow.saveSettings()

Orange/widgets/unsupervised/tests/test_owdbscan.py

@@ -0,0 +1,119 @@
+import numpy as np
+from scipy.sparse import csr_matrix
+
+from Orange.data import Table
+from Orange.widgets.tests.base import WidgetTest
+from Orange.widgets.tests.utils import simulate
+from Orange.widgets.unsupervised.owdbscan import OWDBSCAN
+
+
+class TestOWCSVFileImport(WidgetTest):
+    def setUp(self):
+        self.widget = self.create_widget(OWDBSCAN)
+        self.iris = Table("iris")
+
+    def tearDown(self):
+        self.widgets.remove(self.widget)
+        self.widget.onDeleteWidget()
+        self.widget = None
+
+    def test_cluster(self):
+        w = self.widget
+
+        self.send_signal(w.Inputs.data, self.iris)
+
+        output = self.get_output(w.Outputs.annotated_data)
+        self.assertIsNotNone(output)
+        self.assertEqual(len(self.iris), len(output))
+        self.assertTupleEqual(self.iris.X.shape, output.X.shape)
+        self.assertTupleEqual(self.iris.Y.shape, output.Y.shape)
+        self.assertEqual(2, output.metas.shape[1])
+
+        self.assertEqual("Cluster", str(output.domain.metas[0]))
+        self.assertEqual("DBSCAN Core", str(output.domain.metas[1]))
+
+    def test_bad_input(self):
+        w = self.widget
+
+        self.send_signal(w.Inputs.data, self.iris[:1])
+        self.assertTrue(w.Error.not_enough_instances.is_shown())
+
+        self.send_signal(w.Inputs.data, self.iris[:2])
+        self.assertFalse(w.Error.not_enough_instances.is_shown())
+
+        self.send_signal(w.Inputs.data, self.iris)
+        self.assertFalse(w.Error.not_enough_instances.is_shown())
+
+    def test_data_none(self):
+        w = self.widget
+
+        self.send_signal(w.Inputs.data, self.iris[:5])
+        self.send_signal(w.Inputs.data, None)
+
+        output = self.get_output(w.Outputs.annotated_data)
+        self.assertIsNone(output)
+
+    def test_change_eps(self):
+        w = self.widget
+
+        self.send_signal(w.Inputs.data, self.iris)
+
+        # change parameters
+        self.widget.controls.eps.valueChanged.emit(0.5)
+        output1 = self.get_output(w.Outputs.annotated_data)
+        self.widget.controls.eps.valueChanged.emit(1)
+        output2 = self.get_output(w.Outputs.annotated_data)
+
+        # on this data higher eps has greater sum of clusters - less nan
+        # values
+        self.assertGreater(np.nansum(output2.metas[:, 0]),
+                           np.nansum(output1.metas[:, 0]))
+
+    def test_change_min_samples(self):
+        w = self.widget
+
+        self.send_signal(w.Inputs.data, self.iris)
+
+        # change parameters
+        self.widget.controls.min_samples.valueChanged.emit(5)
+        output1 = self.get_output(w.Outputs.annotated_data)
+        self.widget.controls.min_samples.valueChanged.emit(1)
+        output2 = self.get_output(w.Outputs.annotated_data)
+
+        # on this data lower min_samples has greater sum of clusters - less nan
+        # values
+        self.assertGreater(np.nansum(output2.metas[:, 0]),
+                           np.nansum(output1.metas[:, 0]))
+
+    def test_change_metric_idx(self):
+        w = self.widget
+
+        self.send_signal(w.Inputs.data, self.iris)
+
+        # change parameters
+        cbox = self.widget.controls.metric_idx
+        simulate.combobox_activate_index(cbox, 0)  # Euclidean
+        output1 = self.get_output(w.Outputs.annotated_data)
+        simulate.combobox_activate_index(cbox, 1)  # Manhattan
+        output2 = self.get_output(w.Outputs.annotated_data)
+
+        # Manhattan has more nan clusters
+        self.assertGreater(np.nansum(output1.metas[:, 0]),
+                           np.nansum(output2.metas[:, 0]))
+
+    def test_sparse_data(self):
+        self.iris.X = csr_matrix(self.iris.X)
+
+        w = self.widget
+
+        self.send_signal(w.Inputs.data, self.iris)
+
+        output = self.get_output(w.Outputs.annotated_data)
+        self.assertIsNotNone(output)
+        self.assertEqual(len(self.iris), len(output))
+        self.assertTupleEqual(self.iris.X.shape, output.X.shape)
+        self.assertTupleEqual(self.iris.Y.shape, output.Y.shape)
+        self.assertEqual(2, output.metas.shape[1])
+
+        self.assertEqual("Cluster", str(output.domain.metas[0]))
+        self.assertEqual("DBSCAN Core", str(output.domain.metas[1]))