Merge pull request #3549 from AndrejaKovacic/keep_data_owtransform

[ENH] OWTransform: add option to keep original data #3526
biolab · Jan 25, 2019 · c06cda3 · c06cda3
2 parents cd5a48c + 1d7851c
commit c06cda3
Show file tree

Hide file tree

Showing 2 changed files with 39 additions and 2 deletions.
diff --git a/Orange/widgets/data/owtransform.py b/Orange/widgets/data/owtransform.py
@@ -1,6 +1,9 @@
-from Orange.data import Table
+import numpy as np
+
+from Orange.data import Table, Domain
 from Orange.preprocess.preprocess import Preprocess, Discretize
 from Orange.widgets import gui
+from Orange.widgets.settings import Setting
 from Orange.widgets.utils.sql import check_sql_input
 from Orange.widgets.utils.widgetpreview import WidgetPreview
 from Orange.widgets.widget import OWWidget, Input, Output, Msg
@@ -13,6 +16,8 @@ class OWTransform(OWWidget):
     priority = 2110
     keywords = []
 
+    retain_all_data = Setting(False)
+
     class Inputs:
         data = Input("Data", Table, default=True)
         preprocessor = Input("Preprocessor", Preprocess)
@@ -39,6 +44,11 @@ def __init__(self):
         self.set_input_label_text()
         self.set_preprocessor_label_text()
 
+        self.retain_all_data_cb = gui.checkBox(
+            self.controlArea, self, "retain_all_data", label="Retain all data",
+            callback=self.apply
+            )
+
     def set_input_label_text(self):
         text = "No data on input."
         if self.data is not None:
@@ -83,11 +93,30 @@ def apply(self):
                 self.transformed_data = self.preprocessor(self.data)
             except Exception as ex:   # pylint: disable=broad-except
                 self.Error.pp_error(ex)
-        self.Outputs.transformed_data.send(self.transformed_data)
+
+        if self.retain_all_data:
+            self.Outputs.transformed_data.send(self.merge_data())
+        else:
+            self.Outputs.transformed_data.send(self.transformed_data)
 
         self.set_preprocessor_label_text()
         self.set_output_label_text()
 
+    def merge_data(self):
+        attributes = getattr(self.data.domain, 'attributes')
+        cls_vars = getattr(self.data.domain, 'class_vars')
+        metas_v = getattr(self.data.domain, 'metas')\
+            + getattr(self.transformed_data.domain, 'attributes')
+        domain = Domain(attributes, cls_vars, metas_v)
+        X = self.data.X
+        Y = self.data.Y
+        metas = np.hstack((self.data.metas, self.transformed_data.X))
+        table = Table.from_numpy(domain, X, Y, metas)
+        table.name = getattr(self.data, 'name', '')
+        table.attributes = getattr(self.data, 'attributes', {})
+        table.ids = self.data.ids
+        return table
+
     def send_report(self):
         if self.preprocessor is not None:
             self.report_items("Settings",

diff --git a/Orange/widgets/data/tests/test_owtransform.py b/Orange/widgets/data/tests/test_owtransform.py
@@ -76,6 +76,14 @@ def test_input_pca_preprocessor(self):
         self.assertIsInstance(output, Table)
         self.assertEqual(output.X.shape, (len(self.data), 2))
 
+        # test retain data functionality
+        self.widget.retain_all_data = True
+        self.widget.apply()
+        output = self.get_output(self.widget.Outputs.transformed_data)
+        self.assertIsInstance(output, Table)
+        self.assertEqual(output.X.shape, (len(self.data), 4))
+        self.assertEqual(output.metas.shape, (len(self.data), 2))
+
     def test_error_transforming(self):
         self.send_signal(self.widget.Inputs.data, self.data)
         self.send_signal(self.widget.Inputs.preprocessor, Preprocess())