Merge pull request #4259 from itslarin/fix-data-pandas_compat-table_t…

…o_frame

[FIX] table_to_frame: metas lost on conversion

Orange/data/pandas_compat.py

@@ -78,14 +78,17 @@ def _is_datetime(s):
                             np.column_stack(M) if M else None)
 
 
-def table_to_frame(tab):
+def table_to_frame(tab, include_metas=False):
     """
     Convert Orange.data.Table to pandas.DataFrame
 
     Parameters
     ----------
     tab : Table
 
+    include_metas : bool, (default=False)
+        Include table metas into dataframe.
+
     Returns
     -------
     pandas.DataFrame
@@ -122,6 +125,9 @@ def _columns_to_series(cols, vals):
     if domain.metas:
         metas = _columns_to_series(domain.metas, tab.metas)
     all_series = dict(x + y + metas)
-    original_column_order = [var.name for var in tab.domain.variables]
+    all_vars = tab.domain.variables
+    if include_metas:
+        all_vars += tab.domain.metas
+    original_column_order = [var.name for var in all_vars]
     unsorted_columns_df = pd.DataFrame(all_series)
     return unsorted_columns_df[original_column_order]

Orange/data/tests/test_pandas.py

@@ -1,3 +1,4 @@
+# pylint: disable=import-outside-toplevel
 import unittest
 import numpy as np
 from Orange.data import ContinuousVariable, DiscreteVariable, TimeVariable, Table
@@ -7,6 +8,7 @@
 except ImportError:
     pd = None
 
+
 @unittest.skipIf(pd is None, "Missing package 'pandas'")
 class TestPandasCompat(unittest.TestCase):
     def test_table_from_frame(self):
@@ -73,6 +75,20 @@ def test_table_to_frame(self):
         self.assertEqual(list(df['sepal length'])[0:4], [5.1, 4.9, 4.7, 4.6])
         self.assertEqual(list(df['iris'])[0:2], ['Iris-setosa', 'Iris-setosa'])
 
+    def test_table_to_frame_metas(self):
+        from Orange.data.pandas_compat import table_to_frame
+
+        table = Table("zoo")
+        domain = table.domain
+
+        df = table_to_frame(table)
+        cols = pd.Index([var.name for var in domain.variables])
+        pd.testing.assert_index_equal(df.columns, cols)
+
+        df = table_to_frame(table, include_metas=True)
+        cols = pd.Index([var.name for var in domain.variables + domain.metas])
+        pd.testing.assert_index_equal(df.columns, cols)
+
     @unittest.skip("Convert all Orange demo dataset. It takes about 5s which is way to slow")
     def test_table_to_frame_on_all_orange_dataset(self):
         from os import listdir
@@ -96,3 +112,7 @@ def _get_orange_demo_datasets():
             self.assertEqual(type(df), pd.DataFrame, assert_message)
             self.assertEqual(len(df), len(table), assert_message)
             self.assertEqual(len(df.columns), len(table.domain), assert_message)
+
+
+if __name__ == "__main__":
+    unittest.main()