[FIX] Speed-up slow table_to_frame

Author: PrimozGodec

Orange/data/pandas_compat.py

@@ -368,8 +368,7 @@ def _column_to_series(col, vals):
         elif col.is_continuous:
             dt = float
             # np.nan are not compatible with int column
-            nan_values_in_column = [t for t in vals if np.isnan(t)]
-            if col.number_of_decimals == 0 and len(nan_values_in_column) == 0:
+            if col.number_of_decimals == 0 and not np.any(np.isnan(vals)):
                 dt = int
             result = (col.name, pd.Series(vals).astype(dt))
         elif col.is_string:

Orange/data/tests/test_pandas.py

@@ -7,7 +7,7 @@
 
 from Orange.data import ContinuousVariable, DiscreteVariable, TimeVariable, Table, Domain, \
     StringVariable
-from Orange.data.pandas_compat import OrangeDataFrame
+from Orange.data.pandas_compat import OrangeDataFrame, table_to_frame
 
 try:
     import pandas as pd
@@ -70,7 +70,6 @@ def test_table_from_frame(self):
         self.assertEqual(types, [DiscreteVariable, ContinuousVariable, TimeVariable])
 
     def test_table_to_frame(self):
-        from Orange.data.pandas_compat import table_to_frame
         table = Table("iris")
         df = table_to_frame(table)
         table_column_names = [var.name for var in table.domain.variables]
@@ -81,6 +80,24 @@ 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_nans(self):
+        domain = Domain(
+            [ContinuousVariable("a", number_of_decimals=0), ContinuousVariable("b")]
+        )
+        table = Table(
+            domain, np.column_stack((np.ones(10), np.hstack((np.ones(9), [np.nan]))))
+        )
+
+        df = table_to_frame(table)
+        table_column_names = [var.name for var in table.domain.variables]
+        frame_column_names = df.columns
+
+        self.assertEqual(sorted(table_column_names), sorted(frame_column_names))
+        self.assertEqual(df["a"].dtype, int)
+        self.assertEqual(df["b"].dtype, float)
+        self.assertEqual([1, 1, 1], list(df["a"].iloc[-3:]))
+        self.assertTrue(np.isnan(df["b"].iloc[-1]))
+
     def test_table_to_frame_metas(self):
         from Orange.data.pandas_compat import table_to_frame