Fix Series.div when divide by zero

databricks/koalas/base.py

@@ -184,8 +184,14 @@ def __sub__(self, other):
             return _column_op(spark.Column.__sub__)(self, other)
 
     __mul__ = _column_op(spark.Column.__mul__)
-    __div__ = _numpy_column_op(spark.Column.__div__)
-    __truediv__ = _numpy_column_op(spark.Column.__truediv__)
+
+    def __truediv__(self, other):
+        def truediv(left, right):
+            return F.when(F.lit(right == 0), F.lit(np.inf).__div__(left)).otherwise(
+                left.__truediv__(right)
+            )
+
+        return _numpy_column_op(truediv)(self, other)
 
     def __mod__(self, other):
         def mod(left, right):
@@ -202,18 +208,30 @@ def __radd__(self, other):
 
     __rsub__ = _column_op(spark.Column.__rsub__)
     __rmul__ = _column_op(spark.Column.__rmul__)
-    __rdiv__ = _numpy_column_op(spark.Column.__rdiv__)
-    __rtruediv__ = _numpy_column_op(spark.Column.__rtruediv__)
+
+    def __rtruediv__(self, other):
+        def rtruediv(left, right):
+            return F.when(left == 0, F.lit(np.inf).__div__(right)).otherwise(
+                F.lit(right).__truediv__(left)
+            )
+
+        return _numpy_column_op(rtruediv)(self, other)
 
     def __floordiv__(self, other):
-        return self._with_new_scol(
-            F.floor(_numpy_column_op(spark.Column.__div__)(self, other)._scol)
-        )
+        def floordiv(left, right):
+            return F.when(F.lit(right == 0), F.lit(np.inf).__div__(left)).otherwise(
+                F.floor(left.__div__(right))
+            )
+
+        return _numpy_column_op(floordiv)(self, other)
 
     def __rfloordiv__(self, other):
-        return self._with_new_scol(
-            F.floor(_numpy_column_op(spark.Column.__rdiv__)(self, other)._scol)
-        )
+        def rfloordiv(left, right):
+            return F.when(F.lit(left == 0), F.lit(np.inf).__div__(right)).otherwise(
+                F.floor(F.lit(right).__div__(left))
+            )
+
+        return _numpy_column_op(rfloordiv)(self, other)
 
     def __rmod__(self, other):
         def rmod(left, right):

databricks/koalas/frame.py

@@ -165,7 +165,7 @@
 
 >>> df.rdiv(10)
              angles   degrees
-circle          NaN  0.027778
+circle          inf  0.027778
 triangle   3.333333  0.055556
 rectangle  2.500000  0.027778
 
@@ -177,7 +177,7 @@
 
 >>> df.rtruediv(10)
              angles   degrees
-circle          NaN  0.027778
+circle          inf  0.027778
 triangle   3.333333  0.055556
 rectangle  2.500000  0.027778
 
@@ -225,21 +225,21 @@
 
 >>> df // 10
            angles  degrees
-circle          0       36
-triangle        0       18
-rectangle       0       36
+circle        0.0     36.0
+triangle      0.0     18.0
+rectangle     0.0     36.0
 
 >>> df.floordiv(10)
            angles  degrees
-circle          0       36
-triangle        0       18
-rectangle       0       36
+circle        0.0     36.0
+triangle      0.0     18.0
+rectangle     0.0     36.0
 
->>> df.rfloordiv(10)
+>>> df.rfloordiv(10)  # doctest: +SKIP
            angles  degrees
-circle        NaN        0
-triangle      3.0        0
-rectangle     2.0        0
+circle        inf      0.0
+triangle      3.0      0.0
+rectangle     2.0      0.0
 
 Mod by constant with reverse version.
 

databricks/koalas/indexes.py

@@ -891,7 +891,7 @@ def unique(self, level=None):
 
         Returns
         -------
-        Index without deuplicates
+        Index without duplicates
 
         See Also
         --------

databricks/koalas/tests/test_dataframe.py

@@ -3205,6 +3205,27 @@ def test_squeeze(self):
         for axis in axises:
             self.assert_eq(pdf.squeeze(axis), kdf.squeeze(axis))
 
+    def test_rfloordiv(self):
+        pdf = pd.DataFrame(
+            {"angles": [0, 3, 4], "degrees": [360, 180, 360]},
+            index=["circle", "triangle", "rectangle"],
+            columns=["angles", "degrees"],
+        )
+        kdf = ks.from_pandas(pdf)
+
+        if LooseVersion(pd.__version__) < LooseVersion("1.0.0") and LooseVersion(
+            pd.__version__
+        ) >= LooseVersion("0.24.0"):
+            expected_result = ks.DataFrame(
+                {"angles": [np.inf, 3.0, 2.0], "degrees": [0.0, 0.0, 0.0]},
+                index=["circle", "triangle", "rectangle"],
+                columns=["angles", "degrees"],
+            )
+        else:
+            expected_result = pdf.rfloordiv(10)
+
+        self.assert_eq(kdf.rfloordiv(10), expected_result)
+
     def test_truncate(self):
         pdf1 = pd.DataFrame(
             {

databricks/koalas/tests/test_series.py

@@ -1446,3 +1446,20 @@ def test_squeeze(self):
         kser = ks.Series([90, 91, 85], index=midx)
         pser = kser.to_pandas()
         self.assert_eq(kser.squeeze(), pser.squeeze())
+
+    def test_div_zero(self):
+        pser = pd.Series([100, None, -300, None, 500, -700], name="Koalas")
+        kser = ks.from_pandas(pser)
+
+        self.assert_eq(repr(pser.div(0)), repr(kser.div(0)))
+        self.assert_eq(repr(pser.truediv(0)), repr(kser.truediv(0)))
+        self.assert_eq(repr(pser / 0), repr(kser / 0))
+
+        # floordiv has different behavior in pandas > 1.0.0
+        if LooseVersion(pd.__version__) >= LooseVersion("1.0.0"):
+            self.assert_eq(repr(pser.floordiv(0)), repr(kser.floordiv(0)))
+            self.assert_eq(repr(pser // 0), repr(kser // 0))
+        else:
+            result = ks.Series([np.inf, np.nan, -np.inf, np.nan, np.inf, -np.inf], name="Koalas")
+            self.assert_eq(repr(kser.floordiv(0)), repr(result))
+            self.assert_eq(repr(kser // 0), repr(result))