Don't overflow in DataFrame init with int

For integers smaller than what int64 can
handle, we gracefully default to the object
dtype instead of overflowing.

Author: gfyoung

doc/source/whatsnew/v0.22.0.txt

@@ -186,7 +186,7 @@ Conversion
 ^^^^^^^^^^
 
 - Bug in :class:`Index` constructor with `dtype='uint64'` where int-like floats were not coerced to :class:`UInt64Index` (:issue:`18400`)
-- Bug in the :class:`DataFrame` constructor in which data containing very large positive numbers was causing ``OverflowError`` (:issue:`18584`)
+- Bug in the :class:`DataFrame` constructor in which data containing very large positive or very large negative numbers was causing ``OverflowError`` (:issue:`18584`)
 -
 
 Indexing

pandas/_libs/src/inference.pyx

@@ -184,17 +184,18 @@ cdef class Seen(object):
         In addition to setting a flag that an integer was seen, we
         also set two flags depending on the type of integer seen:
 
-        1) sint_ : a negative (signed) number was encountered
-        2) uint_ : a positive number in the range of [2**63, 2**64)
-                   was encountered
+        1) sint_ : a negative (signed) number in the
+                   range of [-2**63, 0) was encountered
+        2) uint_ : a positive number in the range of
+                   [2**63, 2**64) was encountered
 
         Parameters
         ----------
         val : Python int
             Value with which to set the flags.
         """
         self.int_ = 1
-        self.sint_ = self.sint_ or (val < 0)
+        self.sint_ = self.sint_ or (oINT64_MIN <= val < 0)
         self.uint_ = self.uint_ or (oINT64_MAX < val <= oUINT64_MAX)
 
     @property
@@ -1270,7 +1271,8 @@ def maybe_convert_objects(ndarray[object] objects, bint try_float=0,
             if not seen.null_:
                 seen.saw_int(int(val))
 
-                if (seen.uint_ and seen.sint_) or val > oUINT64_MAX:
+                if ((seen.uint_ and seen.sint_) or
+                        val > oUINT64_MAX or val < oINT64_MIN):
                     seen.object_ = 1
                     break
 

pandas/tests/dtypes/test_inference.py

@@ -388,9 +388,10 @@ def test_convert_numeric_int64_uint64(self, case, coerce):
         result = lib.maybe_convert_numeric(case, set(), coerce_numeric=coerce)
         tm.assert_almost_equal(result, expected)
 
-    def test_convert_uint64_overflow(self):
+    @pytest.mark.parametrize("value", [-2**63 - 1, 2**64])
+    def test_convert_int_overflow(self, value):
         # see gh-18584
-        arr = np.array([2**64], dtype=object)
+        arr = np.array([value], dtype=object)
         result = lib.maybe_convert_objects(arr)
         tm.assert_numpy_array_equal(arr, result)
 

pandas/tests/frame/test_constructors.py

@@ -196,8 +196,10 @@ def test_constructor_overflow_int64(self):
         assert df_crawls['uid'].dtype == np.uint64
 
     @pytest.mark.parametrize("values", [np.array([2**64], dtype=object),
-                                        np.array([2**64]), [2**64]])
-    def test_constructor_overflow_uint64(self, values):
+                                        np.array([2**65]), [2**64 + 1],
+                                        np.array([-2**63 - 4], dtype=object),
+                                        np.array([-2**64 - 1]), [-2**65 - 2]])
+    def test_constructor_int_overflow(self, values):
         # see gh-18584
         value = values[0]
         result = DataFrame(values)