Merge pull request #8443 from unutbu/dtypeO-equals

BUG: NDFrame.equals gives false negatives with dtype=object (GH8437)

Author: jreback

doc/source/v0.15.0.txt

@@ -1006,3 +1006,4 @@ Bug Fixes
 - Bug in ``DataFrame.dropna`` that interpreted non-existent columns in the subset argument as the 'last column' (:issue:`8303`)
 - Bug in Index.intersection on non-monotonic non-unique indexes (:issue:`8362`).
 - Bug in masked series assignment where mismatching types would break alignment (:issue:`8387`)
+- Bug in NDFrame.equals gives false negatives with dtype=object (:issue:`8437`)

pandas/core/internals.py

@@ -13,7 +13,7 @@
                                 ABCSparseSeries, _infer_dtype_from_scalar,
                                 _is_null_datelike_scalar,
                                 is_timedelta64_dtype, is_datetime64_dtype,
-                                _possibly_infer_to_datetimelike)
+                                _possibly_infer_to_datetimelike, array_equivalent)
 from pandas.core.index import Index, MultiIndex, _ensure_index
 from pandas.core.indexing import (_maybe_convert_indices, _length_of_indexer)
 from pandas.core.categorical import Categorical, _maybe_to_categorical, _is_categorical
@@ -1057,7 +1057,7 @@ def func(c, v, o):
 
     def equals(self, other):
         if self.dtype != other.dtype or self.shape != other.shape: return False
-        return np.array_equal(self.values, other.values)
+        return array_equivalent(self.values, other.values)
 
 
 class NonConsolidatableMixIn(object):

pandas/tests/test_generic.py

@@ -1304,6 +1304,21 @@ def test_equals(self):
         df2 = df1.set_index(['floats'], append=True)
         self.assertTrue(df3.equals(df2))
 
+        # GH 8437
+        a = pd.Series([False, np.nan])
+        b = pd.Series([False, np.nan])
+        c = pd.Series(index=range(2))
+        d = pd.Series(index=range(2))
+        e = pd.Series(index=range(2))
+        f = pd.Series(index=range(2))
+        c[:-1] = d[:-1] = e[0] = f[0] = False
+        self.assertTrue(a.equals(a))
+        self.assertTrue(a.equals(b))
+        self.assertTrue(a.equals(c))
+        self.assertTrue(a.equals(d))
+        self.assertFalse(a.equals(e))
+        self.assertTrue(e.equals(f)) 
+        
     def test_describe_raises(self):
         with tm.assertRaises(NotImplementedError):
             tm.makePanel().describe()