Merge pull request #10507 from sinhrks/test_assert

TST: make assertion messages more understandable

Author: sinhrks

pandas/io/tests/test_json/test_pandas.py

@@ -178,7 +178,10 @@ def _check_orient(df, orient, dtype=None, numpy=False,
                 self.assertTrue(df.columns.equals(unser.columns))
             elif orient == "values":
                 # index and cols are not captured in this orientation
-                assert_almost_equal(df.values, unser.values)
+                if numpy is True and df.shape == (0, 0):
+                    assert unser.shape[0] == 0
+                else:
+                    assert_almost_equal(df.values, unser.values)
             elif orient == "split":
                 # index and col labels might not be strings
                 unser.index = [str(i) for i in unser.index]
@@ -670,15 +673,20 @@ def test_doc_example(self):
     def test_misc_example(self):
 
         # parsing unordered input fails
-        result = read_json('[{"a": 1, "b": 2}, {"b":2, "a" :1}]',numpy=True)
-        expected = DataFrame([[1,2],[1,2]],columns=['a','b'])
-        with tm.assertRaisesRegexp(AssertionError,
-                                   '\[index\] left \[.+\], right \[.+\]'):
+        result = read_json('[{"a": 1, "b": 2}, {"b":2, "a" :1}]', numpy=True)
+        expected = DataFrame([[1,2], [1,2]], columns=['a', 'b'])
+
+        error_msg = """DataFrame\\.index are different
+
+DataFrame\\.index values are different \\(100\\.0 %\\)
+\\[left\\]:  Index\\(\\[u?'a', u?'b'\\], dtype='object'\\)
+\\[right\\]: Int64Index\\(\\[0, 1\\], dtype='int64'\\)"""
+        with tm.assertRaisesRegexp(AssertionError, error_msg):
             assert_frame_equal(result, expected)
 
         result = read_json('[{"a": 1, "b": 2}, {"b":2, "a" :1}]')
-        expected = DataFrame([[1,2],[1,2]],columns=['a','b'])
-        assert_frame_equal(result,expected)
+        expected = DataFrame([[1,2], [1,2]], columns=['a','b'])
+        assert_frame_equal(result, expected)
 
     @network
     def test_round_trip_exception_(self):
@@ -739,3 +747,9 @@ def my_handler_raises(obj):
             raise TypeError("raisin")
         self.assertRaises(TypeError, DataFrame({'a': [1, 2, object()]}).to_json,
                           default_handler=my_handler_raises)
+
+
+if __name__ == '__main__':
+    import nose
+    nose.runmodule(argv=[__file__, '-vvs', '-x', '--pdb',
+                         '--pdb-failure', '-s'], exit=False)

pandas/src/testing.pyx

@@ -55,11 +55,39 @@ cpdef assert_dict_equal(a, b, bint compare_keys=True):
 
     return True
 
-cpdef assert_almost_equal(a, b, bint check_less_precise=False):
+cpdef assert_almost_equal(a, b, bint check_less_precise=False,
+                          obj=None, lobj=None, robj=None):
+    """Check that left and right objects are almost equal.
+
+    Parameters
+    ----------
+    a : object
+    b : object
+    check_less_precise : bool, default False
+        Specify comparison precision.
+        5 digits (False) or 3 digits (True) after decimal points are compared.
+    obj : str, default None
+        Specify object name being compared, internally used to show appropriate
+        assertion message
+    lobj : str, default None
+        Specify left object name being compared, internally used to show
+        appropriate assertion message
+    robj : str, default None
+        Specify right object name being compared, internally used to show
+        appropriate assertion message
+    """
+
     cdef:
         int decimal
+        double diff = 0.0
         Py_ssize_t i, na, nb
         double fa, fb
+        bint is_unequal = False
+
+    if lobj is None:
+        lobj = a
+    if robj is None:
+        robj = b
 
     if isinstance(a, dict) or isinstance(b, dict):
         return assert_dict_equal(a, b)
@@ -70,33 +98,62 @@ cpdef assert_almost_equal(a, b, bint check_less_precise=False):
         return True
 
     if isiterable(a):
-        assert isiterable(b), (
-            "First object is iterable, second isn't: %r != %r" % (a, b)
-        )
+
+        if not isiterable(b):
+            from pandas.util.testing import raise_assert_detail
+            if obj is None:
+                obj = 'Iterable'
+            msg = "First object is iterable, second isn't"
+            raise_assert_detail(obj, msg, a, b)
+
         assert has_length(a) and has_length(b), (
             "Can't compare objects without length, one or both is invalid: "
             "(%r, %r)" % (a, b)
         )
 
-        na, nb = len(a), len(b)
-        assert na == nb, (
-            "Length of two iterators not the same: %r != %r" % (na, nb)
-        )
         if isinstance(a, np.ndarray) and isinstance(b, np.ndarray):
+            if obj is None:
+                obj = 'numpy array'
+            na, nb = a.size, b.size
+            if a.shape != b.shape:
+                from pandas.util.testing import raise_assert_detail
+                raise_assert_detail(obj, '{0} shapes are different'.format(obj),
+                                    a.shape, b.shape)
             try:
                 if np.array_equal(a, b):
                     return True
             except:
                 pass
+        else:
+            if obj is None:
+                obj = 'Iterable'
+            na, nb = len(a), len(b)
+
+        if na != nb:
+            from pandas.util.testing import raise_assert_detail
+            raise_assert_detail(obj, '{0} length are different'.format(obj),
+                                na, nb)
+
+        for i in xrange(len(a)):
+            try:
+                assert_almost_equal(a[i], b[i], check_less_precise)
+            except AssertionError:
+                is_unequal = True
+                diff += 1
 
-        for i in xrange(na):
-            assert_almost_equal(a[i], b[i], check_less_precise)
+        if is_unequal:
+            from pandas.util.testing import raise_assert_detail
+            msg = '{0} values are different ({1} %)'.format(obj, np.round(diff * 100.0 / na, 5))
+            raise_assert_detail(obj, msg, lobj, robj)
 
         return True
+
     elif isiterable(b):
-        assert False, (
-            "Second object is iterable, first isn't: %r != %r" % (a, b)
-        )
+        from pandas.util.testing import raise_assert_detail
+        if obj is None:
+            obj = 'Iterable'
+        msg = "Second object is iterable, first isn't"
+        raise_assert_detail(obj, msg, a, b)
 
     if isnull(a):
         assert isnull(b), (

pandas/tests/test_index.py

@@ -3371,7 +3371,10 @@ def test_inplace_mutation_resets_values(self):
 
         # make sure label setting works too
         labels2 = [[0, 0, 0, 0, 0, 0], [0, 0, 0, 0, 0, 0]]
-        exp_values = np.array([(long(1), 'a')] * 6, dtype=object)
+        exp_values = np.empty((6, ), dtype=object)
+        exp_values[:] = [(long(1), 'a')] * 6
+        # must be 1d array of tuples
+        self.assertEqual(exp_values.shape, (6, ))
         new_values = mi2.set_labels(labels2).values
         # not inplace shouldn't change
         assert_almost_equal(mi2._tuples, vals2)
@@ -4772,8 +4775,20 @@ def test_repr_roundtrip(self):
 
         mi = MultiIndex.from_product([list('ab'),range(3)],names=['first','second'])
         str(mi)
-        tm.assert_index_equal(eval(repr(mi)),mi,exact=True)
-
+        
+        if compat.PY3:
+            tm.assert_index_equal(eval(repr(mi)), mi, exact=True)
+        else:
+            result = eval(repr(mi))
+            # string coerces to unicode
+            tm.assert_index_equal(result, mi, exact=False)
+            self.assertEqual(mi.get_level_values('first').inferred_type, 'string')
+            self.assertEqual(result.get_level_values('first').inferred_type, 'unicode')
+            
+        mi_u = MultiIndex.from_product([list(u'ab'),range(3)],names=['first','second'])
+        result = eval(repr(mi_u))
+        tm.assert_index_equal(result, mi_u, exact=True)            
+            
         # formatting
         if compat.PY3:
             str(mi)
@@ -4783,7 +4798,19 @@ def test_repr_roundtrip(self):
         # long format
         mi = MultiIndex.from_product([list('abcdefg'),range(10)],names=['first','second'])
         result = str(mi)
-        tm.assert_index_equal(eval(repr(mi)),mi,exact=True)
+
+        if compat.PY3:
+            tm.assert_index_equal(eval(repr(mi)), mi, exact=True)
+        else:
+            result = eval(repr(mi))
+            # string coerces to unicode
+            tm.assert_index_equal(result, mi, exact=False)
+            self.assertEqual(mi.get_level_values('first').inferred_type, 'string')
+            self.assertEqual(result.get_level_values('first').inferred_type, 'unicode')
+
+        mi = MultiIndex.from_product([list(u'abcdefg'),range(10)],names=['first','second'])
+        result = eval(repr(mi_u))
+        tm.assert_index_equal(result, mi_u, exact=True)     
 
     def test_str(self):
         # tested elsewhere