add comments and tests

Author: reidy-p

doc/source/whatsnew/v0.22.0.txt

@@ -80,6 +80,7 @@ Other API Changes
 - :class:`IntervalIndex` constructor will raise if the ``closed`` parameter conflicts with how the input data is inferred to be closed (:issue:`18421`)
 - Inserting missing values into indexes will work for all types of indexes and automatically insert the correct type of missing value (``NaN``, ``NaT``, etc.) regardless of the type passed in (:issue:`18295`)
 - Restricted ``DateOffset`` keyword arguments. Previously, ``DateOffset`` subclasses allowed arbitrary keyword arguments which could lead to unexpected behavior. Now, only valid arguments will be accepted. (:issue:`17176`, :issue:`18226`).
+- :func:`DataFrame.from_items` provides a more informative error message when passed scalar values (:issue:`17312`)
 
 .. _whatsnew_0220.deprecations:
 

pandas/core/frame.py

@@ -1272,30 +1272,33 @@ def from_items(cls, items, columns=None, orient='columns'):
                 columns = _ensure_index(keys)
                 arrays = values
 
+            # GH 17312
+            # Provide more informative error msg when scalar values passed
             try:
                 return cls._from_arrays(arrays, columns, None)
 
             except ValueError:
                 if not is_nested_list_like(values):
                     raise TypeError('The value in each (key, value) pair must '
-                                    'be an array or a Series')
+                                    'be an array, Series, or dict')
 
         elif orient == 'index':
             if columns is None:
                 raise TypeError("Must pass columns with orient='index'")
 
-            try:
-                keys = _ensure_index(keys)
+            keys = _ensure_index(keys)
 
+            # GH 17312
+            # Provide more informative error msg when scalar values passed
+            try:
                 arr = np.array(values, dtype=object).T
                 data = [lib.maybe_convert_objects(v) for v in arr]
-
                 return cls._from_arrays(data, columns, keys)
 
             except TypeError:
                 if not is_nested_list_like(values):
                     raise TypeError('The value in each (key, value) pair must '
-                                    'be an array or a Series')
+                                    'be an array, Series, or dict')
 
         else:  # pragma: no cover
             raise ValueError("'orient' must be either 'columns' or 'index'")

pandas/tests/frame/test_constructors.py

@@ -268,13 +268,14 @@ def test_constructor_dict(self):
 
         # GH10856
         # dict with scalar values should raise error, even if columns passed
-        with pytest.raises(ValueError):
+        msg = 'If using all scalar values, you must pass an index'
+        with tm.assert_raises_regex(ValueError, msg):
             DataFrame({'a': 0.7})
 
-        with pytest.raises(ValueError):
+        with tm.assert_raises_regex(ValueError, msg):
             DataFrame({'a': 0.7}, columns=['a'])
 
-        with pytest.raises(ValueError):
+        with tm.assert_raises_regex(ValueError, msg):
             DataFrame({'a': 0.7}, columns=['b'])
 
     def test_constructor_multi_index(self):
@@ -1204,15 +1205,16 @@ def test_constructor_from_items(self):
                        columns=['one', 'two', 'three'])
         tm.assert_frame_equal(rs, xp)
 
+    def test_constructor_from_items_scalars(self):
         # GH 17312
         with tm.assert_raises_regex(TypeError,
                                     'The value in each \(key, value\) '
-                                    'pair must be an array or a Series'):
+                                    'pair must be an array, Series, or dict'):
             DataFrame.from_items([('A', 1), ('B', 4)])
 
         with tm.assert_raises_regex(TypeError,
                                     'The value in each \(key, value\) '
-                                    'pair must be an array or a Series'):
+                                    'pair must be an array, Series, or dict'):
             DataFrame.from_items([('A', 1), ('B', 2)], columns=['col1'],
                                  orient='index')