revisions for comments, remove from merge_asof

Nick Eubank · Nick Eubank · commit d7de5fa782bb · 2017-05-10T22:33:42.000-07:00
diff --git a/doc/source/merging.rst b/doc/source/merging.rst
@@ -552,14 +552,17 @@ standard database join operations between DataFrame objects:
 
   .. versionadded:: 0.17.0
 
-- ``validate`` : {None, '1:1', '1:m', 'm:1', 'm:m', "one_to_one", "one_to_many", "many_to_one", "many_to_many"}, default None
+- ``validate`` : String, default None
   If specified, checks if merge is of specified type.
-  * "one_to_one" or "1:1": check if merge keys are unique in both
-  left and right dataset.
-  * "one_to_many" or "1:m": check if merge keys are unique in left
-  dataset.
-  * "many_to_one" or "m:1": check if merge keys are unique in right
-  dataset.
+
+  * "one_to_one" or "1:1": checks if merge keys are unique in both
+    left and right datasets.
+  * "one_to_many" or "1:m": checks if merge keys are unique in left
+    dataset.
+  * "many_to_one" or "m:1": checks if merge keys are unique in right
+    dataset.
+  * "many_to_may" or "m:m": allowed, but does not result in checks. 
+
 
   .. versionadded:: 0.21.0
 
@@ -740,22 +743,45 @@ Users can use the ``validate`` argument to automatically check whether there are
 
 In the following example, there are duplicate values of ``B`` in the right DataFrame. As this is not a one-to-one merge -- as specified in the ``validate`` argument -- an exception will be raised.
 
-.. code-block:: python
+
+.. ipython:: python
 
   left = pd.DataFrame({'A' : [1,2], 'B' : [1, 2]})
   right = pd.DataFrame({'A' : [4,5,6], 'B': [2, 2, 2]})
-  result = pd.merge(left, right, on='B', how='outer', validate="one_to_one");
-  
-  ValueError: Merge keys are not unique in either left or right dataset; not a one-to-one merge
-
 
-If the user is aware of the duplicates in the right `DataFrame` but wants to ensure there are no duplicates in the left DataFrame, one can use the `one_to_many` argument instead, which will not raise an exception. 
+.. code-block:: python
 
-.. ipython:: python
-   :suppress:
+  result = pd.merge(left, right, on='B', how='outer', validate="one_to_one")  
+  
+  ---------------------------------------------------------------------------
+  ValueError                                Traceback (most recent call last)
+  <ipython-input-3-29316387da90> in <module>()
+  ----> 1 result = pd.merge(left, right, on='B', how='outer', validate="one_to_one")
+  
+  /Users/Nick/github/pandas/pandas/core/reshape/merge.py in merge(left, right, how, on, left_on, right_on,   left_index, right_index, sort, suffixes, copy, indicator, validate)
+       53                          right_index=right_index, sort=sort, suffixes=suffixes,
+       54                          copy=copy, indicator=indicator,
+  ---> 55                          validate=validate)
+       56     return op.get_result()
+       57 
+  
+  /Users/Nick/github/pandas/pandas/core/reshape/merge.py in __init__(self, left, right, how, on, left_on,   right_on, axis, left_index, right_index, sort, suffixes, copy, indicator, validate)
+      570         # are in fact unique.
+      571         if validate is not None:
+  --> 572             self._validate(validate)
+      573 
+      574     def get_result(self):
+  
+  /Users/Nick/github/pandas/pandas/core/reshape/merge.py in _validate(self, validate)
+      987                                  " not a one-to-one merge")
+      988             elif not right_unique:
+  --> 989                 raise ValueError("Merge keys are not unique in right dataset;"
+      990                                  " not a one-to-one merge")
+      991 
+  
+  ValueError: Merge keys are not unique in right dataset; not a one-to-one merge    
 
-   left = pd.DataFrame({'A' : [1,2], 'B' : [1, 2]})
-   right = pd.DataFrame({'A' : [4,5,6], 'B': [2, 2, 2]})
+If the user is aware of the duplicates in the right `DataFrame` but wants to ensure there are no duplicates in the left DataFrame, one can use the `one_to_many` argument instead, which will not raise an exception. 
 
 .. ipython:: python
 
diff --git a/pandas/core/frame.py b/pandas/core/frame.py
@@ -174,15 +174,16 @@
 
     .. versionadded:: 0.17.0
 
-validate : {None, '1:1', '1:m', 'm:1', 'm:m', "one_to_one", "one_to_many",
-            "many_to_one", "many_to_many"}, default None
+validate : String, default None
     If specified, checks if merge is of specified type.
+
     * "one_to_one" or "1:1": check if merge keys are unique in both
-    left and right dataset.
+      left and right datasets.
     * "one_to_many" or "1:m": check if merge keys are unique in left
-    dataset.
+      dataset.
     * "many_to_one" or "m:1": check if merge keys are unique in right
-    dataset.
+      dataset.
+    * "many_to_may" or "m:m": allowed, but does not result in checks.
 
     .. versionadded:: 0.21.0
 
diff --git a/pandas/core/reshape/merge.py b/pandas/core/reshape/merge.py
@@ -265,8 +265,7 @@ def merge_asof(left, right, on=None,
                suffixes=('_x', '_y'),
                tolerance=None,
                allow_exact_matches=True,
-               direction='backward',
-               validate=None):
+               direction='backward'):
     """Perform an asof merge. This is similar to a left-join except that we
     match on nearest key rather than equal keys.
 
@@ -344,18 +343,6 @@ def merge_asof(left, right, on=None,
 
         .. versionadded:: 0.20.0
 
-    validate : {None, '1:1', '1:m', 'm:1', 'm:m', "one_to_one", "one_to_many",
-                "many_to_one", "many_to_many"}, default None
-        If specified, checks if merge is of specified type.
-        * "one_to_one" or "1:1": check if merge keys are unique in both
-        left and right dataset.
-        * "one_to_many" or "1:m": check if merge keys are unique in left
-        dataset.
-        * "many_to_one" or "m:1": check if merge keys are unique in right
-        dataset.
-
-    .. versionadded:: 0.21.0
-
 
     Returns
     -------
@@ -498,7 +485,7 @@ def merge_asof(left, right, on=None,
                     suffixes=suffixes,
                     how='asof', tolerance=tolerance,
                     allow_exact_matches=allow_exact_matches,
-                    direction=direction, validate=validate)
+                    direction=direction)
     return op.get_result()
 
 
@@ -979,47 +966,45 @@ def _validate(self, validate):
 
         # Check uniqueness of each
         if self.left_index:
-            left_unique = not (self.orig_left.index.duplicated()).any()
+            left_unique = not self.orig_left.index.is_unique
         else:
             left_unique = MultiIndex.from_arrays(self.left_join_keys
                                                  ).is_unique
 
         if self.right_index:
-            right_unique = not (self.orig_right.index.duplicated()).any()
+            right_unique = not self.orig_right.index.is_unique
         else:
             right_unique = MultiIndex.from_arrays(self.right_join_keys
                                                   ).is_unique
 
-        # Check valid arg
-        if validate not in ['one_to_one', '1:1',
-                            'one_to_many', '1:m',
-                            'many_to_one', 'm:1',
-                            'many_to_many', 'm:m']:
-
-            raise ValueError("Not a valid argument for validate")
-
         # Check data integrity
         if validate in ["one_to_one", "1:1"]:
-            if not left_unique or not right_unique:
+            if not left_unique and not right_unique:
                 raise ValueError("Merge keys are not unique in either left"
                                  " or right dataset; not a one-to-one merge")
-            if not left_unique:
+            elif not left_unique:
                 raise ValueError("Merge keys are not unique in left dataset;"
                                  " not a one-to-one merge")
-            if not right_unique:
+            elif not right_unique:
                 raise ValueError("Merge keys are not unique in right dataset;"
                                  " not a one-to-one merge")
 
-        if validate in ["one_to_many", "1:m"]:
+        elif validate in ["one_to_many", "1:m"]:
             if not left_unique:
                 raise ValueError("Merge keys are not unique in left dataset;"
                                  "not a one-to-many merge")
 
-        if validate in ["many_to_one", "m:1"]:
+        elif validate in ["many_to_one", "m:1"]:
             if not right_unique:
                 raise ValueError("Merge keys are not unique in right dataset;"
                                  " not a many-to-one merge")
 
+        elif validate in ['many_to_many', 'm:m']:
+            pass
+
+        else:
+            raise ValueError("Not a valid argument for validate")
+
 
 def _get_join_indexers(left_keys, right_keys, sort=False, how='inner',
                        **kwargs):
@@ -1072,17 +1057,15 @@ class _OrderedMerge(_MergeOperation):
     def __init__(self, left, right, on=None, left_on=None, right_on=None,
                  left_index=False, right_index=False, axis=1,
                  suffixes=('_x', '_y'), copy=True,
-                 fill_method=None, how='outer',
-                 validate=None):
+                 fill_method=None, how='outer'):
 
         self.fill_method = fill_method
         _MergeOperation.__init__(self, left, right, on=on, left_on=left_on,
                                  left_index=left_index,
                                  right_index=right_index,
                                  right_on=right_on, axis=axis,
                                  how=how, suffixes=suffixes,
-                                 sort=True,  # factorize sorts
-                                 validate=validate
+                                 sort=True  # factorize sorts
                                  )
 
     def get_result(self):
@@ -1179,7 +1162,7 @@ def __init__(self, left, right, on=None, left_on=None, right_on=None,
                  fill_method=None,
                  how='asof', tolerance=None,
                  allow_exact_matches=True,
-                 direction='backward', validate=None):
+                 direction='backward'):
 
         self.by = by
         self.left_by = left_by
@@ -1192,8 +1175,7 @@ def __init__(self, left, right, on=None, left_on=None, right_on=None,
                                right_on=right_on, left_index=left_index,
                                right_index=right_index, axis=axis,
                                how=how, suffixes=suffixes,
-                               fill_method=fill_method,
-                               validate=validate)
+                               fill_method=fill_method)
 
     def _validate_specification(self):
         super(_AsOfMerge, self)._validate_specification()
diff --git a/pandas/tests/reshape/test_merge_asof.py b/pandas/tests/reshape/test_merge_asof.py
@@ -973,29 +973,3 @@ def test_on_float_by_int(self):
             columns=['symbol', 'exch', 'price', 'mpv'])
 
         assert_frame_equal(result, expected)
-
-    def test_validate(self):
-
-        left = pd.DataFrame({'a': [1, 5, 10],
-                             'left_val': ['a', 'b', 'c']})
-        right = pd.DataFrame({'a': [1, 2, 3, 6, 7],
-                              'right_val': [1, 2, 3, 6, 7]})
-        # Simple run 1:1
-        pd.merge_asof(left, right, on='a', validate="1:1")
-
-        # Dups on right
-        right_w_dups = right.append(pd.DataFrame({'a': [7],
-                                                  'right_val': [-2]}))
-        right_w_dups = right_w_dups.sort_values('a')
-
-        pd.merge_asof(left, right_w_dups, on='a', validate="1:m")
-        with pytest.raises(ValueError):
-            pd.merge_asof(left, right_w_dups, on='a', validate="1:1")
-
-        # Dups on left
-        left_w_dups = left.append(pd.DataFrame({'a': [1],
-                                                'left_val': [-2]}))
-        left_w_dups = left_w_dups.sort_values('a')
-        pd.merge_asof(left_w_dups, right, on='a', validate="m:1")
-        with pytest.raises(ValueError):
-            pd.merge_asof(left_w_dups, right_w_dups, on='a', validate="1:1")
