DOC: Improved documentation for DataFrame.join

closes #12188

Author: Eduardo Blancas Reyes <[email protected]>

Closes #12193 from edublancas/master and squashes the following commits:

a66f2ea [Eduardo Blancas Reyes] DOC: improves DataFrame.join documentation
8266cdc [Eduardo Blancas Reyes] DOC: improves DataFrame.join documentation

Author: edublancas

doc/source/merging.rst

@@ -562,10 +562,8 @@ DataFrame instance method, with the calling DataFrame being implicitly
 considered the left object in the join.
 
 The related ``DataFrame.join`` method, uses ``merge`` internally for the
-index-on-index and index-on-column(s) joins, but *joins on indexes* by default
-rather than trying to join on common columns (the default behavior for
-``merge``). If you are joining on index, you may wish to use ``DataFrame.join``
-to save yourself some typing.
+index-on-index (by default) and column(s)-on-index join. If you are joining on
+index only, you may wish to use ``DataFrame.join`` to save yourself some typing.
 
 Brief primer on merge methods (relational algebra)
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

pandas/core/frame.py

@@ -4351,18 +4351,20 @@ def join(self, other, on=None, how='left', lsuffix='', rsuffix='',
             Series is passed, its name attribute must be set, and that will be
             used as the column name in the resulting joined DataFrame
         on : column name, tuple/list of column names, or array-like
-            Column(s) to use for joining, otherwise join on index. If multiples
+            Column(s) in the caller to join on the index in other,
+            otherwise joins index-on-index. If multiples
             columns given, the passed DataFrame must have a MultiIndex. Can
             pass an array as the join key if not already contained in the
             calling DataFrame. Like an Excel VLOOKUP operation
-        how : {'left', 'right', 'outer', 'inner'}
-            How to handle indexes of the two objects. Default: 'left'
-            for joining on index, None otherwise
-
-            * left: use calling frame's index
-            * right: use input frame's index
-            * outer: form union of indexes
-            * inner: use intersection of indexes
+        how : {'left', 'right', 'outer', 'inner'}, default: 'left'
+            How to handle the operation of the two objects.
+
+            * left: use calling frame's index (or column if on is specified)
+            * right: use other frame's index
+            * outer: form union of calling frame's index (or column if on is
+                specified) with other frame's index
+            * inner: form intersection of calling frame's index (or column if
+                on is specified) with other frame's index
         lsuffix : string
             Suffix to use from left frame's overlapping columns
         rsuffix : string
@@ -4376,6 +4378,77 @@ def join(self, other, on=None, how='left', lsuffix='', rsuffix='',
         on, lsuffix, and rsuffix options are not supported when passing a list
         of DataFrame objects
 
+        Examples
+        --------
+        >>> caller = pd.DataFrame({'key': ['K0', 'K1', 'K2', 'K3', 'K4', 'K5'],
+        ...                        'A': ['A0', 'A1', 'A2', 'A3', 'A4', 'A5']})
+
+        >>> caller
+            A key
+        0  A0  K0
+        1  A1  K1
+        2  A2  K2
+        3  A3  K3
+        4  A4  K4
+        5  A5  K5
+
+        >>> other = pd.DataFrame({'key': ['K0', 'K1', 'K2'],
+        ...                       'B': ['B0', 'B1', 'B2']})
+
+        >>> other
+            B key
+        0  B0  K0
+        1  B1  K1
+        2  B2  K2
+
+        Join DataFrames using their indexes.
+
+        >>> caller.join(other, lsuffix='_caller', rsuffix='_other')
+
+        >>>     A key_caller    B key_other
+            0  A0         K0   B0        K0
+            1  A1         K1   B1        K1
+            2  A2         K2   B2        K2
+            3  A3         K3  NaN       NaN
+            4  A4         K4  NaN       NaN
+            5  A5         K5  NaN       NaN
+
+
+        If we want to join using the key columns, we need to set key to be
+        the index in both caller and other. The joined DataFrame will have
+        key as its index.
+
+        >>> caller.set_index('key').join(other.set_index('key'))
+
+        >>>      A    B
+            key
+            K0   A0   B0
+            K1   A1   B1
+            K2   A2   B2
+            K3   A3  NaN
+            K4   A4  NaN
+            K5   A5  NaN
+
+        Another option to join using the key columns is to use the on
+        parameter. DataFrame.join always uses other's index but we can use any
+        column in the caller. This method preserves the original caller's
+        index in the result.
+
+        >>> caller.join(other.set_index('key'), on='key')
+
+        >>>     A key    B
+            0  A0  K0   B0
+            1  A1  K1   B1
+            2  A2  K2   B2
+            3  A3  K3  NaN
+            4  A4  K4  NaN
+            5  A5  K5  NaN
+
+
+        See also
+        --------
+        DataFrame.merge : For column(s)-on-columns(s) operations
+
         Returns
         -------
         joined : DataFrame