DOC: fix PR07 for pandas.merge (pandas-dev#58979)

tuhinsharma121 · web-flow · commit 42f785f8c1a3 · 2024-06-11T08:58:46.000-07:00
diff --git a/ci/code_checks.sh b/ci/code_checks.sh
@@ -464,7 +464,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.io.stata.StataReader.variable_labels RT03,SA01" \
         -i "pandas.io.stata.StataWriter.write_file SA01" \
         -i "pandas.json_normalize RT03,SA01" \
-        -i "pandas.merge PR07" \
         -i "pandas.merge_asof PR07,RT03" \
         -i "pandas.period_range RT03,SA01" \
         -i "pandas.plotting.andrews_curves RT03,SA01" \
diff --git a/pandas/core/reshape/merge.py b/pandas/core/reshape/merge.py
@@ -39,11 +39,7 @@
     npt,
 )
 from pandas.errors import MergeError
-from pandas.util._decorators import (
-    Appender,
-    Substitution,
-    cache_readonly,
-)
+from pandas.util._decorators import cache_readonly
 from pandas.util._exceptions import find_stack_level
 
 from pandas.core.dtypes.base import ExtensionDtype
@@ -95,7 +91,6 @@
     ensure_wrapped_if_datetimelike,
     extract_array,
 )
-from pandas.core.frame import _merge_doc
 from pandas.core.indexes.api import default_index
 from pandas.core.sorting import (
     get_group_index,
@@ -133,8 +128,6 @@
 _known = (np.ndarray, ExtensionArray, Index, ABCSeries)
 
 
-@Substitution("\nleft : DataFrame or named Series")
-@Appender(_merge_doc, indents=0)
 def merge(
     left: DataFrame | Series,
     right: DataFrame | Series,
@@ -150,6 +143,210 @@ def merge(
     indicator: str | bool = False,
     validate: str | None = None,
 ) -> DataFrame:
+    """
+    Merge DataFrame or named Series objects with a database-style join.
+
+    A named Series object is treated as a DataFrame with a single named column.
+
+    The join is done on columns or indexes. If joining columns on
+    columns, the DataFrame indexes *will be ignored*. Otherwise if joining indexes
+    on indexes or indexes on a column or columns, the index will be passed on.
+    When performing a cross merge, no column specifications to merge on are
+    allowed.
+
+    .. warning::
+
+        If both key columns contain rows where the key is a null value, those
+        rows will be matched against each other. This is different from usual SQL
+        join behaviour and can lead to unexpected results.
+
+    Parameters
+    ----------
+    left : DataFrame or named Series
+        First pandas object to merge.
+    right : DataFrame or named Series
+        Second pandas object to merge.
+    how : {'left', 'right', 'outer', 'inner', 'cross'}, default 'inner'
+        Type of merge to be performed.
+
+        * left: use only keys from left frame, similar to a SQL left outer join;
+          preserve key order.
+        * right: use only keys from right frame, similar to a SQL right outer join;
+          preserve key order.
+        * outer: use union of keys from both frames, similar to a SQL full outer
+          join; sort keys lexicographically.
+        * inner: use intersection of keys from both frames, similar to a SQL inner
+          join; preserve the order of the left keys.
+        * cross: creates the cartesian product from both frames, preserves the order
+          of the left keys.
+    on : label or list
+        Column or index level names to join on. These must be found in both
+        DataFrames. If `on` is None and not merging on indexes then this defaults
+        to the intersection of the columns in both DataFrames.
+    left_on : label or list, or array-like
+        Column or index level names to join on in the left DataFrame. Can also
+        be an array or list of arrays of the length of the left DataFrame.
+        These arrays are treated as if they are columns.
+    right_on : label or list, or array-like
+        Column or index level names to join on in the right DataFrame. Can also
+        be an array or list of arrays of the length of the right DataFrame.
+        These arrays are treated as if they are columns.
+    left_index : bool, default False
+        Use the index from the left DataFrame as the join key(s). If it is a
+        MultiIndex, the number of keys in the other DataFrame (either the index
+        or a number of columns) must match the number of levels.
+    right_index : bool, default False
+        Use the index from the right DataFrame as the join key. Same caveats as
+        left_index.
+    sort : bool, default False
+        Sort the join keys lexicographically in the result DataFrame. If False,
+        the order of the join keys depends on the join type (how keyword).
+    suffixes : list-like, default is ("_x", "_y")
+        A length-2 sequence where each element is optionally a string
+        indicating the suffix to add to overlapping column names in
+        `left` and `right` respectively. Pass a value of `None` instead
+        of a string to indicate that the column name from `left` or
+        `right` should be left as-is, with no suffix. At least one of the
+        values must not be None.
+    copy : bool, default False
+        If False, avoid copy if possible.
+
+        .. note::
+            The `copy` keyword will change behavior in pandas 3.0.
+            `Copy-on-Write
+            <https://pandas.pydata.org/docs/dev/user_guide/copy_on_write.html>`__
+            will be enabled by default, which means that all methods with a
+            `copy` keyword will use a lazy copy mechanism to defer the copy and
+            ignore the `copy` keyword. The `copy` keyword will be removed in a
+            future version of pandas.
+
+            You can already get the future behavior and improvements through
+            enabling copy on write ``pd.options.mode.copy_on_write = True``
+
+        .. deprecated:: 3.0.0
+    indicator : bool or str, default False
+        If True, adds a column to the output DataFrame called "_merge" with
+        information on the source of each row. The column can be given a different
+        name by providing a string argument. The column will have a Categorical
+        type with the value of "left_only" for observations whose merge key only
+        appears in the left DataFrame, "right_only" for observations
+        whose merge key only appears in the right DataFrame, and "both"
+        if the observation's merge key is found in both DataFrames.
+
+    validate : str, optional
+        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 datasets.
+        * "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.
+        * "many_to_many" or "m:m": allowed, but does not result in checks.
+
+    Returns
+    -------
+    DataFrame
+        A DataFrame of the two merged objects.
+
+    See Also
+    --------
+    merge_ordered : Merge with optional filling/interpolation.
+    merge_asof : Merge on nearest keys.
+    DataFrame.join : Similar method using indices.
+
+    Examples
+    --------
+    >>> df1 = pd.DataFrame(
+    ...     {"lkey": ["foo", "bar", "baz", "foo"], "value": [1, 2, 3, 5]}
+    ... )
+    >>> df2 = pd.DataFrame(
+    ...     {"rkey": ["foo", "bar", "baz", "foo"], "value": [5, 6, 7, 8]}
+    ... )
+    >>> df1
+        lkey value
+    0   foo      1
+    1   bar      2
+    2   baz      3
+    3   foo      5
+    >>> df2
+        rkey value
+    0   foo      5
+    1   bar      6
+    2   baz      7
+    3   foo      8
+
+    Merge df1 and df2 on the lkey and rkey columns. The value columns have
+    the default suffixes, _x and _y, appended.
+
+    >>> df1.merge(df2, left_on="lkey", right_on="rkey")
+      lkey  value_x rkey  value_y
+    0  foo        1  foo        5
+    1  foo        1  foo        8
+    2  bar        2  bar        6
+    3  baz        3  baz        7
+    4  foo        5  foo        5
+    5  foo        5  foo        8
+
+    Merge DataFrames df1 and df2 with specified left and right suffixes
+    appended to any overlapping columns.
+
+    >>> df1.merge(df2, left_on="lkey", right_on="rkey", suffixes=("_left", "_right"))
+      lkey  value_left rkey  value_right
+    0  foo           1  foo            5
+    1  foo           1  foo            8
+    2  bar           2  bar            6
+    3  baz           3  baz            7
+    4  foo           5  foo            5
+    5  foo           5  foo            8
+
+    Merge DataFrames df1 and df2, but raise an exception if the DataFrames have
+    any overlapping columns.
+
+    >>> df1.merge(df2, left_on="lkey", right_on="rkey", suffixes=(False, False))
+    Traceback (most recent call last):
+    ...
+    ValueError: columns overlap but no suffix specified:
+        Index(['value'], dtype='object')
+
+    >>> df1 = pd.DataFrame({"a": ["foo", "bar"], "b": [1, 2]})
+    >>> df2 = pd.DataFrame({"a": ["foo", "baz"], "c": [3, 4]})
+    >>> df1
+          a  b
+    0   foo  1
+    1   bar  2
+    >>> df2
+          a  c
+    0   foo  3
+    1   baz  4
+
+    >>> df1.merge(df2, how="inner", on="a")
+          a  b  c
+    0   foo  1  3
+
+    >>> df1.merge(df2, how="left", on="a")
+          a  b  c
+    0   foo  1  3.0
+    1   bar  2  NaN
+
+    >>> df1 = pd.DataFrame({"left": ["foo", "bar"]})
+    >>> df2 = pd.DataFrame({"right": [7, 8]})
+    >>> df1
+        left
+    0   foo
+    1   bar
+    >>> df2
+        right
+    0   7
+    1   8
+
+    >>> df1.merge(df2, how="cross")
+       left  right
+    0   foo      7
+    1   foo      8
+    2   bar      7
+    3   bar      8
+    """
     left_df = _validate_operand(left)
     left._check_copy_deprecation(copy)
     right_df = _validate_operand(right)
