PR09 batch 4

pandas/core/frame.py

@@ -5881,13 +5881,13 @@ def pivot(self, index=None, columns=None, values=None):
             hierarchical columns whose top level are the function names
             (inferred from the function objects themselves)
             If dict is passed, the key is column to aggregate and value
-            is function or list of functions
+            is function or list of functions.
         fill_value : scalar, default None
-            Value to replace missing values with
+            Value to replace missing values with.
         margins : bool, default False
-            Add all row / columns (e.g. for subtotal / grand totals)
+            Add all row / columns (e.g. for subtotal / grand totals).
         dropna : bool, default True
-            Do not include columns whose entries are all NaN
+            Do not include columns whose entries are all NaN.
         margins_name : str, default 'All'
             Name of the row / column that will contain the totals
             when margins is True.
@@ -5901,6 +5901,7 @@ def pivot(self, index=None, columns=None, values=None):
         Returns
         -------
         DataFrame
+            An Excel style pivot table.
 
         See Also
         --------

pandas/core/indexes/interval.py

@@ -1407,24 +1407,24 @@ def interval_range(
     Parameters
     ----------
     start : numeric or datetime-like, default None
-        Left bound for generating intervals
+        Left bound for generating intervals.
     end : numeric or datetime-like, default None
-        Right bound for generating intervals
+        Right bound for generating intervals.
     periods : int, default None
-        Number of periods to generate
+        Number of periods to generate.
     freq : numeric, str, or DateOffset, default None
         The length of each interval. Must be consistent with the type of start
         and end, e.g. 2 for numeric, or '5H' for datetime-like.  Default is 1
         for numeric and 'D' for datetime-like.
     name : str, default None
-        Name of the resulting IntervalIndex
+        Name of the resulting IntervalIndex.
     closed : {'left', 'right', 'both', 'neither'}, default 'right'
         Whether the intervals are closed on the left-side, right-side, both
         or neither.
 
     Returns
     -------
-    rng : IntervalIndex
+    IntervalIndex
 
     See Also
     --------

pandas/core/indexes/period.py

@@ -997,28 +997,28 @@ def memory_usage(self, deep=False):
 
 def period_range(start=None, end=None, periods=None, freq=None, name=None):
     """
-    Return a fixed frequency PeriodIndex, with day (calendar) as the default
-    frequency.
+    Return a fixed frequency PeriodIndex.
+
+    The day (calendar) is the default frequency.
 
     Parameters
     ----------
     start : str or period-like, default None
-        Left bound for generating periods
+        Left bound for generating periods.
     end : str or period-like, default None
-        Right bound for generating periods
+        Right bound for generating periods.
     periods : int, default None
-        Number of periods to generate
+        Number of periods to generate.
     freq : str or DateOffset, optional
         Frequency alias. By default the freq is taken from `start` or `end`
         if those are Period objects. Otherwise, the default is ``"D"`` for
         daily frequency.
-
     name : str, default None
-        Name of the resulting PeriodIndex
+        Name of the resulting PeriodIndex.
 
     Returns
     -------
-    prng : PeriodIndex
+    PeriodIndex
 
     Notes
     -----

pandas/core/reshape/melt.py

@@ -206,27 +206,27 @@ def wide_to_long(df, stubnames, i, j, sep: str = "", suffix: str = r"\d+"):
     Parameters
     ----------
     df : DataFrame
-        The wide-format DataFrame
+        The wide-format DataFrame.
     stubnames : str or list-like
         The stub name(s). The wide format variables are assumed to
         start with the stub names.
     i : str or list-like
-        Column(s) to use as id variable(s)
+        Column(s) to use as id variable(s).
     j : str
         The name of the sub-observation variable. What you wish to name your
         suffix in the long format.
     sep : str, default ""
         A character indicating the separation of the variable names
         in the wide format, to be stripped from the names in the long format.
         For example, if your column names are A-suffix1, A-suffix2, you
-        can strip the hyphen by specifying `sep='-'`
+        can strip the hyphen by specifying `sep='-'`.
     suffix : str, default '\\d+'
         A regular expression capturing the wanted suffixes. '\\d+' captures
         numeric suffixes. Suffixes with no numbers could be specified with the
         negated character class '\\D+'. You can also further disambiguate
         suffixes, for example, if your wide variables are of the form
         A-one, B-two,.., and you have an unrelated column A-rating, you can
-        ignore the last one by specifying `suffix='(!?one|two)'`
+        ignore the last one by specifying `suffix='(!?one|two)'`.
 
         .. versionchanged:: 0.23.0
             When all suffixes are numeric, they are cast to int64/float64.
@@ -360,7 +360,7 @@ def wide_to_long(df, stubnames, i, j, sep: str = "", suffix: str = r"\d+"):
 
     >>> stubnames = sorted(
     ...     set([match[0] for match in df.columns.str.findall(
-    ...         r'[A-B]\(.*\)').values if match != [] ])
+    ...         r'[A-B]\(.*\)').values if match != []])
     ... )
     >>> list(stubnames)
     ['A(weekly)', 'B(weekly)']

pandas/core/reshape/merge.py

@@ -176,9 +176,10 @@ def merge_ordered(
     how="outer",
 ):
     """
-    Perform merge with optional filling/interpolation designed for ordered
-    data like time series data. Optionally perform group-wise merge (see
-    examples).
+    Perform merge with optional filling/interpolation.
+
+    Designed for ordered data like time series data. Optionally
+    perform group-wise merge (see examples).
 
     Parameters
     ----------
@@ -189,18 +190,18 @@ def merge_ordered(
     left_on : label or list, or array-like
         Field names to join on in left DataFrame. Can be a vector or list of
         vectors of the length of the DataFrame to use a particular vector as
-        the join key instead of columns
+        the join key instead of columns.
     right_on : label or list, or array-like
         Field names to join on in right DataFrame or vector/list of vectors per
-        left_on docs
+        left_on docs.
     left_by : column name or list of column names
         Group left DataFrame by group columns and merge piece by piece with
-        right DataFrame
+        right DataFrame.
     right_by : column name or list of column names
         Group right DataFrame by group columns and merge piece by piece with
-        left DataFrame
+        left DataFrame.
     fill_method : {'ffill', None}, default None
-        Interpolation method for data
+        Interpolation method for data.
     suffixes : Sequence, 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
@@ -214,13 +215,13 @@ def merge_ordered(
         * left: use only keys from left frame (SQL: left outer join)
         * right: use only keys from right frame (SQL: right outer join)
         * outer: use union of keys from both frames (SQL: full outer join)
-        * inner: use intersection of keys from both frames (SQL: inner join)
+        * inner: use intersection of keys from both frames (SQL: inner join).
 
     Returns
     -------
-    merged : DataFrame
-        The output type will the be same as 'left', if it is a subclass
-        of DataFrame.
+    DataFrame
+        The merged DataFrame output type will the be same as
+        'left', if it is a subclass of DataFrame.
 
     See Also
     --------
@@ -229,15 +230,21 @@ def merge_ordered(
 
     Examples
     --------
-    >>> A                      >>> B
-          key  lvalue group        key  rvalue
-    0   a       1     a        0     b       1
-    1   c       2     a        1     c       2
-    2   e       3     a        2     d       3
+    >>> A
+          key  lvalue group
+    0   a       1     a
+    1   c       2     a
+    2   e       3     a
     3   a       1     b
     4   c       2     b
     5   e       3     b
 
+    >>> B
+        Key  rvalue
+    0     b       1
+    1     c       2
+    2     d       3
+
     >>> merge_ordered(A, B, fill_method='ffill', left_by='group')
       group key  lvalue  rvalue
     0     a   a       1     NaN

pandas/core/tools/datetimes.py

@@ -577,14 +577,13 @@ def to_datetime(
 
     Parameters
     ----------
-    arg : int, float, str, datetime, list, tuple, 1-d array, Series
-           or DataFrame/dict-like
-
+    arg : int, float, str, datetime, list, tuple, 1-d array, Series DataFrame/dict-like
+        The object to convert to a datetime.
     errors : {'ignore', 'raise', 'coerce'}, default 'raise'
-
-        - If 'raise', then invalid parsing will raise an exception
-        - If 'coerce', then invalid parsing will be set as NaT
-        - If 'ignore', then invalid parsing will return the input
+        Behaves as:
+        - If 'raise', then invalid parsing will raise an exception.
+        - If 'coerce', then invalid parsing will be set as NaT.
+        - If 'ignore', then invalid parsing will return the input.
     dayfirst : bool, default False
         Specify a date parse order if `arg` is str or its list-likes.
         If True, parses dates with the day first, eg 10/11/12 is parsed as
@@ -605,7 +604,6 @@ def to_datetime(
         Return UTC DatetimeIndex if True (converting any tz-aware
         datetime.datetime objects as well).
     box : bool, default True
-
         - If True returns a DatetimeIndex or Index-like object
         - If False returns ndarray of values.
 
@@ -615,17 +613,17 @@ def to_datetime(
             respectively.
 
     format : str, default None
-        strftime to parse time, eg "%d/%m/%Y", note that "%f" will parse
+        The strftime to parse time, eg "%d/%m/%Y", note that "%f" will parse
         all the way up to nanoseconds.
         See strftime documentation for more information on choices:
-        https://docs.python.org/3/library/datetime.html#strftime-and-strptime-behavior
+        https://docs.python.org/3/library/datetime.html#strftime-and-strptime-behavior.
     exact : bool, True by default
-
+        Behaves as:
         - If True, require an exact format match.
         - If False, allow the format to match anywhere in the target string.
 
     unit : str, default 'ns'
-        unit of the arg (D,s,ms,us,ns) denote the unit, which is an
+        The unit of the arg (D,s,ms,us,ns) denote the unit, which is an
         integer or float number. This will be based off the origin.
         Example, with unit='ms' and origin='unix' (the default), this
         would calculate the number of milliseconds to the unix epoch start.
@@ -652,11 +650,12 @@ def to_datetime(
         .. versionadded:: 0.23.0
 
         .. versionchanged:: 0.25.0
-            - changed default value from False to True
+            - changed default value from False to True.
 
     Returns
     -------
-    ret : datetime if parsing succeeded.
+    datetime
+        If parsing succeeded.
         Return type depends on input:
 
         - list-like: DatetimeIndex
@@ -712,10 +711,10 @@ def to_datetime(
     4    3/12/2000
     dtype: object
 
-    >>> %timeit pd.to_datetime(s,infer_datetime_format=True)  # doctest: +SKIP
+    >>> %timeit pd.to_datetime(s, infer_datetime_format=True)  # doctest: +SKIP
     100 loops, best of 3: 10.4 ms per loop
 
-    >>> %timeit pd.to_datetime(s,infer_datetime_format=False)  # doctest: +SKIP
+    >>> %timeit pd.to_datetime(s, infer_datetime_format=False)  # doctest: +SKIP
     1 loop, best of 3: 471 ms per loop
 
     Using a unix epoch time

pandas/core/util/hashing.py

@@ -67,11 +67,11 @@ def hash_pandas_object(
     Parameters
     ----------
     index : bool, default True
-        include the index in the hash (if Series/DataFrame)
+        Include the index in the hash (if Series/DataFrame).
     encoding : str, default 'utf8'
-        encoding for data & key when strings
+        Encoding for data & key when strings.
     hash_key : str, default _default_hash_key
-        hash_key for string key to encode
+        Hash_key for string key to encode.
     categorize : bool, default True
         Whether to first categorize object arrays before hashing. This is more
         efficient when the array contains duplicate values.
@@ -253,9 +253,9 @@ def hash_array(
     ----------
     vals : ndarray, Categorical
     encoding : str, default 'utf8'
-        encoding for data & key when strings
+        Encoding for data & key when strings.
     hash_key : str, default _default_hash_key
-        hash_key for string key to encode
+        Hash_key for string key to encode.
     categorize : bool, default True
         Whether to first categorize object arrays before hashing. This is more
         efficient when the array contains duplicate values.

pandas/io/excel/_base.py

@@ -79,7 +79,7 @@
     subset of data is selected with ``usecols``, index_col
     is based on the subset.
 usecols : int, str, list-like, or callable default None
-    Return a subset of the columns.
+    Behavior:
 
     * If None, then parse all columns.
     * If int, then indicates last column to be parsed.
@@ -98,6 +98,8 @@
     * If callable, then evaluate each column name against it and parse the
       column if the callable returns ``True``.
 
+    Returns a subset of the columns according to behavior above.
+
       .. versionadded:: 0.24.0
 
 squeeze : bool, default False

pandas/io/packers.py

@@ -191,7 +191,7 @@ def read_msgpack(path_or_buf, encoding="utf-8", iterator=False, **kwargs):
         ``StringIO``.
     encoding : Encoding for decoding msgpack str type
     iterator : boolean, if True, return an iterator to the unpacker
-               (default is False)
+               (default is False).
 
     Returns
     -------