From 0f76a2a3e39c057dc2cd1d06fa468aaeab3e7198 Mon Sep 17 00:00:00 2001
From: Daniel Saxton <dsaxton@pm.me>
Date: Thu, 1 Oct 2020 08:15:54 -0500
Subject: [PATCH 01/10] DOC: Fix code block line length

---
 doc/source/user_guide/categorical.rst | 20 ++++++--
 doc/source/user_guide/io.rst          | 68 ++++++++++++++++++++++-----
 doc/source/user_guide/reshaping.rst   | 38 +++++++++++++--
 doc/source/user_guide/text.rst        | 23 +++++++--
 doc/source/user_guide/timedeltas.rst  |  5 +-
 setup.cfg                             |  2 +-
 6 files changed, 130 insertions(+), 26 deletions(-)

diff --git a/doc/source/user_guide/categorical.rst b/doc/source/user_guide/categorical.rst
index 6a8e1767ef7e8..06dd7438da3e2 100644
--- a/doc/source/user_guide/categorical.rst
+++ b/doc/source/user_guide/categorical.rst
@@ -513,7 +513,11 @@ The ordering of the categorical is determined by the ``categories`` of that colu
 
    dfs = pd.DataFrame(
        {
-           "A": pd.Categorical(list("bbeebbaa"), categories=["e", "a", "b"], ordered=True),
+           "A": pd.Categorical(
+               list("bbeebbaa"),
+               categories=["e", "a", "b"],
+               ordered=True,
+           ),
            "B": [1, 2, 1, 2, 2, 1, 2, 1],
        }
    )
@@ -642,7 +646,13 @@ Groupby will also show "unused" categories:
     df.groupby("cats").mean()
 
     cats2 = pd.Categorical(["a", "a", "b", "b"], categories=["a", "b", "c"])
-    df2 = pd.DataFrame({"cats": cats2, "B": ["c", "d", "c", "d"], "values": [1, 2, 3, 4]})
+    df2 = pd.DataFrame(
+        {
+            "cats": cats2,
+            "B": ["c", "d", "c", "d"],
+            "values": [1, 2, 3, 4],
+        }
+    )
     df2.groupby(["cats", "B"]).mean()
 
 
@@ -1115,7 +1125,11 @@ You can use ``fillna`` to handle missing values before applying a function.
 .. ipython:: python
 
     df = pd.DataFrame(
-        {"a": [1, 2, 3, 4], "b": ["a", "b", "c", "d"], "cats": pd.Categorical([1, 2, 3, 2])}
+        {
+            "a": [1, 2, 3, 4],
+            "b": ["a", "b", "c", "d"],
+            "cats": pd.Categorical([1, 2, 3, 2])
+        }
     )
     df.apply(lambda row: type(row["cats"]), axis=1)
     df.apply(lambda col: col.dtype, axis=0)
diff --git a/doc/source/user_guide/io.rst b/doc/source/user_guide/io.rst
index e483cebf71614..8c7a5801606b1 100644
--- a/doc/source/user_guide/io.rst
+++ b/doc/source/user_guide/io.rst
@@ -986,7 +986,12 @@ Note that ``infer_datetime_format`` is sensitive to ``dayfirst``.  With
 .. ipython:: python
 
    # Try to infer the format for the index column
-   df = pd.read_csv("foo.csv", index_col=0, parse_dates=True, infer_datetime_format=True)
+   df = pd.read_csv(
+       "foo.csv",
+       index_col=0,
+       parse_dates=True,
+       infer_datetime_format=True,
+   )
    df
 
 .. ipython:: python
@@ -1046,9 +1051,19 @@ writing to a file). For example:
 
    val = "0.3066101993807095471566981359501369297504425048828125"
    data = "a,b,c\n1,2,{0}".format(val)
-   abs(pd.read_csv(StringIO(data), engine="c", float_precision=None)["c"][0] - float(val))
    abs(
-       pd.read_csv(StringIO(data), engine="c", float_precision="high")["c"][0] - float(val)
+       pd.read_csv(
+           StringIO(data),
+           engine="c",
+           float_precision=None
+       )["c"][0] - float(val)
+   )
+   abs(
+       pd.read_csv(
+           StringIO(data),
+           engine="c",
+           float_precision="high"
+       )["c"][0] - float(val)
    )
    abs(
        pd.read_csv(StringIO(data), engine="c", float_precision="round_trip")["c"][0]
@@ -2517,7 +2532,12 @@ columns to strings.
 .. code-block:: python
 
    url_mcc = "https://en.wikipedia.org/wiki/Mobile_country_code"
-   dfs = pd.read_html(url_mcc, match="Telekom Albania", header=0, converters={"MNC": str})
+   dfs = pd.read_html(
+       url_mcc,
+       match="Telekom Albania",
+       header=0,
+       converters={"MNC": str},
+   )
 
 Use some combination of the above:
 
@@ -3570,7 +3590,12 @@ HDFStore will by default not drop rows that are all missing. This behavior can b
 
 .. ipython:: python
 
-   df_with_missing = pd.DataFrame({"col1": [0, np.nan, 2], "col2": [1, np.nan, np.nan]})
+   df_with_missing = pd.DataFrame(
+       {
+           "col1": [0, np.nan, 2],
+           "col2": [1, np.nan, np.nan]
+       }
+   )
    df_with_missing
 
    df_with_missing.to_hdf("file.h5", "df_with_missing", format="table", mode="w")
@@ -3944,7 +3969,8 @@ specified in the format: ``<float>(<unit>)``, where float may be signed (and fra
        {
            "A": pd.Timestamp("20130101"),
            "B": [
-               pd.Timestamp("20130101") + timedelta(days=i, seconds=10) for i in range(10)
+               pd.Timestamp("20130101") + timedelta(days=i, seconds=10)
+               for i in range(10)
            ],
        }
    )
@@ -4241,7 +4267,11 @@ results.
    store.select("df2_mt")
 
    # as a multiple
-   store.select_as_multiple(["df1_mt", "df2_mt"], where=["A>0", "B>0"], selector="df1_mt")
+   store.select_as_multiple(
+       ["df1_mt", "df2_mt"],
+       where=["A>0", "B>0"],
+       selector="df1_mt",
+   )
 
 
 Delete from a table
@@ -4797,8 +4827,16 @@ Read only certain columns of a parquet file.
 
 .. ipython:: python
 
-   result = pd.read_parquet("example_fp.parquet", engine="fastparquet", columns=["a", "b"])
-   result = pd.read_parquet("example_pa.parquet", engine="pyarrow", columns=["a", "b"])
+   result = pd.read_parquet(
+       "example_fp.parquet",
+       engine="fastparquet",
+       columns=["a", "b"],
+   )
+   result = pd.read_parquet(
+       "example_pa.parquet",
+       engine="pyarrow",
+       columns=["a", "b"],
+   )
    result.dtypes
 
 
@@ -5176,7 +5214,11 @@ to pass to :func:`pandas.to_datetime`:
 .. code-block:: python
 
    pd.read_sql_table("data", engine, parse_dates={"Date": "%Y-%m-%d"})
-   pd.read_sql_table("data", engine, parse_dates={"Date": {"format": "%Y-%m-%d %H:%M:%S"}})
+   pd.read_sql_table(
+       "data",
+       engine,
+       parse_dates={"Date": {"format": "%Y-%m-%d %H:%M:%S"}},
+   )
 
 
 You can check if a table exists using :func:`~pandas.io.sql.has_table`
@@ -5593,7 +5635,11 @@ avoid converting categorical columns into ``pd.Categorical``:
 
 .. code-block:: python
 
-    df = pd.read_spss("spss_data.sav", usecols=["foo", "bar"], convert_categoricals=False)
+    df = pd.read_spss(
+        "spss_data.sav",
+        usecols=["foo", "bar"],
+        convert_categoricals=False,
+    )
 
 More information about the SAV and ZSAV file formats is available here_.
 
diff --git a/doc/source/user_guide/reshaping.rst b/doc/source/user_guide/reshaping.rst
index 2061185b25416..315f19723de63 100644
--- a/doc/source/user_guide/reshaping.rst
+++ b/doc/source/user_guide/reshaping.rst
@@ -238,7 +238,13 @@ calling ``sort_index``, of course). Here is a more complex example:
 .. ipython:: python
 
    columns = pd.MultiIndex.from_tuples(
-       [("A", "cat"), ("B", "dog"), ("B", "cat"), ("A", "dog")], names=["exp", "animal"]
+       [
+           ("A", "cat"),
+           ("B", "dog"),
+           ("B", "cat"),
+           ("A", "dog"),
+       ],
+       names=["exp", "animal"],
    )
    index = pd.MultiIndex.from_product(
        [("bar", "baz", "foo", "qux"), ("one", "two")], names=["first", "second"]
@@ -800,14 +806,26 @@ parameter.
 
 .. ipython:: python
 
-   df.pivot_table(values="val0", index="row", columns="col", aggfunc="mean", fill_value=0)
+   df.pivot_table(
+       values="val0",
+       index="row",
+       columns="col",
+       aggfunc="mean",
+       fill_value=0,
+   )
 
 Also note that we can pass in other aggregation functions as well. For example,
 we can also pass in ``sum``.
 
 .. ipython:: python
 
-   df.pivot_table(values="val0", index="row", columns="col", aggfunc="sum", fill_value=0)
+   df.pivot_table(
+       values="val0",
+       index="row",
+       columns="col",
+       aggfunc="sum",
+       fill_value=0,
+   )
 
 Another aggregation we can do is calculate the frequency in which the columns
 and rows occur together a.k.a. "cross tabulation". To do this, we can pass
@@ -825,7 +843,12 @@ We can also perform multiple aggregations. For example, to perform both a
 
 .. ipython:: python
 
-   df.pivot_table(values="val0", index="row", columns="col", aggfunc=["mean", "sum"])
+   df.pivot_table(
+       values="val0",
+       index="row",
+       columns="col",
+       aggfunc=["mean", "sum"],
+   )
 
 Note to aggregate over multiple value columns, we can pass in a list to the
 ``values`` parameter.
@@ -839,7 +862,12 @@ Note to subdivide over multiple columns we can pass in a list to the
 
 .. ipython:: python
 
-   df.pivot_table(values=["val0"], index="row", columns=["item", "col"], aggfunc=["mean"])
+   df.pivot_table(
+       values=["val0"],
+       index="row",
+       columns=["item", "col"],
+       aggfunc=["mean"],
+   )
 
 .. _reshaping.explode:
 
diff --git a/doc/source/user_guide/text.rst b/doc/source/user_guide/text.rst
index 2ada09117273d..1dd567cabd1e2 100644
--- a/doc/source/user_guide/text.rst
+++ b/doc/source/user_guide/text.rst
@@ -261,7 +261,8 @@ i.e., from the end of the string to the beginning of the string:
 .. ipython:: python
 
    s3 = pd.Series(
-       ["A", "B", "C", "Aaba", "Baca", "", np.nan, "CABA", "dog", "cat"], dtype="string"
+       ["A", "B", "C", "Aaba", "Baca", "", np.nan, "CABA", "dog", "cat"],
+       dtype="string",
    )
    s3
    s3.str.replace("^.a|dog", "XX-XX ", case=False)
@@ -515,7 +516,10 @@ DataFrame with one column per group.
 
 .. ipython:: python
 
-   pd.Series(["a1", "b2", "c3"], dtype="string").str.extract(r"([ab])(\d)", expand=False)
+   pd.Series(
+       ["a1", "b2", "c3"],
+       dtype="string",
+   ).str.extract(r"([ab])(\d)", expand=False)
 
 Elements that do not match return a row filled with ``NaN``. Thus, a
 Series of messy strings can be "converted" into a like-indexed Series
@@ -536,7 +540,10 @@ and optional groups like
 
 .. ipython:: python
 
-   pd.Series(["a1", "b2", "3"], dtype="string").str.extract(r"([ab])?(\d)", expand=False)
+   pd.Series(
+       ["a1", "b2", "3"],
+       dtype="string",
+   ).str.extract(r"([ab])?(\d)", expand=False)
 
 can also be used. Note that any capture group names in the regular
 expression will be used for column names; otherwise capture group
@@ -661,13 +668,19 @@ Or whether elements match a pattern:
 
 .. ipython:: python
 
-   pd.Series(["1", "2", "3a", "3b", "03c", "4dx"], dtype="string").str.match(pattern)
+   pd.Series(
+       ["1", "2", "3a", "3b", "03c", "4dx"],
+       dtype="string",
+   ).str.match(pattern)
 
 .. versionadded:: 1.1.0
 
 .. ipython:: python
 
-   pd.Series(["1", "2", "3a", "3b", "03c", "4dx"], dtype="string").str.fullmatch(pattern)
+   pd.Series(
+       ["1", "2", "3a", "3b", "03c", "4dx"],
+       dtype="string",
+   ).str.fullmatch(pattern)
 
 .. note::
 
diff --git a/doc/source/user_guide/timedeltas.rst b/doc/source/user_guide/timedeltas.rst
index 971a415088220..91e694626fe5a 100644
--- a/doc/source/user_guide/timedeltas.rst
+++ b/doc/source/user_guide/timedeltas.rst
@@ -409,7 +409,10 @@ Similarly to other of the datetime-like indices, ``DatetimeIndex`` and ``PeriodI
 
 .. ipython:: python
 
-   s = pd.Series(np.arange(100), index=pd.timedelta_range("1 days", periods=100, freq="h"))
+   s = pd.Series(
+       np.arange(100),
+       index=pd.timedelta_range("1 days", periods=100, freq="h"),
+   )
    s
 
 Selections work similarly, with coercion on string-likes and slices:
diff --git a/setup.cfg b/setup.cfg
index 73986f692b6cd..5a3ad3f0f95b4 100644
--- a/setup.cfg
+++ b/setup.cfg
@@ -33,7 +33,7 @@ exclude =
     env  # exclude asv benchmark environments from linting
 
 [flake8-rst]
-max-line-length = 88
+max-line-length = 84
 bootstrap =
     import numpy as np
     import pandas as pd

From 94ba01018cbe645c54fc39ccb52cb70dc7280d5b Mon Sep 17 00:00:00 2001
From: Daniel Saxton <dsaxton@pm.me>
Date: Thu, 1 Oct 2020 08:24:20 -0500
Subject: [PATCH 02/10] Fix

---
 doc/source/user_guide/categorical.rst | 2 +-
 doc/source/user_guide/io.rst          | 6 +++---
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/doc/source/user_guide/categorical.rst b/doc/source/user_guide/categorical.rst
index 06dd7438da3e2..ad7a5a994f1f6 100644
--- a/doc/source/user_guide/categorical.rst
+++ b/doc/source/user_guide/categorical.rst
@@ -1128,7 +1128,7 @@ You can use ``fillna`` to handle missing values before applying a function.
         {
             "a": [1, 2, 3, 4],
             "b": ["a", "b", "c", "d"],
-            "cats": pd.Categorical([1, 2, 3, 2])
+            "cats": pd.Categorical([1, 2, 3, 2]),
         }
     )
     df.apply(lambda row: type(row["cats"]), axis=1)
diff --git a/doc/source/user_guide/io.rst b/doc/source/user_guide/io.rst
index 8c7a5801606b1..8458f2e91610e 100644
--- a/doc/source/user_guide/io.rst
+++ b/doc/source/user_guide/io.rst
@@ -1055,14 +1055,14 @@ writing to a file). For example:
        pd.read_csv(
            StringIO(data),
            engine="c",
-           float_precision=None
+           float_precision=None,
        )["c"][0] - float(val)
    )
    abs(
        pd.read_csv(
            StringIO(data),
            engine="c",
-           float_precision="high"
+           float_precision="high",
        )["c"][0] - float(val)
    )
    abs(
@@ -3593,7 +3593,7 @@ HDFStore will by default not drop rows that are all missing. This behavior can b
    df_with_missing = pd.DataFrame(
        {
            "col1": [0, np.nan, 2],
-           "col2": [1, np.nan, np.nan]
+           "col2": [1, np.nan, np.nan],
        }
    )
    df_with_missing

From 5b5268e69e1592deca9f88f6ab75f0f5966ca4e2 Mon Sep 17 00:00:00 2001
From: Daniel Saxton <dsaxton@pm.me>
Date: Thu, 1 Oct 2020 09:10:08 -0500
Subject: [PATCH 03/10] Fix

---
 doc/source/user_guide/reshaping.rst | 7 ++++++-
 doc/source/user_guide/text.rst      | 5 ++++-
 2 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/doc/source/user_guide/reshaping.rst b/doc/source/user_guide/reshaping.rst
index 315f19723de63..2a346fe854ff1 100644
--- a/doc/source/user_guide/reshaping.rst
+++ b/doc/source/user_guide/reshaping.rst
@@ -855,7 +855,12 @@ Note to aggregate over multiple value columns, we can pass in a list to the
 
 .. ipython:: python
 
-   df.pivot_table(values=["val0", "val1"], index="row", columns="col", aggfunc=["mean"])
+   df.pivot_table(
+       values=["val0", "val1"],
+       index="row",
+       columns="col",
+       aggfunc=["mean"],
+   )
 
 Note to subdivide over multiple columns we can pass in a list to the
 ``columns`` parameter.
diff --git a/doc/source/user_guide/text.rst b/doc/source/user_guide/text.rst
index 1dd567cabd1e2..2b27d37904599 100644
--- a/doc/source/user_guide/text.rst
+++ b/doc/source/user_guide/text.rst
@@ -662,7 +662,10 @@ You can check whether elements contain a pattern:
 .. ipython:: python
 
    pattern = r"[0-9][a-z]"
-   pd.Series(["1", "2", "3a", "3b", "03c", "4dx"], dtype="string").str.contains(pattern)
+   pd.Series(
+       ["1", "2", "3a", "3b", "03c", "4dx"],
+       dtype="string",
+   ).str.contains(pattern)
 
 Or whether elements match a pattern:
 

From f089659d6151c29b10a6bebd207ff7b8c1f827f0 Mon Sep 17 00:00:00 2001
From: Daniel Saxton <dsaxton@pm.me>
Date: Thu, 1 Oct 2020 09:32:36 -0500
Subject: [PATCH 04/10] Another

---
 doc/source/user_guide/reshaping.rst | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/doc/source/user_guide/reshaping.rst b/doc/source/user_guide/reshaping.rst
index 2a346fe854ff1..77cf43b2e2b19 100644
--- a/doc/source/user_guide/reshaping.rst
+++ b/doc/source/user_guide/reshaping.rst
@@ -432,7 +432,12 @@ We can produce pivot tables from this data very easily:
 
    pd.pivot_table(df, values="D", index=["A", "B"], columns=["C"])
    pd.pivot_table(df, values="D", index=["B"], columns=["A", "C"], aggfunc=np.sum)
-   pd.pivot_table(df, values=["D", "E"], index=["B"], columns=["A", "C"], aggfunc=np.sum)
+   pd.pivot_table(
+       df, values=["D", "E"],
+       index=["B"],
+       columns=["A", "C"],
+       aggfunc=np.sum,
+   )
 
 The result object is a ``DataFrame`` having potentially hierarchical indexes on the
 rows and columns. If the ``values`` column name is not given, the pivot table

From f57fa6c782a3e6183e43bfb30b787eeab251b372 Mon Sep 17 00:00:00 2001
From: Daniel Saxton <dsaxton@pm.me>
Date: Fri, 2 Oct 2020 13:51:05 -0500
Subject: [PATCH 05/10] Fix

---
 .../intro_tutorials/06_calculate_statistics.rst              | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/doc/source/getting_started/intro_tutorials/06_calculate_statistics.rst b/doc/source/getting_started/intro_tutorials/06_calculate_statistics.rst
index 7e919777fdf03..6ce98ba5dbd1b 100644
--- a/doc/source/getting_started/intro_tutorials/06_calculate_statistics.rst
+++ b/doc/source/getting_started/intro_tutorials/06_calculate_statistics.rst
@@ -123,7 +123,10 @@ aggregating statistics for given columns can be defined using the
 .. ipython:: python
 
     titanic.agg(
-        {"Age": ["min", "max", "median", "skew"], "Fare": ["min", "max", "median", "mean"]}
+        {
+            "Age": ["min", "max", "median", "skew"],
+            "Fare": ["min", "max", "median", "mean"],
+        }
     )
 
 .. raw:: html

From 31032a5279251c3df1fd12cbbacfd169168581fa Mon Sep 17 00:00:00 2001
From: Daniel Saxton <dsaxton@pm.me>
Date: Fri, 2 Oct 2020 14:47:13 -0500
Subject: [PATCH 06/10] Fix

---
 doc/source/user_guide/cookbook.rst | 41 +++++++++++++++++++++++++-----
 1 file changed, 34 insertions(+), 7 deletions(-)

diff --git a/doc/source/user_guide/cookbook.rst b/doc/source/user_guide/cookbook.rst
index 0a30d865f3c23..fe17007a70b26 100644
--- a/doc/source/user_guide/cookbook.rst
+++ b/doc/source/user_guide/cookbook.rst
@@ -266,7 +266,9 @@ New columns
 
 .. ipython:: python
 
-   df = pd.DataFrame({"AAA": [1, 1, 1, 2, 2, 2, 3, 3], "BBB": [2, 1, 3, 4, 5, 1, 2, 3]})
+   df = pd.DataFrame(
+       {"AAA": [1, 1, 1, 2, 2, 2, 3, 3], "BBB": [2, 1, 3, 4, 5, 1, 2, 3]}
+   )
    df
 
 Method 1 : idxmin() to get the index of the minimums
@@ -327,7 +329,9 @@ Arithmetic
 
 .. ipython:: python
 
-   cols = pd.MultiIndex.from_tuples([(x, y) for x in ["A", "B", "C"] for y in ["O", "I"]])
+   cols = pd.MultiIndex.from_tuples(
+       [(x, y) for x in ["A", "B", "C"] for y in ["O", "I"]]
+   )
    df = pd.DataFrame(np.random.randn(2, 6), index=["n", "m"], columns=cols)
    df
    df = df.div(df["C"], level=1)
@@ -566,7 +570,9 @@ Unlike agg, apply's callable is passed a sub-DataFrame which gives you access to
 
 .. ipython:: python
 
-   df = pd.DataFrame({"Color": "Red Red Red Blue".split(), "Value": [100, 150, 50, 50]})
+   df = pd.DataFrame(
+       {"Color": "Red Red Red Blue".split(), "Value": [100, 150, 50, 50]}
+   )
    df
    df["Counts"] = df.groupby(["Color"]).transform(len)
    df
@@ -648,7 +654,10 @@ Create a list of dataframes, split using a delineation based on logic included i
    dfs = list(
        zip(
            *df.groupby(
-               (1 * (df["Case"] == "B")).cumsum().rolling(window=3, min_periods=1).median()
+               (1 * (df["Case"] == "B"))
+               .cumsum()
+               .rolling(window=3, min_periods=1)
+               .median()
            )
        )
    )[-1]
@@ -740,7 +749,18 @@ The :ref:`Pivot <reshaping.pivot>` docs.
                "yes",
            ],
            "Passed": ["yes" if x > 50 else "no" for x in grades],
-           "Employed": [True, True, True, False, False, False, False, True, True, False],
+           "Employed": [
+               True,
+               True,
+               True,
+               False,
+               False,
+               False,
+               False,
+               True,
+               True,
+               False,
+           ],
            "Grade": grades,
        }
    )
@@ -791,7 +811,9 @@ Apply
        return pd.Series(aList)
 
 
-   df_orgz = pd.concat({ind: row.apply(SeriesFromSubList) for ind, row in df.iterrows()})
+   df_orgz = pd.concat(
+       {ind: row.apply(SeriesFromSubList) for ind, row in df.iterrows()}
+   )
    df_orgz
 
 `Rolling apply with a DataFrame returning a Series
@@ -1162,7 +1184,12 @@ Option 1: pass rows explicitly to skip rows
     from io import StringIO
 
     pd.read_csv(
-        StringIO(data), sep=";", skiprows=[11, 12], index_col=0, parse_dates=True, header=10
+        StringIO(data),
+        sep=";",
+        skiprows=[11, 12],
+        index_col=0,
+        parse_dates=True,
+        header=10,
     )
 
 Option 2: read column names and then data

From ce985ba41d6d13b2108771eeca7fddf0313b9782 Mon Sep 17 00:00:00 2001
From: Daniel Saxton <dsaxton@pm.me>
Date: Fri, 2 Oct 2020 18:09:12 -0500
Subject: [PATCH 07/10] Fix

---
 doc/source/user_guide/merging.rst | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/doc/source/user_guide/merging.rst b/doc/source/user_guide/merging.rst
index 8dbfc261e6fa8..da16aaf5b3a56 100644
--- a/doc/source/user_guide/merging.rst
+++ b/doc/source/user_guide/merging.rst
@@ -1065,7 +1065,9 @@ join key), using ``join`` may be more convenient. Here is a simple example:
 
 .. ipython:: python
 
-   result = pd.merge(left, right, left_on="key", right_index=True, how="left", sort=False)
+   result = pd.merge(
+       left, right, left_on="key", right_index=True, how="left", sort=False
+   )
 
 .. ipython:: python
    :suppress:
@@ -1196,7 +1198,9 @@ the left argument, as in this example:
    left = pd.DataFrame({"v1": range(12)}, index=leftindex)
    left
 
-   rightindex = pd.MultiIndex.from_product([list("abc"), list("xy")], names=["abc", "xy"])
+   rightindex = pd.MultiIndex.from_product(
+       [list("abc"), list("xy")], names=["abc", "xy"]
+   )
    right = pd.DataFrame({"v2": [100 * i for i in range(1, 7)]}, index=rightindex)
    right
 
@@ -1210,7 +1214,9 @@ done using the following code.
    leftindex = pd.MultiIndex.from_tuples(
        [("K0", "X0"), ("K0", "X1"), ("K1", "X2")], names=["key", "X"]
    )
-   left = pd.DataFrame({"A": ["A0", "A1", "A2"], "B": ["B0", "B1", "B2"]}, index=leftindex)
+   left = pd.DataFrame(
+       {"A": ["A0", "A1", "A2"], "B": ["B0", "B1", "B2"]}, index=leftindex
+   )
 
    rightindex = pd.MultiIndex.from_tuples(
        [("K0", "Y0"), ("K1", "Y1"), ("K2", "Y2"), ("K2", "Y3")], names=["key", "Y"]
@@ -1376,7 +1382,9 @@ one object from values for matching indices in the other. Here is an example:
 
 .. ipython:: python
 
-   df1 = pd.DataFrame([[np.nan, 3.0, 5.0], [-4.6, np.nan, np.nan], [np.nan, 7.0, np.nan]])
+   df1 = pd.DataFrame(
+       [[np.nan, 3.0, 5.0], [-4.6, np.nan, np.nan], [np.nan, 7.0, np.nan]]
+   )
    df2 = pd.DataFrame([[-42.6, np.nan, -8.2], [-5.0, 1.6, 4]], index=[1, 2])
 
 For this, use the :meth:`~DataFrame.combine_first` method:

From 33a2e260f6d91cd72914d5ff026d5eb68472d8da Mon Sep 17 00:00:00 2001
From: Daniel Saxton <dsaxton@pm.me>
Date: Sat, 3 Oct 2020 11:07:15 -0500
Subject: [PATCH 08/10] Fix

---
 doc/source/user_guide/computation.rst   |  6 ++-
 doc/source/user_guide/groupby.rst       |  9 +++-
 doc/source/user_guide/missing_data.rst  |  5 ++-
 doc/source/user_guide/timeseries.rst    | 57 ++++++++++++++++++++-----
 doc/source/user_guide/visualization.rst |  6 ++-
 5 files changed, 67 insertions(+), 16 deletions(-)

diff --git a/doc/source/user_guide/computation.rst b/doc/source/user_guide/computation.rst
index 2f6ac6b06d85e..75fb3380821d8 100644
--- a/doc/source/user_guide/computation.rst
+++ b/doc/source/user_guide/computation.rst
@@ -787,7 +787,11 @@ can even be omitted:
 
 .. ipython:: python
 
-   covs = df[["B", "C", "D"]].rolling(window=50).cov(df[["A", "B", "C"]], pairwise=True)
+   covs = (
+       df[["B", "C", "D"]]
+       .rolling(window=50)
+       .cov(df[["A", "B", "C"]], pairwise=True)
+   )
    covs.loc["2002-09-22":]
 
 .. ipython:: python
diff --git a/doc/source/user_guide/groupby.rst b/doc/source/user_guide/groupby.rst
index 9696f14f03b56..bd0a8a70a3ff7 100644
--- a/doc/source/user_guide/groupby.rst
+++ b/doc/source/user_guide/groupby.rst
@@ -267,7 +267,9 @@ the length of the ``groups`` dict, so it is largely just a convenience:
    height = np.random.normal(60, 10, size=n)
    time = pd.date_range("1/1/2000", periods=n)
    gender = np.random.choice(["male", "female"], size=n)
-   df = pd.DataFrame({"height": height, "weight": weight, "gender": gender}, index=time)
+   df = pd.DataFrame(
+       {"height": height, "weight": weight, "gender": gender}, index=time
+   )
 
 .. ipython:: python
 
@@ -767,7 +769,10 @@ For example, suppose we wished to standardize the data within each group:
    ts.head()
    ts.tail()
 
-   transformed = ts.groupby(lambda x: x.year).transform(lambda x: (x - x.mean()) / x.std())
+   transformed = ts.groupby(lambda x: x.year).transform(
+       lambda x: (x - x.mean()) / x.std()
+   )
+
 
 We would expect the result to now have mean 0 and standard deviation 1 within
 each group, which we can easily check:
diff --git a/doc/source/user_guide/missing_data.rst b/doc/source/user_guide/missing_data.rst
index 3c97cc7da6edb..f83da2e1cc8df 100644
--- a/doc/source/user_guide/missing_data.rst
+++ b/doc/source/user_guide/missing_data.rst
@@ -400,7 +400,10 @@ You can also interpolate with a DataFrame:
 .. ipython:: python
 
    df = pd.DataFrame(
-       {"A": [1, 2.1, np.nan, 4.7, 5.6, 6.8], "B": [0.25, np.nan, np.nan, 4, 12.2, 14.4]}
+       {
+           "A": [1, 2.1, np.nan, 4.7, 5.6, 6.8],
+           "B": [0.25, np.nan, np.nan, 4, 12.2, 14.4],
+       }
    )
    df
    df.interpolate()
diff --git a/doc/source/user_guide/timeseries.rst b/doc/source/user_guide/timeseries.rst
index 11ec90085d9bf..fc25b98daf7b8 100644
--- a/doc/source/user_guide/timeseries.rst
+++ b/doc/source/user_guide/timeseries.rst
@@ -317,7 +317,9 @@ which can be specified. These are computed from the starting point specified by
 
 .. ipython:: python
 
-   pd.to_datetime([1349720105, 1349806505, 1349892905, 1349979305, 1350065705], unit="s")
+   pd.to_datetime(
+       [1349720105, 1349806505, 1349892905, 1349979305, 1350065705], unit="s"
+   )
 
    pd.to_datetime(
        [1349720105100, 1349720105200, 1349720105300, 1349720105400, 1349720105500],
@@ -707,7 +709,9 @@ If the timestamp string is treated as a slice, it can be used to index ``DataFra
 .. ipython:: python
     :okwarning:
 
-    dft_minute = pd.DataFrame({"a": [1, 2, 3], "b": [4, 5, 6]}, index=series_minute.index)
+    dft_minute = pd.DataFrame(
+        {"a": [1, 2, 3], "b": [4, 5, 6]}, index=series_minute.index
+    )
     dft_minute["2011-12-31 23"]
 
 
@@ -748,10 +752,11 @@ With no defaults.
 .. ipython:: python
 
    dft[
-       datetime.datetime(2013, 1, 1, 10, 12, 0): datetime.datetime(2013, 2, 28, 10, 12, 0)
+       datetime.datetime(2013, 1, 1, 10, 12, 0) : datetime.datetime(
+           2013, 2, 28, 10, 12, 0
+       )
    ]
 
-
 Truncating & fancy indexing
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
@@ -1036,8 +1041,15 @@ As an interesting example, let's look at Egypt where a Friday-Saturday weekend i
     # They also observe International Workers' Day so let's
     # add that for a couple of years
 
-    holidays = ["2012-05-01", datetime.datetime(2013, 5, 1), np.datetime64("2014-05-01")]
-    bday_egypt = pd.offsets.CustomBusinessDay(holidays=holidays, weekmask=weekmask_egypt)
+    holidays = [
+        "2012-05-01",
+        datetime.datetime(2013, 5, 1),
+        np.datetime64("2014-05-01"),
+    ]
+    bday_egypt = pd.offsets.CustomBusinessDay(
+        holidays=holidays,
+        weekmask=weekmask_egypt,
+    )
     dt = datetime.datetime(2013, 4, 30)
     dt + 2 * bday_egypt
 
@@ -1417,7 +1429,12 @@ An example of how holidays and holiday calendars are defined:
         rules = [
             USMemorialDay,
             Holiday("July 4th", month=7, day=4, observance=nearest_workday),
-            Holiday("Columbus Day", month=10, day=1, offset=pd.DateOffset(weekday=MO(2))),
+            Holiday(
+                "Columbus Day",
+                month=10,
+                day=1,
+                offset=pd.DateOffset(weekday=MO(2)),
+            ),
         ]
 
 
@@ -2279,7 +2296,12 @@ To return ``dateutil`` time zone objects, append ``dateutil/`` before the string
    rng_dateutil.tz
 
    # dateutil - utc special case
-   rng_utc = pd.date_range("3/6/2012 00:00", periods=3, freq="D", tz=dateutil.tz.tzutc())
+   rng_utc = pd.date_range(
+       "3/6/2012 00:00",
+       periods=3,
+       freq="D",
+       tz=dateutil.tz.tzutc(),
+   )
    rng_utc.tz
 
 .. versionadded:: 0.25.0
@@ -2287,7 +2309,12 @@ To return ``dateutil`` time zone objects, append ``dateutil/`` before the string
 .. ipython:: python
 
    # datetime.timezone
-   rng_utc = pd.date_range("3/6/2012 00:00", periods=3, freq="D", tz=datetime.timezone.utc)
+   rng_utc = pd.date_range(
+       "3/6/2012 00:00",
+       periods=3,
+       freq="D",
+       tz=datetime.timezone.utc,
+   )
    rng_utc.tz
 
 Note that the ``UTC`` time zone is a special case in ``dateutil`` and should be constructed explicitly
@@ -2440,10 +2467,18 @@ control over how they are handled.
 .. ipython:: python
 
    pd.Timestamp(
-       datetime.datetime(2019, 10, 27, 1, 30, 0, 0), tz="dateutil/Europe/London", fold=0
+       datetime.datetime(2019, 10, 27, 1, 30, 0, 0),
+       tz="dateutil/Europe/London",
+       fold=0,
    )
    pd.Timestamp(
-       year=2019, month=10, day=27, hour=1, minute=30, tz="dateutil/Europe/London", fold=1
+       year=2019,
+       month=10,
+       day=27,
+       hour=1,
+       minute=30,
+       tz="dateutil/Europe/London",
+       fold=1,
    )
 
 .. _timeseries.timezone_ambiguous:
diff --git a/doc/source/user_guide/visualization.rst b/doc/source/user_guide/visualization.rst
index 46ab29a52747a..934bc59b29dc5 100644
--- a/doc/source/user_guide/visualization.rst
+++ b/doc/source/user_guide/visualization.rst
@@ -1453,7 +1453,11 @@ Here is an example of one way to easily plot group means with standard deviation
    )
 
    df3 = pd.DataFrame(
-       {"data1": [3, 2, 4, 3, 2, 4, 3, 2], "data2": [6, 5, 7, 5, 4, 5, 6, 5]}, index=ix3
+       {
+           "data1": [3, 2, 4, 3, 2, 4, 3, 2],
+           "data2": [6, 5, 7, 5, 4, 5, 6, 5],
+       },
+       index=ix3,
    )
 
    # Group by index labels and take the means and standard deviations

From aad946880d71fb93ff1034f6dc2fbf58c9cb9df2 Mon Sep 17 00:00:00 2001
From: Daniel Saxton <dsaxton@pm.me>
Date: Sat, 3 Oct 2020 11:45:24 -0500
Subject: [PATCH 09/10] Fix

---
 doc/source/user_guide/timeseries.rst | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/doc/source/user_guide/timeseries.rst b/doc/source/user_guide/timeseries.rst
index fc25b98daf7b8..4141c579e877a 100644
--- a/doc/source/user_guide/timeseries.rst
+++ b/doc/source/user_guide/timeseries.rst
@@ -752,7 +752,7 @@ With no defaults.
 .. ipython:: python
 
    dft[
-       datetime.datetime(2013, 1, 1, 10, 12, 0) : datetime.datetime(
+       datetime.datetime(2013, 1, 1, 10, 12, 0): datetime.datetime(
            2013, 2, 28, 10, 12, 0
        )
    ]

From def814fe54783028ac76d61d3cc1b027938143ed Mon Sep 17 00:00:00 2001
From: Daniel Saxton <dsaxton@pm.me>
Date: Mon, 5 Oct 2020 12:55:19 -0500
Subject: [PATCH 10/10] Fix

---
 doc/source/user_guide/advanced.rst | 11 ++++++---
 doc/source/user_guide/basics.rst   | 36 +++++++++++++++++++++++-------
 doc/source/whatsnew/v0.10.1.rst    |  4 +++-
 doc/source/whatsnew/v0.13.1.rst    |  8 +++++--
 doc/source/whatsnew/v0.14.1.rst    |  4 +++-
 doc/source/whatsnew/v0.17.0.rst    |  4 +++-
 doc/source/whatsnew/v0.19.0.rst    |  4 +++-
 doc/source/whatsnew/v0.8.0.rst     |  4 +++-
 8 files changed, 57 insertions(+), 18 deletions(-)

diff --git a/doc/source/user_guide/advanced.rst b/doc/source/user_guide/advanced.rst
index cec777e0f021e..2cd48ac7adb0e 100644
--- a/doc/source/user_guide/advanced.rst
+++ b/doc/source/user_guide/advanced.rst
@@ -304,7 +304,8 @@ whereas a tuple of lists refer to several values within a level:
 .. ipython:: python
 
    s = pd.Series(
-       [1, 2, 3, 4, 5, 6], index=pd.MultiIndex.from_product([["A", "B"], ["c", "d", "e"]])
+       [1, 2, 3, 4, 5, 6],
+       index=pd.MultiIndex.from_product([["A", "B"], ["c", "d", "e"]]),
    )
    s.loc[[("A", "c"), ("B", "d")]]  # list of tuples
    s.loc[(["A", "B"], ["c", "d"])]  # tuple of lists
@@ -819,7 +820,9 @@ values **not** in the categories, similarly to how you can reindex **any** panda
 
 .. ipython:: python
 
-   df3 = pd.DataFrame({"A": np.arange(3), "B": pd.Series(list("abc")).astype("category")})
+   df3 = pd.DataFrame(
+       {"A": np.arange(3), "B": pd.Series(list("abc")).astype("category")}
+   )
    df3 = df3.set_index("B")
    df3
 
@@ -934,7 +937,9 @@ example, be millisecond offsets.
                np.random.randn(5, 2), index=np.arange(5) * 250.0, columns=list("AB")
            ),
            pd.DataFrame(
-               np.random.randn(6, 2), index=np.arange(4, 10) * 250.1, columns=list("AB")
+               np.random.randn(6, 2),
+               index=np.arange(4, 10) * 250.1,
+               columns=list("AB"),
            ),
        ]
    )
diff --git a/doc/source/user_guide/basics.rst b/doc/source/user_guide/basics.rst
index 8c01913e55318..53fabf94e24e0 100644
--- a/doc/source/user_guide/basics.rst
+++ b/doc/source/user_guide/basics.rst
@@ -464,7 +464,10 @@ which we illustrate:
        {"A": [1.0, np.nan, 3.0, 5.0, np.nan], "B": [np.nan, 2.0, 3.0, np.nan, 6.0]}
    )
    df2 = pd.DataFrame(
-       {"A": [5.0, 2.0, 4.0, np.nan, 3.0, 7.0], "B": [np.nan, np.nan, 3.0, 4.0, 6.0, 8.0]}
+       {
+           "A": [5.0, 2.0, 4.0, np.nan, 3.0, 7.0],
+           "B": [np.nan, np.nan, 3.0, 4.0, 6.0, 8.0],
+       }
    )
    df1
    df2
@@ -712,7 +715,10 @@ Similarly, you can get the most frequently occurring value(s), i.e. the mode, of
     s5 = pd.Series([1, 1, 3, 3, 3, 5, 5, 7, 7, 7])
     s5.mode()
     df5 = pd.DataFrame(
-        {"A": np.random.randint(0, 7, size=50), "B": np.random.randint(-10, 15, size=50)}
+        {
+            "A": np.random.randint(0, 7, size=50),
+            "B": np.random.randint(-10, 15, size=50),
+        }
     )
     df5.mode()
 
@@ -1192,7 +1198,9 @@ to :ref:`merging/joining functionality <merging>`:
 
 .. ipython:: python
 
-   s = pd.Series(["six", "seven", "six", "seven", "six"], index=["a", "b", "c", "d", "e"])
+   s = pd.Series(
+       ["six", "seven", "six", "seven", "six"], index=["a", "b", "c", "d", "e"]
+   )
    t = pd.Series({"six": 6.0, "seven": 7.0})
    s
    s.map(t)
@@ -1494,7 +1502,9 @@ labels).
 
    df = pd.DataFrame(
        {"x": [1, 2, 3, 4, 5, 6], "y": [10, 20, 30, 40, 50, 60]},
-       index=pd.MultiIndex.from_product([["a", "b", "c"], [1, 2]], names=["let", "num"]),
+       index=pd.MultiIndex.from_product(
+           [["a", "b", "c"], [1, 2]], names=["let", "num"]
+       ),
    )
    df
    df.rename_axis(index={"let": "abc"})
@@ -1803,7 +1813,9 @@ used to sort a pandas object by its index levels.
        }
    )
 
-   unsorted_df = df.reindex(index=["a", "d", "c", "b"], columns=["three", "two", "one"])
+   unsorted_df = df.reindex(
+       index=["a", "d", "c", "b"], columns=["three", "two", "one"]
+   )
    unsorted_df
 
    # DataFrame
@@ -1849,7 +1861,9 @@ to use to determine the sorted order.
 
 .. ipython:: python
 
-   df1 = pd.DataFrame({"one": [2, 1, 1, 1], "two": [1, 3, 2, 4], "three": [5, 4, 3, 2]})
+   df1 = pd.DataFrame(
+       {"one": [2, 1, 1, 1], "two": [1, 3, 2, 4], "three": [5, 4, 3, 2]}
+   )
    df1.sort_values(by="two")
 
 The ``by`` parameter can take a list of column names, e.g.:
@@ -1994,7 +2008,9 @@ all levels to ``by``.
 
 .. ipython:: python
 
-   df1.columns = pd.MultiIndex.from_tuples([("a", "one"), ("a", "two"), ("b", "three")])
+   df1.columns = pd.MultiIndex.from_tuples(
+       [("a", "one"), ("a", "two"), ("b", "three")]
+   )
    df1.sort_values(by=("a", "two"))
 
 
@@ -2245,7 +2261,11 @@ to the correct type.
      import datetime
 
      df = pd.DataFrame(
-         [[1, 2], ["a", "b"], [datetime.datetime(2016, 3, 2), datetime.datetime(2016, 3, 2)]]
+         [
+             [1, 2],
+             ["a", "b"],
+             [datetime.datetime(2016, 3, 2), datetime.datetime(2016, 3, 2)],
+         ]
      )
      df = df.T
      df
diff --git a/doc/source/whatsnew/v0.10.1.rst b/doc/source/whatsnew/v0.10.1.rst
index d71a0d5ca68cd..611ac2021fcec 100644
--- a/doc/source/whatsnew/v0.10.1.rst
+++ b/doc/source/whatsnew/v0.10.1.rst
@@ -180,7 +180,9 @@ combined result, by using ``where`` on a selector table.
    store.select("df2_mt")
 
    # as a multiple
-   store.select_as_multiple(["df1_mt", "df2_mt"], where=["A>0", "B>0"], selector="df1_mt")
+   store.select_as_multiple(
+       ["df1_mt", "df2_mt"], where=["A>0", "B>0"], selector="df1_mt"
+   )
 
 .. ipython:: python
    :suppress:
diff --git a/doc/source/whatsnew/v0.13.1.rst b/doc/source/whatsnew/v0.13.1.rst
index 1215786b4cccc..249b9555b7fd4 100644
--- a/doc/source/whatsnew/v0.13.1.rst
+++ b/doc/source/whatsnew/v0.13.1.rst
@@ -101,7 +101,9 @@ Output formatting enhancements
 
   .. ipython:: python
 
-     df = pd.DataFrame([pd.Timestamp("20010101"), pd.Timestamp("20040601")], columns=["age"])
+     df = pd.DataFrame(
+         [pd.Timestamp("20010101"), pd.Timestamp("20040601")], columns=["age"]
+     )
      df["today"] = pd.Timestamp("20130419")
      df["diff"] = df["today"] - df["age"]
      df
@@ -206,7 +208,9 @@ Enhancements
   .. code-block:: python
 
       # Try to infer the format for the index column
-      df = pd.read_csv("foo.csv", index_col=0, parse_dates=True, infer_datetime_format=True)
+      df = pd.read_csv(
+          "foo.csv", index_col=0, parse_dates=True, infer_datetime_format=True
+      )
 
 - ``date_format`` and ``datetime_format`` keywords can now be specified when writing to ``excel``
   files (:issue:`4133`)
diff --git a/doc/source/whatsnew/v0.14.1.rst b/doc/source/whatsnew/v0.14.1.rst
index 78fd182ea86c3..a8f8955c3c1b9 100644
--- a/doc/source/whatsnew/v0.14.1.rst
+++ b/doc/source/whatsnew/v0.14.1.rst
@@ -124,7 +124,9 @@ Enhancements
 
   .. ipython:: python
 
-     rng = pd.date_range("3/6/2012 00:00", periods=10, freq="D", tz="dateutil/Europe/London")
+     rng = pd.date_range(
+         "3/6/2012 00:00", periods=10, freq="D", tz="dateutil/Europe/London"
+     )
      rng.tz
 
   See :ref:`the docs <timeseries.timezone>`.
diff --git a/doc/source/whatsnew/v0.17.0.rst b/doc/source/whatsnew/v0.17.0.rst
index 1658f877f5523..d8f39a7d6e3c0 100644
--- a/doc/source/whatsnew/v0.17.0.rst
+++ b/doc/source/whatsnew/v0.17.0.rst
@@ -786,7 +786,9 @@ Previous behavior:
 
 .. ipython:: python
 
-   df_with_missing = pd.DataFrame({"col1": [0, np.nan, 2], "col2": [1, np.nan, np.nan]})
+   df_with_missing = pd.DataFrame(
+       {"col1": [0, np.nan, 2], "col2": [1, np.nan, np.nan]}
+   )
 
    df_with_missing
 
diff --git a/doc/source/whatsnew/v0.19.0.rst b/doc/source/whatsnew/v0.19.0.rst
index 08ccc1565125f..2ac7b0f54361b 100644
--- a/doc/source/whatsnew/v0.19.0.rst
+++ b/doc/source/whatsnew/v0.19.0.rst
@@ -1091,7 +1091,9 @@ Previously, most ``Index`` classes returned ``np.ndarray``, and ``DatetimeIndex`
 .. ipython:: python
 
    pd.Index([1, 2, 3]).unique()
-   pd.DatetimeIndex(["2011-01-01", "2011-01-02", "2011-01-03"], tz="Asia/Tokyo").unique()
+   pd.DatetimeIndex(
+       ["2011-01-01", "2011-01-02", "2011-01-03"], tz="Asia/Tokyo"
+   ).unique()
 
 .. _whatsnew_0190.api.multiindex:
 
diff --git a/doc/source/whatsnew/v0.8.0.rst b/doc/source/whatsnew/v0.8.0.rst
index 8a84630a28b34..b34c2a5c6a07c 100644
--- a/doc/source/whatsnew/v0.8.0.rst
+++ b/doc/source/whatsnew/v0.8.0.rst
@@ -178,7 +178,9 @@ types. For example, ``'kde'`` is a new option:
 
 .. ipython:: python
 
-   s = pd.Series(np.concatenate((np.random.randn(1000), np.random.randn(1000) * 0.5 + 3)))
+   s = pd.Series(
+       np.concatenate((np.random.randn(1000), np.random.randn(1000) * 0.5 + 3))
+   )
    plt.figure()
    s.hist(density=True, alpha=0.2)
    s.plot(kind="kde")