From 2976283611fc711c2452612d8fd45225cf7a308d Mon Sep 17 00:00:00 2001
From: Erfan Nariman <erfan.nariman@briccanalytics.nl>
Date: Thu, 1 Oct 2020 19:04:31 +0200
Subject: [PATCH 1/6] reformat documentation

---
 .../06_calculate_statistics.rst               |  6 ++-
 .../07_reshape_table_layout.rst               | 39 ++++++++++++-------
 .../intro_tutorials/08_combine_dataframes.rst | 14 +++++--
 .../intro_tutorials/09_timeseries.rst         |  7 ++--
 .../intro_tutorials/10_text_data.rst          |  5 ++-
 test.py                                       |  3 ++
 6 files changed, 49 insertions(+), 25 deletions(-)
 create mode 100644 test.py

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 bd85160d2622a..c7cb54cddb2bf 100644
--- a/doc/source/getting_started/intro_tutorials/06_calculate_statistics.rst
+++ b/doc/source/getting_started/intro_tutorials/06_calculate_statistics.rst
@@ -122,8 +122,10 @@ aggregating statistics for given columns can be defined using the
 
 .. ipython:: python
 
-    titanic.agg({'Age': ['min', 'max', 'median', 'skew'],
-                 'Fare': ['min', 'max', 'median', 'mean']})
+    titanic.agg({
+        "Age": ["min", "max", "median", "skew"],
+        "Fare": ["min", "max", "median", "mean"]
+    })
 
 .. raw:: html
 
diff --git a/doc/source/getting_started/intro_tutorials/07_reshape_table_layout.rst b/doc/source/getting_started/intro_tutorials/07_reshape_table_layout.rst
index c16fec6aaba9f..a04a2a5743de5 100644
--- a/doc/source/getting_started/intro_tutorials/07_reshape_table_layout.rst
+++ b/doc/source/getting_started/intro_tutorials/07_reshape_table_layout.rst
@@ -101,8 +101,11 @@ measurement.
 
 .. ipython:: python
 
-    air_quality = pd.read_csv("data/air_quality_long.csv",
-                              index_col="date.utc", parse_dates=True)
+    air_quality = pd.read_csv(
+        "data/air_quality_long.csv",
+        index_col="date.utc",
+        parse_dates=True
+    )
     air_quality.head()
 
 .. raw:: html
@@ -247,8 +250,10 @@ I want the mean concentrations for :math:`NO_2` and :math:`PM_{2.5}` in each of
 
 .. ipython:: python
 
-    air_quality.pivot_table(values="value", index="location",
-                            columns="parameter", aggfunc="mean")
+    air_quality.pivot_table(
+        values="value", index="location",
+        columns="parameter", aggfunc="mean"
+)
 
 In the case of :meth:`~DataFrame.pivot`, the data is only rearranged. When multiple
 values need to be aggregated (in this specific case, the values on
@@ -266,9 +271,13 @@ the ``margin`` parameter to ``True``:
 
 .. ipython:: python
 
-    air_quality.pivot_table(values="value", index="location",
-                            columns="parameter", aggfunc="mean",
-                            margins=True)
+    air_quality.pivot_table(
+        values="value",
+        index="location",
+        columns="parameter",
+        aggfunc="mean",
+        margins=True
+    )
 
 .. raw:: html
 
@@ -345,12 +354,16 @@ The :func:`pandas.melt` method can be defined in more detail:
 
 .. ipython:: python
 
-    no_2 = no2_pivoted.melt(id_vars="date.utc",
-                            value_vars=["BETR801",
-                                        "FR04014",
-                                        "London Westminster"],
-                            value_name="NO_2",
-                            var_name="id_location")
+    no_2 = no2_pivoted.melt(
+        id_vars="date.utc",
+        value_vars=[
+            "BETR801",
+            "FR04014",
+            "London Westminster"
+        ],
+        value_name="NO_2",
+        var_name="id_location"
+    )
     no_2.head()
 
 The result in the same, but in more detail defined:
diff --git a/doc/source/getting_started/intro_tutorials/08_combine_dataframes.rst b/doc/source/getting_started/intro_tutorials/08_combine_dataframes.rst
index d6da9a0aa4f22..ecbfc61cfb4d3 100644
--- a/doc/source/getting_started/intro_tutorials/08_combine_dataframes.rst
+++ b/doc/source/getting_started/intro_tutorials/08_combine_dataframes.rst
@@ -155,8 +155,10 @@ index. For example:
 
 .. ipython:: python
 
-    air_quality_ = pd.concat([air_quality_pm25, air_quality_no2],
-                             keys=["PM25", "NO2"])
+    air_quality_ = pd.concat([
+        air_quality_pm25, air_quality_no2],
+        keys=["PM25", "NO2"
+    ])
 
 .. ipython:: python
 
@@ -233,8 +235,12 @@ Add the station coordinates, provided by the stations metadata table, to the cor
 
 .. ipython:: python
 
-    air_quality = pd.merge(air_quality, stations_coord,
-                           how='left', on='location')
+    air_quality = pd.merge(
+        air_quality,
+        stations_coord,
+        how='left',
+        on='location'
+    )
     air_quality.head()
 
 Using the :meth:`~pandas.merge` function, for each of the rows in the
diff --git a/doc/source/getting_started/intro_tutorials/09_timeseries.rst b/doc/source/getting_started/intro_tutorials/09_timeseries.rst
index 19351e0e3bc75..598d3514baa15 100644
--- a/doc/source/getting_started/intro_tutorials/09_timeseries.rst
+++ b/doc/source/getting_started/intro_tutorials/09_timeseries.rst
@@ -204,10 +204,9 @@ Plot the typical :math:`NO_2` pattern during the day of our time series of all s
 .. ipython:: python
 
     fig, axs = plt.subplots(figsize=(12, 4))
-    air_quality.groupby(
-        air_quality["datetime"].dt.hour)["value"].mean().plot(kind='bar',
-                                                              rot=0,
-                                                              ax=axs)
+    air_quality.groupby(air_quality["datetime"].dt.hour)["value"].mean().plot(
+        kind='bar', rot=0, ax=axs
+    )
     plt.xlabel("Hour of the day");  # custom x label using matplotlib
     @savefig 09_bar_chart.png
     plt.ylabel("$NO_2 (µg/m^3)$");
diff --git a/doc/source/getting_started/intro_tutorials/10_text_data.rst b/doc/source/getting_started/intro_tutorials/10_text_data.rst
index 93ad35fb1960b..a8ad4b5e03788 100644
--- a/doc/source/getting_started/intro_tutorials/10_text_data.rst
+++ b/doc/source/getting_started/intro_tutorials/10_text_data.rst
@@ -224,8 +224,9 @@ In the "Sex" column, replace values of "male" by "M" and values of "female" by "
 
 .. ipython:: python
 
-    titanic["Sex_short"] = titanic["Sex"].replace({"male": "M",
-                                                   "female": "F"})
+    titanic["Sex_short"] = titanic["Sex"].replace({
+        "male": "M", "female": "F"
+    })
     titanic["Sex_short"]
 
 Whereas :meth:`~Series.replace` is not a string method, it provides a convenient way
diff --git a/test.py b/test.py
new file mode 100644
index 0000000000000..1950b15c290c6
--- /dev/null
+++ b/test.py
@@ -0,0 +1,3 @@
+titanic["Sex_short"] = titanic["Sex"].replace({
+    "male": "M", "female": "F"
+})
\ No newline at end of file

From ad7bb1d77bc8de9ee54799916563952bf370c878 Mon Sep 17 00:00:00 2001
From: Erfan Nariman <erfan.nariman@briccanalytics.nl>
Date: Thu, 1 Oct 2020 19:06:33 +0200
Subject: [PATCH 2/6] remove test file

---
 test.py | 3 ---
 1 file changed, 3 deletions(-)
 delete mode 100644 test.py

diff --git a/test.py b/test.py
deleted file mode 100644
index 1950b15c290c6..0000000000000
--- a/test.py
+++ /dev/null
@@ -1,3 +0,0 @@
-titanic["Sex_short"] = titanic["Sex"].replace({
-    "male": "M", "female": "F"
-})
\ No newline at end of file

From 4aa267acc1c08bb98b45417573f47578cdca5430 Mon Sep 17 00:00:00 2001
From: Erfan Nariman <erfan.nariman@briccanalytics.nl>
Date: Thu, 1 Oct 2020 19:19:53 +0200
Subject: [PATCH 3/6] more code formatting

---
 doc/source/user_guide/10min.rst  | 76 ++++++++++++++++++++------------
 doc/source/user_guide/sparse.rst | 35 ++++++++-------
 2 files changed, 66 insertions(+), 45 deletions(-)

diff --git a/doc/source/user_guide/10min.rst b/doc/source/user_guide/10min.rst
index c3746cbe777a3..b59a684faea06 100644
--- a/doc/source/user_guide/10min.rst
+++ b/doc/source/user_guide/10min.rst
@@ -43,12 +43,16 @@ Creating a :class:`DataFrame` by passing a dict of objects that can be converted
 
 .. ipython:: python
 
-   df2 = pd.DataFrame({'A': 1.,
-                       'B': pd.Timestamp('20130102'),
-                       'C': pd.Series(1, index=list(range(4)), dtype='float32'),
-                       'D': np.array([3] * 4, dtype='int32'),
-                       'E': pd.Categorical(["test", "train", "test", "train"]),
-                       'F': 'foo'})
+   df2 = pd.DataFrame(
+       {
+           "A": 1.0,
+           "B": pd.Timestamp("20130102"),
+           "C": pd.Series(1, index=list(range(4)), dtype="float32"),
+           "D": np.array([3] * 4, dtype="int32"),
+           "E": pd.Categorical(["test", "train", "test", "train"]),
+           "F": "foo",
+       }
+   )
    df2
 
 The columns of the resulting :class:`DataFrame` have different
@@ -512,12 +516,14 @@ See the :ref:`Grouping section <groupby>`.
 
 .. ipython:: python
 
-   df = pd.DataFrame({'A': ['foo', 'bar', 'foo', 'bar',
-                            'foo', 'bar', 'foo', 'foo'],
-                      'B': ['one', 'one', 'two', 'three',
-                            'two', 'two', 'one', 'three'],
-                      'C': np.random.randn(8),
-                      'D': np.random.randn(8)})
+   df = pd.DataFrame(
+       {
+           "A": ["foo", "bar", "foo", "bar", "foo", "bar", "foo", "foo"],
+           "B": ["one", "one", "two", "three", "two", "two", "one", "three"],
+           "C": np.random.randn(8),
+           "D": np.random.randn(8),
+       }
+   )
    df
 
 Grouping and then applying the :meth:`~pandas.core.groupby.GroupBy.sum` function to the resulting
@@ -545,10 +551,14 @@ Stack
 
 .. ipython:: python
 
-   tuples = list(zip(*[['bar', 'bar', 'baz', 'baz',
-                        'foo', 'foo', 'qux', 'qux'],
-                       ['one', 'two', 'one', 'two',
-                        'one', 'two', 'one', 'two']]))
+   tuples = list(
+       zip(
+           *[
+               ["bar", "bar", "baz", "baz", "foo", "foo", "qux", "qux"],
+               ["one", "two", "one", "two", "one", "two", "one", "two"],
+           ]
+       )
+   )
    index = pd.MultiIndex.from_tuples(tuples, names=['first', 'second'])
    df = pd.DataFrame(np.random.randn(8, 2), index=index, columns=['A', 'B'])
    df2 = df[:4]
@@ -578,11 +588,15 @@ See the section on :ref:`Pivot Tables <reshaping.pivot>`.
 
 .. ipython:: python
 
-   df = pd.DataFrame({'A': ['one', 'one', 'two', 'three'] * 3,
-                      'B': ['A', 'B', 'C'] * 4,
-                      'C': ['foo', 'foo', 'foo', 'bar', 'bar', 'bar'] * 2,
-                      'D': np.random.randn(12),
-                      'E': np.random.randn(12)})
+   df = pd.DataFrame(
+       {
+           "A": ["one", "one", "two", "three"] * 3,
+           "B": ["A", "B", "C"] * 4,
+           "C": ["foo", "foo", "foo", "bar", "bar", "bar"] * 2,
+           "D": np.random.randn(12),
+           "E": np.random.randn(12),
+       }
+   )
    df
 
 We can produce pivot tables from this data very easily:
@@ -653,8 +667,10 @@ pandas can include categorical data in a :class:`DataFrame`. For full docs, see
 
 .. ipython:: python
 
-    df = pd.DataFrame({"id": [1, 2, 3, 4, 5, 6],
-                       "raw_grade": ['a', 'b', 'b', 'a', 'a', 'e']})
+   df = pd.DataFrame(
+       {"id": [1, 2, 3, 4, 5, 6], "raw_grade": ["a", "b", "b", "a", "a", "e"]}
+   )
+
 
 Convert the raw grades to a categorical data type.
 
@@ -674,8 +690,9 @@ Reorder the categories and simultaneously add the missing categories (methods un
 
 .. ipython:: python
 
-    df["grade"] = df["grade"].cat.set_categories(["very bad", "bad", "medium",
-                                                  "good", "very good"])
+    df["grade"] = df["grade"].cat.set_categories(
+        ["very bad", "bad", "medium","good", "very good"]
+    )
     df["grade"]
 
 Sorting is per order in the categories, not lexical order.
@@ -705,8 +722,7 @@ We use the standard convention for referencing the matplotlib API:
 
 .. ipython:: python
 
-   ts = pd.Series(np.random.randn(1000),
-                  index=pd.date_range('1/1/2000', periods=1000))
+   ts = pd.Series(np.random.randn(1000), index=pd.date_range("1/1/2000", periods=1000))
    ts = ts.cumsum()
 
    @savefig series_plot_basic.png
@@ -717,8 +733,10 @@ of the columns with labels:
 
 .. ipython:: python
 
-   df = pd.DataFrame(np.random.randn(1000, 4), index=ts.index,
-                     columns=['A', 'B', 'C', 'D'])
+   df = pd.DataFrame(
+       np.random.randn(1000, 4), index=ts.index, columns=["A", "B", "C", "D"]
+   )
+
    df = df.cumsum()
 
    plt.figure()
diff --git a/doc/source/user_guide/sparse.rst b/doc/source/user_guide/sparse.rst
index 35e0e0fb86472..62e35cb994faf 100644
--- a/doc/source/user_guide/sparse.rst
+++ b/doc/source/user_guide/sparse.rst
@@ -303,14 +303,17 @@ The method requires a ``MultiIndex`` with two or more levels.
 .. ipython:: python
 
    s = pd.Series([3.0, np.nan, 1.0, 3.0, np.nan, np.nan])
-   s.index = pd.MultiIndex.from_tuples([(1, 2, 'a', 0),
-                                        (1, 2, 'a', 1),
-                                        (1, 1, 'b', 0),
-                                        (1, 1, 'b', 1),
-                                        (2, 1, 'b', 0),
-                                        (2, 1, 'b', 1)],
-                                       names=['A', 'B', 'C', 'D'])
-   s
+   s.index = pd.MultiIndex.from_tuples(
+       [
+           (1, 2, "a", 0),
+           (1, 2, "a", 1),
+           (1, 1, "b", 0),
+           (1, 1, "b", 1),
+           (2, 1, "b", 0),
+           (2, 1, "b", 1),
+       ],
+       names=["A", "B", "C", "D"],
+   )
    ss = s.astype('Sparse')
    ss
 
@@ -318,9 +321,10 @@ In the example below, we transform the ``Series`` to a sparse representation of
 
 .. ipython:: python
 
-   A, rows, columns = ss.sparse.to_coo(row_levels=['A', 'B'],
-                                       column_levels=['C', 'D'],
-                                       sort_labels=True)
+   A, rows, columns = ss.sparse.to_coo(
+       row_levels=["A", "B"], column_levels=["C", "D"], sort_labels=True
+   )
+
 
    A
    A.todense()
@@ -331,9 +335,9 @@ Specifying different row and column labels (and not sorting them) yields a diffe
 
 .. ipython:: python
 
-   A, rows, columns = ss.sparse.to_coo(row_levels=['A', 'B', 'C'],
-                                       column_levels=['D'],
-                                       sort_labels=False)
+   A, rows, columns = ss.sparse.to_coo(
+       row_levels=["A", "B", "C"], column_levels=["D"], sort_labels=False
+   )
 
    A
    A.todense()
@@ -345,8 +349,7 @@ A convenience method :meth:`Series.sparse.from_coo` is implemented for creating
 .. ipython:: python
 
    from scipy import sparse
-   A = sparse.coo_matrix(([3.0, 1.0, 2.0], ([1, 0, 0], [0, 2, 3])),
-                         shape=(3, 4))
+   A = sparse.coo_matrix(([3.0, 1.0, 2.0], ([1, 0, 0], [0, 2, 3])), shape=(3, 4))
    A
    A.todense()
 

From 9226749ab0fb38fc0403bb738c2665625e214a0d Mon Sep 17 00:00:00 2001
From: Erfan Nariman <erfan.nariman@briccanalytics.nl>
Date: Thu, 1 Oct 2020 23:07:34 +0200
Subject: [PATCH 4/6] all changes with black

---
 .../intro_tutorials/06_calculate_statistics.rst |  7 +++----
 .../intro_tutorials/07_reshape_table_layout.rst | 17 +++++------------
 .../intro_tutorials/08_combine_dataframes.rst   | 12 ++----------
 .../intro_tutorials/10_text_data.rst            |  4 +---
 4 files changed, 11 insertions(+), 29 deletions(-)

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 c7cb54cddb2bf..7e919777fdf03 100644
--- a/doc/source/getting_started/intro_tutorials/06_calculate_statistics.rst
+++ b/doc/source/getting_started/intro_tutorials/06_calculate_statistics.rst
@@ -122,10 +122,9 @@ aggregating statistics for given columns can be defined using the
 
 .. ipython:: python
 
-    titanic.agg({
-        "Age": ["min", "max", "median", "skew"],
-        "Fare": ["min", "max", "median", "mean"]
-    })
+    titanic.agg(
+        {"Age": ["min", "max", "median", "skew"], "Fare": ["min", "max", "median", "mean"]}
+    )
 
 .. raw:: html
 
diff --git a/doc/source/getting_started/intro_tutorials/07_reshape_table_layout.rst b/doc/source/getting_started/intro_tutorials/07_reshape_table_layout.rst
index a04a2a5743de5..706456b47273a 100644
--- a/doc/source/getting_started/intro_tutorials/07_reshape_table_layout.rst
+++ b/doc/source/getting_started/intro_tutorials/07_reshape_table_layout.rst
@@ -102,9 +102,7 @@ measurement.
 .. ipython:: python
 
     air_quality = pd.read_csv(
-        "data/air_quality_long.csv",
-        index_col="date.utc",
-        parse_dates=True
+        "data/air_quality_long.csv", index_col="date.utc", parse_dates=True
     )
     air_quality.head()
 
@@ -251,9 +249,8 @@ I want the mean concentrations for :math:`NO_2` and :math:`PM_{2.5}` in each of
 .. ipython:: python
 
     air_quality.pivot_table(
-        values="value", index="location",
-        columns="parameter", aggfunc="mean"
-)
+        values="value", index="location", columns="parameter", aggfunc="mean"
+    )
 
 In the case of :meth:`~DataFrame.pivot`, the data is only rearranged. When multiple
 values need to be aggregated (in this specific case, the values on
@@ -356,13 +353,9 @@ The :func:`pandas.melt` method can be defined in more detail:
 
     no_2 = no2_pivoted.melt(
         id_vars="date.utc",
-        value_vars=[
-            "BETR801",
-            "FR04014",
-            "London Westminster"
-        ],
+        value_vars=["BETR801", "FR04014", "London Westminster"],
         value_name="NO_2",
-        var_name="id_location"
+        var_name="id_location",
     )
     no_2.head()
 
diff --git a/doc/source/getting_started/intro_tutorials/08_combine_dataframes.rst b/doc/source/getting_started/intro_tutorials/08_combine_dataframes.rst
index ecbfc61cfb4d3..be4c284912db4 100644
--- a/doc/source/getting_started/intro_tutorials/08_combine_dataframes.rst
+++ b/doc/source/getting_started/intro_tutorials/08_combine_dataframes.rst
@@ -155,10 +155,7 @@ index. For example:
 
 .. ipython:: python
 
-    air_quality_ = pd.concat([
-        air_quality_pm25, air_quality_no2],
-        keys=["PM25", "NO2"
-    ])
+    air_quality_ = pd.concat([air_quality_pm25, air_quality_no2], keys=["PM25", "NO2"])
 
 .. ipython:: python
 
@@ -235,12 +232,7 @@ Add the station coordinates, provided by the stations metadata table, to the cor
 
 .. ipython:: python
 
-    air_quality = pd.merge(
-        air_quality,
-        stations_coord,
-        how='left',
-        on='location'
-    )
+    air_quality = pd.merge(air_quality, stations_coord, how="left", on="location")
     air_quality.head()
 
 Using the :meth:`~pandas.merge` function, for each of the rows in the
diff --git a/doc/source/getting_started/intro_tutorials/10_text_data.rst b/doc/source/getting_started/intro_tutorials/10_text_data.rst
index a8ad4b5e03788..b7fb99a98d78f 100644
--- a/doc/source/getting_started/intro_tutorials/10_text_data.rst
+++ b/doc/source/getting_started/intro_tutorials/10_text_data.rst
@@ -224,9 +224,7 @@ In the "Sex" column, replace values of "male" by "M" and values of "female" by "
 
 .. ipython:: python
 
-    titanic["Sex_short"] = titanic["Sex"].replace({
-        "male": "M", "female": "F"
-    })
+    titanic["Sex_short"] = titanic["Sex"].replace({"male": "M", "female": "F"})
     titanic["Sex_short"]
 
 Whereas :meth:`~Series.replace` is not a string method, it provides a convenient way

From 8705ae9895b5ea3cc6439eb31772d896d95f9cae Mon Sep 17 00:00:00 2001
From: Erfan Nariman <erfan.nariman@briccanalytics.nl>
Date: Thu, 1 Oct 2020 23:39:01 +0200
Subject: [PATCH 5/6] add whitespace

---
 doc/source/user_guide/10min.rst | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/doc/source/user_guide/10min.rst b/doc/source/user_guide/10min.rst
index b59a684faea06..673f8689736f1 100644
--- a/doc/source/user_guide/10min.rst
+++ b/doc/source/user_guide/10min.rst
@@ -691,7 +691,7 @@ Reorder the categories and simultaneously add the missing categories (methods un
 .. ipython:: python
 
     df["grade"] = df["grade"].cat.set_categories(
-        ["very bad", "bad", "medium","good", "very good"]
+        ["very bad", "bad", "medium", "good", "very good"]
     )
     df["grade"]
 

From 93404d69e4d1d2633e22bdb226a732f355363ecb Mon Sep 17 00:00:00 2001
From: Daniel Saxton <2658661+dsaxton@users.noreply.github.com>
Date: Thu, 1 Oct 2020 18:38:28 -0500
Subject: [PATCH 6/6] Update
 doc/source/getting_started/intro_tutorials/07_reshape_table_layout.rst

---
 .../getting_started/intro_tutorials/07_reshape_table_layout.rst | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/doc/source/getting_started/intro_tutorials/07_reshape_table_layout.rst b/doc/source/getting_started/intro_tutorials/07_reshape_table_layout.rst
index 706456b47273a..20c36133330c4 100644
--- a/doc/source/getting_started/intro_tutorials/07_reshape_table_layout.rst
+++ b/doc/source/getting_started/intro_tutorials/07_reshape_table_layout.rst
@@ -273,7 +273,7 @@ the ``margin`` parameter to ``True``:
         index="location",
         columns="parameter",
         aggfunc="mean",
-        margins=True
+        margins=True,
     )
 
 .. raw:: html