DOC: doc/source/whatsnew

doc/source/whatsnew/v0.10.0.rst

@@ -49,8 +49,8 @@ talking about:
    :okwarning:
 
    import pandas as pd
-   df = pd.DataFrame(np.random.randn(6, 4),
-                     index=pd.date_range('1/1/2000', periods=6))
+
+   df = pd.DataFrame(np.random.randn(6, 4), index=pd.date_range("1/1/2000", periods=6))
    df
    # deprecated now
    df - df[0]
@@ -184,12 +184,10 @@ labeled the aggregated group with the end of the interval: the next day).
 
     import io
 
-    data = ('a,b,c\n'
-            '1,Yes,2\n'
-            '3,No,4')
+    data = "a,b,c\n" "1,Yes,2\n" "3,No,4"
     print(data)
     pd.read_csv(io.StringIO(data), header=None)
-    pd.read_csv(io.StringIO(data), header=None, prefix='X')
+    pd.read_csv(io.StringIO(data), header=None, prefix="X")
 
 - Values like ``'Yes'`` and ``'No'`` are not interpreted as boolean by default,
   though this can be controlled by new ``true_values`` and ``false_values``
@@ -199,7 +197,7 @@ labeled the aggregated group with the end of the interval: the next day).
 
     print(data)
     pd.read_csv(io.StringIO(data))
-    pd.read_csv(io.StringIO(data), true_values=['Yes'], false_values=['No'])
+    pd.read_csv(io.StringIO(data), true_values=["Yes"], false_values=["No"])
 
 - The file parsers will not recognize non-string values arising from a
   converter function as NA if passed in the ``na_values`` argument. It's better
@@ -210,10 +208,10 @@ labeled the aggregated group with the end of the interval: the next day).
 
 .. ipython:: python
 
-   s = pd.Series([np.nan, 1., 2., np.nan, 4])
+   s = pd.Series([np.nan, 1.0, 2.0, np.nan, 4])
    s
    s.fillna(0)
-   s.fillna(method='pad')
+   s.fillna(method="pad")
 
 Convenience methods ``ffill`` and  ``bfill`` have been added:
 
@@ -229,7 +227,8 @@ Convenience methods ``ffill`` and  ``bfill`` have been added:
   .. ipython:: python
 
       def f(x):
-          return pd.Series([x, x**2], index=['x', 'x^2'])
+          return pd.Series([x, x ** 2], index=["x", "x^2"])
+
 
       s = pd.Series(np.random.rand(5))
       s
@@ -272,20 +271,20 @@ The old behavior of printing out summary information can be achieved via the
 
 .. ipython:: python
 
-   pd.set_option('expand_frame_repr', False)
+   pd.set_option("expand_frame_repr", False)
 
    wide_frame
 
 .. ipython:: python
    :suppress:
 
-   pd.reset_option('expand_frame_repr')
+   pd.reset_option("expand_frame_repr")
 
 The width of each line can be changed via 'line_width' (80 by default):
 
 .. code-block:: python
 
-   pd.set_option('line_width', 40)
+   pd.set_option("line_width", 40)
 
    wide_frame
 

doc/source/whatsnew/v0.10.1.rst

@@ -45,49 +45,51 @@ You may need to upgrade your existing data files. Please visit the
 
    import os
 
-   os.remove('store.h5')
+   os.remove("store.h5")
 
 You can designate (and index) certain columns that you want to be able to
 perform queries on a table, by passing a list to ``data_columns``
 
 .. ipython:: python
 
-   store = pd.HDFStore('store.h5')
-   df = pd.DataFrame(np.random.randn(8, 3),
-                     index=pd.date_range('1/1/2000', periods=8),
-                     columns=['A', 'B', 'C'])
-   df['string'] = 'foo'
-   df.loc[df.index[4:6], 'string'] = np.nan
-   df.loc[df.index[7:9], 'string'] = 'bar'
-   df['string2'] = 'cool'
+   store = pd.HDFStore("store.h5")
+   df = pd.DataFrame(
+       np.random.randn(8, 3),
+       index=pd.date_range("1/1/2000", periods=8),
+       columns=["A", "B", "C"],
+   )
+   df["string"] = "foo"
+   df.loc[df.index[4:6], "string"] = np.nan
+   df.loc[df.index[7:9], "string"] = "bar"
+   df["string2"] = "cool"
    df
 
    # on-disk operations
-   store.append('df', df, data_columns=['B', 'C', 'string', 'string2'])
-   store.select('df', "B>0 and string=='foo'")
+   store.append("df", df, data_columns=["B", "C", "string", "string2"])
+   store.select("df", "B>0 and string=='foo'")
 
    # this is in-memory version of this type of selection
-   df[(df.B > 0) & (df.string == 'foo')]
+   df[(df.B > 0) & (df.string == "foo")]
 
 Retrieving unique values in an indexable or data column.
 
 .. code-block:: python
 
    # note that this is deprecated as of 0.14.0
    # can be replicated by: store.select_column('df','index').unique()
-   store.unique('df', 'index')
-   store.unique('df', 'string')
+   store.unique("df", "index")
+   store.unique("df", "string")
 
 You can now store ``datetime64`` in data columns
 
 .. ipython:: python
 
     df_mixed = df.copy()
-    df_mixed['datetime64'] = pd.Timestamp('20010102')
-    df_mixed.loc[df_mixed.index[3:4], ['A', 'B']] = np.nan
+    df_mixed["datetime64"] = pd.Timestamp("20010102")
+    df_mixed.loc[df_mixed.index[3:4], ["A", "B"]] = np.nan
 
-    store.append('df_mixed', df_mixed)
-    df_mixed1 = store.select('df_mixed')
+    store.append("df_mixed", df_mixed)
+    df_mixed1 = store.select("df_mixed")
     df_mixed1
     df_mixed1.dtypes.value_counts()
 
@@ -97,7 +99,7 @@ columns, this is equivalent to passing a
 
 .. ipython:: python
 
-   store.select('df', columns=['A', 'B'])
+   store.select("df", columns=["A", "B"])
 
 ``HDFStore`` now serializes MultiIndex dataframes when appending tables.
 
@@ -160,29 +162,31 @@ combined result, by using ``where`` on a selector table.
 
 .. ipython:: python
 
-   df_mt = pd.DataFrame(np.random.randn(8, 6),
-                        index=pd.date_range('1/1/2000', periods=8),
-                        columns=['A', 'B', 'C', 'D', 'E', 'F'])
-   df_mt['foo'] = 'bar'
+   df_mt = pd.DataFrame(
+       np.random.randn(8, 6),
+       index=pd.date_range("1/1/2000", periods=8),
+       columns=["A", "B", "C", "D", "E", "F"],
+   )
+   df_mt["foo"] = "bar"
 
    # you can also create the tables individually
-   store.append_to_multiple({'df1_mt': ['A', 'B'], 'df2_mt': None},
-                            df_mt, selector='df1_mt')
+   store.append_to_multiple(
+       {"df1_mt": ["A", "B"], "df2_mt": None}, df_mt, selector="df1_mt"
+   )
    store
 
    # individual tables were created
-   store.select('df1_mt')
-   store.select('df2_mt')
+   store.select("df1_mt")
+   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:
 
    store.close()
-   os.remove('store.h5')
+   os.remove("store.h5")
 
 **Enhancements**
 

doc/source/whatsnew/v0.12.0.rst

@@ -47,7 +47,7 @@ API changes
 
     .. ipython:: python
 
-        p = pd.DataFrame({'first': [4, 5, 8], 'second': [0, 0, 3]})
+        p = pd.DataFrame({"first": [4, 5, 8], "second": [0, 0, 3]})
         p % 0
         p % p
         p / p
@@ -95,8 +95,8 @@ API changes
 
     .. ipython:: python
 
-       df = pd.DataFrame(range(5), index=list('ABCDE'), columns=['a'])
-       mask = (df.a % 2 == 0)
+       df = pd.DataFrame(range(5), index=list("ABCDE"), columns=["a"])
+       mask = df.a % 2 == 0
        mask
 
        # this is what you should use
@@ -141,21 +141,24 @@ API changes
       .. code-block:: python
 
          from pandas.io.parsers import ExcelFile
-         xls = ExcelFile('path_to_file.xls')
-         xls.parse('Sheet1', index_col=None, na_values=['NA'])
+
+         xls = ExcelFile("path_to_file.xls")
+         xls.parse("Sheet1", index_col=None, na_values=["NA"])
 
       With
 
       .. code-block:: python
 
          import pandas as pd
-         pd.read_excel('path_to_file.xls', 'Sheet1', index_col=None, na_values=['NA'])
+
+         pd.read_excel("path_to_file.xls", "Sheet1", index_col=None, na_values=["NA"])
 
     - added top-level function ``read_sql`` that is equivalent to the following
 
       .. code-block:: python
 
          from pandas.io.sql import read_frame
+
          read_frame(...)
 
   - ``DataFrame.to_html`` and ``DataFrame.to_latex`` now accept a path for
@@ -200,7 +203,7 @@ IO enhancements
     .. ipython:: python
        :okwarning:
 
-        df = pd.DataFrame({'a': range(3), 'b': list('abc')})
+        df = pd.DataFrame({"a": range(3), "b": list("abc")})
         print(df)
         html = df.to_html()
         alist = pd.read_html(html, index_col=0)
@@ -248,16 +251,18 @@ IO enhancements
       .. ipython:: python
 
          from pandas._testing import makeCustomDataframe as mkdf
+
          df = mkdf(5, 3, r_idx_nlevels=2, c_idx_nlevels=4)
-         df.to_csv('mi.csv')
-         print(open('mi.csv').read())
-         pd.read_csv('mi.csv', header=[0, 1, 2, 3], index_col=[0, 1])
+         df.to_csv("mi.csv")
+         print(open("mi.csv").read())
+         pd.read_csv("mi.csv", header=[0, 1, 2, 3], index_col=[0, 1])
 
       .. ipython:: python
          :suppress:
 
          import os
-         os.remove('mi.csv')
+
+         os.remove("mi.csv")
 
   - Support for ``HDFStore`` (via ``PyTables 3.0.0``) on Python3
 
@@ -304,8 +309,8 @@ Other enhancements
 
     .. ipython:: python
 
-        df = pd.DataFrame({'a': list('ab..'), 'b': [1, 2, 3, 4]})
-        df.replace(regex=r'\s*\.\s*', value=np.nan)
+        df = pd.DataFrame({"a": list("ab.."), "b": [1, 2, 3, 4]})
+        df.replace(regex=r"\s*\.\s*", value=np.nan)
 
     to replace all occurrences of the string ``'.'`` with zero or more
     instances of surrounding white space with ``NaN``.
@@ -314,7 +319,7 @@ Other enhancements
 
     .. ipython:: python
 
-        df.replace('.', np.nan)
+        df.replace(".", np.nan)
 
     to replace all occurrences of the string ``'.'`` with ``NaN``.
 
@@ -359,16 +364,16 @@ Other enhancements
 
     .. ipython:: python
 
-       dff = pd.DataFrame({'A': np.arange(8), 'B': list('aabbbbcc')})
-       dff.groupby('B').filter(lambda x: len(x) > 2)
+       dff = pd.DataFrame({"A": np.arange(8), "B": list("aabbbbcc")})
+       dff.groupby("B").filter(lambda x: len(x) > 2)
 
     Alternatively, instead of dropping the offending groups, we can return a
     like-indexed objects where the groups that do not pass the filter are
     filled with NaNs.
 
     .. ipython:: python
 
-       dff.groupby('B').filter(lambda x: len(x) > 2, dropna=False)
+       dff.groupby("B").filter(lambda x: len(x) > 2, dropna=False)
 
   - Series and DataFrame hist methods now take a ``figsize`` argument (:issue:`3834`)
 
@@ -397,17 +402,18 @@ Experimental features
 
       from pandas.tseries.offsets import CustomBusinessDay
       from datetime import datetime
+
       # As an interesting example, let's look at Egypt where
       # a Friday-Saturday weekend is observed.
-      weekmask_egypt = 'Sun Mon Tue Wed Thu'
+      weekmask_egypt = "Sun Mon Tue Wed Thu"
       # They also observe International Workers' Day so let's
       # add that for a couple of years
-      holidays = ['2012-05-01', datetime(2013, 5, 1), np.datetime64('2014-05-01')]
+      holidays = ["2012-05-01", datetime(2013, 5, 1), np.datetime64("2014-05-01")]
       bday_egypt = CustomBusinessDay(holidays=holidays, weekmask=weekmask_egypt)
       dt = datetime(2013, 4, 30)
       print(dt + 2 * bday_egypt)
       dts = pd.date_range(dt, periods=5, freq=bday_egypt)
-      print(pd.Series(dts.weekday, dts).map(pd.Series('Mon Tue Wed Thu Fri Sat Sun'.split())))
+      print(pd.Series(dts.weekday, dts).map(pd.Series("Mon Tue Wed Thu Fri Sat Sun".split())))
 
 Bug fixes
 ~~~~~~~~~
@@ -430,14 +436,14 @@ Bug fixes
     .. ipython:: python
         :okwarning:
 
-        strs = 'go', 'bow', 'joe', 'slow'
+        strs = "go", "bow", "joe", "slow"
         ds = pd.Series(strs)
 
         for s in ds.str:
             print(s)
 
         s
-        s.dropna().values.item() == 'w'
+        s.dropna().values.item() == "w"
 
     The last element yielded by the iterator will be a ``Series`` containing
     the last element of the longest string in the ``Series`` with all other