PEP8 fixes

Author: TomAugspurger

pandas/core/reshape/pivot.py

@@ -50,11 +50,11 @@ def pivot_table(data, values=None, index=None, columns=None, aggfunc='mean',
 
     Examples
     --------
-    >>> df = pd.DataFrame({"A": ["foo", "foo", "foo", "foo", "foo", 
-    ...                          "bar", "bar", "bar", "bar"], 
-    ...                    "B": ["one", "one", "one", "two", "two", 
+    >>> df = pd.DataFrame({"A": ["foo", "foo", "foo", "foo", "foo",
+    ...                          "bar", "bar", "bar", "bar"],
+    ...                    "B": ["one", "one", "one", "two", "two",
     ...                          "one", "one", "two", "two"],
-    ...                    "C": ["small", "large", "large", "small", 
+    ...                    "C": ["small", "large", "large", "small",
     ...                          "small", "large", "small", "small",
     ...                          "large"],
     ...                    "D": [1, 2, 2, 3, 3, 4, 5, 6, 7]})
@@ -453,7 +453,7 @@ def crosstab(index, columns, values=None, rownames=None, colnames=None,
     >>> b = np.array(["one", "one", "one", "two", "one", "one",
     ...               "one", "two", "two", "two", "one"], dtype=object)
     >>> c = np.array(["dull", "dull", "shiny", "dull", "dull", "shiny",
-    ...               "shiny", "dull", "shiny", "shiny", "shiny"], 
+    ...               "shiny", "dull", "shiny", "shiny", "shiny"],
     ...               dtype=object)
 
     >>> pd.crosstab(a, [b, c], rownames=['a'], colnames=['b', 'c'])

pandas/core/reshape/reshape.py

@@ -48,13 +48,13 @@ class _Unstacker(object):
     >>> import pandas as pd
     >>> index = pd.MultiIndex.from_tuples([('one', 'a'), ('one', 'b'),
     ...                                    ('two', 'a'), ('two', 'b')])
-    >>> s = pd.Series(np.arange(1, 5), index=index)
+    >>> s = pd.Series(np.arange(1, 5, dtype=np.int64), index=index)
     >>> s
     one  a    1
          b    2
     two  a    3
          b    4
-    dtype: int32
+    dtype: int64
 
     >>> s.unstack(level=-1)
          a  b
@@ -988,17 +988,18 @@ def wide_to_long(df, stubnames, i, j, sep="", suffix='\d+'):
     ...                    'B(quarterly)-2011': np.random.rand(3),
     ...                    'X' : np.random.randint(3, size=3)})
     >>> df['id'] = df.index
-    >>> df # doctest: +NORMALIZE_WHITESPACE
-       A(quarterly)-2010  A(quarterly)-2011  B(quarterly)-2010  B(quarterly)-2011  \
-    0           0.548814           0.544883           0.437587           0.383442
-    1           0.715189           0.423655           0.891773           0.791725
-    2           0.602763           0.645894           0.963663           0.528895
+    >>> df # doctest: +NORMALIZE_WHITESPACE, +ELLIPSIS
+       A(quarterly)-2010  A(quarterly)-2011  B(quarterly)-2010  ...
+    0           0.548814           0.544883           0.437587  ...
+    1           0.715189           0.423655           0.891773  ...
+    2           0.602763           0.645894           0.963663  ...
        X  id
     0  0   0
     1  1   1
     2  1   2
-    
-    >>> pd.wide_to_long(df, ['A(quarterly)', 'B(quarterly)'], i='id', j='year', sep='-')
+
+    >>> pd.wide_to_long(df, ['A(quarterly)', 'B(quarterly)'], i='id',
+    ...                 j='year', sep='-')
     ... # doctest: +NORMALIZE_WHITESPACE
              X  A(quarterly)  B(quarterly)
     id year
@@ -1012,7 +1013,10 @@ def wide_to_long(df, stubnames, i, j, sep="", suffix='\d+'):
     If we have many columns, we could also use a regex to find our
     stubnames and pass that list on to wide_to_long
 
-    >>> stubnames = sorted(set([match[0] for match in df.columns.str.findall('[A-B]\(.*\)').values if match != [] ]))
+    >>> stubnames = sorted(
+    ...     set([match[0] for match in df.columns.str.findall(
+    ...         r'[A-B]\(.*\)').values if match != [] ])
+    ... )
     >>> list(stubnames)
     ['A(quarterly)', 'B(quarterly)']
 
@@ -1133,7 +1137,7 @@ def get_dummies(data, prefix=None, prefix_sep='_', dummy_na=False,
     1  0  1    0
     2  0  0    1
 
-    >>> df = pd.DataFrame({'A': ['a', 'b', 'a'], 'B': ['b', 'a', 'c'], 
+    >>> df = pd.DataFrame({'A': ['a', 'b', 'a'], 'B': ['b', 'a', 'c'],
     ...                    'C': [1, 2, 3]})
 
     >>> pd.get_dummies(df, prefix=['col1', 'col2'])

pandas/core/reshape/tile.py

@@ -75,17 +75,18 @@ def cut(x, bins, right=True, labels=None, retbins=False, precision=3,
     Examples
     --------
     >>> pd.cut(np.array([.2, 1.4, 2.5, 6.2, 9.7, 2.1]), 3, retbins=True)
-    ([(0.19, 3.367], (0.19, 3.367], (0.19, 3.367], (3.367, 6.533], (6.533, 9.7], (0.19, 3.367]]
-    Categories (3, interval[float64]): [(0.19, 3.367] < (3.367, 6.533] < (6.533, 9.7]], array([ 0.1905    ,  3.36666667,  6.53333333,  9.7       ]))
+    ... # doctest: +ELLIPSIS
+    ([(0.19, 3.367], (0.19, 3.367], (0.19, 3.367], (3.367, 6.533], ...
+    Categories (3, interval[float64]): [(0.19, 3.367] < (3.367, 6.533] ...
 
     >>> pd.cut(np.array([.2, 1.4, 2.5, 6.2, 9.7, 2.1]),
-    ...                                  3, labels=["good","medium","bad"])
+    ...        3, labels=["good", "medium", "bad"])
     ... # doctest: +SKIP
     [good, good, good, medium, bad, good]
     Categories (3, object): [good < medium < bad]
 
     >>> pd.cut(np.ones(5), 4, labels=False)
-    array([1, 1, 1, 1, 1], dtype=int64)
+    array([1, 1, 1, 1, 1])
     """
     # NOTE: this binning code is changed a bit from histogram for var(x) == 0
 
@@ -181,15 +182,17 @@ def qcut(x, q, labels=None, retbins=False, precision=3, duplicates='raise'):
     Examples
     --------
     >>> pd.qcut(range(5), 4)
+    ... # doctest: +ELLIPSIS
     [(-0.001, 1.0], (-0.001, 1.0], (1.0, 2.0], (2.0, 3.0], (3.0, 4.0]]
-    Categories (4, interval[float64]): [(-0.001, 1.0] < (1.0, 2.0] < (2.0, 3.0] < (3.0, 4.0]]
+    Categories (4, interval[float64]): [(-0.001, 1.0] < (1.0, 2.0] ...
 
-    >>> pd.qcut(range(5), 3, labels=["good","medium","bad"])
+    >>> pd.qcut(range(5), 3, labels=["good", "medium", "bad"])
+    ... # doctest: +SKIP
     [good, good, medium, bad, bad]
     Categories (3, object): [good < medium < bad]
 
     >>> pd.qcut(range(5), 4, labels=False)
-    array([0, 0, 1, 2, 3], dtype=int64)
+    array([0, 0, 1, 2, 3])
     """
     x_is_series, series_index, name, x = _preprocess_for_cut(x)