DOC: python 3 compatibility in code examples (#15011)

Author: jorisvandenbossche

doc/source/categorical.rst

@@ -129,8 +129,7 @@ To get back to the original Series or `numpy` array, use ``Series.astype(origina
     s
     s2 = s.astype('category')
     s2
-    s3 = s2.astype('string')
-    s3
+    s2.astype(str)
     np.asarray(s2)
 
 If you have already `codes` and `categories`, you can use the :func:`~pandas.Categorical.from_codes`

doc/source/cookbook.rst

@@ -7,6 +7,7 @@
 
    import pandas as pd
    import numpy as np
+   from pandas.compat import StringIO
 
    import random
    import os
@@ -985,9 +986,6 @@ Skip row between header and data
 
 .. ipython:: python
 
-    from io import StringIO
-    import pandas as pd
-
     data = """;;;;
      ;;;;
      ;;;;
@@ -1014,23 +1012,20 @@ Option 1: pass rows explicitly to skiprows
 
 .. ipython:: python
 
-    pd.read_csv(StringIO(data.decode('UTF-8')), sep=';', skiprows=[11,12],
+    pd.read_csv(StringIO(data), sep=';', skiprows=[11,12],
             index_col=0, parse_dates=True, header=10)
 
 Option 2: read column names and then data
 """""""""""""""""""""""""""""""""""""""""
 
 .. ipython:: python
 
-    pd.read_csv(StringIO(data.decode('UTF-8')), sep=';',
-            header=10, parse_dates=True, nrows=10).columns
-    columns = pd.read_csv(StringIO(data.decode('UTF-8')), sep=';',
-                      header=10, parse_dates=True, nrows=10).columns
-    pd.read_csv(StringIO(data.decode('UTF-8')), sep=';',
+    pd.read_csv(StringIO(data), sep=';', header=10, nrows=10).columns
+    columns = pd.read_csv(StringIO(data), sep=';', header=10, nrows=10).columns
+    pd.read_csv(StringIO(data), sep=';', index_col=0,
                 header=12, parse_dates=True, names=columns)
 
 
-
 .. _cookbook.sql:
 
 SQL

doc/source/gotchas.rst

@@ -249,7 +249,7 @@ normal Python ``list``. Monotonicity of an index can be tested with the ``is_mon
 
 .. ipython:: python
 
-    df = pd.DataFrame(index=[2,3,3,4,5], columns=['data'], data=range(5))
+    df = pd.DataFrame(index=[2,3,3,4,5], columns=['data'], data=list(range(5)))
     df.index.is_monotonic_increasing
 
     # no rows 0 or 1, but still returns rows 2, 3 (both of them), and 4:
@@ -263,7 +263,7 @@ On the other hand, if the index is not monotonic, then both slice bounds must be
 
 .. ipython:: python
 
-    df = pd.DataFrame(index=[2,3,1,4,3,5], columns=['data'], data=range(6))
+    df = pd.DataFrame(index=[2,3,1,4,3,5], columns=['data'], data=list(range(6)))
     df.index.is_monotonic_increasing
 
     # OK because 2 and 4 are in the index

doc/source/io.rst

@@ -502,7 +502,7 @@ worth trying.
    .. ipython:: python
         :okwarning:
 
-        df = pd.DataFrame({'col_1':range(500000) + ['a', 'b'] + range(500000)})
+        df = pd.DataFrame({'col_1': list(range(500000)) + ['a', 'b'] + list(range(500000))})
         df.to_csv('foo')
         mixed_df = pd.read_csv('foo')
         mixed_df['col_1'].apply(type).value_counts()

doc/source/reshaping.rst

@@ -650,10 +650,16 @@ handling of NaN:
    because of an ordering bug. See also
    `Here <https://github.com/numpy/numpy/issues/641>`__
 
-.. ipython:: python
+.. code-block:: ipython
+
+    In [2]: pd.factorize(x, sort=True)
+    Out[2]:
+    (array([ 2,  2, -1,  3,  0,  1]),
+     Index([3.14, inf, u'A', u'B'], dtype='object'))
+
+    In [3]: np.unique(x, return_inverse=True)[::-1]
+    Out[3]: (array([3, 3, 0, 4, 1, 2]), array([nan, 3.14, inf, 'A', 'B'], dtype=object))
 
-   pd.factorize(x, sort=True)
-   np.unique(x, return_inverse=True)[::-1]
 
 .. note::
     If you just want to handle one column as a categorical variable (like R's factor),