Merge pull request #4450 from jtratner/change-range-zip-in-docs

DOC: lrange, lzip --> list(range and list(zip

Author: jreback

doc/source/basics.rst

@@ -1093,7 +1093,7 @@ By default integer types are ``int64`` and float types are ``float64``,
 
    DataFrame([1, 2], columns=['a']).dtypes
    DataFrame({'a': [1, 2]}).dtypes
-   DataFrame({'a': 1 }, index=lrange(2)).dtypes
+   DataFrame({'a': 1 }, index=list(range(2))).dtypes
 
 Numpy, however will choose *platform-dependent* types when creating arrays.
 The following **WILL** result in ``int32`` on 32-bit platform.

doc/source/faq.rst

@@ -86,7 +86,7 @@ life easier is missing. In that case you have several options:
        return [x for x in self.columns if 'foo' in x]
 
    pd.DataFrame.just_foo_cols = just_foo_cols # monkey-patch the DataFrame class
-   df = pd.DataFrame([lrange(4)],columns= ["A","foo","foozball","bar"])
+   df = pd.DataFrame([list(range(4))], columns=["A","foo","foozball","bar"])
    df.just_foo_cols()
    del pd.DataFrame.just_foo_cols # you can also remove the new method
 
@@ -259,7 +259,7 @@ using something similar to the following:
 
 .. ipython:: python
 
-   x = np.array(lrange(10), '>i4') # big endian
+   x = np.array(list(range(10)), '>i4') # big endian
    newx = x.byteswap().newbyteorder() # force native byteorder
    s = Series(newx)
 

doc/source/gotchas.rst

@@ -467,7 +467,7 @@ using something similar to the following:
 
 .. ipython:: python
 
-   x = np.array(lrange(10), '>i4') # big endian
+   x = np.array(list(range(10)), '>i4') # big endian
    newx = x.byteswap().newbyteorder() # force native byteorder
    s = Series(newx)
 

doc/source/groupby.rst

@@ -12,7 +12,7 @@
    import matplotlib.pyplot as plt
    plt.close('all')
    options.display.mpl_style='default'
-   from pandas.compat import lzip
+   from pandas.compat import zip
 
 *****************************
 Group By: split-apply-combine
@@ -202,7 +202,7 @@ natural to group by one of the levels of the hierarchy.
 
    arrays = [['bar', 'bar', 'baz', 'baz', 'foo', 'foo', 'qux', 'qux'],
              ['one', 'two', 'one', 'two', 'one', 'two', 'one', 'two']]
-   tuples = lzip(*arrays)
+   tuples = list(zip(*arrays))
    tuples
    index = MultiIndex.from_tuples(tuples, names=['first', 'second'])
    s = Series(randn(8), index=index)
@@ -236,7 +236,7 @@ Also as of v0.6, grouping with multiple levels is supported.
    arrays = [['bar', 'bar', 'baz', 'baz', 'foo', 'foo', 'qux', 'qux'],
              ['doo', 'doo', 'bee', 'bee', 'bop', 'bop', 'bop', 'bop'],
              ['one', 'two', 'one', 'two', 'one', 'two', 'one', 'two']]
-   tuples = lzip(*arrays)
+   tuples = list(zip(*arrays))
    index = MultiIndex.from_tuples(tuples, names=['first', 'second', 'third'])
    s = Series(randn(8), index=index)
 

doc/source/indexing.rst

@@ -13,7 +13,7 @@
    randn = np.random.randn
    randint = np.random.randint
    np.set_printoptions(precision=4, suppress=True)
-   from pandas.compat import lrange, lzip
+   from pandas.compat import range, zip
 
 ***************************
 Indexing and Selecting Data
@@ -294,7 +294,7 @@ The ``.iloc`` attribute is the primary access method. The following are valid in
 
 .. ipython:: python
 
-   s1 = Series(np.random.randn(5),index=lrange(0,10,2))
+   s1 = Series(np.random.randn(5),index=list(range(0,10,2)))
    s1
    s1.iloc[:3]
    s1.iloc[3]
@@ -311,8 +311,8 @@ With a DataFrame
 .. ipython:: python
 
    df1 = DataFrame(np.random.randn(6,4),
-                   index=lrange(0,12,2),
-                   columns=lrange(0,8,2))
+                   index=list(range(0,12,2)),
+                   columns=list(range(0,8,2)))
    df1
 
 Select via integer slicing
@@ -787,7 +787,7 @@ numpy array.  For instance,
 .. ipython:: python
 
   dflookup = DataFrame(np.random.rand(20,4), columns = ['A','B','C','D'])
-  dflookup.lookup(lrange(0,10,2), ['B','C','A','B','D'])
+  dflookup.lookup(list(range(0,10,2)), ['B','C','A','B','D'])
 
 Setting values in mixed-type DataFrame
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -897,7 +897,7 @@ display:
 
 .. ipython:: python
 
-   index = Index(lrange(5), name='rows')
+   index = Index(list(range(5)), name='rows')
    columns = Index(['A', 'B', 'C'], name='cols')
    df = DataFrame(np.random.randn(5, 3), index=index, columns=columns)
    df
@@ -972,7 +972,7 @@ can think of ``MultiIndex`` an array of tuples where each tuple is unique. A
 
    arrays = [['bar', 'bar', 'baz', 'baz', 'foo', 'foo', 'qux', 'qux'],
              ['one', 'two', 'one', 'two', 'one', 'two', 'one', 'two']]
-   tuples = lzip(*arrays)
+   tuples = list(zip(*arrays))
    tuples
    index = MultiIndex.from_tuples(tuples, names=['first', 'second'])
    s = Series(randn(8), index=index)

doc/source/io.rst

@@ -1061,7 +1061,7 @@ Writing to a file, with a date index and a date column
 
    dfj2 = dfj.copy()
    dfj2['date'] = Timestamp('20130101')
-   dfj2['ints'] = lrange(5)
+   dfj2['ints'] = list(range(5))
    dfj2['bools'] = True
    dfj2.index = date_range('20130101',periods=5)
    dfj2.to_json('test.json')
@@ -1156,7 +1156,7 @@ I like my string indicies
 .. ipython:: python
 
    si = DataFrame(np.zeros((4, 4)),
-            columns=lrange(4),
+            columns=list(range(4)),
             index=[str(i) for i in range(4)])
    si
    si.index
@@ -1741,7 +1741,7 @@ similar to how ``read_csv`` and ``to_csv`` work. (new in 0.11.0)
 
 .. ipython:: python
 
-   df_tl = DataFrame(dict(A=lrange(5), B=lrange(5)))
+   df_tl = DataFrame(dict(A=list(range(5)), B=list(range(5))))
    df_tl.to_hdf('store_tl.h5','table',append=True)
    read_hdf('store_tl.h5', 'table', where = ['index>2'])
 
@@ -1863,7 +1863,7 @@ defaults to `nan`.
                            'int' : 1,
                            'bool' : True,
                            'datetime64' : Timestamp('20010102')},
-                         index=lrange(8))
+                         index=list(range(8)))
     df_mixed.ix[3:5,['A', 'B', 'string', 'datetime64']] = np.nan
 
     store.append('df_mixed', df_mixed, min_itemsize = {'values': 50})
@@ -2288,7 +2288,7 @@ Starting in 0.11, passing a ``min_itemsize`` dict will cause all passed columns
 
 .. ipython:: python
 
-   dfs = DataFrame(dict(A = 'foo', B = 'bar'),index=lrange(5))
+   dfs = DataFrame(dict(A = 'foo', B = 'bar'),index=list(range(5)))
    dfs
 
    # A and B have a size of 30

doc/source/missing_data.rst

@@ -363,7 +363,7 @@ Replace the '.' with ``nan`` (str -> str)
 
 .. ipython:: python
 
-   d = {'a': lrange(4), 'b': list('ab..'), 'c': ['a', 'b', nan, 'd']}
+   d = {'a': list(range(4)), 'b': list('ab..'), 'c': ['a', 'b', nan, 'd']}
    df = DataFrame(d)
    df.replace('.', nan)
 
@@ -500,7 +500,7 @@ For example:
    s = Series(randn(5), index=[0, 2, 4, 6, 7])
    s > 0
    (s > 0).dtype
-   crit = (s > 0).reindex(lrange(8))
+   crit = (s > 0).reindex(list(range(8)))
    crit
    crit.dtype
 
@@ -512,7 +512,7 @@ contains NAs, an exception will be generated:
 .. ipython:: python
    :okexcept:
 
-   reindexed = s.reindex(lrange(8)).fillna(0)
+   reindexed = s.reindex(list(range(8))).fillna(0)
    reindexed[crit]
 
 However, these can be filled in using **fillna** and it will work fine:

doc/source/reshaping.rst

@@ -12,7 +12,7 @@
    randn = np.random.randn
    np.set_printoptions(precision=4, suppress=True)
    from pandas.tools.tile import *
-   from pandas.compat import lzip
+   from pandas.compat import zip
 
 **************************
 Reshaping and Pivot Tables
@@ -117,10 +117,10 @@ from the hierarchical indexing section:
 
 .. ipython:: python
 
-   tuples = lzip(*[['bar', 'bar', 'baz', 'baz',
+   tuples = list(zip(*[['bar', 'bar', 'baz', 'baz',
                    'foo', 'foo', 'qux', 'qux'],
                   ['one', 'two', 'one', 'two',
-                   'one', 'two', 'one', 'two']])
+                   'one', 'two', 'one', 'two']]))
    index = MultiIndex.from_tuples(tuples, names=['first', 'second'])
    df = DataFrame(randn(8, 2), index=index, columns=['A', 'B'])
    df2 = df[:4]

doc/source/visualization.rst

@@ -102,7 +102,7 @@ You can plot one column versus another using the `x` and `y` keywords in
    plt.figure()
 
    df3 = DataFrame(randn(1000, 2), columns=['B', 'C']).cumsum()
-   df3['A'] = Series(lrange(len(df)))
+   df3['A'] = Series(list(range(len(df))))
 
    @savefig df_plot_xy.png
    df3.plot(x='A', y='B')