Merge pull request #10136 from jorisvandenbossche/doc-imports

DOC: consistent imports (GH9886) part II

Author: jorisvandenbossche

doc/source/10min.rst

@@ -6,18 +6,16 @@
    :suppress:
 
    import numpy as np
-   import random
+   import pandas as pd
    import os
    np.random.seed(123456)
-   from pandas import options
-   import pandas as pd
    np.set_printoptions(precision=4, suppress=True)
    import matplotlib
    try:
       matplotlib.style.use('ggplot')
    except AttributeError:
-      options.display.mpl_style = 'default'
-   options.display.max_rows=15
+      pd.options.display.mpl_style = 'default'
+   pd.options.display.max_rows = 15
 
    #### portions of this were borrowed from the
    #### Pandas cheatsheet
@@ -298,7 +296,7 @@ Using the :func:`~Series.isin` method for filtering:
 .. ipython:: python
 
    df2 = df.copy()
-   df2['E']=['one', 'one','two','three','four','three']
+   df2['E'] = ['one', 'one','two','three','four','three']
    df2
    df2[df2['E'].isin(['two','four'])]
 
@@ -310,7 +308,7 @@ by the indexes
 
 .. ipython:: python
 
-   s1 = pd.Series([1,2,3,4,5,6],index=pd.date_range('20130102',periods=6))
+   s1 = pd.Series([1,2,3,4,5,6], index=pd.date_range('20130102', periods=6))
    s1
    df['F'] = s1
 
@@ -359,7 +357,7 @@ returns a copy of the data.
 
 .. ipython:: python
 
-   df1 = df.reindex(index=dates[0:4],columns=list(df.columns) + ['E'])
+   df1 = df.reindex(index=dates[0:4], columns=list(df.columns) + ['E'])
    df1.loc[dates[0]:dates[1],'E'] = 1
    df1
 
@@ -409,9 +407,9 @@ In addition, pandas automatically broadcasts along the specified dimension.
 
 .. ipython:: python
 
-   s = pd.Series([1,3,5,np.nan,6,8],index=dates).shift(2)
+   s = pd.Series([1,3,5,np.nan,6,8], index=dates).shift(2)
    s
-   df.sub(s,axis='index')
+   df.sub(s, axis='index')
 
 
 Apply
@@ -431,7 +429,7 @@ See more at :ref:`Histogramming and Discretization <basics.discretization>`
 
 .. ipython:: python
 
-   s = pd.Series(np.random.randint(0,7,size=10))
+   s = pd.Series(np.random.randint(0, 7, size=10))
    s
    s.value_counts()
 
@@ -516,9 +514,9 @@ See the :ref:`Grouping section <groupby>`
 .. ipython:: python
 
    df = pd.DataFrame({'A' : ['foo', 'bar', 'foo', 'bar',
-                            'foo', 'bar', 'foo', 'foo'],
+                             'foo', 'bar', 'foo', 'foo'],
                       'B' : ['one', 'one', 'two', 'three',
-                            'two', 'two', 'one', 'three'],
+                             'two', 'two', 'one', 'three'],
                       'C' : np.random.randn(8),
                       'D' : np.random.randn(8)})
    df

doc/source/advanced.rst

@@ -6,15 +6,10 @@
    :suppress:
 
    import numpy as np
-   import random
-   np.random.seed(123456)
-   from pandas import *
-   options.display.max_rows=15
    import pandas as pd
-   randn = np.random.randn
-   randint = np.random.randint
+   np.random.seed(123456)
    np.set_printoptions(precision=4, suppress=True)
-   from pandas.compat import range, zip
+   pd.options.display.max_rows=15
 
 ******************************
 MultiIndex / Advanced Indexing
@@ -80,10 +75,10 @@ demo different ways to initialize MultiIndexes.
    tuples = list(zip(*arrays))
    tuples
 
-   index = MultiIndex.from_tuples(tuples, names=['first', 'second'])
+   index = pd.MultiIndex.from_tuples(tuples, names=['first', 'second'])
    index
 
-   s = Series(randn(8), index=index)
+   s = pd.Series(np.random.randn(8), index=index)
    s
 
 When you want every pairing of the elements in two iterables, it can be easier
@@ -92,7 +87,7 @@ to use the ``MultiIndex.from_product`` function:
 .. ipython:: python
 
    iterables = [['bar', 'baz', 'foo', 'qux'], ['one', 'two']]
-   MultiIndex.from_product(iterables, names=['first', 'second'])
+   pd.MultiIndex.from_product(iterables, names=['first', 'second'])
 
 As a convenience, you can pass a list of arrays directly into Series or
 DataFrame to construct a MultiIndex automatically:
@@ -101,9 +96,9 @@ DataFrame to construct a MultiIndex automatically:
 
    arrays = [np.array(['bar', 'bar', 'baz', 'baz', 'foo', 'foo', 'qux', 'qux']),
              np.array(['one', 'two', 'one', 'two', 'one', 'two', 'one', 'two'])]
-   s = Series(randn(8), index=arrays)
+   s = pd.Series(np.random.randn(8), index=arrays)
    s
-   df = DataFrame(randn(8, 4), index=arrays)
+   df = pd.DataFrame(np.random.randn(8, 4), index=arrays)
    df
 
 All of the ``MultiIndex`` constructors accept a ``names`` argument which stores
@@ -119,9 +114,9 @@ of the index is up to you:
 
 .. ipython:: python
 
-   df = DataFrame(randn(3, 8), index=['A', 'B', 'C'], columns=index)
+   df = pd.DataFrame(np.random.randn(3, 8), index=['A', 'B', 'C'], columns=index)
    df
-   DataFrame(randn(6, 6), index=index[:6], columns=index[:6])
+   pd.DataFrame(np.random.randn(6, 6), index=index[:6], columns=index[:6])
 
 We've "sparsified" the higher levels of the indexes to make the console output a
 bit easier on the eyes.
@@ -131,7 +126,7 @@ tuples as atomic labels on an axis:
 
 .. ipython:: python
 
-   Series(randn(8), index=tuples)
+   pd.Series(np.random.randn(8), index=tuples)
 
 The reason that the ``MultiIndex`` matters is that it can allow you to do
 grouping, selection, and reshaping operations as we will describe below and in
@@ -282,16 +277,16 @@ As usual, **both sides** of the slicers are included as this is label indexing.
    def mklbl(prefix,n):
        return ["%s%s" % (prefix,i)  for i in range(n)]
 
-   miindex = MultiIndex.from_product([mklbl('A',4),
-                                      mklbl('B',2),
-                                      mklbl('C',4),
-                                      mklbl('D',2)])
-   micolumns = MultiIndex.from_tuples([('a','foo'),('a','bar'),
-                                       ('b','foo'),('b','bah')],
-                                        names=['lvl0', 'lvl1'])
-   dfmi = DataFrame(np.arange(len(miindex)*len(micolumns)).reshape((len(miindex),len(micolumns))),
-                    index=miindex,
-                    columns=micolumns).sortlevel().sortlevel(axis=1)
+   miindex = pd.MultiIndex.from_product([mklbl('A',4),
+                                         mklbl('B',2),
+                                         mklbl('C',4),
+                                         mklbl('D',2)])
+   micolumns = pd.MultiIndex.from_tuples([('a','foo'),('a','bar'),
+                                          ('b','foo'),('b','bah')],
+                                         names=['lvl0', 'lvl1'])
+   dfmi = pd.DataFrame(np.arange(len(miindex)*len(micolumns)).reshape((len(miindex),len(micolumns))),
+                       index=miindex,
+                       columns=micolumns).sortlevel().sortlevel(axis=1)
    dfmi
 
 Basic multi-index slicing using slices, lists, and labels.
@@ -418,9 +413,9 @@ instance:
 
 .. ipython:: python
 
-   midx = MultiIndex(levels=[['zero', 'one'], ['x','y']],
-                     labels=[[1,1,0,0],[1,0,1,0]])
-   df = DataFrame(randn(4,2), index=midx)
+   midx = pd.MultiIndex(levels=[['zero', 'one'], ['x','y']],
+                        labels=[[1,1,0,0],[1,0,1,0]])
+   df = pd.DataFrame(np.random.randn(4,2), index=midx)
    df
    df2 = df.mean(level=0)
    df2
@@ -471,7 +466,7 @@ labels will be sorted lexicographically!
 .. ipython:: python
 
    import random; random.shuffle(tuples)
-   s = Series(randn(8), index=MultiIndex.from_tuples(tuples))
+   s = pd.Series(np.random.randn(8), index=pd.MultiIndex.from_tuples(tuples))
    s
    s.sortlevel(0)
    s.sortlevel(1)
@@ -509,13 +504,13 @@ an exception. Here is a concrete example to illustrate this:
 .. ipython:: python
 
    tuples = [('a', 'a'), ('a', 'b'), ('b', 'a'), ('b', 'b')]
-   idx = MultiIndex.from_tuples(tuples)
+   idx = pd.MultiIndex.from_tuples(tuples)
    idx.lexsort_depth
 
    reordered = idx[[1, 0, 3, 2]]
    reordered.lexsort_depth
 
-   s = Series(randn(4), index=reordered)
+   s = pd.Series(np.random.randn(4), index=reordered)
    s.ix['a':'a']
 
 However:
@@ -540,15 +535,15 @@ index positions. ``take`` will also accept negative integers as relative positio
 
 .. ipython:: python
 
-   index = Index(randint(0, 1000, 10))
+   index = pd.Index(np.random.randint(0, 1000, 10))
    index
 
    positions = [0, 9, 3]
 
    index[positions]
    index.take(positions)
 
-   ser = Series(randn(10))
+   ser = pd.Series(np.random.randn(10))
 
    ser.iloc[positions]
    ser.take(positions)
@@ -558,7 +553,7 @@ row or column positions.
 
 .. ipython:: python
 
-   frm = DataFrame(randn(5, 3))
+   frm = pd.DataFrame(np.random.randn(5, 3))
 
    frm.take([1, 4, 3])
 
@@ -569,11 +564,11 @@ intended to work on boolean indices and may return unexpected results.
 
 .. ipython:: python
 
-   arr = randn(10)
+   arr = np.random.randn(10)
    arr.take([False, False, True, True])
    arr[[0, 1]]
 
-   ser = Series(randn(10))
+   ser = pd.Series(np.random.randn(10))
    ser.take([False, False, True, True])
    ser.ix[[0, 1]]
 
@@ -583,14 +578,14 @@ faster than fancy indexing.
 
 .. ipython::
 
-   arr = randn(10000, 5)
+   arr = np.random.randn(10000, 5)
    indexer = np.arange(10000)
    random.shuffle(indexer)
 
    timeit arr[indexer]
    timeit arr.take(indexer, axis=0)
 
-   ser = Series(arr[:, 0])
+   ser = pd.Series(arr[:, 0])
    timeit ser.ix[indexer]
    timeit ser.take(indexer)
 
@@ -608,10 +603,9 @@ setting the index of a ``DataFrame/Series`` with a ``category`` dtype would conv
 
 .. ipython:: python
 
-   df = DataFrame({'A' : np.arange(6),
-                   'B' : Series(list('aabbca')).astype('category',
-                                                       categories=list('cab'))
-                  })
+   df = pd.DataFrame({'A': np.arange(6),
+                      'B': list('aabbca')})
+   df['B'] = df['B'].astype('category', categories=list('cab'))
    df
    df.dtypes
    df.B.cat.categories
@@ -669,15 +663,15 @@ values NOT in the categories, similarly to how you can reindex ANY pandas index.
 
    .. code-block:: python
 
-      In [10]: df3 = DataFrame({'A' : np.arange(6),
-                                'B' : Series(list('aabbca')).astype('category',
-                                                                    categories=list('abc'))
-                               }).set_index('B')
+      In [9]: df3 = pd.DataFrame({'A' : np.arange(6),
+                                  'B' : pd.Series(list('aabbca')).astype('category')})
+
+      In [11]: df3 = df3.set_index('B')
 
       In [11]: df3.index
       Out[11]: CategoricalIndex([u'a', u'a', u'b', u'b', u'c', u'a'], categories=[u'a', u'b', u'c'], ordered=False, name=u'B', dtype='category')
 
-      In [12]: pd.concat([df2,df3]
+      In [12]: pd.concat([df2, df3]
       TypeError: categories must match existing categories when appending
 
 .. _indexing.float64index:
@@ -702,9 +696,9 @@ same.
 
 .. ipython:: python
 
-   indexf = Index([1.5, 2, 3, 4.5, 5])
+   indexf = pd.Index([1.5, 2, 3, 4.5, 5])
    indexf
-   sf = Series(range(5),index=indexf)
+   sf = pd.Series(range(5), index=indexf)
    sf
 
 Scalar selection for ``[],.ix,.loc`` will always be label based. An integer will match an equal float index (e.g. ``3`` is equivalent to ``3.0``)
@@ -746,17 +740,17 @@ In non-float indexes, slicing using floats will raise a ``TypeError``
 
 .. code-block:: python
 
-   In [1]: Series(range(5))[3.5]
+   In [1]: pd.Series(range(5))[3.5]
    TypeError: the label [3.5] is not a proper indexer for this index type (Int64Index)
 
-   In [1]: Series(range(5))[3.5:4.5]
+   In [1]: pd.Series(range(5))[3.5:4.5]
    TypeError: the slice start [3.5] is not a proper indexer for this index type (Int64Index)
 
 Using a scalar float indexer will be deprecated in a future version, but is allowed for now.
 
 .. code-block:: python
 
-   In [3]: Series(range(5))[3.0]
+   In [3]: pd.Series(range(5))[3.0]
    Out[3]: 3
 
 Here is a typical use-case for using this type of indexing. Imagine that you have a somewhat
@@ -765,12 +759,12 @@ example be millisecond offsets.
 
 .. ipython:: python
 
-   dfir = concat([DataFrame(randn(5,2),
-                     index=np.arange(5) * 250.0,
-                     columns=list('AB')),
-                  DataFrame(randn(6,2),
-                     index=np.arange(4,10) * 250.1,
-                     columns=list('AB'))])
+   dfir = pd.concat([pd.DataFrame(np.random.randn(5,2),
+                                  index=np.arange(5) * 250.0,
+                                  columns=list('AB')),
+                     pd.DataFrame(np.random.randn(6,2),
+                                  index=np.arange(4,10) * 250.1,
+                                  columns=list('AB'))])
    dfir
 
 Selection operations then will always work on a value basis, for all selection operators.