Merge branch 'master' of https://github.com/pydata/pandas

Author: Brendan Boerner

doc/source/api.rst

@@ -374,6 +374,8 @@ Reindexing / Selection / Label manipulation
 
    Series.align
    Series.drop
+   Series.drop_duplicates
+   Series.duplicated
    Series.equals
    Series.first
    Series.head
@@ -1165,6 +1167,8 @@ Modifying and Computations
    Index.diff
    Index.sym_diff
    Index.drop
+   Index.drop_duplicates
+   Index.duplicated
    Index.equals
    Index.factorize
    Index.identical

doc/source/indexing.rst

@@ -1476,6 +1476,7 @@ You can control the action of a chained assignment via the option ``mode.chained
 which can take the values ``['raise','warn',None]``, where showing a warning is the default.
 
 .. ipython:: python
+   :okwarning:
 
    dfb = DataFrame({'a' : ['one', 'one', 'two',
                            'three', 'two', 'one', 'six'],

doc/source/io.rst

@@ -2722,7 +2722,7 @@ The default is 50,000 rows returned in a chunk.
 
    .. code-block:: python
 
-      for df in read_hdf('store.h5','df', chunsize=3):
+      for df in read_hdf('store.h5','df', chunksize=3):
           print(df)
 
 Note, that the chunksize keyword applies to the **source** rows. So if you

doc/source/reshaping.rst

@@ -151,6 +151,15 @@ unstacks the **last level**:
    stacked.unstack(1)
    stacked.unstack(0)
 
+.. _reshaping.unstack_by_name:
+
+If the indexes have names, you can use the level names instead of specifying
+the level numbers:
+
+.. ipython:: python
+
+   stacked.unstack('second')
+
 Notice that the ``stack`` and ``unstack`` methods implicitly sort the index
 levels involved. Hence a call to ``stack`` and then ``unstack``, or viceversa,
 will result in a **sorted** copy of the original DataFrame or Series:
@@ -165,15 +174,6 @@ will result in a **sorted** copy of the original DataFrame or Series:
 while the above code will raise a ``TypeError`` if the call to ``sort`` is
 removed.
 
-.. _reshaping.unstack_by_name:
-
-If the indexes have names, you can use the level names instead of specifying
-the level numbers:
-
-.. ipython:: python
-
-   stacked.unstack('second')
-
 .. _reshaping.stack_multiple:
 
 Multiple Levels
@@ -218,6 +218,8 @@ calling ``sortlevel``, of course). Here is a more complex example:
    columns = MultiIndex.from_tuples([('A', 'cat'), ('B', 'dog'),
                                      ('B', 'cat'), ('A', 'dog')],
                                     names=['exp', 'animal'])
+   index = MultiIndex.from_product([('bar', 'baz', 'foo', 'qux'), ('one', 'two')],
+                                   names=['first', 'second'])
    df = DataFrame(randn(8, 4), index=index, columns=columns)
    df2 = df.ix[[0, 1, 2, 4, 5, 7]]
    df2

doc/source/v0.15.0.txt

@@ -223,6 +223,15 @@ API changes
      s
      s.loc[['D']]
 
+- ``Index`` now supports ``duplicated`` and ``drop_duplicates``. (:issue:`4060`)
+
+  .. ipython:: python
+
+     idx = Index([1, 2, 3, 4, 1, 2])
+     idx
+     idx.duplicated()
+     idx.drop_duplicates()
+
 .. _whatsnew_0150.dt:
 
 .dt accessor
@@ -437,6 +446,7 @@ There are no experimental changes in 0.15.0
 
 Bug Fixes
 ~~~~~~~~~
+- Bug in multiindexes dtypes getting mixed up when DataFrame is saved to SQL table (:issue:`8021`)
 - Bug in Series 0-division with a float and integer operand dtypes  (:issue:`7785`)
 - Bug in ``Series.astype("unicode")`` not calling ``unicode`` on the values correctly (:issue:`7758`)
 - Bug in ``DataFrame.as_matrix()`` with mixed ``datetime64[ns]`` and ``timedelta64[ns]`` dtypes (:issue:`7778`)
@@ -454,7 +464,7 @@ Bug Fixes
 - Bug in pickle deserialization that failed for pre-0.14.1 containers with dup items trying to avoid ambiguity
   when matching block and manager items, when there's only one block there's no ambiguity (:issue:`7794`)
 
-
+- Bug in HDFStore iteration when passing a where (:issue:`8014`)
 
 - Bug in repeated timeseries line and area plot may result in ``ValueError`` or incorrect kind (:issue:`7733`)
 
@@ -516,7 +526,7 @@ Bug Fixes
   times were returned when crossing DST boundaries (:issue:`7835`, :issue:`7901`).
 
 
-
+- Bug in area plot draws legend with incorrect ``alpha`` when ``stacked=True`` (:issue:`8027`)
 
 - ``Period`` and ``PeriodIndex`` addition/subtraction with ``np.timedelta64`` results in incorrect internal representations (:issue:`7740`)
 

pandas/core/base.py

@@ -8,8 +8,14 @@
 from pandas.core import common as com
 import pandas.core.nanops as nanops
 import pandas.tslib as tslib
+import pandas.lib as lib
 from pandas.util.decorators import Appender, cache_readonly
 
+
+_shared_docs = dict()
+_indexops_doc_kwargs = dict(klass='IndexOpsMixin', inplace='')
+
+
 class StringMixin(object):
 
     """implements string methods so long as object defines a `__unicode__`
@@ -474,12 +480,66 @@ def searchsorted(self, key, side='left'):
         #### needs tests/doc-string
         return self.values.searchsorted(key, side=side)
 
+    _shared_docs['drop_duplicates'] = (
+        """Return %(klass)s with duplicate values removed
+
+        Parameters
+        ----------
+        take_last : boolean, default False
+            Take the last observed index in a group. Default first
+        %(inplace)s
+
+        Returns
+        -------
+        deduplicated : %(klass)s
+        """)
+
+    @Appender(_shared_docs['drop_duplicates'] % _indexops_doc_kwargs)
+    def drop_duplicates(self, take_last=False, inplace=False):
+        duplicated = self.duplicated(take_last=take_last)
+        result = self[~duplicated.values]
+        if inplace:
+            return self._update_inplace(result)
+        else:
+            return result
+
+    _shared_docs['duplicated'] = (
+        """Return boolean %(klass)s denoting duplicate values
+
+        Parameters
+        ----------
+        take_last : boolean, default False
+            Take the last observed index in a group. Default first
+
+        Returns
+        -------
+        duplicated : %(klass)s
+        """)
+
+    @Appender(_shared_docs['duplicated'] % _indexops_doc_kwargs)
+    def duplicated(self, take_last=False):
+        keys = com._ensure_object(self.values)
+        duplicated = lib.duplicated(keys, take_last=take_last)
+        try:
+            return self._constructor(duplicated,
+                                     index=self.index).__finalize__(self)
+        except AttributeError:
+            from pandas.core.index import Index
+            return Index(duplicated)
+
     #----------------------------------------------------------------------
     # unbox reductions
 
     all = _unbox(np.ndarray.all)
     any = _unbox(np.ndarray.any)
 
+    #----------------------------------------------------------------------
+    # abstracts
+
+    def _update_inplace(self, result):
+        raise NotImplementedError
+
+
 class DatetimeIndexOpsMixin(object):
     """ common ops mixin to support a unified inteface datetimelike Index """
 
@@ -497,7 +557,6 @@ def _box_values(self, values):
         """
         apply box func to passed values
         """
-        import pandas.lib as lib
         return lib.map_infer(values, self._box_func)
 
     @cache_readonly

pandas/core/index.py

@@ -12,7 +12,7 @@
 import pandas.algos as _algos
 import pandas.index as _index
 from pandas.lib import Timestamp, is_datetime_array
-from pandas.core.base import PandasObject, FrozenList, FrozenNDArray, IndexOpsMixin
+from pandas.core.base import PandasObject, FrozenList, FrozenNDArray, IndexOpsMixin, _shared_docs
 from pandas.util.decorators import Appender, cache_readonly, deprecate
 from pandas.core.common import isnull, array_equivalent
 import pandas.core.common as com
@@ -30,6 +30,8 @@
 
 _unsortable_types = frozenset(('mixed', 'mixed-integer'))
 
+_index_doc_kwargs = dict(klass='Index', inplace='')
+
 
 def _try_get_item(x):
     try:
@@ -209,6 +211,10 @@ def _simple_new(cls, values, name=None, **kwargs):
         result._reset_identity()
         return result
 
+    def _update_inplace(self, result):
+        # guard when called from IndexOpsMixin
+        raise TypeError("Index can't be updated inplace")
+
     def is_(self, other):
         """
         More flexible, faster check like ``is`` but that works through views
@@ -2022,6 +2028,15 @@ def drop(self, labels):
             raise ValueError('labels %s not contained in axis' % labels[mask])
         return self.delete(indexer)
 
+    @Appender(_shared_docs['drop_duplicates'] % _index_doc_kwargs)
+    def drop_duplicates(self, take_last=False):
+        result = super(Index, self).drop_duplicates(take_last=take_last)
+        return self._constructor(result)
+
+    @Appender(_shared_docs['duplicated'] % _index_doc_kwargs)
+    def duplicated(self, take_last=False):
+        return super(Index, self).duplicated(take_last=take_last)
+
     @classmethod
     def _add_numeric_methods_disabled(cls):
         """ add in numeric methods to disable """

pandas/core/series.py

@@ -52,10 +52,13 @@
 
 __all__ = ['Series']
 
+
 _shared_doc_kwargs = dict(
     axes='index',
     klass='Series',
-    axes_single_arg="{0,'index'}"
+    axes_single_arg="{0,'index'}",
+    inplace="""inplace : boolean, default False
+            If True, performs operation inplace and returns None."""
 )
 
 
@@ -265,6 +268,9 @@ def _set_subtyp(self, is_all_dates):
         else:
             object.__setattr__(self, '_subtyp', 'series')
 
+    def _update_inplace(self, result):
+        return generic.NDFrame._update_inplace(self, result)
+
     # ndarray compatibility
     @property
     def dtype(self):
@@ -1114,45 +1120,14 @@ def mode(self):
         from pandas.core.algorithms import mode
         return mode(self)
 
+    @Appender(base._shared_docs['drop_duplicates'] % _shared_doc_kwargs)
     def drop_duplicates(self, take_last=False, inplace=False):
-        """
-        Return Series with duplicate values removed
-
-        Parameters
-        ----------
-        take_last : boolean, default False
-            Take the last observed index in a group. Default first
-        inplace : boolean, default False
-            If True, performs operation inplace and returns None.
-
-        Returns
-        -------
-        deduplicated : Series
-        """
-        duplicated = self.duplicated(take_last=take_last)
-        result = self[-duplicated]
-        if inplace:
-            return self._update_inplace(result)
-        else:
-            return result
+        return super(Series, self).drop_duplicates(take_last=take_last,
+                                                   inplace=inplace)
 
+    @Appender(base._shared_docs['duplicated'] % _shared_doc_kwargs)
     def duplicated(self, take_last=False):
-        """
-        Return boolean Series denoting duplicate values
-
-        Parameters
-        ----------
-        take_last : boolean, default False
-            Take the last observed index in a group. Default first
-
-        Returns
-        -------
-        duplicated : Series
-        """
-        keys = _ensure_object(self.values)
-        duplicated = lib.duplicated(keys, take_last=take_last)
-        return self._constructor(duplicated,
-                                 index=self.index).__finalize__(self)
+        return super(Series, self).duplicated(take_last=take_last)
 
     def idxmin(self, axis=None, out=None, skipna=True):
         """