Merge branch 'master' into bug16524

Author: preddy5

ci/build_docs.sh

@@ -59,6 +59,15 @@ if [ "$DOC" ]; then
     git remote -v
 
     git push origin gh-pages -f
+
+    echo "Running doctests"
+    cd "$TRAVIS_BUILD_DIR"
+    pytest --doctest-modules \
+           pandas/core/reshape/concat.py \
+           pandas/core/reshape/pivot.py \
+           pandas/core/reshape/reshape.py \
+           pandas/core/reshape/tile.py
+
 fi
 
 exit 0

doc/source/api.rst

@@ -1286,6 +1286,8 @@ Attributes
    Index.is_monotonic
    Index.is_monotonic_increasing
    Index.is_monotonic_decreasing
+   Index.is_strictly_monotonic_increasing
+   Index.is_strictly_monotonic_decreasing
    Index.is_unique
    Index.has_duplicates
    Index.dtype

doc/source/whatsnew/v0.20.2.txt

@@ -21,6 +21,7 @@ Enhancements
 
 - Unblocked access to additional compression types supported in pytables: 'blosc:blosclz, 'blosc:lz4', 'blosc:lz4hc', 'blosc:snappy', 'blosc:zlib', 'blosc:zstd' (:issue:`14478`)
 - ``Series`` provides a ``to_latex`` method (:issue:`16180`)
+- Added :attr:`Index.is_strictly_monotonic_increasing` and :attr:`Index.is_strictly_monotonic_decreasing` properties (:issue:`16515`)
 
 .. _whatsnew_0202.performance:
 
@@ -40,13 +41,14 @@ Bug Fixes
 - Silenced a warning on some Windows environments about "tput: terminal attributes: No such device or address" when
   detecting the terminal size. This fix only applies to python 3 (:issue:`16496`)
 - Bug in using ``pathlib.Path`` or ``py.path.local`` objects with io functions (:issue:`16291`)
+- Bug in ``Index.symmetric_difference()`` on two equal MultiIndex's, results in a TypeError (:issue `13490`)
 - Bug in ``DataFrame.update()`` with ``overwrite=False`` and ``NaN values`` (:issue:`15593`)
-- Bug in ``Series`` with dtype='category' (:issue:`16524`)
-
-
-
+- Passing an invalid engine to :func:`read_csv` now raises an informative
+  ``ValueError`` rather than ``UnboundLocalError``. (:issue:`16511`)
+- Bug in :func:`unique` on an array of tuples (:issue:`16519`)
+- Bug in :func:`cut`` when ``labels`` are set, resulting in incorrect label ordering (:issue:`16459`)
 - Fixed a compatibility issue with IPython 6.0's tab completion showing deprecation warnings on Categoricals (:issue:`16409`)
-
+- Bug in ``Series`` with dtype='category' (:issue:`16524`)
 
 Conversion
 ^^^^^^^^^^
@@ -59,15 +61,18 @@ Indexing
 ^^^^^^^^
 
 - Bug in ``DataFrame.reset_index(level=)`` with single level index (:issue:`16263`)
-
+- Bug in partial string indexing with a monotonic, but not strictly-monotonic, index incorrectly reversing the slice bounds (:issue:`16515`)
 
 I/O
 ^^^
 
 - Bug in pd.read_csv() when comment is passed in space deliminted text files (:issue:`16472`)
 - Bug that would force importing of the clipboard routines unnecessarily, potentially causing an import error on startup (:issue:`16288`)
 - Bug that raised IndexError HTML-rendering an empty DataFrame (:issue:`15953`)
+- Bug in ``pd.read_csv()`` in which tarfile object inputs were raising an error in Python 2.x for the C engine (:issue:`16530`)
+- Bug where ``DataFrame.to_html()`` ignored the ``index_names`` parameter (:issue:`16493`)
 
+- Bug in ``HDFStore.select_as_multiple()`` where start/stop arguments were not respected (:issue:`16209`)
 
 Plotting
 ^^^^^^^^
@@ -84,6 +89,7 @@ Groupby/Resample/Rolling
 
 - Bug creating datetime rolling window on an empty DataFrame (:issue:`15819`)
 - Bug in ``rolling.cov()`` with offset window (:issue:`16058`)
+- Bug in ``.resample()`` and ``.groupby()`` when aggregating on integers (:issue:`16361`)
 
 
 Sparse
@@ -98,6 +104,7 @@ Reshaping
 - Bug in ``pd.wide_to_long()`` where no error was raised when ``i`` was not a unique identifier (:issue:`16382`)
 - Bug in ``Series.isin(..)`` with a list of tuples (:issue:`16394`)
 - Bug in construction of a ``DataFrame`` with mixed dtypes including an all-NaT column. (:issue:`16395`)
+- Bug in ``DataFrame.agg()`` and ``Series.agg()`` with aggregating on non-callable attributes (:issue:`16405`)
 
 
 Numeric

pandas/_libs/index.pyx

@@ -152,7 +152,7 @@ cdef class IndexEngine:
 
         try:
             return self.mapping.get_item(val)
-        except TypeError:
+        except (TypeError, ValueError):
             raise KeyError(val)
 
     cdef inline _get_loc_duplicates(self, object val):
@@ -470,7 +470,7 @@ cdef class DatetimeEngine(Int64Engine):
         try:
             val = _to_i8(val)
             return self.mapping.get_item(val)
-        except TypeError:
+        except (TypeError, ValueError):
             self._date_check_type(val)
             raise KeyError(val)
 

pandas/core/algorithms.py

@@ -163,7 +163,7 @@ def _ensure_arraylike(values):
                                ABCIndexClass, ABCSeries)):
         inferred = lib.infer_dtype(values)
         if inferred in ['mixed', 'string', 'unicode']:
-            values = np.asarray(values, dtype=object)
+            values = lib.list_to_object_array(values)
         else:
             values = np.asarray(values)
     return values
@@ -328,6 +328,11 @@ def unique(values):
     [b, a, c]
     Categories (3, object): [a < b < c]
 
+    An array of tuples
+
+    >>> pd.unique([('a', 'b'), ('b', 'a'), ('a', 'c'), ('b', 'a')])
+    array([('a', 'b'), ('b', 'a'), ('a', 'c')], dtype=object)
+
     See Also
     --------
     pandas.Index.unique

pandas/core/base.py

@@ -378,7 +378,7 @@ def aggregate(self, func, *args, **kwargs):
     def _try_aggregate_string_function(self, arg, *args, **kwargs):
         """
         if arg is a string, then try to operate on it:
-        - try to find a function on ourselves
+        - try to find a function (or attribute) on ourselves
         - try to find a numpy function
         - raise
 
@@ -387,7 +387,15 @@ def _try_aggregate_string_function(self, arg, *args, **kwargs):
 
         f = getattr(self, arg, None)
         if f is not None:
-            return f(*args, **kwargs)
+            if callable(f):
+                return f(*args, **kwargs)
+
+            # people may try to aggregate on a non-callable attribute
+            # but don't let them think they can pass args to it
+            assert len(args) == 0
+            assert len([kwarg for kwarg in kwargs
+                        if kwarg not in ['axis', '_level']]) == 0
+            return f
 
         f = getattr(np, arg, None)
         if f is not None:

pandas/core/dtypes/inference.py

@@ -171,7 +171,7 @@ def is_file_like(obj):
     if not (hasattr(obj, 'read') or hasattr(obj, 'write')):
         return False
 
-    if not is_iterator(obj):
+    if not hasattr(obj, "__iter__"):
         return False
 
     return True

pandas/core/frame.py

@@ -1918,7 +1918,7 @@ def get_value(self, index, col, takeable=False):
 
         try:
             return engine.get_value(series._values, index)
-        except TypeError:
+        except (TypeError, ValueError):
 
             # we cannot handle direct indexing
             # use positional

pandas/core/generic.py

@@ -2366,9 +2366,14 @@ def add_suffix(self, suffix):
         1   A    1    1
         """
 
-    def sort_values(self, by, axis=0, ascending=True, inplace=False,
+    def sort_values(self, by=None, axis=0, ascending=True, inplace=False,
                     kind='quicksort', na_position='last'):
-        raise AbstractMethodError(self)
+        """
+        NOT IMPLEMENTED: do not call this method, as sorting values is not
+        supported for Panel objects and will raise an error.
+        """
+        raise NotImplementedError("sort_values has not been implemented "
+                                  "on Panel or Panel4D objects.")
 
     _shared_docs['sort_index'] = """
         Sort object by labels (along an axis)

pandas/core/groupby.py

@@ -3337,13 +3337,15 @@ def _cython_agg_blocks(self, how, alt=None, numeric_only=True):
                 obj = self.obj[data.items[locs]]
                 s = groupby(obj, self.grouper)
                 result = s.aggregate(lambda x: alt(x, axis=self.axis))
-                result = result._data.blocks[0]
+                newb = result._data.blocks[0]
 
-            # see if we can cast the block back to the original dtype
-            result = block._try_coerce_and_cast_result(result)
+            finally:
+
+                # see if we can cast the block back to the original dtype
+                result = block._try_coerce_and_cast_result(result)
+                newb = block.make_block(result)
 
             new_items.append(locs)
-            newb = block.make_block_same_class(result)
             new_blocks.append(newb)
 
         if len(new_blocks) == 0:

pandas/core/indexes/base.py

@@ -1191,6 +1191,15 @@ def is_monotonic_increasing(self):
         """
         return if the index is monotonic increasing (only equal or
         increasing) values.
+
+        Examples
+        --------
+        >>> Index([1, 2, 3]).is_monotonic_increasing
+        True
+        >>> Index([1, 2, 2]).is_monotonic_increasing
+        True
+        >>> Index([1, 3, 2]).is_monotonic_increasing
+        False
         """
         return self._engine.is_monotonic_increasing
 
@@ -1199,9 +1208,50 @@ def is_monotonic_decreasing(self):
         """
         return if the index is monotonic decreasing (only equal or
         decreasing) values.
+
+        Examples
+        --------
+        >>> Index([3, 2, 1]).is_monotonic_decreasing
+        True
+        >>> Index([3, 2, 2]).is_monotonic_decreasing
+        True
+        >>> Index([3, 1, 2]).is_monotonic_decreasing
+        False
         """
         return self._engine.is_monotonic_decreasing
 
+    @property
+    def is_strictly_monotonic_increasing(self):
+        """return if the index is strictly monotonic increasing
+        (only increasing) values
+
+        Examples
+        --------
+        >>> Index([1, 2, 3]).is_strictly_monotonic_increasing
+        True
+        >>> Index([1, 2, 2]).is_strictly_monotonic_increasing
+        False
+        >>> Index([1, 3, 2]).is_strictly_monotonic_increasing
+        False
+        """
+        return self.is_unique and self.is_monotonic_increasing
+
+    @property
+    def is_strictly_monotonic_decreasing(self):
+        """return if the index is strictly monotonic decreasing
+        (only decreasing) values
+
+        Examples
+        --------
+        >>> Index([3, 2, 1]).is_strictly_monotonic_decreasing
+        True
+        >>> Index([3, 2, 2]).is_strictly_monotonic_decreasing
+        False
+        >>> Index([3, 1, 2]).is_strictly_monotonic_decreasing
+        False
+        """
+        return self.is_unique and self.is_monotonic_decreasing
+
     def is_lexsorted_for_tuple(self, tup):
         return True
 
@@ -1590,7 +1640,7 @@ def __contains__(self, key):
         hash(key)
         try:
             return key in self._engine
-        except TypeError:
+        except (TypeError, ValueError):
             return False
 
     _index_shared_docs['contains'] = """
@@ -1610,7 +1660,7 @@ def contains(self, key):
         hash(key)
         try:
             return key in self._engine
-        except TypeError:
+        except (TypeError, ValueError):
             return False
 
     def __hash__(self):

pandas/core/indexes/datetimes.py

@@ -1472,7 +1472,7 @@ def _maybe_cast_slice_bound(self, label, side, kind):
             # the bounds need swapped if index is reverse sorted and has a
             # length > 1 (is_monotonic_decreasing gives True for empty
             # and length 1 index)
-            if self.is_monotonic_decreasing and len(self) > 1:
+            if self.is_strictly_monotonic_decreasing and len(self) > 1:
                 return upper if side == 'left' else lower
             return lower if side == 'left' else upper
         else:

pandas/core/indexes/multi.py

@@ -414,6 +414,12 @@ def view(self, cls=None):
         return result
 
     def _shallow_copy_with_infer(self, values=None, **kwargs):
+        # On equal MultiIndexes the difference is empty.
+        # Therefore, an empty MultiIndex is returned GH13490
+        if len(values) == 0:
+            return MultiIndex(levels=[[] for _ in range(self.nlevels)],
+                              labels=[[] for _ in range(self.nlevels)],
+                              **kwargs)
         return self._shallow_copy(values, **kwargs)
 
     @Appender(_index_shared_docs['_shallow_copy'])

pandas/core/reshape/concat.py

@@ -197,6 +197,8 @@ def concat(objs, axis=0, join='outer', join_axes=None, ignore_index=False,
        0
     a  2
     >>> pd.concat([df5, df6], verify_integrity=True)
+    Traceback (most recent call last):
+        ...
     ValueError: Indexes have overlapping values: ['a']
     """
     op = _Concatenator(objs, axis=axis, join_axes=join_axes,