Merge remote-tracking branch 'upstream/master' into makbigc-enh-21801-2

Author: TomAugspurger

asv_bench/benchmarks/categoricals.py

@@ -1,5 +1,3 @@
-import warnings
-
 import numpy as np
 import pandas as pd
 import pandas.util.testing as tm
@@ -133,15 +131,10 @@ def setup(self):
 
         self.s_str = pd.Series(tm.makeCategoricalIndex(N, ncats)).astype(str)
         self.s_str_cat = self.s_str.astype('category')
-        with warnings.catch_warnings(record=True):
-            self.s_str_cat_ordered = self.s_str.astype('category',
-                                                       ordered=True)
-
+        self.s_str_cat_ordered = self.s_str_cat.cat.as_ordered()
         self.s_int = pd.Series(np.random.randint(0, ncats, size=N))
         self.s_int_cat = self.s_int.astype('category')
-        with warnings.catch_warnings(record=True):
-            self.s_int_cat_ordered = self.s_int.astype('category',
-                                                       ordered=True)
+        self.s_int_cat_ordered = self.s_int_cat.cat.as_ordered()
 
     def time_rank_string(self):
         self.s_str.rank()

doc/source/getting_started/basics.rst

@@ -784,6 +784,7 @@ In this case, provide ``pipe`` with a tuple of ``(callable, data_keyword)``.
 For example, we can fit a regression using statsmodels. Their API expects a formula first and a ``DataFrame`` as the second argument, ``data``. We pass in the function, keyword pair ``(sm.ols, 'data')`` to ``pipe``:
 
 .. ipython:: python
+   :okwarning:
 
    import statsmodels.formula.api as sm
 

doc/source/whatsnew/v0.11.0.rst

@@ -377,15 +377,31 @@ Enhancements
 
   - ``Squeeze`` to possibly remove length 1 dimensions from an object.
 
-    .. ipython:: python
-       :okwarning:
-
-       p = pd.Panel(np.random.randn(3, 4, 4), items=['ItemA', 'ItemB', 'ItemC'],
-                    major_axis=pd.date_range('20010102', periods=4),
-                    minor_axis=['A', 'B', 'C', 'D'])
-       p
-       p.reindex(items=['ItemA']).squeeze()
-       p.reindex(items=['ItemA'], minor=['B']).squeeze()
+    .. code-block:: python
+
+       >>> p = pd.Panel(np.random.randn(3, 4, 4), items=['ItemA', 'ItemB', 'ItemC'],
+       ...              major_axis=pd.date_range('20010102', periods=4),
+       ...              minor_axis=['A', 'B', 'C', 'D'])
+       >>> p
+       <class 'pandas.core.panel.Panel'>
+       Dimensions: 3 (items) x 4 (major_axis) x 4 (minor_axis)
+       Items axis: ItemA to ItemC
+       Major_axis axis: 2001-01-02 00:00:00 to 2001-01-05 00:00:00
+       Minor_axis axis: A to D
+
+       >>> p.reindex(items=['ItemA']).squeeze()
+                          A         B         C         D
+       2001-01-02  0.926089 -2.026458  0.501277 -0.204683
+       2001-01-03 -0.076524  1.081161  1.141361  0.479243
+       2001-01-04  0.641817 -0.185352  1.824568  0.809152
+       2001-01-05  0.575237  0.669934  1.398014 -0.399338
+
+       >>> p.reindex(items=['ItemA'], minor=['B']).squeeze()
+       2001-01-02   -2.026458
+       2001-01-03    1.081161
+       2001-01-04   -0.185352
+       2001-01-05    0.669934
+       Freq: D, Name: B, dtype: float64
 
   - In ``pd.io.data.Options``,
 

doc/source/whatsnew/v0.15.0.rst

@@ -701,14 +701,19 @@ Other notable API changes:
 
   This can also be seen in multi-axis indexing with a ``Panel``.
 
-  .. ipython:: python
-     :okwarning:
+  .. code-block:: python
+
+     >>> p = pd.Panel(np.arange(2 * 3 * 4).reshape(2, 3, 4),
+     ...              items=['ItemA', 'ItemB'],
+     ...              major_axis=[1, 2, 3],
+     ...              minor_axis=['A', 'B', 'C', 'D'])
+     >>> p
+     <class 'pandas.core.panel.Panel'>
+     Dimensions: 2 (items) x 3 (major_axis) x 4 (minor_axis)
+     Items axis: ItemA to ItemB
+     Major_axis axis: 1 to 3
+     Minor_axis axis: A to D
 
-     p = pd.Panel(np.arange(2 * 3 * 4).reshape(2, 3, 4),
-                  items=['ItemA', 'ItemB'],
-                  major_axis=[1, 2, 3],
-                  minor_axis=['A', 'B', 'C', 'D'])
-     p
 
   The following would raise ``KeyError`` prior to 0.15.0:
 

doc/source/whatsnew/v0.15.2.rst

@@ -160,11 +160,16 @@ Other enhancements:
 
 - ``Panel`` now supports the ``all`` and ``any`` aggregation functions. (:issue:`8302`):
 
-  .. ipython:: python
-     :okwarning:
+  .. code-block:: python
 
-     p = pd.Panel(np.random.rand(2, 5, 4) > 0.1)
-     p.all()
+     >>> p = pd.Panel(np.random.rand(2, 5, 4) > 0.1)
+     >>> p.all()
+            0      1      2     3
+     0   True   True   True  True
+     1   True  False   True  True
+     2   True   True   True  True
+     3  False   True  False  True
+     4   True   True   True  True
 
 - Added support for ``utcfromtimestamp()``, ``fromtimestamp()``, and ``combine()`` on `Timestamp` class (:issue:`5351`).
 - Added Google Analytics (`pandas.io.ga`) basic documentation (:issue:`8835`). See `here <http://pandas.pydata.org/pandas-docs/version/0.15.2/remote_data.html#remote-data-ga>`__.

pandas/__init__.py

@@ -65,8 +65,7 @@
 
     # misc
     np, Grouper, factorize, unique, value_counts, NamedAgg,
-    array, Categorical, set_eng_float_format, Series, DataFrame,
-    Panel)
+    array, Categorical, set_eng_float_format, Series, DataFrame)
 
 from pandas.core.sparse.api import (
     SparseArray, SparseDataFrame, SparseSeries, SparseDtype)
@@ -118,6 +117,30 @@
 __git_version__ = v.get('full-revisionid')
 del get_versions, v
 
+
+# GH 27101
+# TODO: remove Panel compat in 1.0
+if pandas.compat.PY37:
+    def __getattr__(name):
+        if name == 'Panel':
+            import warnings
+            warnings.warn(
+                "The Panel class is removed from pandas. Accessing it "
+                "from the top-level namespace will also be removed in "
+                "the next version",
+                FutureWarning, stacklevel=2)
+
+            class Panel:
+                pass
+
+            return Panel
+        raise AttributeError(
+            "module 'pandas' has no attribute '{}'".format(name))
+else:
+    class Panel:
+        pass
+
+
 # module level doc-string
 __doc__ = """
 pandas - a powerful data analysis and manipulation library for Python

pandas/core/api.py

@@ -35,7 +35,6 @@
 
 from pandas.core.series import Series
 from pandas.core.frame import DataFrame
-from pandas.core.panel import Panel
 
 # TODO: Remove import when statsmodels updates #18264
 from pandas.core.reshape.reshape import get_dummies

pandas/core/dtypes/generic.py

@@ -45,7 +45,6 @@ def _check(cls, inst):
 ABCDataFrame = create_pandas_abc_type("ABCDataFrame", "_typ", ("dataframe", ))
 ABCSparseDataFrame = create_pandas_abc_type("ABCSparseDataFrame", "_subtyp",
                                             ("sparse_frame", ))
-ABCPanel = create_pandas_abc_type("ABCPanel", "_typ", ("panel",))
 ABCSparseSeries = create_pandas_abc_type("ABCSparseSeries", "_subtyp",
                                          ('sparse_series',
                                           'sparse_time_series'))

pandas/core/internals/concat.py

@@ -376,8 +376,6 @@ def is_uniform_join_units(join_units):
         all(not ju.is_na or ju.block.is_extension for ju in join_units) and
         # no blocks with indexers (as then the dimensions do not fit)
         all(not ju.indexers for ju in join_units) and
-        # disregard Panels
-        all(ju.block.ndim <= 2 for ju in join_units) and
         # only use this path when there is something to concatenate
         len(join_units) > 1)
 

pandas/core/internals/managers.py

@@ -42,7 +42,7 @@
 
 class BlockManager(PandasObject):
     """
-    Core internal data structure to implement DataFrame, Series, Panel, etc.
+    Core internal data structure to implement DataFrame, Series, etc.
 
     Manage a bunch of labeled 2D mixed-type ndarrays. Essentially it's a
     lightweight blocked set of labeled data to be manipulated by the DataFrame