Merge pull request #3787 from hayd/read_pickle_and_to_pickle

CLN deprecate save&load in favour of to_pickle&read_pickle

Author: hayd

RELEASE.rst

@@ -137,6 +137,8 @@ pandas 0.11.1
     - removed ``Excel`` support to ``pandas.io.excel``
     - added top-level ``pd.read_sql`` and ``to_sql`` DataFrame methods
     - removed ``clipboard`` support to ``pandas.io.clipboard``
+    - replace top-level and instance methods ``save`` and ``load`` with top-level ``read_pickle`` and
+    ``to_pickle`` instance method, ``save`` and ``load`` will give deprecation warning.  
   - the ``method`` and ``axis`` arguments of ``DataFrame.replace()`` are
     deprecated
   - Implement ``__nonzero__`` for ``NDFrame`` objects (GH3691_, GH3696_)

doc/source/api.rst

@@ -13,13 +13,12 @@ Input/Output
 Pickling
 ~~~~~~~~
 
-.. currentmodule:: pandas.core.common
+.. currentmodule:: pandas.io.pickle
 
 .. autosummary::
    :toctree: generated/
 
-   load
-   save
+   read_pickle
 
 Flat File
 ~~~~~~~~~
@@ -378,8 +377,7 @@ Serialization / IO / Conversion
    :toctree: generated/
 
    Series.from_csv
-   Series.load
-   Series.save
+   Series.to_pickle
    Series.to_csv
    Series.to_dict
    Series.to_sparse
@@ -601,8 +599,7 @@ Serialization / IO / Conversion
    DataFrame.from_items
    DataFrame.from_records
    DataFrame.info
-   DataFrame.load
-   DataFrame.save
+   DataFrame.to_pickle
    DataFrame.to_csv
    DataFrame.to_hdf
    DataFrame.to_dict
@@ -770,8 +767,7 @@ Serialization / IO / Conversion
    :toctree: generated/
 
    Panel.from_dict
-   Panel.load
-   Panel.save
+   Panel.to_pickle
    Panel.to_excel
    Panel.to_sparse
    Panel.to_frame

doc/source/basics.rst

@@ -1207,46 +1207,6 @@ While float dtypes are unchanged.
    casted
    casted.dtypes
 
-.. _basics.serialize:
-
-Pickling and serialization
---------------------------
-
-All pandas objects are equipped with ``save`` methods which use Python's
-``cPickle`` module to save data structures to disk using the pickle format.
-
-.. ipython:: python
-
-   df
-   df.save('foo.pickle')
-
-The ``load`` function in the ``pandas`` namespace can be used to load any
-pickled pandas object (or any other pickled object) from file:
-
-
-.. ipython:: python
-
-   load('foo.pickle')
-
-There is also a ``save`` function which takes any object as its first argument:
-
-.. ipython:: python
-
-   save(df, 'foo.pickle')
-   load('foo.pickle')
-
-.. ipython:: python
-   :suppress:
-
-   import os
-   os.remove('foo.pickle')
-
-.. warning::
-
-   Loading pickled data received from untrusted sources can be unsafe.
-
-   See: http://docs.python.org/2.7/library/pickle.html
-
 
 Working with package options
 ----------------------------

doc/source/io.rst

@@ -39,6 +39,7 @@ object.
     * ``read_html``
     * ``read_stata``
     * ``read_clipboard``
+    * ``read_pickle``
 
 The corresponding ``writer`` functions are object methods that are accessed like ``df.to_csv()``
 
@@ -50,6 +51,7 @@ The corresponding ``writer`` functions are object methods that are accessed like
     * ``to_html``
     * ``to_stata``
     * ``to_clipboard``
+    * ``to_pickle``
 
 .. _io.read_csv_table:
 
@@ -1442,7 +1444,42 @@ We can see that we got the same content back, which we had earlier written to th
    You may need to install xclip or xsel (with gtk or PyQt4 modules) on Linux to use these methods.
 
 
+.. _io.serialize:
 
+Pickling and serialization
+--------------------------
+
+All pandas objects are equipped with ``to_pickle`` methods which use Python's
+``cPickle`` module to save data structures to disk using the pickle format.
+
+.. ipython:: python
+
+   df
+   df.to_pickle('foo.pkl')
+
+The ``read_pickle`` function in the ``pandas`` namespace can be used to load
+any pickled pandas object (or any other pickled object) from file:
+
+
+.. ipython:: python
+
+   read_pickle('foo.pkl')
+
+.. ipython:: python
+   :suppress:
+
+   import os
+   os.remove('foo.pkl')
+
+.. warning::
+
+   Loading pickled data received from untrusted sources can be unsafe.
+
+   See: http://docs.python.org/2.7/library/pickle.html
+
+.. note::
+
+    These methods were previously ``save`` and ``load``, now deprecated.
 
 .. _io.excel:
 

pandas/core/api.py

@@ -4,7 +4,7 @@
 import numpy as np
 
 from pandas.core.algorithms import factorize, match, unique, value_counts
-from pandas.core.common import isnull, notnull, save, load
+from pandas.core.common import isnull, notnull
 from pandas.core.categorical import Categorical, Factor
 from pandas.core.format import (set_printoptions, reset_printoptions,
                                 set_eng_float_format)
@@ -28,6 +28,7 @@
 
 # legacy
 from pandas.core.daterange import DateRange  # deprecated
+from pandas.core.common import save, load # deprecated, remove in 0.12
 import pandas.core.datetools as datetools
 
 from pandas.core.config import get_option, set_option, reset_option,\

pandas/core/common.py

@@ -1,11 +1,6 @@
 """
 Misc tools for implementing data structures
 """
-# XXX: HACK for NumPy 1.5.1 to suppress warnings
-try:
-    import cPickle as pickle
-except ImportError:  # pragma: no cover
-    import pickle
 
 import itertools
 from datetime import datetime
@@ -1668,49 +1663,6 @@ def _all_none(*args):
     return True
 
 
-def save(obj, path):
-    """
-    Pickle (serialize) object to input file path
-
-    Parameters
-    ----------
-    obj : any object
-    path : string
-        File path
-    """
-    f = open(path, 'wb')
-    try:
-        pickle.dump(obj, f, protocol=pickle.HIGHEST_PROTOCOL)
-    finally:
-        f.close()
-
-
-def load(path):
-    """
-    Load pickled pandas object (or any other pickled object) from the specified
-    file path
-
-    Warning: Loading pickled data received from untrusted sources can be unsafe.
-    See: http://docs.python.org/2.7/library/pickle.html
-
-    Parameters
-    ----------
-    path : string
-        File path
-
-    Returns
-    -------
-    unpickled : type of object stored in file
-    """
-    try:
-        with open(path,'rb') as fh:
-            return pickle.load(fh)
-    except:
-        if not py3compat.PY3:
-            raise
-        with open(path,'rb') as fh:
-            return pickle.load(fh, encoding='latin1')
-
 class UTF8Recoder:
     """
     Iterator that reads an encoded stream and reencodes the input to UTF-8
@@ -2109,3 +2061,40 @@ def console_encode(object, **kwds):
     """
     return pprint_thing_encoded(object,
                                 get_option("display.encoding"))
+
+def load(path):  # TODO remove in 0.12
+    """
+    Load pickled pandas object (or any other pickled object) from the specified
+    file path
+
+    Warning: Loading pickled data received from untrusted sources can be unsafe.
+    See: http://docs.python.org/2.7/library/pickle.html
+
+    Parameters
+    ----------
+    path : string
+        File path
+
+    Returns
+    -------
+    unpickled : type of object stored in file
+    """
+    import warnings
+    warnings.warn("load is deprecated, use read_pickle", FutureWarning)
+    from pandas.io.pickle import read_pickle
+    return read_pickle(path)
+
+def save(obj, path):  # TODO remove in 0.12
+    '''
+    Pickle (serialize) object to input file path
+
+    Parameters
+    ----------
+    obj : any object
+    path : string
+        File path
+    '''
+    import warnings
+    warnings.warn("save is deprecated, use obj.to_pickle", FutureWarning)
+    from pandas.io.pickle import to_pickle
+    return to_pickle(obj, path)

pandas/core/generic.py

@@ -24,12 +24,29 @@ class PandasObject(object):
     _AXIS_ALIASES = {}
     _AXIS_NAMES = dict((v, k) for k, v in _AXIS_NUMBERS.iteritems())
 
-    def save(self, path):
-        com.save(self, path)
+    def to_pickle(self, path):
+        """
+        Pickle (serialize) object to input file path
 
-    @classmethod
-    def load(cls, path):
-        return com.load(path)
+        Parameters
+        ----------
+        path : string
+            File path
+        """
+        from pandas.io.pickle import to_pickle
+        return to_pickle(self, path)
+
+    def save(self, path):  # TODO remove in 0.12
+        import warnings
+        from pandas.io.pickle import to_pickle
+        warnings.warn("save is deprecated, use to_pickle", FutureWarning)
+        return to_pickle(self, path)
+
+    def load(self, path):  # TODO remove in 0.12
+        import warnings
+        from pandas.io.pickle import read_pickle
+        warnings.warn("load is deprecated, use pd.read_pickle", FutureWarning)
+        return read_pickle(path)
 
     def __hash__(self):
         raise TypeError('{0!r} objects are mutable, thus they cannot be'

pandas/io/api.py

@@ -10,3 +10,4 @@
 from pandas.io.html import read_html
 from pandas.io.sql import read_sql
 from pandas.io.stata import read_stata
+from pandas.io.pickle import read_pickle

pandas/io/pickle.py

@@ -0,0 +1,48 @@
+# XXX: HACK for NumPy 1.5.1 to suppress warnings
+try:
+    import cPickle as pickle
+except ImportError:  # pragma: no cover
+    import pickle
+
+def to_pickle(obj, path):
+    """
+    Pickle (serialize) object to input file path
+
+    Parameters
+    ----------
+    obj : any object
+    path : string
+        File path
+    """
+    f = open(path, 'wb')
+    try:
+        pickle.dump(obj, f, protocol=pickle.HIGHEST_PROTOCOL)
+    finally:
+        f.close()
+
+def read_pickle(path):
+    """
+    Load pickled pandas object (or any other pickled object) from the specified
+    file path
+
+    Warning: Loading pickled data received from untrusted sources can be unsafe.
+    See: http://docs.python.org/2.7/library/pickle.html
+
+    Parameters
+    ----------
+    path : string
+        File path
+
+    Returns
+    -------
+    unpickled : type of object stored in file
+    """
+    try:
+        with open(path,'rb') as fh:
+            return pickle.load(fh)
+    except:
+        from pandas.util import py3compat
+        if not py3compat.PY3:
+            raise
+        with open(path,'rb') as fh:
+            return pickle.load(fh, encoding='latin1')

pandas/sparse/tests/test_sparse.py

@@ -9,6 +9,7 @@
 
 from numpy import nan
 import numpy as np
+import pandas as pd
 dec = np.testing.dec
 
 from pandas.util.testing import (assert_almost_equal, assert_series_equal,

pandas/tests/test_index.py

@@ -1080,7 +1080,7 @@ def test_legacy_v2_unpickle(self):
         pth, _ = os.path.split(os.path.abspath(__file__))
         filepath = os.path.join(pth, 'data', 'mindex_073.pickle')
 
-        obj = com.load(filepath)
+        obj = pd.read_pickle(filepath)
 
         obj2 = MultiIndex.from_tuples(obj.values)
         self.assert_(obj.equals(obj2))