Merge pull request #3912 from cpcloud/try-convert-when-plotting

FIX/ENH: attempt soft conversion of object series before raising a TypeError when plotting

Author: cpcloud

RELEASE.rst

@@ -77,8 +77,10 @@ pandas 0.11.1
     dependencies offered for Linux) (GH3837_).
   - Plotting functions now raise a ``TypeError`` before trying to plot anything
     if the associated objects have have a dtype of ``object`` (GH1818_,
-    GH3572_). This happens before any drawing takes place which elimnates any
-    spurious plots from showing up.
+    GH3572_, GH3911_, GH3912_), but they will try to convert object arrays to
+    numeric arrays if possible so that you can still plot, for example, an
+    object array with floats. This happens before any drawing takes place which
+    elimnates any spurious plots from showing up.
   - Added Faq section on repr display options, to help users customize their setup.
   - ``where`` operations that result in block splitting are much faster (GH3733_)
   - Series and DataFrame hist methods now take a ``figsize`` argument (GH3834_)
@@ -341,13 +343,13 @@ pandas 0.11.1
 .. _GH3834: https://github.com/pydata/pandas/issues/3834
 .. _GH3873: https://github.com/pydata/pandas/issues/3873
 .. _GH3877: https://github.com/pydata/pandas/issues/3877
+.. _GH3659: https://github.com/pydata/pandas/issues/3659
+.. _GH3679: https://github.com/pydata/pandas/issues/3679
 .. _GH3880: https://github.com/pydata/pandas/issues/3880
-<<<<<<< HEAD
 .. _GH3911: https://github.com/pydata/pandas/issues/3911
-=======
 .. _GH3907: https://github.com/pydata/pandas/issues/3907
->>>>>>> 7b5933247b80174de4ba571e95a1add809dd9d09
-
+.. _GH3911: https://github.com/pydata/pandas/issues/3911
+.. _GH3912: https://github.com/pydata/pandas/issues/3912
 
 pandas 0.11.0
 =============

doc/source/v0.11.1.txt

@@ -300,9 +300,11 @@ Bug Fixes
 ~~~~~~~~~
 
   - Plotting functions now raise a ``TypeError`` before trying to plot anything
-    if the associated objects have have a ``dtype`` of ``object`` (GH1818_,
-    GH3572_).  This happens before any drawing takes place which elimnates any
-    spurious plots from showing up.
+    if the associated objects have have a dtype of ``object`` (GH1818_,
+    GH3572_, GH3911_, GH3912_), but they will try to convert object arrays to
+    numeric arrays if possible so that you can still plot, for example, an
+    object array with floats. This happens before any drawing takes place which
+    elimnates any spurious plots from showing up.
 
   - ``fillna`` methods now raise a ``TypeError`` if the ``value`` parameter is
     a list or tuple.
@@ -416,3 +418,5 @@ on GitHub for a complete list.
 .. _GH3659: https://github.com/pydata/pandas/issues/3659
 .. _GH3679: https://github.com/pydata/pandas/issues/3679
 .. _GH3907: https://github.com/pydata/pandas/issues/3907
+.. _GH3911: https://github.com/pydata/pandas/issues/3911
+.. _GH3912: https://github.com/pydata/pandas/issues/3912

pandas/io/common.py

@@ -9,6 +9,10 @@
 _VALID_URLS.discard('')
 
 
+class PerformanceWarning(Warning):
+    pass
+
+
 def _is_url(url):
     """Check to see if a URL has a valid protocol.
 
@@ -26,27 +30,29 @@ def _is_url(url):
     except:
         return False
 
+
 def _is_s3_url(url):
-    """ Check for an s3 url """
+    """Check for an s3 url"""
     try:
         return urlparse.urlparse(url).scheme == 's3'
     except:
         return False
 
+
 def get_filepath_or_buffer(filepath_or_buffer, encoding=None):
-    """ if the filepath_or_buffer is a url, translate and return the buffer
-        passthru otherwise
-
-        Parameters
-        ----------
-        filepath_or_buffer : a url, filepath, or buffer
-        encoding : the encoding to use to decode py3 bytes, default is 'utf-8'
-
-        Returns
-        -------
-        a filepath_or_buffer, the encoding
-        
-        """
+    """
+    If the filepath_or_buffer is a url, translate and return the buffer
+    passthru otherwise.
+
+    Parameters
+    ----------
+    filepath_or_buffer : a url, filepath, or buffer
+    encoding : the encoding to use to decode py3 bytes, default is 'utf-8'
+
+    Returns
+    -------
+    a filepath_or_buffer, the encoding
+    """
 
     if _is_url(filepath_or_buffer):
         from urllib2 import urlopen

pandas/io/pytables.py

@@ -12,23 +12,22 @@
 import warnings
 
 import numpy as np
-from pandas import (
-    Series, TimeSeries, DataFrame, Panel, Panel4D, Index,
-    MultiIndex, Int64Index, Timestamp
-)
+from pandas import (Series, TimeSeries, DataFrame, Panel, Panel4D, Index,
+                    MultiIndex, Int64Index, Timestamp)
 from pandas.sparse.api import SparseSeries, SparseDataFrame, SparsePanel
 from pandas.sparse.array import BlockIndex, IntIndex
 from pandas.tseries.api import PeriodIndex, DatetimeIndex
-from pandas.core.common import adjoin, isnull, is_list_like
-from pandas.core.algorithms import match, unique, factorize
+from pandas.core.common import adjoin, is_list_like
+from pandas.core.algorithms import match, unique
 from pandas.core.categorical import Categorical
-from pandas.core.common import _asarray_tuplesafe, _try_sort
+from pandas.core.common import _asarray_tuplesafe
 from pandas.core.internals import BlockManager, make_block
 from pandas.core.reshape import block2d_to_blocknd, factor_indexer
-from pandas.core.index import Int64Index, _ensure_index
+from pandas.core.index import _ensure_index
 import pandas.core.common as com
 from pandas.tools.merge import concat
 from pandas.util import py3compat
+from pandas.io.common import PerformanceWarning
 
 import pandas.lib as lib
 import pandas.algos as algos
@@ -42,32 +41,46 @@
 # PY3 encoding if we don't specify
 _default_encoding = 'UTF-8'
 
+
 def _ensure_decoded(s):
     """ if we have bytes, decode them to unicde """
     if isinstance(s, np.bytes_):
         s = s.decode('UTF-8')
     return s
+
+
 def _ensure_encoding(encoding):
     # set the encoding if we need
     if encoding is None:
         if py3compat.PY3:
             encoding = _default_encoding
     return encoding
 
-class IncompatibilityWarning(Warning): pass
+
+class IncompatibilityWarning(Warning):
+    pass
+
+
 incompatibility_doc = """
-where criteria is being ignored as this version [%s] is too old (or not-defined),
-read the file in and write it out to a new file to upgrade (with the copy_to method)
+where criteria is being ignored as this version [%s] is too old (or
+not-defined), read the file in and write it out to a new file to upgrade (with
+the copy_to method)
 """
-class AttributeConflictWarning(Warning): pass
+
+
+class AttributeConflictWarning(Warning):
+    pass
+
+
 attribute_conflict_doc = """
-the [%s] attribute of the existing index is [%s] which conflicts with the new [%s],
-resetting the attribute to None
+the [%s] attribute of the existing index is [%s] which conflicts with the new
+[%s], resetting the attribute to None
 """
-class PerformanceWarning(Warning): pass
+
+
 performance_doc = """
-your performance may suffer as PyTables will pickle object types that it cannot map
-directly to c-types [inferred_type->%s,key->%s] [items->%s]
+your performance may suffer as PyTables will pickle object types that it cannot
+map directly to c-types [inferred_type->%s,key->%s] [items->%s]
 """
 
 # map object types

pandas/tests/test_graphics.py

@@ -10,6 +10,7 @@
 from pandas.util.testing import ensure_clean
 from pandas.core.config import set_option
 
+
 import numpy as np
 
 from numpy.testing import assert_array_equal
@@ -189,15 +190,22 @@ def test_bootstrap_plot(self):
         from pandas.tools.plotting import bootstrap_plot
         _check_plot_works(bootstrap_plot, self.ts, size=10)
 
-    @slow
-    def test_all_invalid_plot_data(self):
+    def test_invalid_plot_data(self):
         s = Series(list('abcd'))
         kinds = 'line', 'bar', 'barh', 'kde', 'density'
 
         for kind in kinds:
             self.assertRaises(TypeError, s.plot, kind=kind)
 
     @slow
+    def test_valid_object_plot(self):
+        from pandas.io.common import PerformanceWarning
+        s = Series(range(10), dtype=object)
+        kinds = 'line', 'bar', 'barh', 'kde', 'density'
+
+        for kind in kinds:
+            _check_plot_works(s.plot, kind=kind)
+
     def test_partially_invalid_plot_data(self):
         s = Series(['a', 'b', 1.0, 2])
         kinds = 'line', 'bar', 'barh', 'kde', 'density'

pandas/tools/plotting.py

@@ -878,15 +878,20 @@ def _get_layout(self):
 
     def _compute_plot_data(self):
         try:
-            # might be a frame
+            # might be an ndframe
             numeric_data = self.data._get_numeric_data()
-        except AttributeError:
-            # a series, but no object dtypes allowed!
-            if self.data.dtype == np.object_:
-                raise TypeError('invalid dtype for plotting, please cast to a '
-                                'numeric dtype explicitly if you want to plot')
-
+        except AttributeError:  # TODO: rm in 0.12 (series-inherit-ndframe)
             numeric_data = self.data
+            orig_dtype = numeric_data.dtype
+
+            # possible object array of numeric data
+            if orig_dtype == np.object_:
+                numeric_data = numeric_data.convert_objects()  # soft convert
+
+                # still an object dtype so we can't plot it
+                if numeric_data.dtype == np.object_:
+                    raise TypeError('Series has object dtype and cannot be'
+                                    ' converted: no numeric data to plot')
 
         try:
             is_empty = numeric_data.empty
@@ -895,7 +900,8 @@ def _compute_plot_data(self):
 
         # no empty frames or series allowed
         if is_empty:
-            raise TypeError('No numeric data to plot')
+            raise TypeError('Empty {0!r}: no numeric data to '
+                            'plot'.format(numeric_data.__class__.__name__))
 
         self.data = numeric_data
 

pandas/util/testing.py

@@ -7,6 +7,7 @@
 import string
 import sys
 import tempfile
+import warnings
 
 from contextlib import contextmanager  # contextlib is available since 2.5
 
@@ -39,7 +40,7 @@
 
 def rands(n):
     choices = string.ascii_letters + string.digits
-    return ''.join([random.choice(choices) for _ in xrange(n)])
+    return ''.join(random.choice(choices) for _ in xrange(n))
 
 
 def randu(n):
@@ -746,3 +747,48 @@ def stdin_encoding(encoding=None):
     sys.stdin = SimpleMock(sys.stdin, "encoding", encoding)
     yield
     sys.stdin = _stdin
+
+
+@contextmanager
+def assert_produces_warning(expected_warning=Warning, filter_level="always"):
+    """
+    Context manager for running code that expects to raise (or not raise)
+    warnings.  Checks that code raises the expected warning and only the
+    expected warning. Pass ``False`` or ``None`` to check that it does *not*
+    raise a warning. Defaults to ``exception.Warning``, baseclass of all
+    Warnings. (basically a wrapper around ``warnings.catch_warnings``).
+
+    >>> import warnings
+    >>> with assert_produces_warning():
+    ...     warnings.warn(UserWarning())
+    ...
+    >>> with assert_produces_warning(False):
+    ...     warnings.warn(RuntimeWarning())
+    ...
+    Traceback (most recent call last):
+        ...
+    AssertionError: Caused unexpected warning(s): ['RuntimeWarning'].
+    >>> with assert_produces_warning(UserWarning):
+    ...     warnings.warn(RuntimeWarning())
+    Traceback (most recent call last):
+        ...
+    AssertionError: Did not see expected warning of class 'UserWarning'.
+
+    ..warn:: This is *not* thread-safe.
+    """
+    with warnings.catch_warnings(record=True) as w:
+        saw_warning = False
+        warnings.simplefilter(filter_level)
+        yield w
+        extra_warnings = []
+        for actual_warning in w:
+            if (expected_warning and issubclass(actual_warning.category,
+                                                expected_warning)):
+                saw_warning = True
+            else:
+                extra_warnings.append(actual_warning.category.__name__)
+        if expected_warning:
+            assert saw_warning, ("Did not see expected warning of class %r."
+                                 % expected_warning.__name__)
+            assert not extra_warnings, ("Caused unexpected warning(s): %r."
+                                        % extra_warnings)