Merge pull request #7954 from cpcloud/drop-np16

CI: Drop numpy 1.6 support

Author: cpcloud

README.md

@@ -90,7 +90,7 @@ pip install pandas
 ```
 
 ## Dependencies
-- [NumPy](http://www.numpy.org): 1.6.1 or higher
+- [NumPy](http://www.numpy.org): 1.7.0 or higher
 - [python-dateutil](http://labix.org/python-dateutil): 1.5 or higher
 - [pytz](http://pytz.sourceforge.net)
     - Needed for time zone support with ``pandas.date_range``

ci/requirements-2.6.txt

@@ -1,4 +1,4 @@
-numpy==1.6.1
+numpy==1.7.0
 cython==0.19.1
 python-dateutil==1.5
 pytz==2013b

ci/requirements-2.7_LOCALE.txt

@@ -4,7 +4,7 @@ xlwt==0.7.5
 openpyxl==1.6.2
 xlsxwriter==0.4.6
 xlrd==0.9.2
-numpy==1.6.1
+numpy==1.7.1
 cython==0.19.1
 bottleneck==0.6.0
 matplotlib==1.3.0

doc/source/install.rst

@@ -247,7 +247,7 @@ installed), make sure you have `nose
 Dependencies
 ------------
 
-  * `NumPy <http://www.numpy.org>`__: 1.6.1 or higher
+  * `NumPy <http://www.numpy.org>`__: 1.7.0 or higher
   * `python-dateutil <http://labix.org/python-dateutil>`__ 1.5
   * `pytz <http://pytz.sourceforge.net/>`__
      * Needed for time zone support

doc/source/timeseries.rst

@@ -1685,23 +1685,3 @@ yields another ``timedelta64[ns]`` dtypes Series.
 
    td * -1
    td * Series([1,2,3,4])
-
-Numpy < 1.7 Compatibility
-~~~~~~~~~~~~~~~~~~~~~~~~~
-
-Numpy < 1.7 has a broken ``timedelta64`` type that does not correctly work
-for arithmetic. pandas bypasses this, but for frequency conversion as above,
-you need to create the divisor yourself. The ``np.timetimedelta64`` type only
-has 1 argument, the number of **micro** seconds.
-
-The following are equivalent statements in the two versions of numpy.
-
-.. code-block:: python
-
-   from distutils.version import LooseVersion
-   if LooseVersion(np.__version__) <= '1.6.2':
-       y / np.timedelta(86400*int(1e6))
-       y / np.timedelta(int(1e6))
-   else:
-       y / np.timedelta64(1,'D')
-       y / np.timedelta64(1,'s')

doc/source/v0.15.0.txt

@@ -7,6 +7,12 @@ This is a major release from 0.14.1 and includes a small number of API changes,
 enhancements, and performance improvements along with a large number of bug fixes. We recommend that all
 users upgrade to this version.
 
+.. warning::
+
+   pandas >= 0.15.0 will no longer support compatibility with NumPy versions <
+   1.7.0. If you want to use the latest versions of pandas, please upgrade to
+   NumPy >= 1.7.0.
+
 - Highlights include:
 
   - The ``Categorical`` type was integrated as a first-class pandas type, see :ref:`here <whatsnew_0150.cat>`

pandas/__init__.py

@@ -1,5 +1,6 @@
 # pylint: disable-msg=W0614,W0401,W0611,W0622
 
+
 __docformat__ = 'restructuredtext'
 
 try:
@@ -18,6 +19,7 @@
 from datetime import datetime
 import numpy as np
 
+
 # XXX: HACK for NumPy 1.5.1 to suppress warnings
 try:
     np.seterr(all='ignore')
@@ -27,14 +29,20 @@
 # numpy versioning
 from distutils.version import LooseVersion
 _np_version = np.version.short_version
-_np_version_under1p6 = LooseVersion(_np_version) < '1.6'
-_np_version_under1p7 = LooseVersion(_np_version) < '1.7'
 _np_version_under1p8 = LooseVersion(_np_version) < '1.8'
 _np_version_under1p9 = LooseVersion(_np_version) < '1.9'
 
+
 from pandas.version import version as __version__
 from pandas.info import __doc__
 
+
+if LooseVersion(_np_version) < '1.7.0':
+    raise ImportError('pandas {0} is incompatible with numpy < 1.7.0, '
+                      'your numpy version is {1}. Please upgrade numpy to'
+                      ' >= 1.7.0 to use pandas version {0}'.format(__version__,
+                                                                   _np_version))
+
 # let init-time option registration happen
 import pandas.core.config_init
 

pandas/core/base.py

@@ -298,7 +298,12 @@ def ndim(self):
 
     def item(self):
         """ return the first element of the underlying data as a python scalar """
-        return self.values.item()
+        try:
+            return self.values.item()
+        except IndexError:
+            # copy numpy's message here because Py26 raises an IndexError
+            raise ValueError('can only convert an array of size 1 to a '
+                             'Python scalar')
 
     @property
     def data(self):

pandas/core/common.py

@@ -1848,6 +1848,8 @@ def _possibly_cast_to_datetime(value, dtype, coerce=False):
     """ try to cast the array/value to a datetimelike dtype, converting float
     nan to iNaT
     """
+    from pandas.tseries.timedeltas import _possibly_cast_to_timedelta
+    from pandas.tseries.tools import to_datetime
 
     if dtype is not None:
         if isinstance(dtype, compat.string_types):
@@ -1886,13 +1888,11 @@ def _possibly_cast_to_datetime(value, dtype, coerce=False):
                 elif np.prod(value.shape) and value.dtype != dtype:
                     try:
                         if is_datetime64:
-                            from pandas.tseries.tools import to_datetime
                             value = to_datetime(value, coerce=coerce).values
                         elif is_timedelta64:
-                            from pandas.tseries.timedeltas import \
-                                _possibly_cast_to_timedelta
-                            value = _possibly_cast_to_timedelta(value, coerce='compat', dtype=dtype)
-                    except:
+                            value = _possibly_cast_to_timedelta(value,
+                                                                dtype=dtype)
+                    except (AttributeError, ValueError):
                         pass
 
     else:
@@ -1901,28 +1901,20 @@ def _possibly_cast_to_datetime(value, dtype, coerce=False):
 
         # catch a datetime/timedelta that is not of ns variety
         # and no coercion specified
-        if (is_array and value.dtype.kind in ['M','m']):
+        if is_array and value.dtype.kind in ['M', 'm']:
             dtype = value.dtype
 
             if dtype.kind == 'M' and dtype != _NS_DTYPE:
                 value = value.astype(_NS_DTYPE)
 
             elif dtype.kind == 'm' and dtype != _TD_DTYPE:
-                from pandas.tseries.timedeltas import \
-                     _possibly_cast_to_timedelta
-                value = _possibly_cast_to_timedelta(value, coerce='compat')
+                value = _possibly_cast_to_timedelta(value)
 
         # only do this if we have an array and the dtype of the array is not
         # setup already we are not an integer/object, so don't bother with this
         # conversion
-        elif (is_array and not (
-            issubclass(value.dtype.type, np.integer) or
-            value.dtype == np.object_)):
-            pass
-
-        # try to infer if we have a datetimelike here
-        # otherwise pass thru
-        else:
+        elif not (is_array and not (issubclass(value.dtype.type, np.integer) or
+                                    value.dtype == np.object_)):
             value = _possibly_infer_to_datetimelike(value)
 
     return value

pandas/core/generic.py

@@ -16,7 +16,7 @@
 from pandas.core.internals import BlockManager
 import pandas.core.common as com
 import pandas.core.datetools as datetools
-from pandas import compat, _np_version_under1p7
+from pandas import compat
 from pandas.compat import map, zip, lrange, string_types, isidentifier, lmap
 from pandas.core.common import (isnull, notnull, is_list_like,
                                 _values_from_object, _maybe_promote,
@@ -3613,21 +3613,6 @@ def abs(self):
         -------
         abs: type of caller
         """
-
-        # suprimo numpy 1.6 hacking
-        # for timedeltas
-        if _np_version_under1p7:
-
-            def _convert_timedeltas(x):
-                if x.dtype.kind == 'm':
-                    return np.abs(x.view('i8')).astype(x.dtype)
-                return np.abs(x)
-
-            if self.ndim == 1:
-                return _convert_timedeltas(self)
-            elif self.ndim == 2:
-                return  self.apply(_convert_timedeltas)
-
         return np.abs(self)
 
     _shared_docs['describe'] = """

pandas/core/groupby.py

@@ -26,7 +26,6 @@
                                is_timedelta64_dtype, is_datetime64_dtype,
                                is_categorical_dtype, _values_from_object)
 from pandas.core.config import option_context
-from pandas import _np_version_under1p7
 import pandas.lib as lib
 from pandas.lib import Timestamp
 import pandas.tslib as tslib
@@ -2764,18 +2763,21 @@ def _wrap_applied_output(self, keys, values, not_indexed_same=False):
 
                         # normally use vstack as its faster than concat
                         # and if we have mi-columns
-                        if not _np_version_under1p7 or isinstance(v.index,MultiIndex) or key_index is None:
-                            stacked_values = np.vstack([np.asarray(x) for x in values])
-                            result = DataFrame(stacked_values,index=key_index,columns=index)
+                        if isinstance(v.index, MultiIndex) or key_index is None:
+                            stacked_values = np.vstack(map(np.asarray, values))
+                            result = DataFrame(stacked_values, index=key_index,
+                                               columns=index)
                         else:
                             # GH5788 instead of stacking; concat gets the dtypes correct
                             from pandas.tools.merge import concat
-                            result = concat(values,keys=key_index,names=key_index.names,
+                            result = concat(values, keys=key_index,
+                                            names=key_index.names,
                                             axis=self.axis).unstack()
                             result.columns = index
                     else:
-                        stacked_values = np.vstack([np.asarray(x) for x in values])
-                        result = DataFrame(stacked_values.T,index=v.index,columns=key_index)
+                        stacked_values = np.vstack(map(np.asarray, values))
+                        result = DataFrame(stacked_values.T, index=v.index,
+                                           columns=key_index)
 
                 except (ValueError, AttributeError):
                     # GH1738: values is list of arrays of unequal lengths fall

pandas/core/internals.py

@@ -25,7 +25,7 @@
 from pandas.util.decorators import cache_readonly
 
 from pandas.tslib import Timestamp
-from pandas import compat, _np_version_under1p7
+from pandas import compat
 from pandas.compat import range, map, zip, u
 from pandas.tseries.timedeltas import _coerce_scalar_to_timedelta_type
 
@@ -1298,10 +1298,8 @@ def to_native_types(self, slicer=None, na_rep=None, **kwargs):
     def get_values(self, dtype=None):
         # return object dtypes as datetime.timedeltas
         if dtype == object:
-            if _np_version_under1p7:
-                return self.values.astype('object')
             return lib.map_infer(self.values.ravel(),
-                                 lambda x: timedelta(microseconds=x.item()/1000)
+                                 lambda x: timedelta(microseconds=x.item() / 1000)
                                  ).reshape(self.values.shape)
         return self.values
 

pandas/core/ops.py

@@ -258,9 +258,7 @@ def __init__(self, left, right, name):
         self.is_datetime_lhs = com.is_datetime64_dtype(left)
         self.is_integer_lhs = left.dtype.kind in ['i', 'u']
         self.is_datetime_rhs = com.is_datetime64_dtype(rvalues)
-        self.is_timedelta_rhs = (com.is_timedelta64_dtype(rvalues)
-                                 or (not self.is_datetime_rhs
-                                     and pd._np_version_under1p7))
+        self.is_timedelta_rhs = com.is_timedelta64_dtype(rvalues)
         self.is_integer_rhs = rvalues.dtype.kind in ('i', 'u')
 
         self._validate()
@@ -318,7 +316,7 @@ def _convert_to_array(self, values, name=None, other=None):
         """converts values to ndarray"""
         from pandas.tseries.timedeltas import _possibly_cast_to_timedelta
 
-        coerce = 'compat' if pd._np_version_under1p7 else True
+        coerce = True
         if not is_list_like(values):
             values = np.array([values])
         inferred_type = lib.infer_dtype(values)
@@ -648,13 +646,7 @@ def _radd_compat(left, right):
     try:
         output = radd(left, right)
     except TypeError:
-        cond = (pd._np_version_under1p6 and
-                left.dtype == np.object_)
-        if cond:  # pragma: no cover
-            output = np.empty_like(left)
-            output.flat[:] = [radd(x, right) for x in left.flat]
-        else:
-            raise
+        raise
 
     return output
 

pandas/io/pytables.py

@@ -14,7 +14,7 @@
 
 import numpy as np
 from pandas import (Series, TimeSeries, DataFrame, Panel, Panel4D, Index,
-                    MultiIndex, Int64Index, Timestamp, _np_version_under1p7)
+                    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
@@ -1721,9 +1721,6 @@ def set_atom(self, block, block_items, existing_col, min_itemsize,
         if inferred_type == 'datetime64':
             self.set_atom_datetime64(block)
         elif dtype == 'timedelta64[ns]':
-            if _np_version_under1p7:
-                raise TypeError(
-                    "timdelta64 is not supported under under numpy < 1.7")
             self.set_atom_timedelta64(block)
         elif inferred_type == 'date':
             raise TypeError(
@@ -2240,9 +2237,6 @@ def read_array(self, key):
             if dtype == u('datetime64'):
                 ret = np.array(ret, dtype='M8[ns]')
             elif dtype == u('timedelta64'):
-                if _np_version_under1p7:
-                    raise TypeError(
-                        "timedelta64 is not supported under under numpy < 1.7")
                 ret = np.array(ret, dtype='m8[ns]')
 
         if transposed:

pandas/io/tests/test_json/test_pandas.py

@@ -601,8 +601,6 @@ def test_url(self):
             self.assertEqual(result[c].dtype, 'datetime64[ns]')
 
     def test_timedelta(self):
-        tm._skip_if_not_numpy17_friendly()
-
         from datetime import timedelta
         converter = lambda x: pd.to_timedelta(x,unit='ms')
 

pandas/io/tests/test_pytables.py

@@ -22,7 +22,7 @@
                                  assert_frame_equal,
                                  assert_series_equal)
 from pandas import concat, Timestamp
-from pandas import compat, _np_version_under1p7
+from pandas import compat
 from pandas.compat import range, lrange, u
 from pandas.util.testing import assert_produces_warning
 
@@ -2159,8 +2159,6 @@ def setTZ(tz):
             setTZ(orig_tz)
 
     def test_append_with_timedelta(self):
-        tm._skip_if_not_numpy17_friendly()
-
         # GH 3577
         # append timedelta
 

pandas/io/tests/test_sql.py

@@ -36,7 +36,6 @@
 
 import pandas.io.sql as sql
 import pandas.util.testing as tm
-from pandas import _np_version_under1p7
 
 
 try:
@@ -509,8 +508,6 @@ def test_date_and_index(self):
 
     def test_timedelta(self):
         # see #6921
-        tm._skip_if_not_numpy17_friendly()
-
         df = to_timedelta(Series(['00:00:01', '00:00:03'], name='foo')).to_frame()
         with tm.assert_produces_warning(UserWarning):
             df.to_sql('test_timedelta', self.conn)