Merge branch 'master' of https://github.com/pandas-dev/pandas into inline_cleanup

Author: jbrockmendel

asv_bench/benchmarks/index_object.py

@@ -199,3 +199,23 @@ def time_datetime_level_values_full(self):
 
     def time_datetime_level_values_sliced(self):
         self.mi[:10].values
+
+
+class Range(object):
+    goal_time = 0.2
+
+    def setup(self):
+        self.idx_inc = RangeIndex(start=0, stop=10**7, step=3)
+        self.idx_dec = RangeIndex(start=10**7, stop=-1, step=-3)
+
+    def time_max(self):
+        self.idx_inc.max()
+
+    def time_max_trivial(self):
+        self.idx_dec.max()
+
+    def time_min(self):
+        self.idx_dec.min()
+
+    def time_min_trivial(self):
+        self.idx_inc.min()

asv_bench/benchmarks/timestamp.py

@@ -81,3 +81,9 @@ def time_replace_across_dst(self):
 
     def time_replace_None(self):
         self.ts_tz.replace(tzinfo=None)
+
+    def time_to_pydatetime(self):
+        self.ts.to_pydatetime()
+
+    def time_to_pydatetime_tz(self):
+        self.ts_tz.to_pydatetime()

ci/requirements-3.6.build

@@ -2,7 +2,5 @@ python=3.6*
 python-dateutil
 pytz
 nomkl
+numpy
 cython
-
-# pin numpy that is built for all our deps
-numpy=1.13.1=py36_blas_openblas_201

doc/source/api.rst

@@ -1416,6 +1416,20 @@ Selecting
    Index.slice_indexer
    Index.slice_locs
 
+.. _api.numericindex:
+
+Numeric Index
+-------------
+
+.. autosummary::
+   :toctree: generated/
+   :template: autosummary/class_without_autosummary.rst
+
+   RangeIndex
+   Int64Index
+   UInt64Index
+   Float64Index
+
 .. _api.categoricalindex:
 
 CategoricalIndex

doc/source/whatsnew/v0.21.0.txt

@@ -116,6 +116,7 @@ Other Enhancements
 - :func:`Styler.where` has been implemented. It is as a convenience for :func:`Styler.applymap` and enables simple DataFrame styling on the Jupyter notebook (:issue:`17474`).
 - :func:`MultiIndex.is_monotonic_decreasing` has been implemented.  Previously returned ``False`` in all cases. (:issue:`16554`)
 - :func:`Categorical.rename_categories` now accepts a dict-like argument as `new_categories` and only updates the categories found in that dict. (:issue:`17336`)
+- :func:`read_excel` raises ``ImportError`` with a better message if ``xlrd`` is not installed. (:issue:`17613`)
 
 
 .. _whatsnew_0210.api_breaking:
@@ -134,7 +135,7 @@ We have updated our minimum supported versions of dependencies (:issue:`15206`,
 
    +--------------+-----------------+----------+
    | Package      | Minimum Version | Required |
-   +======================+=========+==========+
+   +==============+=================+==========+
    | Numpy        | 1.9.0           |    X     |
    +--------------+-----------------+----------+
    | Matplotlib   | 1.4.3           |          |
@@ -240,54 +241,53 @@ New Behaviour:
 Dtype Conversions
 ^^^^^^^^^^^^^^^^^
 
-- Previously assignments, ``.where()`` and ``.fillna()`` with a ``bool`` assignment, would coerce to
-  same the type (e.g. int / float), or raise for datetimelikes. These will now preseve the bools with ``object`` dtypes. (:issue:`16821`).
+Previously assignments, ``.where()`` and ``.fillna()`` with a ``bool`` assignment, would coerce to same the type (e.g. int / float), or raise for datetimelikes. These will now preseve the bools with ``object`` dtypes. (:issue:`16821`).
 
-  .. ipython:: python
+.. ipython:: python
 
-     s = Series([1, 2, 3])
+   s = Series([1, 2, 3])
 
-  .. code-block:: python
+.. code-block:: python
 
-     In [5]: s[1] = True
+   In [5]: s[1] = True
 
-     In [6]: s
-     Out[6]:
-     0    1
-     1    1
-     2    3
-     dtype: int64
+   In [6]: s
+   Out[6]:
+   0    1
+   1    1
+   2    3
+   dtype: int64
 
-  New Behavior
+New Behavior
 
-  .. ipython:: python
+.. ipython:: python
 
-     s[1] = True
-     s
+   s[1] = True
+   s
 
-- Previously, as assignment to a datetimelike with a non-datetimelike would coerce the
-  non-datetime-like item being assigned (:issue:`14145`).
+Previously, as assignment to a datetimelike with a non-datetimelike would coerce the
+non-datetime-like item being assigned (:issue:`14145`).
 
-  .. ipython:: python
+.. ipython:: python
 
-     s = pd.Series([pd.Timestamp('2011-01-01'), pd.Timestamp('2012-01-01')])
+   s = pd.Series([pd.Timestamp('2011-01-01'), pd.Timestamp('2012-01-01')])
 
-  .. code-block:: python
+.. code-block:: python
 
-     In [1]: s[1] = 1
+   In [1]: s[1] = 1
 
-     In [2]: s
-     Out[2]:
-     0   2011-01-01 00:00:00.000000000
-     1   1970-01-01 00:00:00.000000001
-     dtype: datetime64[ns]
+   In [2]: s
+   Out[2]:
+   0   2011-01-01 00:00:00.000000000
+   1   1970-01-01 00:00:00.000000001
+   dtype: datetime64[ns]
 
-  These now coerce to ``object`` dtype.
+These now coerce to ``object`` dtype.
 
-  .. ipython:: python
+.. ipython:: python
 
-     s[1] = 1
-     s
+   s[1] = 1
+   s
 
 - Inconsistent behavior in ``.where()`` with datetimelikes which would raise rather than coerce to ``object`` (:issue:`16402`)
 - Bug in assignment against ``int64`` data with ``np.ndarray`` with ``float64`` dtype may keep ``int64`` dtype (:issue:`14001`)
@@ -337,26 +337,26 @@ UTC Localization with Series
 
 Previously, :func:`to_datetime` did not localize datetime ``Series`` data when ``utc=True`` was passed. Now, :func:`to_datetime` will correctly localize ``Series`` with a ``datetime64[ns, UTC]`` dtype to be consistent with how list-like and ``Index`` data are handled. (:issue:`6415`).
 
-  Previous Behavior
+Previous Behavior
 
-  .. ipython:: python
+.. ipython:: python
 
-     s = Series(['20130101 00:00:00'] * 3)
+   s = Series(['20130101 00:00:00'] * 3)
 
-  .. code-block:: ipython
+.. code-block:: ipython
 
-     In [12]: pd.to_datetime(s, utc=True)
-     Out[12]:
-     0   2013-01-01
-     1   2013-01-01
-     2   2013-01-01
-     dtype: datetime64[ns]
+   In [12]: pd.to_datetime(s, utc=True)
+   Out[12]:
+   0   2013-01-01
+   1   2013-01-01
+   2   2013-01-01
+   dtype: datetime64[ns]
 
-  New Behavior
+New Behavior
 
-  .. ipython:: python
+.. ipython:: python
 
-     pd.to_datetime(s, utc=True)
+   pd.to_datetime(s, utc=True)
 
 Additionally, DataFrames with datetime columns that were parsed by :func:`read_sql_table` and :func:`read_sql_query` will also be localized to UTC only if the original SQL columns were timezone aware datetime columns.
 
@@ -409,9 +409,9 @@ Previous Behavior:
 
 New Behavior:
 
-  .. ipython:: python
+.. ipython:: python
 
-     pd.interval_range(start=0, end=4)
+   pd.interval_range(start=0, end=4)
 
 .. _whatsnew_0210.api:
 
@@ -473,6 +473,15 @@ Performance Improvements
 - Improved performance of :meth:`Categorical.set_categories` by not materializing the values (:issue:`17508`)
 - :attr:`Timestamp.microsecond` no longer re-computes on attribute access (:issue:`17331`)
 - Improved performance of the :class:`CategoricalIndex` for data that is already categorical dtype (:issue:`17513`)
+- Improved performance of :meth:`RangeIndex.min` and :meth:`RangeIndex.max` by using ``RangeIndex`` properties to perform the computations (:issue:`17607`)
+
+.. _whatsnew_0210.docs:
+
+Documentation Changes
+~~~~~~~~~~~~~~~~~~~~~
+
+- Several ``NaT`` method docstrings (e.g. :func:`NaT.ctime`) were incorrect (:issue:`17327`)
+- The documentation has had references to versions < v0.17 removed and cleaned up (:issue:`17442`, :issue:`17442`, :issue:`17404` & :issue:`17504`)
 
 .. _whatsnew_0210.bug_fixes:
 
@@ -522,12 +531,13 @@ I/O
 - Bug in :func:`read_stata` where the index was not set (:issue:`16342`)
 - Bug in :func:`read_html` where import check fails when run in multiple threads (:issue:`16928`)
 - Bug in :func:`read_csv` where automatic delimiter detection caused a ``TypeError`` to be thrown when a bad line was encountered rather than the correct error message (:issue:`13374`)
+- Bug in ``DataFrame.to_html()`` with ``notebook=True`` where DataFrames with named indices or non-MultiIndex indices had undesired horizontal or vertical alignment for column or row labels, respectively (:issue:`16792`)
 
 Plotting
 ^^^^^^^^
 - Bug in plotting methods using ``secondary_y`` and ``fontsize`` not setting secondary axis font size (:issue:`12565`)
 - Bug when plotting ``timedelta`` and ``datetime`` dtypes on y-axis (:issue:`16953`)
-- Line plots no longer assume monotonic x data when calculating xlims, they show the entire lines now even for unsorted x data. (:issue:`11310`)(:issue:`11471`)
+- Line plots no longer assume monotonic x data when calculating xlims, they show the entire lines now even for unsorted x data. (:issue:`11310`, :issue:`11471`)
 - With matplotlib 2.0.0 and above, calculation of x limits for line plots is left to matplotlib, so that its new default settings are applied. (:issue:`15495`)
 - Bug in ``Series.plot.bar`` or ``DataFramee.plot.bar`` with ``y`` not respecting user-passed ``color`` (:issue:`16822`)
 
@@ -572,10 +582,8 @@ Numeric
 Categorical
 ^^^^^^^^^^^
 - Bug in :func:`Series.isin` when called with a categorical (:issue`16639`)
-- Bug in the categorical constructor with empty values and categories causing
-  the ``.categories`` to be an empty ``Float64Index`` rather than an empty
-  ``Index`` with object dtype (:issue:`17248`)
-- Bug in categorical operations with :ref:`Series.cat <categorical.cat>' not preserving the original Series' name (:issue:`17509`)
+- Bug in the categorical constructor with empty values and categories causing the ``.categories`` to be an empty ``Float64Index`` rather than an empty ``Index`` with object dtype (:issue:`17248`)
+- Bug in categorical operations with :ref:`Series.cat <categorical.cat>' not preserving the original Series' name (:issue:`17509`)
 
 PyPy
 ^^^^
@@ -590,5 +598,3 @@ PyPy
 Other
 ^^^^^
 - Bug in :func:`eval` where the ``inplace`` parameter was being incorrectly handled (:issue:`16732`)
-- Several ``NaT`` method docstrings (e.g. :func:`NaT.ctime`) were incorrect (:issue:`17327`)
-- The documentation has had references to versions < v0.17 removed and cleaned up (:issue:`17442`, :issue:`17442`, :issue:`17404` & :issue:`17504`)

pandas/_libs/lib.pyx

@@ -1907,5 +1907,4 @@ cdef class BlockPlacement:
 
 
 include "reduce.pyx"
-include "properties.pyx"
 include "inference.pyx"

pandas/_libs/src/properties.pyx renamed to pandas/_libs/properties.pyx

@@ -1,5 +1,8 @@
+
+from cython cimport Py_ssize_t
+
 from cpython cimport (
-    PyDict_Contains, PyDict_GetItem, PyDict_GetItem, PyDict_SetItem)
+    PyDict_Contains, PyDict_GetItem, PyDict_SetItem)
 
 
 cdef class cache_readonly(object):

pandas/_libs/tslib.pyx

@@ -1158,18 +1158,13 @@ cdef class _Timestamp(datetime):
 
         If warn=True, issue a warning if nanoseconds is nonzero.
         """
-        cdef:
-            pandas_datetimestruct dts
-            _TSObject ts
-
         if self.nanosecond != 0 and warn:
             warnings.warn("Discarding nonzero nanoseconds in conversion",
                           UserWarning, stacklevel=2)
-        ts = convert_to_tsobject(self, self.tzinfo, None, 0, 0)
-        dts = ts.dts
-        return datetime(dts.year, dts.month, dts.day,
-                        dts.hour, dts.min, dts.sec,
-                        dts.us, ts.tzinfo)
+
+        return datetime(self.year, self.month, self.day,
+                        self.hour, self.minute, self.second,
+                        self.microsecond, self.tzinfo)
 
     cpdef to_datetime64(self):
         """ Returns a numpy.datetime64 object with 'ns' precision """

pandas/core/generic.py

@@ -9,7 +9,7 @@
 import numpy as np
 import pandas as pd
 
-from pandas._libs import tslib, lib
+from pandas._libs import tslib, lib, properties
 from pandas.core.dtypes.common import (
     _ensure_int64,
     _ensure_object,
@@ -258,7 +258,7 @@ def _setup_axes(cls, axes, info_axis=None, stat_axis=None, aliases=None,
         if build_axes:
 
             def set_axis(a, i):
-                setattr(cls, a, lib.AxisProperty(i))
+                setattr(cls, a, properties.AxisProperty(i))
                 cls._internal_names_set.add(a)
 
             if axes_are_reversed:

pandas/core/indexes/range.py

@@ -269,6 +269,24 @@ def copy(self, name=None, deep=False, dtype=None, **kwargs):
         return RangeIndex(name=name, fastpath=True,
                           **dict(self._get_data_as_items()))
 
+    def _minmax(self, meth):
+        no_steps = len(self) - 1
+        if no_steps == -1:
+            return np.nan
+        elif ((meth == 'min' and self._step > 0) or
+              (meth == 'max' and self._step < 0)):
+            return self._start
+
+        return self._start + self._step * no_steps
+
+    def min(self):
+        """The minimum value of the RangeIndex"""
+        return self._minmax('min')
+
+    def max(self):
+        """The maximum value of the RangeIndex"""
+        return self._minmax('max')
+
     def argsort(self, *args, **kwargs):
         """
         Returns the indices that would sort the index and its

pandas/io/excel.py

@@ -239,12 +239,17 @@ class ExcelFile(object):
 
     def __init__(self, io, **kwds):
 
-        import xlrd  # throw an ImportError if we need to
+        err_msg = "Install xlrd >= 0.9.0 for Excel support"
 
-        ver = tuple(map(int, xlrd.__VERSION__.split(".")[:2]))
-        if ver < (0, 9):  # pragma: no cover
-            raise ImportError("pandas requires xlrd >= 0.9.0 for excel "
-                              "support, current version " + xlrd.__VERSION__)
+        try:
+            import xlrd
+        except ImportError:
+            raise ImportError(err_msg)
+        else:
+            ver = tuple(map(int, xlrd.__VERSION__.split(".")[:2]))
+            if ver < (0, 9):  # pragma: no cover
+                raise ImportError(err_msg +
+                                  ". Current version " + xlrd.__VERSION__)
 
         # could be a str, ExcelFile, Book, etc.
         self.io = io