Merge pull request pandas-dev#10 from jbrockmendel/disown8

Another rebase

Author: TomAugspurger

asv_bench/benchmarks/period.py

@@ -1,5 +1,6 @@
 from pandas import (
     DataFrame, Period, PeriodIndex, Series, date_range, period_range)
+from pandas.tseries.frequencies import to_offset
 
 
 class PeriodProperties(object):
@@ -35,25 +36,48 @@ def time_asfreq(self, freq):
         self.per.asfreq('A')
 
 
+class PeriodConstructor(object):
+    params = [['D'], [True, False]]
+    param_names = ['freq', 'is_offset']
+
+    def setup(self, freq, is_offset):
+        if is_offset:
+            self.freq = to_offset(freq)
+        else:
+            self.freq = freq
+
+    def time_period_constructor(self, freq, is_offset):
+        Period('2012-06-01', freq=freq)
+
+
 class PeriodIndexConstructor(object):
 
-    params = ['D']
-    param_names = ['freq']
+    params = [['D'], [True, False]]
+    param_names = ['freq', 'is_offset']
 
-    def setup(self, freq):
+    def setup(self, freq, is_offset):
         self.rng = date_range('1985', periods=1000)
         self.rng2 = date_range('1985', periods=1000).to_pydatetime()
         self.ints = list(range(2000, 3000))
-
-    def time_from_date_range(self, freq):
+        self.daily_ints = date_range('1/1/2000', periods=1000,
+                                     freq=freq).strftime('%Y%m%d').map(int)
+        if is_offset:
+            self.freq = to_offset(freq)
+        else:
+            self.freq = freq
+
+    def time_from_date_range(self, freq, is_offset):
         PeriodIndex(self.rng, freq=freq)
 
-    def time_from_pydatetime(self, freq):
+    def time_from_pydatetime(self, freq, is_offset):
         PeriodIndex(self.rng2, freq=freq)
 
-    def time_from_ints(self, freq):
+    def time_from_ints(self, freq, is_offset):
         PeriodIndex(self.ints, freq=freq)
 
+    def time_from_ints_daily(self, freq, is_offset):
+        PeriodIndex(self.daily_ints, freq=freq)
+
 
 class DataFramePeriodColumn(object):
 

doc/source/whatsnew/v0.24.0.rst

@@ -1320,6 +1320,7 @@ Performance Improvements
 - Improved performance of :meth:`~DataFrame.where` for Categorical data (:issue:`24077`)
 - Improved performance of iterating over a :class:`Series`. Using :meth:`DataFrame.itertuples` now creates iterators
   without internally allocating lists of all elements (:issue:`20783`)
+- Improved performance of :class:`Period` constructor, additionally benefitting ``PeriodArray`` and ``PeriodIndex`` creation (:issue:`24084` and :issue:`24118`)
 
 .. _whatsnew_0240.docs:
 

pandas/_libs/tslibs/parsing.pyx

@@ -47,6 +47,20 @@ cdef set _not_datelike_strings = {'a', 'A', 'm', 'M', 'p', 'P', 't', 'T'}
 
 # ----------------------------------------------------------------------
 
+_get_option = None
+
+
+def get_option(param):
+    """ Defer import of get_option to break an import cycle that caused
+    significant performance degradation in Period construction. See
+    GH#24118 for details
+    """
+    global _get_option
+    if _get_option is None:
+        from pandas.core.config import get_option
+        _get_option = get_option
+    return _get_option(param)
+
 
 def parse_datetime_string(date_string, freq=None, dayfirst=False,
                           yearfirst=False, **kwargs):
@@ -117,7 +131,6 @@ def parse_time_string(arg, freq=None, dayfirst=None, yearfirst=None):
         freq = freq.rule_code
 
     if dayfirst is None or yearfirst is None:
-        from pandas.core.config import get_option
         if dayfirst is None:
             dayfirst = get_option("display.date_dayfirst")
         if yearfirst is None:

pandas/conftest.py

@@ -275,7 +275,12 @@ def join_type(request):
 
 
 @pytest.fixture
-def datapath(request):
+def strict_data_files(pytestconfig):
+    return pytestconfig.getoption("--strict-data-files")
+
+
+@pytest.fixture
+def datapath(strict_data_files):
     """Get the path to a data file.
 
     Parameters
@@ -297,7 +302,7 @@ def datapath(request):
     def deco(*args):
         path = os.path.join(BASE_PATH, *args)
         if not os.path.exists(path):
-            if request.config.getoption("--strict-data-files"):
+            if strict_data_files:
                 msg = "Could not find file {} and --strict-data-files is set."
                 raise ValueError(msg.format(path))
             else:

pandas/core/arrays/datetimelike.py

@@ -499,6 +499,10 @@ def __setitem__(
 
         if is_list_like(value):
             is_slice = isinstance(key, slice)
+
+            if lib.is_scalar(key):
+                raise ValueError("setting an array element with a sequence.")
+
             if (not is_slice
                     and len(key) != len(value)
                     and not com.is_bool_indexer(key)):

pandas/core/base.py

@@ -973,10 +973,16 @@ def _ndarray_values(self):
     def empty(self):
         return not self.size
 
-    def max(self):
+    def max(self, axis=None, skipna=True):
         """
         Return the maximum value of the Index.
 
+        Parameters
+        ----------
+        axis : int, optional
+            For compatibility with NumPy. Only 0 or None are allowed.
+        skipna : bool, default True
+
         Returns
         -------
         scalar
@@ -1004,22 +1010,36 @@ def max(self):
         >>> idx.max()
         ('b', 2)
         """
-        return nanops.nanmax(self.values)
+        nv.validate_minmax_axis(axis)
+        return nanops.nanmax(self._values, skipna=skipna)
 
-    def argmax(self, axis=None):
+    def argmax(self, axis=None, skipna=True):
         """
         Return a ndarray of the maximum argument indexer.
 
+        Parameters
+        ----------
+        axis : {None}
+            Dummy argument for consistency with Series
+        skipna : bool, default True
+
         See Also
         --------
         numpy.ndarray.argmax
         """
-        return nanops.nanargmax(self.values)
+        nv.validate_minmax_axis(axis)
+        return nanops.nanargmax(self._values, skipna=skipna)
 
-    def min(self):
+    def min(self, axis=None, skipna=True):
         """
         Return the minimum value of the Index.
 
+        Parameters
+        ----------
+        axis : {None}
+            Dummy argument for consistency with Series
+        skipna : bool, default True
+
         Returns
         -------
         scalar
@@ -1047,17 +1067,25 @@ def min(self):
         >>> idx.min()
         ('a', 1)
         """
-        return nanops.nanmin(self.values)
+        nv.validate_minmax_axis(axis)
+        return nanops.nanmin(self._values, skipna=skipna)
 
-    def argmin(self, axis=None):
+    def argmin(self, axis=None, skipna=True):
         """
         Return a ndarray of the minimum argument indexer.
 
+        Parameters
+        ----------
+        axis : {None}
+            Dummy argument for consistency with Series
+        skipna : bool, default True
+
         See Also
         --------
         numpy.ndarray.argmin
         """
-        return nanops.nanargmin(self.values)
+        nv.validate_minmax_axis(axis)
+        return nanops.nanargmin(self._values, skipna=skipna)
 
     def tolist(self):
         """
@@ -1110,7 +1138,7 @@ def _reduce(self, op, name, axis=0, skipna=True, numeric_only=None,
         if func is None:
             raise TypeError("{klass} cannot perform the operation {op}".format(
                             klass=self.__class__.__name__, op=name))
-        return func(**kwds)
+        return func(skipna=skipna, **kwds)
 
     def _map_values(self, mapper, na_action=None):
         """

pandas/core/dtypes/missing.py

@@ -198,6 +198,8 @@ def _isna_ndarraylike(obj):
         else:
             values = obj
         result = values.isna()
+    elif isinstance(obj, ABCDatetimeArray):
+        return obj.isna()
     elif is_string_dtype(dtype):
         # Working around NumPy ticket 1542
         shape = values.shape

pandas/core/indexes/datetimelike.py

@@ -41,6 +41,7 @@ class DatetimeIndexOpsMixin(ExtensionOpsMixin):
     # override DatetimeLikeArrayMixin method
     copy = Index.copy
     view = Index.view
+    __setitem__ = Index.__setitem__
 
     # DatetimeLikeArrayMixin assumes subclasses are mutable, so these are
     # properties there.  They can be made into cache_readonly for Index
@@ -324,35 +325,41 @@ def tolist(self):
         """
         return list(self.astype(object))
 
-    def min(self, axis=None, *args, **kwargs):
+    def min(self, axis=None, skipna=True, *args, **kwargs):
         """
         Return the minimum value of the Index or minimum along
         an axis.
 
         See Also
         --------
         numpy.ndarray.min
+        Series.min : Return the minimum value in a Series.
         """
         nv.validate_min(args, kwargs)
         nv.validate_minmax_axis(axis)
 
-        try:
-            i8 = self.asi8
+        if not len(self):
+            return self._na_value
 
+        i8 = self.asi8
+        try:
             # quick check
             if len(i8) and self.is_monotonic:
                 if i8[0] != iNaT:
                     return self._box_func(i8[0])
 
             if self.hasnans:
-                min_stamp = self[~self._isnan].asi8.min()
+                if skipna:
+                    min_stamp = self[~self._isnan].asi8.min()
+                else:
+                    return self._na_value
             else:
                 min_stamp = i8.min()
             return self._box_func(min_stamp)
         except ValueError:
             return self._na_value
 
-    def argmin(self, axis=None, *args, **kwargs):
+    def argmin(self, axis=None, skipna=True, *args, **kwargs):
         """
         Returns the indices of the minimum values along an axis.
 
@@ -369,41 +376,47 @@ def argmin(self, axis=None, *args, **kwargs):
         i8 = self.asi8
         if self.hasnans:
             mask = self._isnan
-            if mask.all():
+            if mask.all() or not skipna:
                 return -1
             i8 = i8.copy()
             i8[mask] = np.iinfo('int64').max
         return i8.argmin()
 
-    def max(self, axis=None, *args, **kwargs):
+    def max(self, axis=None, skipna=True, *args, **kwargs):
         """
         Return the maximum value of the Index or maximum along
         an axis.
 
         See Also
         --------
         numpy.ndarray.max
+        Series.max : Return the maximum value in a Series.
         """
         nv.validate_max(args, kwargs)
         nv.validate_minmax_axis(axis)
 
-        try:
-            i8 = self.asi8
+        if not len(self):
+            return self._na_value
 
+        i8 = self.asi8
+        try:
             # quick check
             if len(i8) and self.is_monotonic:
                 if i8[-1] != iNaT:
                     return self._box_func(i8[-1])
 
             if self.hasnans:
-                max_stamp = self[~self._isnan].asi8.max()
+                if skipna:
+                    max_stamp = self[~self._isnan].asi8.max()
+                else:
+                    return self._na_value
             else:
                 max_stamp = i8.max()
             return self._box_func(max_stamp)
         except ValueError:
             return self._na_value
 
-    def argmax(self, axis=None, *args, **kwargs):
+    def argmax(self, axis=None, skipna=True, *args, **kwargs):
         """
         Returns the indices of the maximum values along an axis.
 
@@ -420,7 +433,7 @@ def argmax(self, axis=None, *args, **kwargs):
         i8 = self.asi8
         if self.hasnans:
             mask = self._isnan
-            if mask.all():
+            if mask.all() or not skipna:
                 return -1
             i8 = i8.copy()
             i8[mask] = 0

pandas/core/indexes/range.py

@@ -297,12 +297,14 @@ def _minmax(self, meth):
 
         return self._start + self._step * no_steps
 
-    def min(self):
+    def min(self, axis=None, skipna=True):
         """The minimum value of the RangeIndex"""
+        nv.validate_minmax_axis(axis)
         return self._minmax('min')
 
-    def max(self):
+    def max(self, axis=None, skipna=True):
         """The maximum value of the RangeIndex"""
+        nv.validate_minmax_axis(axis)
         return self._minmax('max')
 
     def argsort(self, *args, **kwargs):