CLN: reorg pandas.tseries (#16040)

* CLN: move pandas/tseries/resample.py -> pandas/core/resample.py

closes #13634

* CLN: move pandas.tseries.period -> pandas.core.indexes.period

* CLN: move pandas.tseries.tdi -> pandas.core.indexes.timedeltas

* CLN: move pandas.tseries.base -> pandas.core.indexes.datetimelike

* CLN: pandas.tseries.common -> pandas.core.indexes.accessors

* CLN: move pandas.tseries.index -> pandas.core.indexes.datetimes

* CLN: move pandas.tseries.timedeltas, pandas.tseries.tools -> pandas.core.tools

* move to_numeric to pandas.core.tools.numeric

Author: jreback

doc/source/api.rst

@@ -1761,7 +1761,7 @@ The following methods are available only for ``DataFrameGroupBy`` objects.
 
 Resampling
 ----------
-.. currentmodule:: pandas.tseries.resample
+.. currentmodule:: pandas.core.resample
 
 Resampler objects are returned by resample calls: :func:`pandas.DataFrame.resample`, :func:`pandas.Series.resample`.
 

pandas/_libs/period.pyx

@@ -34,7 +34,7 @@ from tslib cimport (
 )
 
 from pandas.tseries import offsets
-from pandas.tseries.tools import parse_time_string
+from pandas.core.tools.datetimes import parse_time_string
 from pandas.tseries import frequencies
 
 cdef int64_t NPY_NAT = util.get_nat()

pandas/_libs/tslib.pyx

@@ -502,7 +502,7 @@ class Timestamp(_Timestamp):
         """
         Return an period of which this timestamp is an observation.
         """
-        from pandas.tseries.period import Period
+        from pandas import Period
 
         if freq is None:
             freq = self.freq

pandas/compat/pickle_compat.py

@@ -94,7 +94,13 @@ def load_reduce(self):
     ('pandas.indexes.range', 'RangeIndex'):
         ('pandas.core.indexes.range', 'RangeIndex'),
     ('pandas.indexes.multi', 'MultiIndex'):
-        ('pandas.core.indexes.multi', 'MultiIndex')
+        ('pandas.core.indexes.multi', 'MultiIndex'),
+    ('pandas.tseries.index', '_new_DatetimeIndex'):
+        ('pandas.core.indexes.datetimes', '_new_DatetimeIndex'),
+    ('pandas.tseries.index', 'DatetimeIndex'):
+        ('pandas.core.indexes.datetimes', 'DatetimeIndex'),
+    ('pandas.tseries.period', 'PeriodIndex'):
+        ('pandas.core.indexes.period', 'PeriodIndex')
 }
 
 

pandas/core/api.py

@@ -11,7 +11,12 @@
 from pandas.io.formats.format import set_eng_float_format
 from pandas.core.index import (Index, CategoricalIndex, Int64Index,
                                UInt64Index, RangeIndex, Float64Index,
-                               MultiIndex, IntervalIndex)
+                               MultiIndex, IntervalIndex,
+                               TimedeltaIndex, DatetimeIndex,
+                               PeriodIndex, NaT)
+from pandas.core.indexes.period import Period, period_range, pnow
+from pandas.core.indexes.timedeltas import Timedelta, timedelta_range
+from pandas.core.indexes.datetimes import Timestamp, date_range, bdate_range
 from pandas.core.indexes.interval import Interval, interval_range
 
 from pandas.core.series import Series
@@ -23,13 +28,11 @@
     lreshape, wide_to_long)
 
 from pandas.core.indexing import IndexSlice
-from pandas.core.dtypes.cast import to_numeric
+from pandas.core.tools.numeric import to_numeric
 from pandas.tseries.offsets import DateOffset
-from pandas.tseries.tools import to_datetime
-from pandas.tseries.index import (DatetimeIndex, Timestamp,
-                                  date_range, bdate_range)
-from pandas.tseries.tdi import TimedeltaIndex, Timedelta
-from pandas.tseries.period import Period, PeriodIndex
+from pandas.core.tools.datetimes import to_datetime
+from pandas.core.tools.timedeltas import to_timedelta
+from pandas.core.resample import TimeGrouper
 
 # see gh-14094.
 from pandas.util.depr_module import _DeprecatedModule

pandas/core/computation/pytables.py

@@ -14,7 +14,7 @@
 from pandas.core.computation.ops import is_term, UndefinedVariableError
 from pandas.core.computation.expr import BaseExprVisitor
 from pandas.core.computation.common import _ensure_decoded
-from pandas.tseries.timedeltas import _coerce_scalar_to_timedelta_type
+from pandas.core.tools.timedeltas import _coerce_scalar_to_timedelta_type
 
 
 class Scope(expr.Scope):

pandas/core/datetools.py

@@ -4,7 +4,7 @@
 
 import warnings
 
-from pandas.tseries.tools import *
+from pandas.core.tools.datetimes import *
 from pandas.tseries.offsets import *
 from pandas.tseries.frequencies import *
 

pandas/core/dtypes/cast.py

@@ -5,7 +5,6 @@
 import numpy as np
 import warnings
 
-import pandas as pd
 from pandas._libs import tslib, lib
 from pandas._libs.tslib import iNaT
 from pandas.compat import string_types, text_type, PY3
@@ -19,8 +18,6 @@
                      is_integer_dtype,
                      is_datetime_or_timedelta_dtype,
                      is_bool_dtype, is_scalar,
-                     is_numeric_dtype, is_decimal,
-                     is_number,
                      _string_dtypes,
                      _coerce_to_dtype,
                      _ensure_int8, _ensure_int16,
@@ -29,7 +26,7 @@
                      _POSSIBLY_CAST_DTYPES)
 from .dtypes import ExtensionDtype, DatetimeTZDtype, PeriodDtype
 from .generic import (ABCDatetimeIndex, ABCPeriodIndex,
-                      ABCSeries, ABCIndexClass)
+                      ABCSeries)
 from .missing import isnull, notnull
 from .inference import is_list_like
 
@@ -548,7 +545,7 @@ def coerce_to_dtypes(result, dtypes):
     if len(result) != len(dtypes):
         raise AssertionError("_coerce_to_dtypes requires equal len arrays")
 
-    from pandas.tseries.timedeltas import _coerce_scalar_to_timedelta_type
+    from pandas.core.tools.timedeltas import _coerce_scalar_to_timedelta_type
 
     def conv(r, dtype):
         try:
@@ -670,7 +667,7 @@ def maybe_convert_objects(values, convert_dates=True, convert_numeric=True,
     if convert_timedeltas and values.dtype == np.object_:
 
         if convert_timedeltas == 'coerce':
-            from pandas.tseries.timedeltas import to_timedelta
+            from pandas.core.tools.timedeltas import to_timedelta
             new_values = to_timedelta(values, coerce=True)
 
             # if we are all nans then leave me alone
@@ -872,8 +869,8 @@ def maybe_cast_to_datetime(value, dtype, errors='raise'):
     """ try to cast the array/value to a datetimelike dtype, converting float
     nan to iNaT
     """
-    from pandas.tseries.timedeltas import to_timedelta
-    from pandas.tseries.tools import to_datetime
+    from pandas.core.tools.timedeltas import to_timedelta
+    from pandas.core.tools.datetimes import to_datetime
 
     if dtype is not None:
         if isinstance(dtype, string_types):
@@ -1029,161 +1026,3 @@ def find_common_type(types):
             return np.object
 
     return np.find_common_type(types, [])
-
-
-def to_numeric(arg, errors='raise', downcast=None):
-    """
-    Convert argument to a numeric type.
-
-    Parameters
-    ----------
-    arg : list, tuple, 1-d array, or Series
-    errors : {'ignore', 'raise', 'coerce'}, default 'raise'
-        - If 'raise', then invalid parsing will raise an exception
-        - If 'coerce', then invalid parsing will be set as NaN
-        - If 'ignore', then invalid parsing will return the input
-    downcast : {'integer', 'signed', 'unsigned', 'float'} , default None
-        If not None, and if the data has been successfully cast to a
-        numerical dtype (or if the data was numeric to begin with),
-        downcast that resulting data to the smallest numerical dtype
-        possible according to the following rules:
-
-        - 'integer' or 'signed': smallest signed int dtype (min.: np.int8)
-        - 'unsigned': smallest unsigned int dtype (min.: np.uint8)
-        - 'float': smallest float dtype (min.: np.float32)
-
-        As this behaviour is separate from the core conversion to
-        numeric values, any errors raised during the downcasting
-        will be surfaced regardless of the value of the 'errors' input.
-
-        In addition, downcasting will only occur if the size
-        of the resulting data's dtype is strictly larger than
-        the dtype it is to be cast to, so if none of the dtypes
-        checked satisfy that specification, no downcasting will be
-        performed on the data.
-
-        .. versionadded:: 0.19.0
-
-    Returns
-    -------
-    ret : numeric if parsing succeeded.
-        Return type depends on input.  Series if Series, otherwise ndarray
-
-    Examples
-    --------
-    Take separate series and convert to numeric, coercing when told to
-
-    >>> import pandas as pd
-    >>> s = pd.Series(['1.0', '2', -3])
-    >>> pd.to_numeric(s)
-    0    1.0
-    1    2.0
-    2   -3.0
-    dtype: float64
-    >>> pd.to_numeric(s, downcast='float')
-    0    1.0
-    1    2.0
-    2   -3.0
-    dtype: float32
-    >>> pd.to_numeric(s, downcast='signed')
-    0    1
-    1    2
-    2   -3
-    dtype: int8
-    >>> s = pd.Series(['apple', '1.0', '2', -3])
-    >>> pd.to_numeric(s, errors='ignore')
-    0    apple
-    1      1.0
-    2        2
-    3       -3
-    dtype: object
-    >>> pd.to_numeric(s, errors='coerce')
-    0    NaN
-    1    1.0
-    2    2.0
-    3   -3.0
-    dtype: float64
-    """
-    if downcast not in (None, 'integer', 'signed', 'unsigned', 'float'):
-        raise ValueError('invalid downcasting method provided')
-
-    is_series = False
-    is_index = False
-    is_scalars = False
-
-    if isinstance(arg, ABCSeries):
-        is_series = True
-        values = arg.values
-    elif isinstance(arg, ABCIndexClass):
-        is_index = True
-        values = arg.asi8
-        if values is None:
-            values = arg.values
-    elif isinstance(arg, (list, tuple)):
-        values = np.array(arg, dtype='O')
-    elif is_scalar(arg):
-        if is_decimal(arg):
-            return float(arg)
-        if is_number(arg):
-            return arg
-        is_scalars = True
-        values = np.array([arg], dtype='O')
-    elif getattr(arg, 'ndim', 1) > 1:
-        raise TypeError('arg must be a list, tuple, 1-d array, or Series')
-    else:
-        values = arg
-
-    try:
-        if is_numeric_dtype(values):
-            pass
-        elif is_datetime_or_timedelta_dtype(values):
-            values = values.astype(np.int64)
-        else:
-            values = _ensure_object(values)
-            coerce_numeric = False if errors in ('ignore', 'raise') else True
-            values = lib.maybe_convert_numeric(values, set(),
-                                               coerce_numeric=coerce_numeric)
-
-    except Exception:
-        if errors == 'raise':
-            raise
-
-    # attempt downcast only if the data has been successfully converted
-    # to a numerical dtype and if a downcast method has been specified
-    if downcast is not None and is_numeric_dtype(values):
-        typecodes = None
-
-        if downcast in ('integer', 'signed'):
-            typecodes = np.typecodes['Integer']
-        elif downcast == 'unsigned' and np.min(values) >= 0:
-            typecodes = np.typecodes['UnsignedInteger']
-        elif downcast == 'float':
-            typecodes = np.typecodes['Float']
-
-            # pandas support goes only to np.float32,
-            # as float dtypes smaller than that are
-            # extremely rare and not well supported
-            float_32_char = np.dtype(np.float32).char
-            float_32_ind = typecodes.index(float_32_char)
-            typecodes = typecodes[float_32_ind:]
-
-        if typecodes is not None:
-            # from smallest to largest
-            for dtype in typecodes:
-                if np.dtype(dtype).itemsize <= values.dtype.itemsize:
-                    values = maybe_downcast_to_dtype(values, dtype)
-
-                    # successful conversion
-                    if values.dtype == dtype:
-                        break
-
-    if is_series:
-        return pd.Series(values, index=arg.index, name=arg.name)
-    elif is_index:
-        # because we want to coerce to numeric if possible,
-        # do not use _shallow_copy_with_infer
-        return pd.Index(values, name=arg.name)
-    elif is_scalars:
-        return values[0]
-    else:
-        return values

pandas/core/frame.py

@@ -82,9 +82,9 @@
 from pandas.util.decorators import Appender, Substitution
 from pandas.util.validators import validate_bool_kwarg
 
-from pandas.tseries.period import PeriodIndex
-from pandas.tseries.index import DatetimeIndex
-from pandas.tseries.tdi import TimedeltaIndex
+from pandas.core.indexes.period import PeriodIndex
+from pandas.core.indexes.datetimes import DatetimeIndex
+from pandas.core.indexes.timedeltas import TimedeltaIndex
 
 import pandas.core.base as base
 import pandas.core.common as com

pandas/core/generic.py

@@ -37,8 +37,8 @@
 from pandas.core.index import (Index, MultiIndex, _ensure_index,
                                InvalidIndexError)
 import pandas.core.indexing as indexing
-from pandas.tseries.index import DatetimeIndex
-from pandas.tseries.period import PeriodIndex, Period
+from pandas.core.indexes.datetimes import DatetimeIndex
+from pandas.core.indexes.period import PeriodIndex, Period
 from pandas.core.internals import BlockManager
 import pandas.core.algorithms as algos
 import pandas.core.common as com
@@ -4363,7 +4363,7 @@ def asfreq(self, freq, method=None, how=None, normalize=False,
         To learn more about the frequency strings, please see `this link
         <http://pandas.pydata.org/pandas-docs/stable/timeseries.html#offset-aliases>`__.
         """
-        from pandas.tseries.resample import asfreq
+        from pandas.core.resample import asfreq
         return asfreq(self, freq, method=method, how=how, normalize=normalize,
                       fill_value=fill_value)
 
@@ -4573,8 +4573,8 @@ def resample(self, rule, how=None, axis=0, fill_method=None, closed=None,
         2000-01-01 00:00:00  0  6  12  18
         2000-01-01 00:03:00  0  4   8  12
         """
-        from pandas.tseries.resample import (resample,
-                                             _maybe_process_deprecations)
+        from pandas.core.resample import (resample,
+                                          _maybe_process_deprecations)
         axis = self._get_axis_number(axis)
         r = resample(self, freq=rule, label=label, closed=closed,
                      axis=axis, kind=kind, loffset=loffset,
@@ -5361,7 +5361,7 @@ def truncate(self, before=None, after=None, axis=None, copy=True):
         # if we have a date index, convert to dates, otherwise
         # treat like a slice
         if ax.is_all_dates:
-            from pandas.tseries.tools import to_datetime
+            from pandas.core.tools.datetimes import to_datetime
             before = to_datetime(before)
             after = to_datetime(after)
 

pandas/core/groupby.py

@@ -232,7 +232,7 @@ class Grouper(object):
 
     def __new__(cls, *args, **kwargs):
         if kwargs.get('freq') is not None:
-            from pandas.tseries.resample import TimeGrouper
+            from pandas.core.resample import TimeGrouper
             cls = TimeGrouper
         return super(Grouper, cls).__new__(cls)
 
@@ -1227,7 +1227,7 @@ def resample(self, rule, *args, **kwargs):
         Provide resampling when using a TimeGrouper
         Return a new grouper with our resampler appended
         """
-        from pandas.tseries.resample import get_resampler_for_grouping
+        from pandas.core.resample import get_resampler_for_grouping
         return get_resampler_for_grouping(self, rule, *args, **kwargs)
 
     @Substitution(name='groupby')
@@ -3509,7 +3509,7 @@ def _decide_output_index(self, output, labels):
 
     def _wrap_applied_output(self, keys, values, not_indexed_same=False):
         from pandas.core.index import _all_indexes_same
-        from pandas.core.dtypes.cast import to_numeric
+        from pandas.core.tools.numeric import to_numeric
 
         if len(keys) == 0:
             return DataFrame(index=keys)