CLN: assorted cleanups, annotations, de-privatizing (#33497)

* de-privatize

* CLN: assorted cleanups, annotations

Author: jbrockmendel

pandas/_libs/tslibs/offsets.pyx

@@ -157,8 +157,8 @@ cdef _wrap_timedelta_result(result):
     """
     if PyDelta_Check(result):
         # convert Timedelta back to a Tick
-        from pandas.tseries.offsets import _delta_to_tick
-        return _delta_to_tick(result)
+        from pandas.tseries.offsets import delta_to_tick
+        return delta_to_tick(result)
 
     return result
 

pandas/core/arrays/period.py

@@ -39,7 +39,7 @@
 import pandas.core.common as com
 
 from pandas.tseries import frequencies
-from pandas.tseries.offsets import DateOffset, Tick, _delta_to_tick
+from pandas.tseries.offsets import DateOffset, Tick, delta_to_tick
 
 
 def _field_accessor(name: str, alias: int, docstring=None):
@@ -487,7 +487,7 @@ def _time_shift(self, periods, freq=None):
     def _box_func(self):
         return lambda x: Period._from_ordinal(ordinal=x, freq=self.freq)
 
-    def asfreq(self, freq=None, how="E") -> "PeriodArray":
+    def asfreq(self, freq=None, how: str = "E") -> "PeriodArray":
         """
         Convert the Period Array/Index to the specified frequency `freq`.
 
@@ -759,7 +759,7 @@ def raise_on_incompatible(left, right):
     elif isinstance(right, (ABCPeriodIndex, PeriodArray, Period, DateOffset)):
         other_freq = right.freqstr
     else:
-        other_freq = _delta_to_tick(Timedelta(right)).freqstr
+        other_freq = delta_to_tick(Timedelta(right)).freqstr
 
     msg = DIFFERENT_FREQ.format(
         cls=type(left).__name__, own_freq=left.freqstr, other_freq=other_freq

pandas/core/indexes/accessors.py

@@ -428,7 +428,6 @@ def __new__(cls, data: "Series"):
         # we need to choose which parent (datetime or timedelta) is
         # appropriate. Since we're checking the dtypes anyway, we'll just
         # do all the validation here.
-        from pandas import Series
 
         if not isinstance(data, ABCSeries):
             raise TypeError(
@@ -437,7 +436,7 @@ def __new__(cls, data: "Series"):
 
         orig = data if is_categorical_dtype(data) else None
         if orig is not None:
-            data = Series(
+            data = data._constructor(
                 orig.array,
                 name=orig.name,
                 copy=False,

pandas/core/indexes/period.py

@@ -6,9 +6,8 @@
 
 from pandas._libs import index as libindex
 from pandas._libs.lib import no_default
-from pandas._libs.tslibs import frequencies as libfrequencies, resolution
+from pandas._libs.tslibs import Period, frequencies as libfrequencies, resolution
 from pandas._libs.tslibs.parsing import parse_time_string
-from pandas._libs.tslibs.period import Period
 from pandas._typing import DtypeObj, Label
 from pandas.util._decorators import Appender, cache_readonly, doc
 

pandas/core/indexes/timedeltas.py

@@ -29,16 +29,7 @@
 
 
 @inherit_names(
-    [
-        "_box_values",
-        "__neg__",
-        "__pos__",
-        "__abs__",
-        "total_seconds",
-        "round",
-        "floor",
-        "ceil",
-    ]
+    ["__neg__", "__pos__", "__abs__", "total_seconds", "round", "floor", "ceil"]
     + TimedeltaArray._field_ops,
     TimedeltaArray,
     wrap=True,

pandas/core/internals/blocks.py

@@ -216,7 +216,7 @@ def get_block_values_for_json(self) -> np.ndarray:
         """
         This is used in the JSON C code.
         """
-        # TODO(2DEA): reshape will be unnecessary with 2D EAs
+        # TODO(EA2D): reshape will be unnecessary with 2D EAs
         return np.asarray(self.values).reshape(self.shape)
 
     @property
@@ -341,6 +341,7 @@ def apply(self, func, **kwargs) -> List["Block"]:
     def _split_op_result(self, result) -> List["Block"]:
         # See also: split_and_operate
         if is_extension_array_dtype(result) and result.ndim > 1:
+            # TODO(EA2D): unnecessary with 2D EAs
             # if we get a 2D ExtensionArray, we need to split it into 1D pieces
             nbs = []
             for i, loc in enumerate(self.mgr_locs):
@@ -1548,7 +1549,7 @@ def __init__(self, values, placement, ndim=None):
         super().__init__(values, placement, ndim=ndim)
 
         if self.ndim == 2 and len(self.mgr_locs) != 1:
-            # TODO(2DEA): check unnecessary with 2D EAs
+            # TODO(EA2D): check unnecessary with 2D EAs
             raise AssertionError("block.size != values.size")
 
     @property
@@ -2273,7 +2274,7 @@ def equals(self, other) -> bool:
     def quantile(self, qs, interpolation="linear", axis=0):
         naive = self.values.view("M8[ns]")
 
-        # kludge for 2D block with 1D values
+        # TODO(EA2D): kludge for 2D block with 1D values
         naive = naive.reshape(self.shape)
 
         blk = self.make_block(naive)
@@ -2398,7 +2399,7 @@ def f(mask, val, idx):
                 copy=copy,
             )
             if isinstance(values, np.ndarray):
-                # TODO: allow EA once reshape is supported
+                # TODO(EA2D): allow EA once reshape is supported
                 values = values.reshape(shape)
 
             return values

pandas/core/internals/concat.py

@@ -5,7 +5,7 @@
 
 import numpy as np
 
-from pandas._libs import internals as libinternals, tslibs
+from pandas._libs import NaT, internals as libinternals
 from pandas.util._decorators import cache_readonly
 
 from pandas.core.dtypes.cast import maybe_promote
@@ -406,7 +406,7 @@ def _get_empty_dtype_and_na(join_units):
         # GH-25014. We use NaT instead of iNaT, since this eventually
         # ends up in DatetimeArray.take, which does not allow iNaT.
         dtype = upcast_classes["datetimetz"]
-        return dtype[0], tslibs.NaT
+        return dtype[0], NaT
     elif "datetime" in upcast_classes:
         return np.dtype("M8[ns]"), np.datetime64("NaT", "ns")
     elif "timedelta" in upcast_classes:

pandas/core/resample.py

@@ -323,7 +323,7 @@ def _gotitem(self, key, ndim: int, subset=None):
         Parameters
         ----------
         key : string / list of selections
-        ndim : 1,2
+        ndim : {1, 2}
             requested ndim of result
         subset : object, default None
             subset to act on

pandas/tests/arithmetic/test_timedelta64.py

@@ -313,7 +313,9 @@ def test_subtraction_ops(self):
         tm.assert_index_equal(result, expected, check_names=False)
 
         result = dti - td
-        expected = DatetimeIndex(["20121231", "20130101", "20130102"], name="bar")
+        expected = DatetimeIndex(
+            ["20121231", "20130101", "20130102"], freq="D", name="bar"
+        )
         tm.assert_index_equal(result, expected, check_names=False)
 
         result = dt - tdi
@@ -401,7 +403,9 @@ def _check(result, expected):
         _check(result, expected)
 
         result = dti_tz - td
-        expected = DatetimeIndex(["20121231", "20130101", "20130102"], tz="US/Eastern")
+        expected = DatetimeIndex(
+            ["20121231", "20130101", "20130102"], tz="US/Eastern", freq="D"
+        )
         tm.assert_index_equal(result, expected)
 
     def test_dti_tdi_numeric_ops(self):

pandas/tests/series/methods/test_replace.py

@@ -186,11 +186,7 @@ def check_replace(to_rep, val, expected):
         check_replace(tr, v, e)
 
         # test an object with dates + floats + integers + strings
-        dr = (
-            pd.date_range("1/1/2001", "1/10/2001", freq="D")
-            .to_series()
-            .reset_index(drop=True)
-        )
+        dr = pd.Series(pd.date_range("1/1/2001", "1/10/2001", freq="D"))
         result = dr.astype(object).replace([dr[0], dr[1], dr[2]], [1.0, 2, "a"])
         expected = pd.Series([1.0, 2, "a"] + dr[3:].tolist(), dtype=object)
         tm.assert_series_equal(result, expected)

pandas/tests/tseries/offsets/test_ticks.py

@@ -33,11 +33,11 @@ def test_apply_ticks():
 def test_delta_to_tick():
     delta = timedelta(3)
 
-    tick = offsets._delta_to_tick(delta)
+    tick = offsets.delta_to_tick(delta)
     assert tick == offsets.Day(3)
 
     td = Timedelta(nanoseconds=5)
-    tick = offsets._delta_to_tick(td)
+    tick = offsets.delta_to_tick(td)
     assert tick == Nano(5)
 
 

pandas/tseries/offsets.py

@@ -2548,7 +2548,7 @@ def __add__(self, other):
             if type(self) == type(other):
                 return type(self)(self.n + other.n)
             else:
-                return _delta_to_tick(self.delta + other.delta)
+                return delta_to_tick(self.delta + other.delta)
         elif isinstance(other, Period):
             return other + self
         try:
@@ -2635,7 +2635,7 @@ def is_anchored(self) -> bool:
         return False
 
 
-def _delta_to_tick(delta: timedelta) -> Tick:
+def delta_to_tick(delta: timedelta) -> Tick:
     if delta.microseconds == 0 and getattr(delta, "nanoseconds", 0) == 0:
         # nanoseconds only for pd.Timedelta
         if delta.seconds == 0: