DEPR: remove Int64Index, UInt64Index, Float64Index from public namespace (pandas-dev#49670)

* DEPR: remove Int64Index, UInt64Index, Float64Index * fix isort * fix stuff * fix pyright & mypy * fix isort * fix mypy Co-authored-by: Terji Petersen <terjipetersen@Terjis-Air.fritz.box>

Author: topper-123

asv_bench/benchmarks/hash_functions.py

@@ -57,14 +57,14 @@ def time_unique(self, exponent):
 class NumericSeriesIndexing:
 
  params = [
- (pd.Int64Index, pd.UInt64Index, pd.Float64Index),
+ (np.int64, np.uint64, np.float64),
  (10**4, 10**5, 5 * 10**5, 10**6, 5 * 10**6),
  ]
- param_names = ["index_dtype", "N"]
+ param_names = ["dtype", "N"]
 
- def setup(self, index, N):
- vals = np.array(list(range(55)) + [54] + list(range(55, N - 1)))
- indices = index(vals)
+ def setup(self, dtype, N):
+ vals = np.array(list(range(55)) + [54] + list(range(55, N - 1)), dtype=dtype)
+ indices = pd.Index(vals)
  self.data = pd.Series(np.arange(N), index=indices)
 
  def time_loc_slice(self, index, N):
@@ -75,15 +75,15 @@ def time_loc_slice(self, index, N):
 class NumericSeriesIndexingShuffled:
 
  params = [
- (pd.Int64Index, pd.UInt64Index, pd.Float64Index),
+ (np.int64, np.uint64, np.float64),
  (10**4, 10**5, 5 * 10**5, 10**6, 5 * 10**6),
  ]
- param_names = ["index_dtype", "N"]
+ param_names = ["dtype", "N"]
 
- def setup(self, index, N):
- vals = np.array(list(range(55)) + [54] + list(range(55, N - 1)))
+ def setup(self, dtype, N):
+ vals = np.array(list(range(55)) + [54] + list(range(55, N - 1)), dtype=dtype)
  np.random.shuffle(vals)
- indices = index(vals)
+ indices = pd.Index(vals)
  self.data = pd.Series(np.arange(N), index=indices)
 
  def time_loc_slice(self, index, N):

asv_bench/benchmarks/index_cached_properties.py

@@ -30,7 +30,7 @@ def setup(self, index_type):
  elif index_type == "DatetimeIndex":
  self.idx = pd.date_range("1/1/2000", freq="T", periods=N)
  elif index_type == "Int64Index":
- self.idx = pd.Index(range(N))
+ self.idx = pd.Index(range(N), dtype="int64")
  elif index_type == "PeriodIndex":
  self.idx = pd.period_range("1/1/2000", freq="T", periods=N)
  elif index_type == "RangeIndex":
@@ -40,9 +40,9 @@ def setup(self, index_type):
  elif index_type == "TimedeltaIndex":
  self.idx = pd.TimedeltaIndex(range(N))
  elif index_type == "Float64Index":
- self.idx = pd.Float64Index(range(N))
+ self.idx = pd.Index(range(N), dtype="float64")
  elif index_type == "UInt64Index":
- self.idx = pd.UInt64Index(range(N))
+ self.idx = pd.Index(range(N), dtype="uint64")
  elif index_type == "CategoricalIndex":
  self.idx = pd.CategoricalIndex(range(N), range(N))
  else:

asv_bench/benchmarks/index_object.py

@@ -4,7 +4,6 @@
 
 from pandas import (
  DatetimeIndex,
- Float64Index,
  Index,
  IntervalIndex,
  MultiIndex,
@@ -202,8 +201,8 @@ class Float64IndexMethod:
  # GH 13166
  def setup(self):
  N = 100_000
- a = np.arange(N)
- self.ind = Float64Index(a * 4.8000000418824129e-08)
+ a = np.arange(N, dtype=np.float64)
+ self.ind = Index(a * 4.8000000418824129e-08)
 
  def time_get_loc(self):
  self.ind.get_loc(0)

asv_bench/benchmarks/indexing.py

@@ -12,12 +12,10 @@
 from pandas import (
  CategoricalIndex,
  DataFrame,
- Float64Index,
- Int64Index,
+ Index,
  IntervalIndex,
  MultiIndex,
  Series,
- UInt64Index,
  concat,
  date_range,
  option_context,
@@ -30,17 +28,17 @@
 class NumericSeriesIndexing:
 
  params = [
- (Int64Index, UInt64Index, Float64Index),
+ (np.int64, np.uint64, np.float64),
  ("unique_monotonic_inc", "nonunique_monotonic_inc"),
  ]
- param_names = ["index_dtype", "index_structure"]
+ param_names = ["dtype", "index_structure"]
 
- def setup(self, index, index_structure):
+ def setup(self, dtype, index_structure):
  N = 10**6
  indices = {
- "unique_monotonic_inc": index(range(N)),
- "nonunique_monotonic_inc": index(
- list(range(55)) + [54] + list(range(55, N - 1))
+ "unique_monotonic_inc": Index(range(N), dtype=dtype),
+ "nonunique_monotonic_inc": Index(
+ list(range(55)) + [54] + list(range(55, N - 1)), dtype=dtype
  ),
  }
  self.data = Series(np.random.rand(N), index=indices[index_structure])
@@ -159,17 +157,17 @@ def time_boolean_rows_boolean(self):
 class DataFrameNumericIndexing:
 
  params = [
- (Int64Index, UInt64Index, Float64Index),
+ (np.int64, np.uint64, np.float64),
  ("unique_monotonic_inc", "nonunique_monotonic_inc"),
  ]
- param_names = ["index_dtype", "index_structure"]
+ param_names = ["dtype", "index_structure"]
 
- def setup(self, index, index_structure):
+ def setup(self, dtype, index_structure):
  N = 10**5
  indices = {
- "unique_monotonic_inc": index(range(N)),
- "nonunique_monotonic_inc": index(
- list(range(55)) + [54] + list(range(55, N - 1))
+ "unique_monotonic_inc": Index(range(N), dtype=dtype),
+ "nonunique_monotonic_inc": Index(
+ list(range(55)) + [54] + list(range(55, N - 1)), dtype=dtype
  ),
  }
  self.idx_dupe = np.array(range(30)) * 99
@@ -201,7 +199,7 @@ class Take:
  def setup(self, index):
  N = 100000
  indexes = {
- "int": Int64Index(np.arange(N)),
+ "int": Index(np.arange(N), dtype=np.int64),
  "datetime": date_range("2011-01-01", freq="S", periods=N),
  }
  index = indexes[index]

doc/source/reference/indexing.rst

@@ -166,9 +166,6 @@ Numeric Index
  :template: autosummary/class_without_autosummary.rst
 
  RangeIndex
- Int64Index
- UInt64Index
- Float64Index
 
 .. We need this autosummary so that the methods are generated.
 .. Separate block, since they aren't classes.

pandas/__init__.py

@@ -183,38 +183,6 @@
 __git_version__ = v.get("full-revisionid")
 del get_versions, v
 
-# GH 27101
-__deprecated_num_index_names = ["Float64Index", "Int64Index", "UInt64Index"]
-
-
-def __dir__() -> list[str]:
- # GH43028
- # Int64Index etc. are deprecated, but we still want them to be available in the dir.
- # Remove in Pandas 2.0, when we remove Int64Index etc. from the code base.
- return list(globals().keys()) + __deprecated_num_index_names
-
-
-def __getattr__(name):
- import warnings
-
- if name in __deprecated_num_index_names:
- warnings.warn(
- f"pandas.{name} is deprecated "
- "and will be removed from pandas in a future version. "
- "Use pandas.Index with the appropriate dtype instead.",
- FutureWarning,
- stacklevel=2,
- )
- from pandas.core.api import Float64Index, Int64Index, UInt64Index
-
- return {
- "Float64Index": Float64Index,
- "Int64Index": Int64Index,
- "UInt64Index": UInt64Index,
- }[name]
-
- raise AttributeError(f"module 'pandas' has no attribute '{name}'")
-
 
 # module level doc-string
 __doc__ = """

pandas/conftest.py

@@ -62,6 +62,7 @@
  Series,
  Timedelta,
  Timestamp,
+ compat,
 )
 import pandas._testing as tm
 from pandas.core import ops
@@ -79,7 +80,7 @@
  has_pyarrow = True
 
 zoneinfo = None
-if pd.compat.PY39:
+if compat.PY39:
  # Import "zoneinfo" could not be resolved (reportMissingImports)
  import zoneinfo # type: ignore[no-redef]
 

pandas/core/arrays/datetimelike.py

@@ -1354,8 +1354,9 @@ def _addsub_object_array(self, other: np.ndarray, op):
 
  res_values = op(self.astype("O"), np.asarray(other))
 
- result = pd_array(res_values.ravel())
- result = extract_array(result, extract_numpy=True).reshape(self.shape)
+ ext_arr = pd_array(res_values.ravel())
+ result = cast(np.ndarray, extract_array(ext_arr, extract_numpy=True))
+ result = result.reshape(self.shape)
  return result
 
  def _time_shift(

pandas/core/construction.py

@@ -66,10 +66,10 @@
 
 if TYPE_CHECKING:
  from pandas import (
- ExtensionArray,
  Index,
  Series,
  )
+ from pandas.core.arrays.base import ExtensionArray
 
 
 def array(

pandas/core/dtypes/generic.py

@@ -13,16 +13,13 @@
  CategoricalIndex,
  DataFrame,
  DatetimeIndex,
- Float64Index,
  Index,
- Int64Index,
  IntervalIndex,
  MultiIndex,
  PeriodIndex,
  RangeIndex,
  Series,
  TimedeltaIndex,
- UInt64Index,
  )
  from pandas.core.arrays import (
  DatetimeArray,
@@ -32,6 +29,11 @@
  TimedeltaArray,
  )
  from pandas.core.generic import NDFrame
+ from pandas.core.indexes.api import (
+ Float64Index,
+ Int64Index,
+ UInt64Index,
+ )
 
 
 # define abstract base classes to enable isinstance type checking on our