PERF: extract_array -> _values

pandas/core/algorithms.py

@@ -84,7 +84,7 @@
 
 from pandas.core.array_algos.take import take_nd
 from pandas.core.construction import (
-    array,
+    array as pd_array,
     ensure_wrapped_if_datetimelike,
     extract_array,
 )
@@ -474,7 +474,7 @@ def isin(comps: AnyArrayLike, values: AnyArrayLike) -> np.ndarray:
 
     elif needs_i8_conversion(comps.dtype):
         # Dispatch to DatetimeLikeArrayMixin.isin
-        return array(comps).isin(values)
+        return pd_array(comps).isin(values)
     elif needs_i8_conversion(values.dtype) and not is_object_dtype(comps.dtype):
         # e.g. comps are integers and values are datetime64s
         return np.zeros(comps.shape, dtype=bool)
@@ -1566,7 +1566,7 @@ def searchsorted(arr, value, side="left", sorter=None) -> np.ndarray:
         if is_scalar(value):
             value = dtype.type(value)
         else:
-            value = array(value, dtype=dtype)
+            value = pd_array(value, dtype=dtype)
     elif not (
         is_object_dtype(arr) or is_numeric_dtype(arr) or is_categorical_dtype(arr)
     ):

pandas/core/arrays/categorical.py

@@ -97,7 +97,7 @@
 )
 import pandas.core.common as com
 from pandas.core.construction import (
-    array,
+    array as pd_array,
     extract_array,
     sanitize_array,
 )
@@ -498,7 +498,7 @@ def astype(self, dtype: Dtype, copy: bool = True) -> ArrayLike:
 
         # TODO: consolidate with ndarray case?
         elif is_extension_array_dtype(dtype):
-            result = array(self, dtype=dtype, copy=copy)
+            result = pd_array(self, dtype=dtype, copy=copy)
 
         elif is_integer_dtype(dtype) and self.isna().any():
             raise ValueError("Cannot convert float NaN to integer")

pandas/core/arrays/datetimelike.py

@@ -106,7 +106,7 @@
 )
 import pandas.core.common as com
 from pandas.core.construction import (
-    array,
+    array as pd_array,
     extract_array,
 )
 from pandas.core.indexers import (
@@ -719,7 +719,7 @@ def _validate_listlike(self, value, allow_object: bool = False):
 
         # Do type inference if necessary up front
         # e.g. we passed PeriodIndex.values and got an ndarray of Periods
-        value = array(value)
+        value = pd_array(value)
         value = extract_array(value, extract_numpy=True)
 
         if is_dtype_equal(value.dtype, "string"):
@@ -1207,7 +1207,7 @@ def _addsub_object_array(self, other: np.ndarray, op):
         assert self.shape == other.shape, (self.shape, other.shape)
 
         res_values = op(self.astype("O"), np.asarray(other))
-        result = array(res_values.ravel())
+        result = pd_array(res_values.ravel())
         result = extract_array(result, extract_numpy=True).reshape(self.shape)
         return result
 

pandas/core/arrays/interval.py

@@ -76,7 +76,7 @@
 from pandas.core.arrays.categorical import Categorical
 import pandas.core.common as com
 from pandas.core.construction import (
-    array,
+    array as pd_array,
     ensure_wrapped_if_datetimelike,
     extract_array,
 )
@@ -661,7 +661,7 @@ def _cmp_method(self, other, op):
         if is_list_like(other):
             if len(self) != len(other):
                 raise ValueError("Lengths must match to compare")
-            other = array(other)
+            other = pd_array(other)
         elif not isinstance(other, Interval):
             # non-interval scalar -> no matches
             return invalid_comparison(self, other, op)

pandas/core/construction.py

@@ -303,6 +303,7 @@ def array(
         raise ValueError(msg)
 
     if dtype is None and isinstance(data, (ABCSeries, ABCIndex, ABCExtensionArray)):
+        # Note: we exclude np.ndarray here, will do type inference on it
         dtype = data.dtype
 
     data = extract_array(data, extract_numpy=True)

pandas/core/dtypes/concat.py

@@ -25,7 +25,7 @@
 from pandas.core.arrays import ExtensionArray
 from pandas.core.arrays.sparse import SparseArray
 from pandas.core.construction import (
-    array,
+    array as pd_array,
     ensure_wrapped_if_datetimelike,
 )
 
@@ -66,7 +66,7 @@ def _cast_to_common_type(arr: ArrayLike, dtype: DtypeObj) -> ArrayLike:
 
     if is_extension_array_dtype(dtype) and isinstance(arr, np.ndarray):
         # numpy's astype cannot handle ExtensionDtypes
-        return array(arr, dtype=dtype, copy=False)
+        return pd_array(arr, dtype=dtype, copy=False)
     return arr.astype(dtype, copy=False)
 
 

pandas/core/series.py

@@ -804,7 +804,7 @@ def __array__(self, dtype: Optional[NpDtype] = None) -> np.ndarray:
         array(['1999-12-31T23:00:00.000000000', ...],
               dtype='datetime64[ns]')
         """
-        return np.asarray(self.array, dtype)
+        return np.asarray(self._values, dtype)
 
     # ----------------------------------------------------------------------
     # Unary Methods
@@ -1798,7 +1798,7 @@ def count(self, level=None):
         2
         """
         if level is None:
-            return notna(self.array).sum()
+            return notna(self._values).sum()
         elif not isinstance(self.index, MultiIndex):
             raise ValueError("Series.count level is only valid with a MultiIndex")
 
@@ -2498,7 +2498,7 @@ def diff(self, periods: int = 1) -> Series:
         --------
         {examples}
         """
-        result = algorithms.diff(self.array, periods)
+        result = algorithms.diff(self._values, periods)
         return self._constructor(result, index=self.index).__finalize__(
             self, method="diff"
         )
@@ -3808,7 +3808,7 @@ def explode(self, ignore_index: bool = False) -> Series:
         if not len(self) or not is_object_dtype(self):
             return self.copy()
 
-        values, counts = reshape.explode(np.asarray(self.array))
+        values, counts = reshape.explode(np.asarray(self._values))
 
         if ignore_index:
             index = ibase.default_index(len(values))
@@ -5013,7 +5013,7 @@ def _cmp_method(self, other, op):
         if isinstance(other, Series) and not self._indexed_same(other):
             raise ValueError("Can only compare identically-labeled Series objects")
 
-        lvalues = extract_array(self, extract_numpy=True)
+        lvalues = self._values
         rvalues = extract_array(other, extract_numpy=True)
 
         res_values = ops.comparison_op(lvalues, rvalues, op)
@@ -5024,7 +5024,7 @@ def _logical_method(self, other, op):
         res_name = ops.get_op_result_name(self, other)
         self, other = ops.align_method_SERIES(self, other, align_asobject=True)
 
-        lvalues = extract_array(self, extract_numpy=True)
+        lvalues = self._values
         rvalues = extract_array(other, extract_numpy=True)
 
         res_values = ops.logical_op(lvalues, rvalues, op)
@@ -5034,7 +5034,7 @@ def _arith_method(self, other, op):
         res_name = ops.get_op_result_name(self, other)
         self, other = ops.align_method_SERIES(self, other)
 
-        lvalues = extract_array(self, extract_numpy=True)
+        lvalues = self._values
         rvalues = extract_array(other, extract_numpy=True)
         result = ops.arithmetic_op(lvalues, rvalues, op)