CLN: remove internal usage of integer_array() (pandas-dev#38289)

Author: jorisvandenbossche

pandas/core/arrays/__init__.py

@@ -7,7 +7,7 @@
 from pandas.core.arrays.categorical import Categorical
 from pandas.core.arrays.datetimes import DatetimeArray
 from pandas.core.arrays.floating import FloatingArray
-from pandas.core.arrays.integer import IntegerArray, integer_array
+from pandas.core.arrays.integer import IntegerArray
 from pandas.core.arrays.interval import IntervalArray
 from pandas.core.arrays.masked import BaseMaskedArray
 from pandas.core.arrays.numpy_ import PandasArray, PandasDtype
@@ -26,7 +26,6 @@
     "DatetimeArray",
     "FloatingArray",
     "IntegerArray",
-    "integer_array",
     "IntervalArray",
     "PandasArray",
     "PandasDtype",

pandas/core/arrays/integer.py

@@ -121,29 +121,6 @@ def __from_arrow__(
         return IntegerArray._concat_same_type(results)
 
 
-def integer_array(values, dtype=None, copy: bool = False) -> "IntegerArray":
-    """
-    Infer and return an integer array of the values.
-
-    Parameters
-    ----------
-    values : 1D list-like
-    dtype : dtype, optional
-        dtype to coerce
-    copy : bool, default False
-
-    Returns
-    -------
-    IntegerArray
-
-    Raises
-    ------
-    TypeError if incompatible types
-    """
-    values, mask = coerce_to_array(values, dtype=dtype, copy=copy)
-    return IntegerArray(values, mask)
-
-
 def safe_cast(values, dtype, copy: bool):
     """
     Safely cast the values to the dtype if they
@@ -360,7 +337,8 @@ def __abs__(self):
     def _from_sequence(
         cls, scalars, *, dtype=None, copy: bool = False
     ) -> "IntegerArray":
-        return integer_array(scalars, dtype=dtype, copy=copy)
+        values, mask = coerce_to_array(scalars, dtype=dtype, copy=copy)
+        return IntegerArray(values, mask)
 
     @classmethod
     def _from_sequence_of_strings(

pandas/tests/arrays/integer/conftest.py

@@ -1,7 +1,7 @@
 import numpy as np
 import pytest
 
-from pandas.core.arrays import integer_array
+import pandas as pd
 from pandas.core.arrays.integer import (
     Int8Dtype,
     Int16Dtype,
@@ -32,15 +32,15 @@ def dtype(request):
 
 @pytest.fixture
 def data(dtype):
-    return integer_array(
+    return pd.array(
         list(range(8)) + [np.nan] + list(range(10, 98)) + [np.nan] + [99, 100],
         dtype=dtype,
     )
 
 
 @pytest.fixture
 def data_missing(dtype):
-    return integer_array([np.nan, 1], dtype=dtype)
+    return pd.array([np.nan, 1], dtype=dtype)
 
 
 @pytest.fixture(params=["data", "data_missing"])

pandas/tests/arrays/integer/test_arithmetic.py

@@ -7,7 +7,7 @@
 
 import pandas as pd
 import pandas._testing as tm
-from pandas.core.arrays import FloatingArray, integer_array
+from pandas.core.arrays import FloatingArray
 import pandas.core.ops as ops
 
 # Basic test for the arithmetic array ops
@@ -131,10 +131,10 @@ def test_pow_scalar():
 
 
 def test_pow_array():
-    a = integer_array([0, 0, 0, 1, 1, 1, None, None, None])
-    b = integer_array([0, 1, None, 0, 1, None, 0, 1, None])
+    a = pd.array([0, 0, 0, 1, 1, 1, None, None, None])
+    b = pd.array([0, 1, None, 0, 1, None, 0, 1, None])
     result = a ** b
-    expected = integer_array([1, 0, None, 1, 1, 1, 1, None, None])
+    expected = pd.array([1, 0, None, 1, 1, 1, 1, None, None])
     tm.assert_extension_array_equal(result, expected)
 
 
@@ -149,7 +149,7 @@ def test_rpow_one_to_na():
 
 @pytest.mark.parametrize("other", [0, 0.5])
 def test_numpy_zero_dim_ndarray(other):
-    arr = integer_array([1, None, 2])
+    arr = pd.array([1, None, 2])
     result = arr + np.array(other)
     expected = arr + other
     tm.assert_equal(result, expected)
@@ -265,7 +265,7 @@ def test_reduce_to_float(op):
         {
             "A": ["a", "b", "b"],
             "B": [1, None, 3],
-            "C": integer_array([1, None, 3], dtype="Int64"),
+            "C": pd.array([1, None, 3], dtype="Int64"),
         }
     )
 
@@ -277,10 +277,7 @@ def test_reduce_to_float(op):
     result = getattr(df.groupby("A"), op)()
 
     expected = pd.DataFrame(
-        {
-            "B": np.array([1.0, 3.0]),
-            "C": pd.array([1, 3], dtype="Float64"),
-        },
+        {"B": np.array([1.0, 3.0]), "C": pd.array([1, 3], dtype="Float64")},
         index=pd.Index(["a", "b"], name="A"),
     )
     tm.assert_frame_equal(result, expected)

pandas/tests/arrays/integer/test_construction.py

@@ -4,10 +4,15 @@
 import pandas as pd
 import pandas._testing as tm
 from pandas.api.types import is_integer
-from pandas.core.arrays import IntegerArray, integer_array
+from pandas.core.arrays import IntegerArray
 from pandas.core.arrays.integer import Int8Dtype, Int32Dtype, Int64Dtype
 
 
+@pytest.fixture(params=[pd.array, IntegerArray._from_sequence])
+def constructor(request):
+    return request.param
+
+
 def test_uses_pandas_na():
     a = pd.array([1, None], dtype=Int64Dtype())
     assert a[1] is pd.NA
@@ -65,7 +70,7 @@ def test_integer_array_constructor():
     mask = np.array([False, False, False, True], dtype="bool")
 
     result = IntegerArray(values, mask)
-    expected = integer_array([1, 2, 3, np.nan], dtype="int64")
+    expected = pd.array([1, 2, 3, np.nan], dtype="Int64")
     tm.assert_extension_array_equal(result, expected)
 
     msg = r".* should be .* numpy array. Use the 'pd.array' function instead"
@@ -82,21 +87,6 @@ def test_integer_array_constructor():
         IntegerArray(values)
 
 
-@pytest.mark.parametrize(
-    "a, b",
-    [
-        ([1, None], [1, np.nan]),
-        ([None], [np.nan]),
-        ([None, np.nan], [np.nan, np.nan]),
-        ([np.nan, np.nan], [np.nan, np.nan]),
-    ],
-)
-def test_integer_array_constructor_none_is_nan(a, b):
-    result = integer_array(a)
-    expected = integer_array(b)
-    tm.assert_extension_array_equal(result, expected)
-
-
 def test_integer_array_constructor_copy():
     values = np.array([1, 2, 3, 4], dtype="int64")
     mask = np.array([False, False, False, True], dtype="bool")
@@ -110,6 +100,21 @@ def test_integer_array_constructor_copy():
     assert result._mask is not mask
 
 
+@pytest.mark.parametrize(
+    "a, b",
+    [
+        ([1, None], [1, np.nan]),
+        ([None], [np.nan]),
+        ([None, np.nan], [np.nan, np.nan]),
+        ([np.nan, np.nan], [np.nan, np.nan]),
+    ],
+)
+def test_to_integer_array_none_is_nan(a, b):
+    result = pd.array(a, dtype="Int64")
+    expected = pd.array(b, dtype="Int64")
+    tm.assert_extension_array_equal(result, expected)
+
+
 @pytest.mark.parametrize(
     "values",
     [
@@ -129,42 +134,46 @@ def test_to_integer_array_error(values):
     msg = (
         r"(:?.* cannot be converted to an IntegerDtype)"
         r"|(:?values must be a 1D list-like)"
+        r"|(Cannot pass scalar)"
     )
+    with pytest.raises((ValueError, TypeError), match=msg):
+        pd.array(values, dtype="Int64")
+
     with pytest.raises(TypeError, match=msg):
-        integer_array(values)
+        IntegerArray._from_sequence(values)
 
 
-def test_to_integer_array_inferred_dtype():
+def test_to_integer_array_inferred_dtype(constructor):
     # if values has dtype -> respect it
-    result = integer_array(np.array([1, 2], dtype="int8"))
+    result = constructor(np.array([1, 2], dtype="int8"))
     assert result.dtype == Int8Dtype()
-    result = integer_array(np.array([1, 2], dtype="int32"))
+    result = constructor(np.array([1, 2], dtype="int32"))
     assert result.dtype == Int32Dtype()
 
     # if values have no dtype -> always int64
-    result = integer_array([1, 2])
+    result = constructor([1, 2])
     assert result.dtype == Int64Dtype()
 
 
-def test_to_integer_array_dtype_keyword():
-    result = integer_array([1, 2], dtype="int8")
+def test_to_integer_array_dtype_keyword(constructor):
+    result = constructor([1, 2], dtype="Int8")
     assert result.dtype == Int8Dtype()
 
     # if values has dtype -> override it
-    result = integer_array(np.array([1, 2], dtype="int8"), dtype="int32")
+    result = constructor(np.array([1, 2], dtype="int8"), dtype="Int32")
     assert result.dtype == Int32Dtype()
 
 
 def test_to_integer_array_float():
-    result = integer_array([1.0, 2.0])
-    expected = integer_array([1, 2])
+    result = IntegerArray._from_sequence([1.0, 2.0])
+    expected = pd.array([1, 2], dtype="Int64")
     tm.assert_extension_array_equal(result, expected)
 
     with pytest.raises(TypeError, match="cannot safely cast non-equivalent"):
-        integer_array([1.5, 2.0])
+        IntegerArray._from_sequence([1.5, 2.0])
 
     # for float dtypes, the itemsize is not preserved
-    result = integer_array(np.array([1.0, 2.0], dtype="float32"))
+    result = IntegerArray._from_sequence(np.array([1.0, 2.0], dtype="float32"))
     assert result.dtype == Int64Dtype()
 
 
@@ -176,10 +185,12 @@ def test_to_integer_array_float():
         ([False, True, np.nan], [0, 1, np.nan], Int64Dtype(), Int64Dtype()),
     ],
 )
-def test_to_integer_array_bool(bool_values, int_values, target_dtype, expected_dtype):
-    result = integer_array(bool_values, dtype=target_dtype)
+def test_to_integer_array_bool(
+    constructor, bool_values, int_values, target_dtype, expected_dtype
+):
+    result = constructor(bool_values, dtype=target_dtype)
     assert result.dtype == expected_dtype
-    expected = integer_array(int_values, dtype=target_dtype)
+    expected = pd.array(int_values, dtype=target_dtype)
     tm.assert_extension_array_equal(result, expected)
 
 
@@ -193,7 +204,7 @@ def test_to_integer_array_bool(bool_values, int_values, target_dtype, expected_d
 )
 def test_to_integer_array(values, to_dtype, result_dtype):
     # convert existing arrays to IntegerArrays
-    result = integer_array(values, dtype=to_dtype)
+    result = IntegerArray._from_sequence(values, dtype=to_dtype)
     assert result.dtype == result_dtype()
-    expected = integer_array(values, dtype=result_dtype())
+    expected = pd.array(values, dtype=result_dtype())
     tm.assert_extension_array_equal(result, expected)

pandas/tests/arrays/integer/test_dtypes.py

@@ -5,7 +5,6 @@
 
 import pandas as pd
 import pandas._testing as tm
-from pandas.core.arrays import integer_array
 from pandas.core.arrays.integer import Int8Dtype, UInt32Dtype
 
 
@@ -28,7 +27,7 @@ def test_preserve_dtypes(op):
         {
             "A": ["a", "b", "b"],
             "B": [1, None, 3],
-            "C": integer_array([1, None, 3], dtype="Int64"),
+            "C": pd.array([1, None, 3], dtype="Int64"),
         }
     )
 
@@ -43,15 +42,15 @@ def test_preserve_dtypes(op):
     result = getattr(df.groupby("A"), op)()
 
     expected = pd.DataFrame(
-        {"B": np.array([1.0, 3.0]), "C": integer_array([1, 3], dtype="Int64")},
+        {"B": np.array([1.0, 3.0]), "C": pd.array([1, 3], dtype="Int64")},
         index=pd.Index(["a", "b"], name="A"),
     )
     tm.assert_frame_equal(result, expected)
 
 
 def test_astype_nansafe():
     # see gh-22343
-    arr = integer_array([np.nan, 1, 2], dtype="Int8")
+    arr = pd.array([np.nan, 1, 2], dtype="Int8")
     msg = "cannot convert to 'uint32'-dtype NumPy array with missing values."
 
     with pytest.raises(ValueError, match=msg):
@@ -69,7 +68,7 @@ def test_construct_index(all_data, dropna):
     else:
         other = all_data
 
-    result = pd.Index(integer_array(other, dtype=all_data.dtype))
+    result = pd.Index(pd.array(other, dtype=all_data.dtype))
     expected = pd.Index(other, dtype=object)
 
     tm.assert_index_equal(result, expected)
@@ -229,14 +228,14 @@ def test_construct_cast_invalid(dtype):
     msg = "cannot safely"
     arr = [1.2, 2.3, 3.7]
     with pytest.raises(TypeError, match=msg):
-        integer_array(arr, dtype=dtype)
+        pd.array(arr, dtype=dtype)
 
     with pytest.raises(TypeError, match=msg):
         pd.Series(arr).astype(dtype)
 
     arr = [1.2, 2.3, 3.7, np.nan]
     with pytest.raises(TypeError, match=msg):
-        integer_array(arr, dtype=dtype)
+        pd.array(arr, dtype=dtype)
 
     with pytest.raises(TypeError, match=msg):
         pd.Series(arr).astype(dtype)