def test_to_integer_array_error(values): # error in converting existing arrays to IntegerArrays 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): IntegerArray._from_sequence(values)
def test_to_integer_array_float(): 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"): IntegerArray._from_sequence([1.5, 2.0]) # for float dtypes, the itemsize is not preserved result = IntegerArray._from_sequence(np.array([1.0, 2.0], dtype="float32")) assert result.dtype == Int64Dtype()
def test_to_integer_array_str(): result = IntegerArray._from_sequence(["1", "2", None]) expected = pd.array([1, 2, np.nan], dtype="Int64") tm.assert_extension_array_equal(result, expected) with pytest.raises(ValueError, match=r"invalid literal for int\(\) with base 10: .*"): IntegerArray._from_sequence(["1", "2", ""]) with pytest.raises(ValueError, match=r"invalid literal for int\(\) with base 10: .*"): IntegerArray._from_sequence(["1.5", "2.0"])
def test_to_integer_array_error(values): # error in converting existing arrays to IntegerArrays msg = "|".join([ r"cannot be converted to an IntegerDtype", r"invalid literal for int\(\) with base 10:", 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((ValueError, TypeError), match=msg): IntegerArray._from_sequence(values)
def array( data: Union[Sequence[object], AnyArrayLike], dtype: Optional[Dtype] = None, copy: bool = True, ) -> "ExtensionArray": """ Create an array. .. versionadded:: 0.24.0 Parameters ---------- data : Sequence of objects The scalars inside `data` should be instances of the scalar type for `dtype`. It's expected that `data` represents a 1-dimensional array of data. When `data` is an Index or Series, the underlying array will be extracted from `data`. dtype : str, np.dtype, or ExtensionDtype, optional The dtype to use for the array. This may be a NumPy dtype or an extension type registered with pandas using :meth:`pandas.api.extensions.register_extension_dtype`. If not specified, there are two possibilities: 1. When `data` is a :class:`Series`, :class:`Index`, or :class:`ExtensionArray`, the `dtype` will be taken from the data. 2. Otherwise, pandas will attempt to infer the `dtype` from the data. Note that when `data` is a NumPy array, ``data.dtype`` is *not* used for inferring the array type. This is because NumPy cannot represent all the types of data that can be held in extension arrays. Currently, pandas will infer an extension dtype for sequences of ============================== ===================================== Scalar Type Array Type ============================== ===================================== :class:`pandas.Interval` :class:`pandas.arrays.IntervalArray` :class:`pandas.Period` :class:`pandas.arrays.PeriodArray` :class:`datetime.datetime` :class:`pandas.arrays.DatetimeArray` :class:`datetime.timedelta` :class:`pandas.arrays.TimedeltaArray` :class:`int` :class:`pandas.arrays.IntegerArray` :class:`str` :class:`pandas.arrays.StringArray` :class:`bool` :class:`pandas.arrays.BooleanArray` ============================== ===================================== For all other cases, NumPy's usual inference rules will be used. .. versionchanged:: 1.0.0 Pandas infers nullable-integer dtype for integer data, string dtype for string data, and nullable-boolean dtype for boolean data. copy : bool, default True Whether to copy the data, even if not necessary. Depending on the type of `data`, creating the new array may require copying data, even if ``copy=False``. Returns ------- ExtensionArray The newly created array. Raises ------ ValueError When `data` is not 1-dimensional. See Also -------- numpy.array : Construct a NumPy array. Series : Construct a pandas Series. Index : Construct a pandas Index. arrays.PandasArray : ExtensionArray wrapping a NumPy array. Series.array : Extract the array stored within a Series. Notes ----- Omitting the `dtype` argument means pandas will attempt to infer the best array type from the values in the data. As new array types are added by pandas and 3rd party libraries, the "best" array type may change. We recommend specifying `dtype` to ensure that 1. the correct array type for the data is returned 2. the returned array type doesn't change as new extension types are added by pandas and third-party libraries Additionally, if the underlying memory representation of the returned array matters, we recommend specifying the `dtype` as a concrete object rather than a string alias or allowing it to be inferred. For example, a future version of pandas or a 3rd-party library may include a dedicated ExtensionArray for string data. In this event, the following would no longer return a :class:`arrays.PandasArray` backed by a NumPy array. >>> pd.array(['a', 'b'], dtype=str) <PandasArray> ['a', 'b'] Length: 2, dtype: str32 This would instead return the new ExtensionArray dedicated for string data. If you really need the new array to be backed by a NumPy array, specify that in the dtype. >>> pd.array(['a', 'b'], dtype=np.dtype("<U1")) <PandasArray> ['a', 'b'] Length: 2, dtype: str32 Finally, Pandas has arrays that mostly overlap with NumPy * :class:`arrays.DatetimeArray` * :class:`arrays.TimedeltaArray` When data with a ``datetime64[ns]`` or ``timedelta64[ns]`` dtype is passed, pandas will always return a ``DatetimeArray`` or ``TimedeltaArray`` rather than a ``PandasArray``. This is for symmetry with the case of timezone-aware data, which NumPy does not natively support. >>> pd.array(['2015', '2016'], dtype='datetime64[ns]') <DatetimeArray> ['2015-01-01 00:00:00', '2016-01-01 00:00:00'] Length: 2, dtype: datetime64[ns] >>> pd.array(["1H", "2H"], dtype='timedelta64[ns]') <TimedeltaArray> ['0 days 01:00:00', '0 days 02:00:00'] Length: 2, dtype: timedelta64[ns] Examples -------- If a dtype is not specified, pandas will infer the best dtype from the values. See the description of `dtype` for the types pandas infers for. >>> pd.array([1, 2]) <IntegerArray> [1, 2] Length: 2, dtype: Int64 >>> pd.array([1, 2, np.nan]) <IntegerArray> [1, 2, <NA>] Length: 3, dtype: Int64 >>> pd.array(["a", None, "c"]) <StringArray> ['a', <NA>, 'c'] Length: 3, dtype: string >>> pd.array([pd.Period('2000', freq="D"), pd.Period("2000", freq="D")]) <PeriodArray> ['2000-01-01', '2000-01-01'] Length: 2, dtype: period[D] You can use the string alias for `dtype` >>> pd.array(['a', 'b', 'a'], dtype='category') [a, b, a] Categories (2, object): [a, b] Or specify the actual dtype >>> pd.array(['a', 'b', 'a'], ... dtype=pd.CategoricalDtype(['a', 'b', 'c'], ordered=True)) [a, b, a] Categories (3, object): [a < b < c] If pandas does not infer a dedicated extension type a :class:`arrays.PandasArray` is returned. >>> pd.array([1.1, 2.2]) <PandasArray> [1.1, 2.2] Length: 2, dtype: float64 As mentioned in the "Notes" section, new extension types may be added in the future (by pandas or 3rd party libraries), causing the return value to no longer be a :class:`arrays.PandasArray`. Specify the `dtype` as a NumPy dtype if you need to ensure there's no future change in behavior. >>> pd.array([1, 2], dtype=np.dtype("int32")) <PandasArray> [1, 2] Length: 2, dtype: int32 `data` must be 1-dimensional. A ValueError is raised when the input has the wrong dimensionality. >>> pd.array(1) Traceback (most recent call last): ... ValueError: Cannot pass scalar '1' to 'pandas.array'. """ from pandas.core.arrays import ( period_array, BooleanArray, IntegerArray, IntervalArray, PandasArray, DatetimeArray, TimedeltaArray, StringArray, ) if lib.is_scalar(data): msg = f"Cannot pass scalar '{data}' to 'pandas.array'." raise ValueError(msg) if dtype is None and isinstance( data, (ABCSeries, ABCIndexClass, ABCExtensionArray)): dtype = data.dtype data = extract_array(data, extract_numpy=True) # this returns None for not-found dtypes. if isinstance(dtype, str): dtype = registry.find(dtype) or dtype if is_extension_array_dtype(dtype): cls = cast(ExtensionDtype, dtype).construct_array_type() return cls._from_sequence(data, dtype=dtype, copy=copy) if dtype is None: inferred_dtype = lib.infer_dtype(data, skipna=True) if inferred_dtype == "period": try: return period_array(data, copy=copy) except IncompatibleFrequency: # We may have a mixture of frequencies. # We choose to return an ndarray, rather than raising. pass elif inferred_dtype == "interval": try: return IntervalArray(data, copy=copy) except ValueError: # We may have a mixture of `closed` here. # We choose to return an ndarray, rather than raising. pass elif inferred_dtype.startswith("datetime"): # datetime, datetime64 try: return DatetimeArray._from_sequence(data, copy=copy) except ValueError: # Mixture of timezones, fall back to PandasArray pass elif inferred_dtype.startswith("timedelta"): # timedelta, timedelta64 return TimedeltaArray._from_sequence(data, copy=copy) elif inferred_dtype == "string": return StringArray._from_sequence(data, copy=copy) elif inferred_dtype == "integer": return IntegerArray._from_sequence(data, copy=copy) elif inferred_dtype == "boolean": return BooleanArray._from_sequence(data, copy=copy) # Pandas overrides NumPy for # 1. datetime64[ns] # 2. timedelta64[ns] # so that a DatetimeArray is returned. if is_datetime64_ns_dtype(dtype): return DatetimeArray._from_sequence(data, dtype=dtype, copy=copy) elif is_timedelta64_ns_dtype(dtype): return TimedeltaArray._from_sequence(data, dtype=dtype, copy=copy) result = PandasArray._from_sequence(data, dtype=dtype, copy=copy) return result
def test_to_integer_array(values, to_dtype, result_dtype): # convert existing arrays to IntegerArrays result = IntegerArray._from_sequence(values, dtype=to_dtype) assert result.dtype == result_dtype() expected = pd.array(values, dtype=result_dtype()) tm.assert_extension_array_equal(result, expected)