def hash_array(
vals: ArrayLike,
encoding: str = "utf8",
hash_key: str = _default_hash_key,
categorize: bool = True,
) -> np.ndarray:
"""
Given a 1d array, return an array of deterministic integers.
Parameters
----------
vals : ndarray or ExtensionArray
encoding : str, default 'utf8'
Encoding for data & key when strings.
hash_key : str, default _default_hash_key
Hash_key for string key to encode.
categorize : bool, default True
Whether to first categorize object arrays before hashing. This is more
efficient when the array contains duplicate values.
Returns
-------
ndarray[np.uint64, ndim=1]
Hashed values, same length as the vals.
"""
if not hasattr(vals, "dtype"):
raise TypeError("must pass a ndarray-like")
dtype = vals.dtype
# For categoricals, we hash the categories, then remap the codes to the
# hash values. (This check is above the complex check so that we don't ask
# numpy if categorical is a subdtype of complex, as it will choke).
if is_categorical_dtype(dtype):
vals = cast("Categorical", vals)
return _hash_categorical(vals, encoding, hash_key)
elif isinstance(vals, ABCExtensionArray):
vals, _ = vals._values_for_factorize()
elif not isinstance(vals, np.ndarray):
# GH#42003
raise TypeError(
"hash_array requires np.ndarray or ExtensionArray, not "
f"{type(vals).__name__}. Use hash_pandas_object instead."
)
return _hash_ndarray(vals, encoding, hash_key, categorize)
def hash_array(
vals: ArrayLike,
encoding: str = "utf8",
hash_key: str = _default_hash_key,
categorize: bool = True,
) -> np.ndarray:
"""
Given a 1d array, return an array of deterministic integers.
Parameters
----------
vals : ndarray or ExtensionArray
encoding : str, default 'utf8'
Encoding for data & key when strings.
hash_key : str, default _default_hash_key
Hash_key for string key to encode.
categorize : bool, default True
Whether to first categorize object arrays before hashing. This is more
efficient when the array contains duplicate values.
Returns
-------
1d uint64 numpy array of hash values, same length as the vals
"""
if not hasattr(vals, "dtype"):
raise TypeError("must pass a ndarray-like")
dtype = vals.dtype
# For categoricals, we hash the categories, then remap the codes to the
# hash values. (This check is above the complex check so that we don't ask
# numpy if categorical is a subdtype of complex, as it will choke).
if is_categorical_dtype(dtype):
# error: Incompatible types in assignment (expression has type "Categorical",
# variable has type "ndarray")
vals = cast("Categorical", vals) # type: ignore[assignment]
# error: Argument 1 to "_hash_categorical" has incompatible type "ndarray";
# expected "Categorical"
return _hash_categorical(vals, encoding, hash_key) # type: ignore[arg-type]
elif is_extension_array_dtype(dtype):
# error: Incompatible types in assignment (expression has type "ndarray",
# variable has type "ExtensionArray")
# error: "ndarray" has no attribute "_values_for_factorize"
vals, _ = vals._values_for_factorize() # type: ignore[assignment,attr-defined]
# error: Argument 1 to "_hash_ndarray" has incompatible type "ExtensionArray";
# expected "ndarray"
return _hash_ndarray(vals, encoding, hash_key, categorize) # type: ignore[arg-type]
