Как использовать методы вменения sklearn для numpy.void (запись или структурированный массив, я не уверен) ndarray

Как использовать методы вменения sklearn для numpy.void (запись или структурированный массив, я не уверен) ndarray ⇐ Python

Ответить

1 сообщение • Страница 1 из 1

Anonymous

Как использовать методы вменения sklearn для numpy.void (запись или структурированный массив, я не уверен) ndarray

Цитата

Сообщение Anonymous » 09 ноя 2025, 18:13

Код:

Код: Выделить всё

import numpy as np
import sklearn as skl

data = np.genfromtxt("water_potability.csv", delimiter = ",", names = True)
print(data)
print(data.shape)
print(type(data[0]))
imputer = skl.impute.SimpleImputer()
imputer.fit_transform(data)

(часть) Water_potability.csv:

Код: Выделить всё

ph,Hardness,Solids,Chloramines,Sulfate,Conductivity,Organic_carbon,Trihalomethanes,Turbidity,Potability
,204.8904554713363,20791.318980747026,7.300211873184757,368.51644134980336,564.3086541722439,10.3797830780847,86.9909704615088,2.9631353806316407,0
3.71608007538699,129.42292051494425,18630.057857970347,6.635245883862,,592.8853591348523,15.180013116357259,56.32907628451764,4.500656274942408,0
8.099124189298397,224.23625939355776,19909.541732292393,9.275883602694089,,418.6062130644815,16.868636929550973,66.42009251176368,3.0559337496641685,0
...
9.41951031641321,175.76264629629543,33155.578218312294,7.350233233214412,,432.04478304536786,11.039069688154314,69.84540029205144,3.298875498646556,1
5.1267629233515315,230.60375750846123,11983.869376336363,6.303356534249105,,402.883113121781,11.168946221056501,77.48821310275477,4.708658467526655,1
7.874671357791283,195.10229858610904,17404.17706105066,7.509305856927908,,327.4597604610721,16.140367626166324,78.69844632549504,2.309149056634923,1

У меня есть ndarray типа элемента numpy.void, который на самом деле является numpy.record или структурированным массивом (я не уверен, каким именно, я просто знаю, что у него есть имена полей).
Когда я пытаюсь использовать SimpleImputer sklearn (или другие импутеры), он выдает исключение:

Код: Выделить всё

[(       nan, 204.89045547, 20791.31898075, 7.30021187, 368.51644135, 564.30865417, 10.37978308, 86.99097046, 2.96313538, 0.)
(3.71608008, 129.42292051, 18630.05785797, 6.63524588,          nan, 592.88535913, 15.18001312, 56.32907628, 4.50065627, 0.)
(8.09912419, 224.23625939, 19909.54173229, 9.2758836 ,          nan, 418.60621306, 16.86863693, 66.42009251, 3.05593375, 0.)
...
(9.41951032, 175.7626463 , 33155.57821831, 7.35023323,          nan, 432.04478305, 11.03906969, 69.84540029, 3.2988755 , 1.)
(5.12676292, 230.60375751, 11983.86937634, 6.30335653,          nan, 402.88311312, 11.16894622, 77.4882131 , 4.70865847, 1.)
(7.87467136, 195.10229859, 17404.17706105, 7.50930586,          nan, 327.45976046, 16.14036763, 78.69844633, 2.30914906, 1.)]
(3276,)

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
Cell In[4], line 9
7 print(type(data[0]))
8 imputer = skl.impute.SimpleImputer()
----> 9 imputer.fit_transform(data)

File ~\AppData\Local\Programs\Python\Python311\Lib\site-packages\sklearn\utils\_set_output.py:316, in _wrap_method_output..wrapped(self, X, *args, **kwargs)
314 @wraps(f)
315 def wrapped(self, X, *args, **kwargs):
--> 316     data_to_wrap = f(self, X, *args, **kwargs)
317     if isinstance(data_to_wrap, tuple):
318         # only wrap the first output for cross decomposition
319         return_tuple = (
320             _wrap_data_with_container(method, data_to_wrap[0], X, self),
321             *data_to_wrap[1:],
322         )

File ~\AppData\Local\Programs\Python\Python311\Lib\site-packages\sklearn\base.py:894, in TransformerMixin.fit_transform(self, X, y, **fit_params)
879         warnings.warn(
880             (
881                 f"This object ({self.__class__.__name__}) has a `transform`"
(...)    889             UserWarning,
890         )
892 if y is None:
893     # fit method of arity 1 (unsupervised transformation)
--> 894     return self.fit(X, **fit_params).transform(X)
895 else:
896     # fit method of arity 2 (supervised transformation)
897     return self.fit(X, y, **fit_params).transform(X)

File ~\AppData\Local\Programs\Python\Python311\Lib\site-packages\sklearn\base.py:1365, in _fit_context..decorator..wrapper(estimator, *args, **kwargs)
1358     estimator._validate_params()
1360 with config_context(
1361     skip_parameter_validation=(
1362         prefer_skip_nested_validation or global_skip_validation
1363     )
1364 ):
->  1365     return fit_method(estimator, *args, **kwargs)

File ~\AppData\Local\Programs\Python\Python311\Lib\site-packages\sklearn\impute\_base.py:452, in SimpleImputer.fit(self, X, y)
434 @_fit_context(prefer_skip_nested_validation=True)
435 def fit(self, X, y=None):
436     """Fit the imputer on `X`.
437
438     Parameters
(...)    450         Fitted estimator.
451     """
--> 452     X = self._validate_input(X, in_fit=True)
454     # default fill_value is 0 for numerical input and "missing_value"
455     # otherwise
456     if self.fill_value is None:

File ~\AppData\Local\Programs\Python\Python311\Lib\site-packages\sklearn\impute\_base.py:360, in SimpleImputer._validate_input(self, X, in_fit)
357     ensure_all_finite = True
359 try:
--> 360     X = validate_data(
361         self,
362         X,
363         reset=in_fit,
364         accept_sparse="csc",
365         dtype=dtype,
366         force_writeable=True if not in_fit else None,
367         ensure_all_finite=ensure_all_finite,
368         copy=self.copy,
369     )
370 except ValueError as ve:
371     if "could not convert" in str(ve):

File ~\AppData\Local\Programs\Python\Python311\Lib\site-packages\sklearn\utils\validation.py:2954, in validate_data(_estimator, X, y, reset, validate_separately, skip_check_array, **check_params)
2952         out = X, y
2953 elif not no_val_X and no_val_y:
-> 2954     out = check_array(X, input_name="X", **check_params)
2955 elif no_val_X and not no_val_y:
2956     out = _check_y(y, **check_params)

File ~\AppData\Local\Programs\Python\Python311\Lib\site-packages\sklearn\utils\validation.py:1053, in check_array(array, accept_sparse, accept_large_sparse, dtype, order, copy, force_writeable, force_all_finite, ensure_all_finite, ensure_non_negative, ensure_2d, allow_nd, ensure_min_samples, ensure_min_features, estimator, input_name)
1051         array = xp.astype(array, dtype, copy=False)
1052     else:
-> 1053         array = _asarray_with_order(array, order=order, dtype=dtype, xp=xp)
1054 except ComplexWarning as complex_warning:
1055     raise ValueError(
1056         "Complex data not supported\n{}\n".format(array)
1057     ) from complex_warning

File ~\AppData\Local\Programs\Python\Python311\Lib\site-packages\sklearn\utils\_array_api.py:757, in _asarray_with_order(array, dtype, order, copy, xp, device)
755     array = numpy.array(array, order=order, dtype=dtype)
756 else:
--> 757     array = numpy.asarray(array, order=order, dtype=dtype)
759 # At this point array is a NumPy ndarray. We convert it to an array
760 # container that is consistent with the input's namespace.
761 return xp.asarray(array)

TypeError: Cannot cast array data from dtype([('ph', '

Подробнее здесь: [url]https://stackoverflow.com/questions/79794144/how-to-use-sklearn-imputation-methods-on-numpy-void-record-or-structured-array[/url]

1762701184

Anonymous

Код:
[code]import numpy as np
import sklearn as skl

data = np.genfromtxt("water_potability.csv", delimiter = ",", names = True)
print(data)
print(data.shape)
print(type(data[0]))
imputer = skl.impute.SimpleImputer()
imputer.fit_transform(data)
[/code]
(часть) Water_potability.csv:
[code]ph,Hardness,Solids,Chloramines,Sulfate,Conductivity,Organic_carbon,Trihalomethanes,Turbidity,Potability
,204.8904554713363,20791.318980747026,7.300211873184757,368.51644134980336,564.3086541722439,10.3797830780847,86.9909704615088,2.9631353806316407,0
3.71608007538699,129.42292051494425,18630.057857970347,6.635245883862,,592.8853591348523,15.180013116357259,56.32907628451764,4.500656274942408,0
8.099124189298397,224.23625939355776,19909.541732292393,9.275883602694089,,418.6062130644815,16.868636929550973,66.42009251176368,3.0559337496641685,0
...
9.41951031641321,175.76264629629543,33155.578218312294,7.350233233214412,,432.04478304536786,11.039069688154314,69.84540029205144,3.298875498646556,1
5.1267629233515315,230.60375750846123,11983.869376336363,6.303356534249105,,402.883113121781,11.168946221056501,77.48821310275477,4.708658467526655,1
7.874671357791283,195.10229858610904,17404.17706105066,7.509305856927908,,327.4597604610721,16.140367626166324,78.69844632549504,2.309149056634923,1
[/code]
У меня есть ndarray типа элемента numpy.void, который на самом деле является numpy.record или структурированным массивом (я не уверен, каким именно, я просто знаю, что у него есть имена полей).
Когда я пытаюсь использовать SimpleImputer sklearn (или другие импутеры), он выдает исключение:
[code][(       nan, 204.89045547, 20791.31898075, 7.30021187, 368.51644135, 564.30865417, 10.37978308, 86.99097046, 2.96313538, 0.)
(3.71608008, 129.42292051, 18630.05785797, 6.63524588,          nan, 592.88535913, 15.18001312, 56.32907628, 4.50065627, 0.)
(8.09912419, 224.23625939, 19909.54173229, 9.2758836 ,          nan, 418.60621306, 16.86863693, 66.42009251, 3.05593375, 0.)
...
(9.41951032, 175.7626463 , 33155.57821831, 7.35023323,          nan, 432.04478305, 11.03906969, 69.84540029, 3.2988755 , 1.)
(5.12676292, 230.60375751, 11983.86937634, 6.30335653,          nan, 402.88311312, 11.16894622, 77.4882131 , 4.70865847, 1.)
(7.87467136, 195.10229859, 17404.17706105, 7.50930586,          nan, 327.45976046, 16.14036763, 78.69844633, 2.30914906, 1.)]
(3276,)

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
Cell In[4], line 9
7 print(type(data[0]))
8 imputer = skl.impute.SimpleImputer()
----> 9 imputer.fit_transform(data)

File ~\AppData\Local\Programs\Python\Python311\Lib\site-packages\sklearn\utils\_set_output.py:316, in _wrap_method_output..wrapped(self, X, *args, **kwargs)
314 @wraps(f)
315 def wrapped(self, X, *args, **kwargs):
--> 316     data_to_wrap = f(self, X, *args, **kwargs)
317     if isinstance(data_to_wrap, tuple):
318         # only wrap the first output for cross decomposition
319         return_tuple = (
320             _wrap_data_with_container(method, data_to_wrap[0], X, self),
321             *data_to_wrap[1:],
322         )

File ~\AppData\Local\Programs\Python\Python311\Lib\site-packages\sklearn\base.py:894, in TransformerMixin.fit_transform(self, X, y, **fit_params)
879         warnings.warn(
880             (
881                 f"This object ({self.__class__.__name__}) has a `transform`"
(...)    889             UserWarning,
890         )
892 if y is None:
893     # fit method of arity 1 (unsupervised transformation)
--> 894     return self.fit(X, **fit_params).transform(X)
895 else:
896     # fit method of arity 2 (supervised transformation)
897     return self.fit(X, y, **fit_params).transform(X)

File ~\AppData\Local\Programs\Python\Python311\Lib\site-packages\sklearn\base.py:1365, in _fit_context..decorator..wrapper(estimator, *args, **kwargs)
1358     estimator._validate_params()
1360 with config_context(
1361     skip_parameter_validation=(
1362         prefer_skip_nested_validation or global_skip_validation
1363     )
1364 ):
->  1365     return fit_method(estimator, *args, **kwargs)

File ~\AppData\Local\Programs\Python\Python311\Lib\site-packages\sklearn\impute\_base.py:452, in SimpleImputer.fit(self, X, y)
434 @_fit_context(prefer_skip_nested_validation=True)
435 def fit(self, X, y=None):
436     """Fit the imputer on `X`.
437
438     Parameters
(...)    450         Fitted estimator.
451     """
--> 452     X = self._validate_input(X, in_fit=True)
454     # default fill_value is 0 for numerical input and "missing_value"
455     # otherwise
456     if self.fill_value is None:

File ~\AppData\Local\Programs\Python\Python311\Lib\site-packages\sklearn\impute\_base.py:360, in SimpleImputer._validate_input(self, X, in_fit)
357     ensure_all_finite = True
359 try:
--> 360     X = validate_data(
361         self,
362         X,
363         reset=in_fit,
364         accept_sparse="csc",
365         dtype=dtype,
366         force_writeable=True if not in_fit else None,
367         ensure_all_finite=ensure_all_finite,
368         copy=self.copy,
369     )
370 except ValueError as ve:
371     if "could not convert" in str(ve):

File ~\AppData\Local\Programs\Python\Python311\Lib\site-packages\sklearn\utils\validation.py:2954, in validate_data(_estimator, X, y, reset, validate_separately, skip_check_array, **check_params)
2952         out = X, y
2953 elif not no_val_X and no_val_y:
-> 2954     out = check_array(X, input_name="X", **check_params)
2955 elif no_val_X and not no_val_y:
2956     out = _check_y(y, **check_params)

File ~\AppData\Local\Programs\Python\Python311\Lib\site-packages\sklearn\utils\validation.py:1053, in check_array(array, accept_sparse, accept_large_sparse, dtype, order, copy, force_writeable, force_all_finite, ensure_all_finite, ensure_non_negative, ensure_2d, allow_nd, ensure_min_samples, ensure_min_features, estimator, input_name)
1051         array = xp.astype(array, dtype, copy=False)
1052     else:
-> 1053         array = _asarray_with_order(array, order=order, dtype=dtype, xp=xp)
1054 except ComplexWarning as complex_warning:
1055     raise ValueError(
1056         "Complex data not supported\n{}\n".format(array)
1057     ) from complex_warning

File ~\AppData\Local\Programs\Python\Python311\Lib\site-packages\sklearn\utils\_array_api.py:757, in _asarray_with_order(array, dtype, order, copy, xp, device)
755     array = numpy.array(array, order=order, dtype=dtype)
756 else:
--> 757     array = numpy.asarray(array, order=order, dtype=dtype)
759 # At this point array is a NumPy ndarray. We convert it to an array
760 # container that is consistent with the input's namespace.
761 return xp.asarray(array)

TypeError: Cannot cast array data from dtype([('ph', '

Подробнее здесь: [url]https://stackoverflow.com/questions/79794144/how-to-use-sklearn-imputation-methods-on-numpy-void-record-or-structured-array[/url]