module BaseEstimator : sig ... endmodule ClassifierMixin : sig ... endmodule LinearClassifierMixin : sig ... endmodule LinearDiscriminantAnalysis : sig ... endmodule QuadraticDiscriminantAnalysis : sig ... endmodule StandardScaler : sig ... endmodule TransformerMixin : sig ... endval check_X_y :
?accept_sparse:
[ `String of string | `Bool of bool | `StringList of string list ] ->
?accept_large_sparse:bool ->
?dtype:
[ `String of string
| `Dtype of Py.Object.t
| `TypeList of Py.Object.t
| `None ] ->
?order:[ `F | `C | `None ] ->
?copy:bool ->
?force_all_finite:[ `Bool of bool | `Allow_nan ] ->
?ensure_2d:bool ->
?allow_nd:bool ->
?multi_output:bool ->
?ensure_min_samples:int ->
?ensure_min_features:int ->
?y_numeric:bool ->
?warn_on_dtype:[ `Bool of bool | `None ] ->
?estimator:[ `String of string | `Estimator of Py.Object.t ] ->
x:
[ `Ndarray of Ndarray.t
| `ArrayLike of Py.Object.t
| `SparseMatrix of Csr_matrix.t ] ->
y:
[ `Ndarray of Ndarray.t
| `ArrayLike of Py.Object.t
| `SparseMatrix of Csr_matrix.t ] ->
unit ->
Py.Object.t * Py.Object.tInput validation for standard estimators.
Checks X and y for consistent length, enforces X to be 2D and y 1D. By default, X is checked to be non-empty and containing only finite values. Standard input checks are also applied to y, such as checking that y does not have np.nan or np.inf targets. For multi-label y, set multi_output=True to allow 2D and sparse y. If the dtype of X is object, attempt converting to float, raising on failure.
Parameters ---------- X : nd-array, list or sparse matrix Input data.
y : nd-array, list or sparse matrix Labels.
accept_sparse : string, boolean or list of string (default=False) Strings representing allowed sparse matrix formats, such as 'csc', 'csr', etc. If the input is sparse but not in the allowed format, it will be converted to the first listed format. True allows the input to be any format. False means that a sparse matrix input will raise an error.
accept_large_sparse : bool (default=True) If a CSR, CSC, COO or BSR sparse matrix is supplied and accepted by accept_sparse, accept_large_sparse will cause it to be accepted only if its indices are stored with a 32-bit dtype.
.. versionadded:: 0.20
dtype : string, type, list of types or None (default="numeric") Data type of result. If None, the dtype of the input is preserved. If "numeric", dtype is preserved unless array.dtype is object. If dtype is a list of types, conversion on the first type is only performed if the dtype of the input is not in the list.
order : 'F', 'C' or None (default=None) Whether an array will be forced to be fortran or c-style.
copy : boolean (default=False) Whether a forced copy will be triggered. If copy=False, a copy might be triggered by a conversion.
force_all_finite : boolean or 'allow-nan', (default=True) Whether to raise an error on np.inf and np.nan in X. This parameter does not influence whether y can have np.inf or np.nan values. The possibilities are:
.. versionadded:: 0.20 ``force_all_finite`` accepts the string ``'allow-nan'``.
ensure_2d : boolean (default=True) Whether to raise a value error if X is not 2D.
allow_nd : boolean (default=False) Whether to allow X.ndim > 2.
multi_output : boolean (default=False) Whether to allow 2D y (array or sparse matrix). If false, y will be validated as a vector. y cannot have np.nan or np.inf values if multi_output=True.
ensure_min_samples : int (default=1) Make sure that X has a minimum number of samples in its first axis (rows for a 2D array).
ensure_min_features : int (default=1) Make sure that the 2D array has some minimum number of features (columns). The default value of 1 rejects empty datasets. This check is only enforced when X has effectively 2 dimensions or is originally 1D and ``ensure_2d`` is True. Setting to 0 disables this check.
y_numeric : boolean (default=False) Whether to ensure that y has a numeric type. If dtype of y is object, it is converted to float64. Should only be used for regression algorithms.
warn_on_dtype : boolean or None, optional (default=None) Raise DataConversionWarning if the dtype of the input data structure does not match the requested dtype, causing a memory copy.
.. deprecated:: 0.21 ``warn_on_dtype`` is deprecated in version 0.21 and will be removed in 0.23.
estimator : str or estimator instance (default=None) If passed, include the name of the estimator in warning messages.
Returns ------- X_converted : object The converted and validated X.
y_converted : object The converted and validated y.
val check_array :
?accept_sparse:
[ `String of string | `Bool of bool | `StringList of string list ] ->
?accept_large_sparse:bool ->
?dtype:
[ `String of string
| `Dtype of Py.Object.t
| `TypeList of Py.Object.t
| `None ] ->
?order:[ `F | `C | `None ] ->
?copy:bool ->
?force_all_finite:[ `Bool of bool | `Allow_nan ] ->
?ensure_2d:bool ->
?allow_nd:bool ->
?ensure_min_samples:int ->
?ensure_min_features:int ->
?warn_on_dtype:[ `Bool of bool | `None ] ->
?estimator:[ `String of string | `Estimator of Py.Object.t ] ->
array:Py.Object.t ->
unit ->
Py.Object.tInput validation on an array, list, sparse matrix or similar.
By default, the input is checked to be a non-empty 2D array containing only finite values. If the dtype of the array is object, attempt converting to float, raising on failure.
Parameters ---------- array : object Input object to check / convert.
accept_sparse : string, boolean or list/tuple of strings (default=False) Strings representing allowed sparse matrix formats, such as 'csc', 'csr', etc. If the input is sparse but not in the allowed format, it will be converted to the first listed format. True allows the input to be any format. False means that a sparse matrix input will raise an error.
accept_large_sparse : bool (default=True) If a CSR, CSC, COO or BSR sparse matrix is supplied and accepted by accept_sparse, accept_large_sparse=False will cause it to be accepted only if its indices are stored with a 32-bit dtype.
.. versionadded:: 0.20
dtype : string, type, list of types or None (default="numeric") Data type of result. If None, the dtype of the input is preserved. If "numeric", dtype is preserved unless array.dtype is object. If dtype is a list of types, conversion on the first type is only performed if the dtype of the input is not in the list.
order : 'F', 'C' or None (default=None) Whether an array will be forced to be fortran or c-style. When order is None (default), then if copy=False, nothing is ensured about the memory layout of the output array; otherwise (copy=True) the memory layout of the returned array is kept as close as possible to the original array.
copy : boolean (default=False) Whether a forced copy will be triggered. If copy=False, a copy might be triggered by a conversion.
force_all_finite : boolean or 'allow-nan', (default=True) Whether to raise an error on np.inf and np.nan in array. The possibilities are:
For object dtyped data, only np.nan is checked and not np.inf.
.. versionadded:: 0.20 ``force_all_finite`` accepts the string ``'allow-nan'``.
ensure_2d : boolean (default=True) Whether to raise a value error if array is not 2D.
allow_nd : boolean (default=False) Whether to allow array.ndim > 2.
ensure_min_samples : int (default=1) Make sure that the array has a minimum number of samples in its first axis (rows for a 2D array). Setting to 0 disables this check.
ensure_min_features : int (default=1) Make sure that the 2D array has some minimum number of features (columns). The default value of 1 rejects empty datasets. This check is only enforced when the input data has effectively 2 dimensions or is originally 1D and ``ensure_2d`` is True. Setting to 0 disables this check.
warn_on_dtype : boolean or None, optional (default=None) Raise DataConversionWarning if the dtype of the input data structure does not match the requested dtype, causing a memory copy.
.. deprecated:: 0.21 ``warn_on_dtype`` is deprecated in version 0.21 and will be removed in 0.23.
estimator : str or estimator instance (default=None) If passed, include the name of the estimator in warning messages.
Returns ------- array_converted : object The converted and validated array.
val check_classification_targets : y:Ndarray.t -> unit -> Py.Object.tEnsure that target y is of a non-regression type.
Only the following target types (as defined in type_of_target) are allowed: 'binary', 'multiclass', 'multiclass-multioutput', 'multilabel-indicator', 'multilabel-sequences'
Parameters ---------- y : array-like
val check_is_fitted :
?attributes:
[ `String of string
| `ArrayLike of Py.Object.t
| `StringList of string list ] ->
?msg:string ->
?all_or_any:[ `Callable of Py.Object.t | `PyObject of Py.Object.t ] ->
estimator:Py.Object.t ->
unit ->
Py.Object.tPerform is_fitted validation for estimator.
Checks if the estimator is fitted by verifying the presence of fitted attributes (ending with a trailing underscore) and otherwise raises a NotFittedError with the given message.
This utility is meant to be used internally by estimators themselves, typically in their own predict / transform methods.
Parameters ---------- estimator : estimator instance. estimator instance for which the check is performed.
attributes : str, list or tuple of str, default=None Attribute name(s) given as string or a list/tuple of strings Eg.: ``"coef_", "estimator_", ..., "coef_"``
If `None`, `estimator` is considered fitted if there exist an attribute that ends with a underscore and does not start with double underscore.
msg : string The default error message is, "This %(name)s instance is not fitted yet. Call 'fit' with appropriate arguments before using this estimator."
For custom messages if "%(name)s" is present in the message string, it is substituted for the estimator name.
Eg. : "Estimator, %(name)s, must be fitted before sparsifying".
all_or_any : callable, all, any, default all Specify whether all or any of the given attributes must exist.
Returns ------- None
Raises ------ NotFittedError If the attributes are not found.
val empirical_covariance :
?assume_centered:bool ->
x:Ndarray.t ->
unit ->
Py.Object.tComputes the Maximum likelihood covariance estimator
Parameters ---------- X : ndarray, shape (n_samples, n_features) Data from which to compute the covariance estimate
assume_centered : boolean If True, data will not be centered before computation. Useful when working with data whose mean is almost, but not exactly zero. If False, data will be centered before computation.
Returns ------- covariance : 2D ndarray, shape (n_features, n_features) Empirical covariance (Maximum Likelihood Estimator).
val ledoit_wolf :
?assume_centered:bool ->
?block_size:int ->
x:Ndarray.t ->
unit ->
Ndarray.t * floatEstimates the shrunk Ledoit-Wolf covariance matrix.
Read more in the :ref:`User Guide <shrunk_covariance>`.
Parameters ---------- X : array-like, shape (n_samples, n_features) Data from which to compute the covariance estimate
assume_centered : boolean, default=False If True, data will not be centered before computation. Useful to work with data whose mean is significantly equal to zero but is not exactly zero. If False, data will be centered before computation.
block_size : int, default=1000 Size of the blocks into which the covariance matrix will be split. This is purely a memory optimization and does not affect results.
Returns ------- shrunk_cov : array-like, shape (n_features, n_features) Shrunk covariance.
shrinkage : float Coefficient in the convex combination used for the computation of the shrunk estimate.
Notes ----- The regularized (shrunk) covariance is:
(1 - shrinkage) * cov + shrinkage * mu * np.identity(n_features)
where mu = trace(cov) / n_features
val shrunk_covariance :
?shrinkage:[ `Float of float | `PyObject of Py.Object.t ] ->
emp_cov:Ndarray.t ->
unit ->
Ndarray.tCalculates a covariance matrix shrunk on the diagonal
Read more in the :ref:`User Guide <shrunk_covariance>`.
Parameters ---------- emp_cov : array-like, shape (n_features, n_features) Covariance matrix to be shrunk
shrinkage : float, 0 <= shrinkage <= 1 Coefficient in the convex combination used for the computation of the shrunk estimate.
Returns ------- shrunk_cov : array-like Shrunk covariance.
Notes ----- The regularized (shrunk) covariance is given by:
(1 - shrinkage) * cov + shrinkage * mu * np.identity(n_features)
where mu = trace(cov) / n_features
val softmax : ?copy:bool -> x:Py.Object.t -> unit -> Ndarray.tCalculate the softmax function.
The softmax function is calculated by np.exp(X) / np.sum(np.exp(X), axis=1)
This will cause overflow when large values are exponentiated. Hence the largest value in each row is subtracted from each data point to prevent this.
Parameters ---------- X : array-like of floats, shape (M, N) Argument to the logistic function
copy : bool, optional Copy X or not.
Returns ------- out : array, shape (M, N) Softmax function evaluated at every point in x
val unique_labels : Py.Object.t list -> Ndarray.tExtract an ordered array of unique labels
We don't allow:
At the moment, we also don't allow "multiclass-multioutput" input type.
Parameters ---------- *ys : array-likes
Returns ------- out : numpy array of shape n_unique_labels An ordered array of unique labels.
Examples -------- >>> from sklearn.utils.multiclass import unique_labels >>> unique_labels(3, 5, 5, 5, 7, 7) array(3, 5, 7) >>> unique_labels(1, 2, 3, 4, 2, 2, 3, 4) array(1, 2, 3, 4) >>> unique_labels(1, 2, 10, 5, 11) array( 1, 2, 5, 10, 11)