Add algorithms docs (#916) (#922)

* added algorithms docs

* fix whitespace

* fix pep8

* fix docs for version < 0.23

(cherry picked from commit 6f01ba6)

Co-authored-by: Vladislav <[email protected]>

Author: mergify[bot]

daal4py/sklearn/cluster/_dbscan.py

@@ -272,4 +272,29 @@ def fit(self, X, y=None, sample_weight=None):
 
     @support_usm_ndarray()
     def fit_predict(self, X, y=None, sample_weight=None):
+        """
+        Compute clusters from a data or distance matrix and predict labels.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features), or \
+            (n_samples, n_samples)
+            Training instances to cluster, or distances between instances if
+            ``metric='precomputed'``. If a sparse matrix is provided, it will
+            be converted into a sparse ``csr_matrix``.
+
+        y : Ignored
+            Not used, present here for API consistency by convention.
+
+        sample_weight : array-like of shape (n_samples,), default=None
+            Weight of each sample, such that a sample with a weight of at least
+            ``min_samples`` is by itself a core sample; a sample with a
+            negative weight may inhibit its eps-neighbor from being core.
+            Note that weights are absolute, and default to 1.
+
+        Returns
+        -------
+        labels : ndarray of shape (n_samples,)
+            Cluster labels. Noisy samples are given the label -1.
+        """
         return super().fit_predict(X, y, sample_weight)

daal4py/sklearn/cluster/_k_means_0_22.py

@@ -331,12 +331,82 @@ def __init__(self, n_clusters=8, init='k-means++', n_init=10,
 
     @support_usm_ndarray()
     def fit(self, X, y=None, sample_weight=None):
+        """
+        Compute k-means clustering.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features)
+            Training instances to cluster. It must be noted that the data
+            will be converted to C ordering, which will cause a memory
+            copy if the given data is not C-contiguous.
+            If a sparse matrix is passed, a copy will be made if it's not in
+            CSR format.
+
+        y : Ignored
+            Not used, present here for API consistency by convention.
+
+        sample_weight : array-like of shape (n_samples,), default=None
+            The weights for each observation in X. If None, all observations
+            are assigned equal weight.
+
+            .. versionadded:: 0.20
+
+        Returns
+        -------
+        self : object
+            Fitted estimator.
+        """
         return _fit(self, X, y=y, sample_weight=sample_weight)
 
     @support_usm_ndarray()
     def predict(self, X, sample_weight=None):
+        """
+        Predict the closest cluster each sample in X belongs to.
+
+        In the vector quantization literature, `cluster_centers_` is called
+        the code book and each value returned by `predict` is the index of
+        the closest code in the code book.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features)
+            New data to predict.
+
+        sample_weight : array-like of shape (n_samples,), default=None
+            The weights for each observation in X. If None, all observations
+            are assigned equal weight.
+
+        Returns
+        -------
+        labels : ndarray of shape (n_samples,)
+            Index of the cluster each sample belongs to.
+        """
         return _predict(self, X, sample_weight=sample_weight)
 
     @support_usm_ndarray()
     def fit_predict(self, X, y=None, sample_weight=None):
+        """
+        Compute cluster centers and predict cluster index for each sample.
+
+        Convenience method; equivalent to calling fit(X) followed by
+        predict(X).
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features)
+            New data to transform.
+
+        y : Ignored
+            Not used, present here for API consistency by convention.
+
+        sample_weight : array-like of shape (n_samples,), default=None
+            The weights for each observation in X. If None, all observations
+            are assigned equal weight.
+
+        Returns
+        -------
+        labels : ndarray of shape (n_samples,)
+            Index of the cluster each sample belongs to.
+        """
         return super().fit_predict(X, y, sample_weight)

daal4py/sklearn/cluster/_k_means_0_23.py

@@ -448,12 +448,82 @@ def __init__(
 
     @support_usm_ndarray()
     def fit(self, X, y=None, sample_weight=None):
+        """
+        Compute k-means clustering.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features)
+            Training instances to cluster. It must be noted that the data
+            will be converted to C ordering, which will cause a memory
+            copy if the given data is not C-contiguous.
+            If a sparse matrix is passed, a copy will be made if it's not in
+            CSR format.
+
+        y : Ignored
+            Not used, present here for API consistency by convention.
+
+        sample_weight : array-like of shape (n_samples,), default=None
+            The weights for each observation in X. If None, all observations
+            are assigned equal weight.
+
+            .. versionadded:: 0.20
+
+        Returns
+        -------
+        self : object
+            Fitted estimator.
+        """
         return _fit(self, X, y=y, sample_weight=sample_weight)
 
     @support_usm_ndarray()
     def predict(self, X, sample_weight=None):
+        """
+        Predict the closest cluster each sample in X belongs to.
+
+        In the vector quantization literature, `cluster_centers_` is called
+        the code book and each value returned by `predict` is the index of
+        the closest code in the code book.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features)
+            New data to predict.
+
+        sample_weight : array-like of shape (n_samples,), default=None
+            The weights for each observation in X. If None, all observations
+            are assigned equal weight.
+
+        Returns
+        -------
+        labels : ndarray of shape (n_samples,)
+            Index of the cluster each sample belongs to.
+        """
         return _predict(self, X, sample_weight=sample_weight)
 
     @support_usm_ndarray()
     def fit_predict(self, X, y=None, sample_weight=None):
+        """
+        Compute cluster centers and predict cluster index for each sample.
+
+        Convenience method; equivalent to calling fit(X) followed by
+        predict(X).
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features)
+            New data to transform.
+
+        y : Ignored
+            Not used, present here for API consistency by convention.
+
+        sample_weight : array-like of shape (n_samples,), default=None
+            The weights for each observation in X. If None, all observations
+            are assigned equal weight.
+
+        Returns
+        -------
+        labels : ndarray of shape (n_samples,)
+            Index of the cluster each sample belongs to.
+        """
         return super().fit_predict(X, y, sample_weight)

daal4py/sklearn/decomposition/_pca.py

@@ -43,6 +43,8 @@
 
 
 class PCA(PCA_original):
+    __doc__ = PCA_original.__doc__
+
     def __init__(
         self,
         n_components=None,
@@ -291,6 +293,24 @@ def _transform_daal4py(self, X, whiten=False, scale_eigenvalues=True, check_X=Tr
 
     @support_usm_ndarray()
     def transform(self, X):
+        """
+        Apply dimensionality reduction to X.
+
+        X is projected on the first principal components previously extracted
+        from a training set.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            New data, where `n_samples` is the number of samples
+            and `n_features` is the number of features.
+
+        Returns
+        -------
+        X_new : array-like of shape (n_samples, n_components)
+            Projection of X in the first principal components, where `n_samples`
+            is the number of samples and `n_components` is the number of the components.
+        """
         _patching_status = PatchingConditionsChain(
             "sklearn.decomposition.PCA.transform")
         _dal_ready = _patching_status.and_conditions([
@@ -305,6 +325,28 @@ def transform(self, X):
 
     @support_usm_ndarray()
     def fit_transform(self, X, y=None):
+        """
+        Fit the model with X and apply the dimensionality reduction on X.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Training data, where `n_samples` is the number of samples
+            and `n_features` is the number of features.
+
+        y : Ignored
+            Ignored.
+
+        Returns
+        -------
+        X_new : ndarray of shape (n_samples, n_components)
+            Transformed values.
+
+        Notes
+        -----
+        This method returns a Fortran-ordered array. To convert it to a
+        C-ordered array, use 'np.ascontiguousarray'.
+        """
         U, S, _ = self._fit(X)
 
         _patching_status = PatchingConditionsChain(