[MRG+2] Update the repo for release (#295)

* Get rid of deprecations

* Some more modifications

* more modifs and fixes

* remove flake8 error

* some fixes

* fix

* Fixes

* Fixes

* Add SCML and change version number

* add warning for scml, and fix doc generation

* small fix

* fix

Author: wdevazelhes

README.rst

@@ -11,6 +11,7 @@ metric-learn contains efficient Python implementations of several popular superv
 -  Information Theoretic Metric Learning (ITML)
 -  Sparse Determinant Metric Learning (SDML)
 -  Least Squares Metric Learning (LSML)
+-  Sparse Compositional Metric Learning (SCML)
 -  Neighborhood Components Analysis (NCA)
 -  Local Fisher Discriminant Analysis (LFDA)
 -  Relative Components Analysis (RCA)

doc/conf.py

@@ -24,8 +24,8 @@
              u'Bellet and Nathalie Vauquier')
 author = (u'CJ Carey, Yuan Tang, William de Vazelhes, Aurélien Bellet and '
           u'Nathalie Vauquier')
-version = '0.5.0'
-release = '0.5.0'
+version = '0.6.0'
+release = '0.6.0'
 language = 'en'
 
 exclude_patterns = ['_build']

doc/modules.rst

@@ -0,0 +1,7 @@
+metric_learn
+============
+
+.. toctree::
+   :maxdepth: 4
+
+   metric_learn

doc/supervised.rst

@@ -50,7 +50,7 @@ classes will be large. To do so, we fit the metric learner (example:
 >>> from metric_learn import NCA
 >>> nca = NCA(random_state=42)
 >>> nca.fit(X, y)
-NCA(init=None, max_iter=100, n_components=None, num_dims='deprecated',
+NCA(init='auto', max_iter=100, n_components=None,
   preprocessor=None, random_state=42, tol=None, verbose=False)
 
 

doc/weakly_supervised.rst

@@ -135,7 +135,7 @@ are respected.
 >>> mmc = MMC(random_state=42)
 >>> mmc.fit(tuples, y)
 MMC(A0='deprecated', convergence_threshold=0.001, diagonal=False,
-  diagonal_c=1.0, init=None, max_iter=100, max_proj=10000,
+  diagonal_c=1.0, init='auto', max_iter=100, max_proj=10000,
   preprocessor=None, random_state=42, verbose=False)
 
 Or alternatively (using a preprocessor):
@@ -250,8 +250,8 @@ tuples).
 >>> y_pairs = np.array([1, -1])
 >>> mmc = MMC(random_state=42)
 >>> mmc.fit(pairs, y_pairs)
-MMC(A0='deprecated', convergence_threshold=0.001, diagonal=False,
-    diagonal_c=1.0, init=None, max_iter=100, max_proj=10000, preprocessor=None,
+MMC(convergence_threshold=0.001, diagonal=False,
+    diagonal_c=1.0, init='auto', max_iter=100, max_proj=10000, preprocessor=None,
     random_state=42, verbose=False)
 
 Here, we learned a metric that puts the two first points closer

examples/plot_metric_learning_examples.py

@@ -289,7 +289,7 @@ def plot_tsne(X, y, colormap=plt.cm.Paired):
 # - See more in the documentation of the class :py:class:`LFDA
 #   <metric_learn.LFDA>`
 
-lfda = metric_learn.LFDA(k=2, num_dims=2)
+lfda = metric_learn.LFDA(k=2, n_components=2)
 X_lfda = lfda.fit_transform(X, y)
 
 plot_tsne(X_lfda, y)

metric_learn/_version.py

@@ -1 +1 @@
-__version__ = '0.5.0'
+__version__ = '0.6.0'

metric_learn/base_metric.py

@@ -9,7 +9,6 @@
 import numpy as np
 from abc import ABCMeta, abstractmethod
 from ._util import ArrayIndexer, check_input, validate_vector
-import warnings
 
 
 class BaseMetricLearner(BaseEstimator, metaclass=ABCMeta):
@@ -285,15 +284,6 @@ def metric_fun(u, v, squared=False):
 
   get_metric.__doc__ = BaseMetricLearner.get_metric.__doc__
 
-  def metric(self):
-    """Deprecated. Will be removed in v0.6.0. Use `get_mahalanobis_matrix`
-    instead"""
-    # TODO: remove this method in version 0.6.0
-    warnings.warn(("`metric` is deprecated since version 0.5.0 and will be "
-                   "removed in 0.6.0. Use `get_mahalanobis_matrix` instead."),
-                  DeprecationWarning)
-    return self.get_mahalanobis_matrix()
-
   def get_mahalanobis_matrix(self):
     """Returns a copy of the Mahalanobis matrix learned by the metric learner.
 

metric_learn/itml.py

@@ -2,9 +2,7 @@
 Information Theoretic Metric Learning (ITML)
 """
 
-import warnings
 import numpy as np
-from sklearn.exceptions import ChangedBehaviorWarning
 from sklearn.metrics import pairwise_distances
 from sklearn.utils.validation import check_array
 from sklearn.base import TransformerMixin
@@ -19,23 +17,17 @@ class _BaseITML(MahalanobisMixin):
   _tuple_size = 2  # constraints are pairs
 
   def __init__(self, gamma=1., max_iter=1000, convergence_threshold=1e-3,
-               prior='identity', A0='deprecated', verbose=False,
+               prior='identity', verbose=False,
                preprocessor=None, random_state=None):
     self.gamma = gamma
     self.max_iter = max_iter
     self.convergence_threshold = convergence_threshold
     self.prior = prior
-    self.A0 = A0
     self.verbose = verbose
     self.random_state = random_state
     super(_BaseITML, self).__init__(preprocessor)
 
   def _fit(self, pairs, y, bounds=None):
-    if self.A0 != 'deprecated':
-      warnings.warn('"A0" parameter is not used.'
-                    ' It has been deprecated in version 0.5.0 and will be'
-                    'removed in 0.6.0. Use "prior" instead.',
-                    DeprecationWarning)
     pairs, y = self._prepare_inputs(pairs, y,
                                     type_of_inputs='tuples')
     # init bounds
@@ -155,11 +147,6 @@ class ITML(_BaseITML, _PairsClassifierMixin):
       (n_features, n_features), that will be used as such to set the
       prior.
 
-  A0 : Not used
-    .. deprecated:: 0.5.0
-      `A0` was deprecated in version 0.5.0 and will
-      be removed in 0.6.0. Use 'prior' instead.
-
   verbose : bool, optional (default=False)
     If True, prints information while learning
 
@@ -276,21 +263,10 @@ class ITML_Supervised(_BaseITML, TransformerMixin):
   convergence_threshold : float, optional (default=1e-3)
     Tolerance of the optimization procedure.
 
-  num_labeled : Not used
-    .. deprecated:: 0.5.0
-      `num_labeled` was deprecated in version 0.5.0 and will
-      be removed in 0.6.0.
-
   num_constraints : int, optional (default=None)
     Number of constraints to generate. If None, default to `20 *
     num_classes**2`.
 
-  bounds : Not used
-    .. deprecated:: 0.5.0
-      `bounds` was deprecated in version 0.5.0 and will
-      be removed in 0.6.0. Set `bounds` at fit time instead :
-      `itml_supervised.fit(X, y, bounds=...)`
-
   prior : string or numpy array, optional (default='identity')
     Initialization of the Mahalanobis matrix. Possible options are
     'identity', 'covariance', 'random', and a numpy array of shape
@@ -313,11 +289,6 @@ class ITML_Supervised(_BaseITML, TransformerMixin):
       (n_features, n_features), that will be used as such to set the
       prior.
 
-  A0 : Not used
-    .. deprecated:: 0.5.0
-      `A0` was deprecated in version 0.5.0 and will
-      be removed in 0.6.0. Use 'prior' instead.
-
   verbose : bool, optional (default=False)
     If True, prints information while learning
 
@@ -368,18 +339,15 @@ class ITML_Supervised(_BaseITML, TransformerMixin):
   """
 
   def __init__(self, gamma=1.0, max_iter=1000, convergence_threshold=1e-3,
-               num_labeled='deprecated', num_constraints=None,
-               bounds='deprecated', prior='identity', A0='deprecated',
+               num_constraints=None, prior='identity',
                verbose=False, preprocessor=None, random_state=None):
     _BaseITML.__init__(self, gamma=gamma, max_iter=max_iter,
                        convergence_threshold=convergence_threshold,
-                       A0=A0, prior=prior, verbose=verbose,
+                       prior=prior, verbose=verbose,
                        preprocessor=preprocessor, random_state=random_state)
-    self.num_labeled = num_labeled
     self.num_constraints = num_constraints
-    self.bounds = bounds
 
-  def fit(self, X, y, random_state='deprecated', bounds=None):
+  def fit(self, X, y, bounds=None):
     """Create constraints from labels and learn the ITML model.
 
 
@@ -391,12 +359,6 @@ def fit(self, X, y, random_state='deprecated', bounds=None):
     y : (n) array-like
       Data labels.
 
-    random_state : Not used
-      .. deprecated:: 0.5.0
-        `random_state` in the `fit` function was deprecated in version 0.5.0
-        and will be removed in 0.6.0. Set `random_state` at initialization
-        instead (when instantiating a new `ITML_Supervised` object).
-
     bounds : array-like of two numbers
       Bounds on similarity, aside slack variables, s.t.
       ``d(a, b) < bounds_[0]`` for all given pairs of similar points ``a``
@@ -406,28 +368,6 @@ def fit(self, X, y, random_state='deprecated', bounds=None):
       set to the 5th and 95th percentile of the pairwise distances among all
       points in the training data `X`.
     """
-    # TODO: remove these in v0.6.0
-    if self.num_labeled != 'deprecated':
-      warnings.warn('"num_labeled" parameter is not used.'
-                    ' It has been deprecated in version 0.5.0 and will be'
-                    ' removed in 0.6.0', DeprecationWarning)
-    if self.bounds != 'deprecated':
-      warnings.warn('"bounds" parameter from initialization is not used.'
-                    ' It has been deprecated in version 0.5.0 and will be'
-                    ' removed in 0.6.0. Use the "bounds" parameter of this '
-                    'fit method instead.', DeprecationWarning)
-    if random_state != 'deprecated':
-      warnings.warn('"random_state" parameter in the `fit` function is '
-                    'deprecated. Set `random_state` at initialization '
-                    'instead (when instantiating a new `ITML_Supervised` '
-                    'object).', DeprecationWarning)
-    else:
-      warnings.warn('As of v0.5.0, `ITML_Supervised` now uses the '
-                    '`random_state` given at initialization to sample '
-                    'constraints, not the default `np.random` from the `fit` '
-                    'method, since this argument is now deprecated. '
-                    'This warning will disappear in v0.6.0.',
-                    ChangedBehaviorWarning)
     X, y = self._prepare_inputs(X, y, ensure_min_samples=2)
     num_constraints = self.num_constraints
     if num_constraints is None:

metric_learn/lfda.py

@@ -27,11 +27,6 @@ class LFDA(MahalanobisMixin, TransformerMixin):
   n_components : int or None, optional (default=None)
     Dimensionality of reduced space (if None, defaults to dimension of X).
 
-  num_dims : Not used
-    .. deprecated:: 0.5.0
-      `num_dims` was deprecated in version 0.5.0 and will
-      be removed in 0.6.0. Use `n_components` instead.
-
   k : int, optional (default=None)
     Number of nearest neighbors used in local scaling method. If None,
     defaults to min(7, n_features - 1).
@@ -81,12 +76,11 @@ class LFDA(MahalanobisMixin, TransformerMixin):
         -discriminant-analysis-on-beer-style-clustering.html#>`_.
   '''
 
-  def __init__(self, n_components=None, num_dims='deprecated',
+  def __init__(self, n_components=None,
                k=None, embedding_type='weighted', preprocessor=None):
     if embedding_type not in ('weighted', 'orthonormalized', 'plain'):
       raise ValueError('Invalid embedding_type: %r' % embedding_type)
     self.n_components = n_components
-    self.num_dims = num_dims
     self.embedding_type = embedding_type
     self.k = k
     super(LFDA, self).__init__(preprocessor)
@@ -102,11 +96,6 @@ def fit(self, X, y):
     y : (n,) array-like
         Class labels, one per point of data.
     '''
-    if self.num_dims != 'deprecated':
-      warnings.warn('"num_dims" parameter is not used.'
-                    ' It has been deprecated in version 0.5.0 and will be'
-                    ' removed in 0.6.0. Use "n_components" instead',
-                    DeprecationWarning)
     X, y = self._prepare_inputs(X, y, ensure_min_samples=2)
     unique_classes, y = np.unique(y, return_inverse=True)
     n, d = X.shape

metric_learn/lmnn.py

@@ -2,9 +2,7 @@
 Large Margin Nearest Neighbor Metric learning (LMNN)
 """
 import numpy as np
-import warnings
 from collections import Counter
-from sklearn.exceptions import ChangedBehaviorWarning
 from sklearn.metrics import euclidean_distances
 from sklearn.base import TransformerMixin
 
@@ -25,12 +23,10 @@ class LMNN(MahalanobisMixin, TransformerMixin):
 
   Parameters
   ----------
-  init : None, string or numpy array, optional (default=None)
+  init : string or numpy array, optional (default='auto')
     Initialization of the linear transformation. Possible options are
     'auto', 'pca', 'identity', 'random', and a numpy array of shape
-    (n_features_a, n_features_b). If None, will be set automatically to
-    'auto' (this option is to raise a warning if 'init' is not set, and
-    stays to its default value None, in v0.5.0).
+    (n_features_a, n_features_b).
 
     'auto'
       Depending on ``n_components``, the most reasonable initialization
@@ -83,11 +79,6 @@ class LMNN(MahalanobisMixin, TransformerMixin):
     Tolerance of the optimization procedure. If the objective value varies
     less than `tol`, we consider the algorithm has converged and stop it.
 
-  use_pca : Not used
-    .. deprecated:: 0.5.0
-      `use_pca` was deprecated in version 0.5.0 and will
-      be removed in 0.6.0.
-
   verbose : bool, optional (default=False)
     Whether to print the progress of the optimization procedure.
 
@@ -102,11 +93,6 @@ class LMNN(MahalanobisMixin, TransformerMixin):
   n_components : int or None, optional (default=None)
     Dimensionality of reduced space (if None, defaults to dimension of X).
 
-  num_dims : Not used
-    .. deprecated:: 0.5.0
-      `num_dims` was deprecated in version 0.5.0 and will
-      be removed in 0.6.0. Use `n_components` instead.
-
   random_state : int or numpy.RandomState or None, optional (default=None)
     A pseudo random number generator object or a seed for it if int. If
     ``init='random'``, ``random_state`` is used to initialize the random
@@ -142,35 +128,23 @@ class LMNN(MahalanobisMixin, TransformerMixin):
          2005.
   """
 
-  def __init__(self, init=None, k=3, min_iter=50, max_iter=1000,
+  def __init__(self, init='auto', k=3, min_iter=50, max_iter=1000,
                learn_rate=1e-7, regularization=0.5, convergence_tol=0.001,
-               use_pca='deprecated', verbose=False, preprocessor=None,
-               n_components=None, num_dims='deprecated', random_state=None):
+               verbose=False, preprocessor=None,
+               n_components=None, random_state=None):
     self.init = init
     self.k = k
     self.min_iter = min_iter
     self.max_iter = max_iter
     self.learn_rate = learn_rate
     self.regularization = regularization
     self.convergence_tol = convergence_tol
-    self.use_pca = use_pca
     self.verbose = verbose
     self.n_components = n_components
-    self.num_dims = num_dims
     self.random_state = random_state
     super(LMNN, self).__init__(preprocessor)
 
   def fit(self, X, y):
-    if self.num_dims != 'deprecated':
-      warnings.warn('"num_dims" parameter is not used.'
-                    ' It has been deprecated in version 0.5.0 and will be'
-                    ' removed in 0.6.0. Use "n_components" instead',
-                    DeprecationWarning)
-    if self.use_pca != 'deprecated':
-      warnings.warn('"use_pca" parameter is not used.'
-                    ' It has been deprecated in version 0.5.0 and will be'
-                    ' removed in 0.6.0.',
-                    DeprecationWarning)
     k = self.k
     reg = self.regularization
     learn_rate = self.learn_rate
@@ -184,20 +158,7 @@ def fit(self, X, y):
       raise ValueError('Must have one label per point.')
     self.labels_ = np.arange(len(unique_labels))
 
-    # if the init is the default (None), we raise a warning
-    if self.init is None:
-      # TODO: replace init=None by init='auto' in v0.6.0 and remove the warning
-      msg = ("Warning, no init was set (`init=None`). As of version 0.5.0, "
-             "the default init will now be set to 'auto', instead of the "
-             "previous identity matrix. If you still want to use the identity "
-             "matrix as before, set init='identity'. This warning "
-             "will disappear in v0.6.0, and `init` parameter's default value "
-             "will be set to 'auto'.")
-      warnings.warn(msg, ChangedBehaviorWarning)
-      init = 'auto'
-    else:
-      init = self.init
-    self.components_ = _initialize_components(output_dim, X, y, init,
+    self.components_ = _initialize_components(output_dim, X, y, self.init,
                                               self.verbose,
                                               random_state=self.random_state)
     required_k = np.bincount(label_inds).min()