Python base.Classifier类代码示例

    def __init__(self, k=2, dfx=squared_euclidean_distance,
                 voting='weighted', **kwargs):
        """
        Parameters
        ----------
        k : unsigned integer
          Number of nearest neighbours to be used for voting.
        dfx : functor
          Function to compute the distances between training and test samples.
          Default: squared euclidean distance
        voting : str
          Voting method used to derive predictions from the nearest neighbors.
          Possible values are 'majority' (simple majority of classes
          determines vote) and 'weighted' (votes are weighted according to the
          relative frequencies of each class in the training data).
        **kwargs
          Additional arguments are passed to the base class.
        """

        # init base class first
        Classifier.__init__(self, **kwargs)

        self.__k = k
        self.__dfx = dfx
        self.__voting = voting
        self.__data = None
        self.__weights = None

    def __init__(self, skl_learner, tags=None, enforce_dim=None,
                 **kwargs):
        """
        Parameters
        ----------
        skl_learner
          Existing instance of a learner from skl.  It should
          implement `fit` and `predict`.  If `predict_proba` is
          available in the interface, then conditional attribute
          `probabilities` becomes available as well
        tags : list of string
          What additional tags to attach to this learner.  Tags are
          used in the queries to classifier or regression warehouses.
        enforce_dim : None or int, optional
          If not None, it would enforce given dimensionality for
          ``predict`` call, if all other trailing dimensions are
          degenerate.
        """

        self._skl_learner = skl_learner
        self.enforce_dim = enforce_dim
        if tags:
            # So we make a per-instance copy
            self.__tags__ = self.__tags__ + tags
        Classifier.__init__(self, **kwargs)

    def __init__(self, lm=None, **kwargs):
        """
        Initialize a ridge regression analysis.

        Parameters
        ----------
        lm : float
          the penalty term lambda.
          (Defaults to .05*nFeatures)
        """
        # init base class first
        Classifier.__init__(self, **kwargs)

        # pylint happiness
        self.w = None

        # It does not make sense to calculate a confusion matrix for a
        # ridge regression
        self.ca.enable('training_stats', False)

        # verify that they specified lambda
        self.__lm = lm

        # store train method config
        self.__implementation = 'direct'

    def __init__(self, **kwargs):
        """Initialize an SMLR classifier.
        """

        """
        TODO:
         # Add in likelihood calculation
         # Add kernels, not just direct methods.
         """
        # init base class first
        Classifier.__init__(self, **kwargs)

        if _cStepwiseRegression is None and self.params.implementation == 'C':
            warning('SMLR: C implementation is not available.'
                    ' Using pure Python one')
            self.params.implementation = 'Python'

        # pylint friendly initializations
        self._ulabels = None
        """Unigue labels from the training set."""
        self.__weights_all = None
        """Contains all weights including bias values"""
        self.__weights = None
        """Just the weights, without the biases"""
        self.__biases = None
        """The biases, will remain none if has_bias is False"""

    def __init__(self, sigma_p = None, sigma_noise=1.0, **kwargs):
        """Initialize a BLR regression analysis.

        Parameters
        ----------
        sigma_noise : float
          the standard deviation of the gaussian noise.
          (Defaults to 0.1)

        """
        # init base class first
        Classifier.__init__(self, **kwargs)

        # pylint happiness
        self.w = None

        # It does not make sense to calculate a confusion matrix for a
        # BLR:
        self.ca.enable('training_stats', False)

        # set the prior on w: N(0,sigma_p) , specifying the covariance
        # sigma_p on w:
        self.sigma_p = sigma_p

        # set noise level:
        self.sigma_noise = sigma_noise

        self.ca.predicted_variances = None
        self.ca.log_marginal_likelihood = None
        # Yarik: what was those about??? just for future in
        #        compute_log_marginal_likelihood ?
        # self.targets = None
        pass

    def __init__(self, lm=1, criterion=1, reduced=0.0, maxiter=20, **kwargs):
        """
        Initialize a penalized logistic regression analysis

        Parameters
        ----------
        lm : int
          the penalty term lambda.
        criterion : int
          the criterion applied to judge convergence.
        reduced : float
          if not 0, the rank of the data is reduced before
          performing the calculations. In that case, reduce is taken
          as the fraction of the first singular value, at which a
          dimension is not considered significant anymore. A
          reasonable criterion is reduced=0.01
        maxiter : int
          maximum number of iterations. If no convergence occurs
          after this number of iterations, an exception is raised.
        """
        # init base class first
        Classifier.__init__(self, **kwargs)

        self.__lm   = lm
        self.__criterion = criterion
        self.__reduced = reduced
        self.__maxiter = maxiter

    def __init__(self, model_type="lasso", trace=False, normalize=True,
                 intercept=True, max_steps=None, use_Gram=False, **kwargs):
        """
        Initialize LARS.

        See the help in R for further details on the following parameters:

        Parameters
        ----------
        model_type : string
          Type of LARS to run. Can be one of ('lasso', 'lar',
          'forward.stagewise', 'stepwise').
        trace : boolean
          Whether to print progress in R as it works.
        normalize : boolean
          Whether to normalize the L2 Norm.
        intercept : boolean
          Whether to add a non-penalized intercept to the model.
        max_steps : None or int
          If not None, specify the total number of iterations to run. Each
          iteration adds a feature, but leaving it none will add until
          convergence.
        use_Gram : boolean
          Whether to compute the Gram matrix (this should be false if you
          have more features than samples.)
        """
        # init base class first
        Classifier.__init__(self, **kwargs)

        if not model_type in known_models:
            raise ValueError('Unknown model %s for LARS is specified. Known' %
                             model_type + 'are %s' % `known_models`)

        # set up the params
        self.__type = model_type
        self.__normalize = normalize
        self.__intercept = intercept
        self.__trace = trace
        self.__max_steps = max_steps
        self.__use_Gram = use_Gram

        # pylint friendly initializations
        self.__lowest_Cp_step = None
        self.__weights = None
        """The beta weights for each feature."""
        self.__trained_model = None
        """The model object after training that will be used for

 def __repr__(self):
     """String representation of `SKLLearnerWrapper`
     """
     prefixes = [repr(self._skl_learner)]
     if self.__tags__ != ['skl']:
         prefixes += ['tags=%r' % [t for t in self.__tags__ if t != 'skl']]
     prefixes += _repr_attrs(self, ['enforce_dim'])
     return Classifier.__repr__(self, prefixes=prefixes)

    def __init__(self, **kwargs):
        """
        Initialize GLM-Net.

        See the help in R for further details on the parameters
        """
        # init base class first
        Classifier.__init__(self, **kwargs)

        # pylint friendly initializations
        self._utargets = None
        self.__weights = None
        """The beta weights for each feature."""
        self.__trained_model = None
        """The model object after training that will be used for
        predictions."""
        self.__last_lambda = None
        """Lambda obtained on the last step"""

    def __init__(self, **kwargs):
        """Initialize an GNB classifier.
        """

        # init base class first
        Classifier.__init__(self, **kwargs)

        # pylint friendly initializations
        self.means = None
        """Means of features per class"""
        self.variances = None
        """Variances per class, but "vars" is taken ;)"""
        self.ulabels = None
        """Labels classifier was trained on"""
        self.priors = None
        """Class probabilities"""

        # Define internal state of classifier
        self._norm_weight = None

    def __init__(self, kernel=None, **kwargs):
        """Initialize a GPR regression analysis.

        Parameters
        ----------
        kernel : Kernel
          a kernel object defining the covariance between instances.
          (Defaults to SquaredExponentialKernel if None in arguments)
        """
        # init base class first
        Classifier.__init__(self, **kwargs)

        # It does not make sense to calculate a confusion matrix for a GPR
        # XXX it does ;) it will be a RegressionStatistics actually ;-)
        # So if someone desires -- let him have it
        # self.ca.enable('training_stats', False)

        # set kernel:
        if kernel is None:
            kernel = SquaredExponentialKernel()
            debug("GPR",
                  "No kernel was provided, falling back to default: %s"
                  % kernel)
        self.__kernel = kernel

        # append proper clf_internal depending on the kernel
        # TODO: add "__tags__" to kernels since the check
        #       below does not scale
        if isinstance(kernel, GeneralizedLinearKernel) or \
           isinstance(kernel, LinearKernel):
            self.__tags__ += ['linear']
        else:
            self.__tags__ += ['non-linear']

        if externals.exists('openopt') \
               and not 'has_sensitivity' in self.__tags__:
            self.__tags__ += ['has_sensitivity']

        # No need to initialize conditional attributes. Unless they got set
        # they would raise an exception self.predicted_variances =
        # None self.log_marginal_likelihood = None
        self._init_internals()
        pass

    def __init__(self, lm=1.0, trace=False, normalize=True,
                 intercept=True, max_steps=None, **kwargs):
        """
        Initialize ENET.

        See the help in R for further details on the following parameters:

        Parameters
        ----------
        lm : float
          Penalty parameter.  0 will perform LARS with no ridge regression.
          Default is 1.0.
        trace : boolean
          Whether to print progress in R as it works.
        normalize : boolean
          Whether to normalize the L2 Norm.
        intercept : boolean
          Whether to add a non-penalized intercept to the model.
        max_steps : None or int
          If not None, specify the total number of iterations to run. Each
          iteration adds a feature, but leaving it none will add until
          convergence.
        """
        # init base class first
        Classifier.__init__(self, **kwargs)

        # set up the params
        self.__lm = lm
        self.__normalize = normalize
        self.__intercept = intercept
        self.__trace = trace
        self.__max_steps = max_steps

        # pylint friendly initializations
        self.__weights = None
        """The beta weights for each feature."""
        self.__trained_model = None
        """The model object after training that will be used for
        predictions."""

        # It does not make sense to calculate a confusion matrix for a
        # regression
        self.ca.enable('training_stats', False)

    def __init__(self, **kwargs):
        """Initialize a GDA classifier.
        """

        # init base class first
        Classifier.__init__(self, **kwargs)

        # pylint friendly initializations
        self.means = None
        """Means of features per class"""
        self.cov = None
        """Co-variances per class, but "vars" is taken ;)"""
        self.ulabels = None
        """Labels classifier was trained on"""
        self.priors = None
        """Class probabilities"""
        self.nsamples_per_class = None
        """Number of samples per class - used by derived classes"""

        # Define internal state of classifier
        self._norm_weight = None

    def __init__(self, **kwargs):
        """Initialize an GNB classifier.
        """

        # init base class first
        Classifier.__init__(self, **kwargs)

        # pylint friendly initializations
        self.means = None
        """Means of features per class"""
        self.variances = None
        """Variances per class, but "vars" is taken ;)"""
        self.ulabels = None
        """Labels classifier was trained on"""
        self.priors = None
        """Class probabilities"""

        # Define internal state of classifier
        self._norm_weight = None

        # Add 'has_sensitivity' tag if classifier is linear
        if self.params.common_variance:
            self.__tags__ = self.__tags__ + ['has_sensitivity']

    def __init__(self, learner, kwargs=None, kwargs_predict=None,
                 tags=None, **kwargs_):
        """
        Parameters
        ----------
        learner : string
        kwargs : dict, optional
        kwargs_predict : dict, optional
        tags : list of string
          What additional tags to attach to this classifier.  Tags are
          used in the queries to classifier or regression warehouses.
        """

        self._learner = learner

        self._kwargs = kwargs or {}
        self._kwargs_predict = kwargs_predict or {}

        if tags:
            # So we make a per-instance copy
            self.__tags__ = self.__tags__ + tags

        Classifier.__init__(self, **kwargs_)