Python decomposition.DictionaryLearning类代码示例

def test_dict_learning_lassocd_readonly_data():
    n_components = 12
    with TempMemmap(X) as X_read_only:
        dico = DictionaryLearning(n_components, transform_algorithm='lasso_cd',
                                  transform_alpha=0.001, random_state=0, n_jobs=-1)
        code = dico.fit(X_read_only).transform(X_read_only)
        assert_array_almost_equal(np.dot(code, dico.components_), X_read_only, decimal=2)

def test_dict_learning_split():
    n_atoms = 5
    dico = DictionaryLearning(n_atoms, transform_algorithm='threshold')
    code = dico.fit(X).transform(X)
    dico.split_sign = True
    split_code = dico.transform(X)

    assert_array_equal(split_code[:, :n_atoms] - split_code[:, n_atoms:], code)

def test_dict_learning_shapes():
    n_components = 5
    dico = DictionaryLearning(n_components, random_state=0).fit(X)
    assert_equal(dico.components_.shape, (n_components, n_features))

    n_components = 1
    dico = DictionaryLearning(n_components, random_state=0).fit(X)
    assert_equal(dico.components_.shape, (n_components, n_features))
    assert_equal(dico.transform(X).shape, (X.shape[0], n_components))

def trainLowDict(buffer):
    print('Learning the dictionary...')
    t0 = time()
    dico = DictionaryLearning(n_components=100, alpha=1, max_iter=100,verbose=1)

    V = dico.fit(buffer).components_
    E = dico.error_
    dt = time() - t0
    print('done in %.2fs.' % dt)
    return V,E

def test_dict_learning_split():
    n_components = 5
    dico = DictionaryLearning(n_components, transform_algorithm='threshold',
                              random_state=0)
    code = dico.fit(X).transform(X)
    dico.split_sign = True
    split_code = dico.transform(X)

    assert_array_equal(split_code[:, :n_components] -
                       split_code[:, n_components:], code)

def test_dict_learning_reconstruction():
    n_components = 12
    dico = DictionaryLearning(n_components, transform_algorithm='omp',
                              transform_alpha=0.001, random_state=0)
    code = dico.fit(X).transform(X)
    assert_array_almost_equal(np.dot(code, dico.components_), X)

    dico.set_params(transform_algorithm='lasso_lars')
    code = dico.transform(X)
    assert_array_almost_equal(np.dot(code, dico.components_), X, decimal=2)

def test_dict_learning_nonzero_coefs():
    n_components = 4
    dico = DictionaryLearning(n_components, transform_algorithm='lars',
                              transform_n_nonzero_coefs=3, random_state=0)
    code = dico.fit(X).transform(X[np.newaxis, 1])
    assert_true(len(np.flatnonzero(code)) == 3)

    dico.set_params(transform_algorithm='omp')
    code = dico.transform(X[np.newaxis, 1])
    assert_equal(len(np.flatnonzero(code)), 3)

def sparse_coding(dimension, input_x, alpha, iteration, tolerance):
	#dl = DictionaryLearning(dimension)
	dl = DictionaryLearning(dimension, alpha, iteration, tolerance) 
	dl.fit(input_x)
	#np.set_printoptions(precision=3, suppress=True)
	#print code
	#print dl.components_
	print "error:", dl.error_[-1]
	
	return dl

def test_dict_learning_reconstruction_parallel():
    # regression test that parallel reconstruction works with n_jobs=-1
    n_components = 12
    dico = DictionaryLearning(n_components, transform_algorithm='omp',
                              transform_alpha=0.001, random_state=0, n_jobs=-1)
    code = dico.fit(X).transform(X)
    assert_array_almost_equal(np.dot(code, dico.components_), X)

    dico.set_params(transform_algorithm='lasso_lars')
    code = dico.transform(X)
    assert_array_almost_equal(np.dot(code, dico.components_), X, decimal=2)

    def __init__(self, model_filename=None):
        if model_filename is not None:
            self.load_model(model_filename)
        else:
            # default model params
            self.n_components = SparseCoding.DEFAULT_MODEL_PARAMS['n_components']
            self.n_features = SparseCoding.DEFAULT_MODEL_PARAMS['n_features']
            self.max_iter = SparseCoding.DEFAULT_MODEL_PARAMS['max_iter']
            self.random_state = SparseCoding.DEFAULT_MODEL_PARAMS['random_state']
            self.dict_init = SparseCoding.DEFAULT_MODEL_PARAMS['dict_init']
            self.code_init = SparseCoding.DEFAULT_MODEL_PARAMS['code_init']

            # initialize Dictionary Learning object with default params and weights
            self.DL_obj = DictionaryLearning(n_components=self.n_components,
                                       alpha=1,
                                       max_iter=self.max_iter,
                                       tol=1e-08,
                                       fit_algorithm='lars',
                                       transform_algorithm='omp',
                                       transform_n_nonzero_coefs=None,
                                       transform_alpha=None,
                                       n_jobs=1,
                                       code_init=self.code_init,
                                       dict_init=self.dict_init,
                                       verbose=False,
                                       split_sign=False,
                                       random_state=self.random_state)

def test_dict_learning_positivity(transform_algorithm,
                                  positive_code,
                                  positive_dict):
    n_components = 5
    dico = DictionaryLearning(
        n_components, transform_algorithm=transform_algorithm, random_state=0,
        positive_code=positive_code, positive_dict=positive_dict).fit(X)
    code = dico.transform(X)
    if positive_dict:
        assert_true((dico.components_ >= 0).all())
    else:
        assert_true((dico.components_ < 0).any())
    if positive_code:
        assert_true((code >= 0).all())
    else:
        assert_true((code < 0).any())

def get_dic_per_cluster(clust_q, data_cluster, dataq, i, out_q=None, kerPCA=False):
    if out_q is not None:
        name = mpc.current_process().name
        print name, 'Starting'
    else:
        print 'Starting estimation of dic %i...' % i
    # parse the feature vectors for each cluster
    for q in clust_q:
        data_cluster = np.vstack((data_cluster, dataq[q]))
    # remove useless first line
    data_cluster = data_cluster[1:, :]
    # learn the sparse code for that cluster
    if kerPCA is False:
        dict_learn = DictionaryLearning(n_jobs=10)
        dict_learn.fit(data_cluster)
    else:
        print 'Doing kernel PCA...'
        print data_cluster.shape
        dict_learn = KernelPCA(kernel="rbf", gamma=10, n_components=3)
        #dict_learn = PCA(n_components=10)
        dict_learn.fit(data_cluster)
    if out_q is not None:
        res = {}
        res[i] = dict_learn
        out_q.put(res)
        print name, 'Exiting'
    else:
        print 'Finished.'
        return dict_learn   # dict(i = dict_learn)

def create_dictionary_dl(lmbd, K=100, N=10000, dir_mnist='save_exp/mnist'):

    import os.path as osp
    fname = osp.join(dir_mnist, "D_mnist_K{}_lmbd{}.npy".format(K, lmbd))
    if osp.exists(fname):
        D = np.load(fname)
    else:
        from sklearn.decomposition import DictionaryLearning
        mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
        im = mnist.train.next_batch(N)[0]
        im = im.reshape(N, 28, 28)
        im = [imresize(a, (17, 17), interp='bilinear', mode='L')-.5
              for a in im]
        X = np.array(im).reshape(N, -1)
        print(X.shape)

        dl = DictionaryLearning(K, alpha=lmbd*N, fit_algorithm='cd',
                                n_jobs=-1, verbose=1)
        dl.fit(X)
        D = dl.components_.reshape(K, -1)
        np.save(fname, D)
    return D

    def __init__(self, num_components=10,
                 catalog_name='unknown',
                 alpha = 0.001,
                 transform_alpha = 0.01,
                 max_iter = 2000,
                 tol = 1e-9,
                 n_jobs = 1,
                 verbose = True,
                 random_state = None):

        self._decomposition   = 'Sparse Coding'
        self._num_components  = num_components
        self._catalog_name    = catalog_name
        self._alpha           = alpha
        self._transform_alpha = 0.001
        self._n_jobs          = n_jobs
        self._random_state    = random_state

        self._DL = DictionaryLearning(n_components=self._num_components,
                              alpha           = self._alpha,
                              transform_alpha = self._transform_alpha,
                              n_jobs          = self._n_jobs,
                              verbose         = verbose,
                              random_state    = self._random_state)

class SC(object):
    """
    Wrapper for sklearn package.  Performs sparse coding

    Sparse Coding, or Dictionary Learning has 5 methods:
       - fit(waveforms)
       update class instance with Sparse Coding fit

       - fit_transform()
       do what fit() does, but additionally return the projection onto new basis space

       - inverse_transform(A)
       inverses the decomposition, returns waveforms for an input A, using Z^\dagger

       - get_basis()
       returns the basis vectors Z^\dagger

       - get_params()
       returns metadata used for fits.
    """
    def __init__(self, num_components=10,
                 catalog_name='unknown',
                 alpha = 0.001,
                 transform_alpha = 0.01,
                 max_iter = 2000,
                 tol = 1e-9,
                 n_jobs = 1,
                 verbose = True,
                 random_state = None):

        self._decomposition   = 'Sparse Coding'
        self._num_components  = num_components
        self._catalog_name    = catalog_name
        self._alpha           = alpha
        self._transform_alpha = 0.001
        self._n_jobs          = n_jobs
        self._random_state    = random_state

        self._DL = DictionaryLearning(n_components=self._num_components,
                              alpha           = self._alpha,
                              transform_alpha = self._transform_alpha,
                              n_jobs          = self._n_jobs,
                              verbose         = verbose,
                              random_state    = self._random_state)

    def fit(self,waveforms):
        # TODO make sure there are more columns than rows (transpose if not)
        # normalize waveforms
        self._waveforms = waveforms
        self._DL.fit(self._waveforms)

    def fit_transform(self,waveforms):
        # TODO make sure there are more columns than rows (transpose if not)
        # normalize waveforms
        self._waveforms = waveforms
        self._A = self._DL.fit_transform(self._waveforms)
        return self._A

    def inverse_transform(self,A):
        # convert basis back to waveforms using fit
        new_waveforms = self._DL.inverse_transform(A)
        return new_waveforms

    def get_params(self):
        # TODO know what catalog was used! (include waveform metadata)
        params = self._DL.get_params()
        params['num_components'] = params.pop('n_components')
        params['Decompositon'] = self._decomposition
        return params

    def get_basis(self):
        """ Return the SPCA basis vectors (Z^\dagger)"""
        return self._DL.components_