Python sklearn.decomposition 模块，DictionaryLearning() 实例源码

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 learn_dictionary(patches, n_c=512, a=1, n_i=100, n_j=3, es=5, fit_algorithm='lars'):
    dic = DictionaryLearning(n_components=n_c, alpha=a, max_iter=n_i,
                             n_jobs=n_j, fit_algorithm=fit_algorithm)
    print ("Start learning dictionary: n_c: "+str(n_c)+", alpha: "+str(a)+", n_i: " +
           str(n_i)+", es: "+str(es)+", n_j: "+str(n_j))
    v2 = dic.fit(patches).components_
    d2 = v2.reshape(n_c, es, es, es)  # e.g. 512x5x5x5
    return d2

def test_DictionaryLearning():
    '''
    test the DL method
    :return: None
    '''
    X=[[1,2,3,4,5],
       [6,7,8,9,10],
       [10,9,8,7,6,],
       [5,4,3,2,1] ]
    print("before transform:",X)
    dct=DictionaryLearning(n_components=3)
    dct.fit(X)
    print("components is :",dct.components_)
    print("after transform:",dct.transform(X))

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

def test_dict_learning_overcomplete():
    n_components = 12
    dico = DictionaryLearning(n_components, random_state=0).fit(X)
    assert_true(dico.components_.shape == (n_components, n_features))

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)

    # used to test lars here too, but there's no guarantee the number of
    # nonzero atoms is right.

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 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_unknown_fit_algorithm():
    n_components = 5
    dico = DictionaryLearning(n_components, fit_algorithm='<unknown>')
    assert_raises(ValueError, dico.fit, X)

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)