2

我正在研究应用内核主成分分析 (KPCA) 来降低我的特征矩阵集的维数，从而获得一组数据点。我浏览了 scikit learn 包中 KPCA 中使用的参数，并了解到如果选择其中一个参数应该起作用（例如，如果选择了 gamma，则不使用度数和系数）。此外，我通过以下链接查看了用于分类模型的超参数方法：

我尝试编写 hyperopt 代码并将其与 KPCA 结合起来，但是，在处理 PCA 模型评分的领域中，我不断遇到错误。我知道 KPCA 没有分数才能找到 PCA 模型的准确性，那么，我该如何克服这个错误呢？我尝试了几种评分方法，但我从 inverse_fit 或数组大小中得到错误。请在下面找到代码和错误消息。

代码：

from sklearn.decomposition import PCA, KernelPCA, SparsePCA, IncrementalPCA
from hyperopt import hp, tpe, atpe, fmin, Trials, rand, STATUS_OK

# Implementing Hyperparamater method:
models = {'pca'      : PCA,
          'kpca'     : KernelPCA,
          'spca'     : SparsePCA,
          # 'ipca'     : IncrementalPCA
          }

def search_space(model):
    # Initialising variables:
    model = model.lower()
    space = {}

    # Calling the models:
    if model == 'pca':
        space = {'svd_solver'        : hp.choice('svd_solver', ["auto", "full", "arpack", "randomized"]),
                 }

    elif model == 'kpca':
        space = {'kernel'            : hp.choice('kernel', ['linear', 'poly', 'rbf', 'sigmoid', 'cosine', 'precomputed']),
                 'gamma'             : hp.choice('gamma', np.arange(0.03, 0.05, 0.002)),
                 'degree'            : hp.choice('degree', range(1, 10, 1)),
                 'coef0'             : hp.choice('coef0', np.arange(1, 10, 0.2))
                 }

    elif model == 'spca':
        space = {'alpha'             : hp.choice('alpha', np.arange(1.0, 15.0, 0.2)),
                 'ridge_alpha'       : hp.choice('ridge_alpha', np.linspace(0.01, 0.3, 30)),
                 'method'            : hp.choice('method', ['lars', 'cd']),
                 'max_iter'          : hp.choice('max_iter', [1000, 1500, 2000, 2500, 3000])
                 }

    # elif model == 'ipca':
    #     space = {'batch_size'        : hp.choice('batch_size', ['gini', 'entropy']),
    #              }
    space['model'] = model
    return space

def obj_fnc(params):
    model = params.get('model').lower()
    # X_ = scale_normalize(params, X[:])
    del params['model']
    clf = models[model](**params)
    return (get_acc_status(clf, X))

def get_acc_status(clf, X):
    X_reduced = clf.fit_transform(X)
    # X_prereduced = clf.fit_inverse_transform(X_reduced)
    # acc = -1 * mean_squared_error(X, X_prereduced)
    X_prereduced = clf.inverse_transform(X_reduced)
    # acc = -1 * mean_absolute_error(X, X_prereduced)
    acc = -1 * r2_score(X, X_prereduced)
    # acc = cross_val_score(clf, X).mean()
    return {'loss': -acc, 'status': STATUS_OK}

##### Hyperparameter optimisation:
# Running Bayesian Optimisation to get the best parameters:
start = time.time()

# Create the algorithms
tpe_algo = tpe.suggest
# rand_algo = rand.suggest
# atpe_algo = atpe.suggest

# Assigning model:
model = 'kpca'

# Creating the trial objects:
hypopt_trials = Trials()

# Getting the best parameters:
best_params = fmin(obj_fnc, search_space(model), algo=tpe_algo, max_evals=500, trials=hypopt_trials)
print("Best params: ", best_params)
print('Best accuracy: ', hypopt_trials.best_trial['result']['loss'])
print("[INFO] Baye. Opt. search took {:.2f} seconds".format(time.time() - start))

# Calling parameters:
## PCA:
svd_solver = ["auto", "full", "arpack", "randomized"]
## KPCA:
kernel =  ["linear", "poly", "rbf", "sigmoid", "cosine", "precomputed"]
gamma = np.arange(0.1, 0.9, 0.01)
degree = range(1, 10, 1)
coef0 = np.arange(1, 10, 0.2)
kernel_gamma = ["poly", "rbf", "sigmoid"]
kernel_degree = "poly"
kernel_coef0 = "sigmoid"
## SPCA:
alpha = np.arange(1.0, 15.0, 0.2)
ridge_alpha = np.linspace(0.01, 0.3, 30)
method = ['lars', 'cd']
max_iter = [1000, 1500, 2000, 2500, 3000]

# Creating the PCA models:
# pca = PCA(n_components=2, svd_solver=svd_solver[best_params['svd_solver'])
if any(x in best_params for x in kernel_gamma):
    pca = KernelPCA(n_components=2, kernel=kernel[best_params['kernel']], gamma='{0}'.format(gamma[best_params['gamma']]))
    if any(x in best_params for x in kernel_degree):
        pca = KernelPCA(n_components=2, kernel=kernel[best_params['kernel']], gamma='{0}'.format(gamma[best_params['gamma']]), degree='{0}'.format(degree[best_params['degree']]), coef0='{0}'.format(coef0[best_params['coef0']]))                  
    if any(x in best_params for x in kernel_coef0):
        pca = KernelPCA(n_components=2, kernel=kernel[best_params['kernel']], gamma='{0}'.format(gamma[best_params['gamma']]), coef0='{0}'.format(coef0[best_params['coef0']]))                  
# pca = SparsePCA(n_components=2, alpha='{0}'.format(alpha[best_params['alpha']]), ridge_alpha='{0}'.format(ridge_alpha[best_params['ridge_alpha']]), method=method[best_params['method']], max_iter='{0}'.format(max_iter[best_params['max_iter']]))
# pca = IncrementalPCA(n_components=2)
print('Model: ', pca)
PrincipalComponents = pca.fit_transform(X_std)
principalDf = pd.DataFrame(data = PrincipalComponents, columns = ['principal component 1', 'principal component 2'])
finalDf = pd.concat([principalDf, dataframe[['Label']]], axis = 1)
print('Principal Component Analysis: ')
print(principalDf)

错误信息：

错误信息 (1)：

ValueError: There are significant negative eigenvalues (1.11715 of the maximum positive). Either the matrix is not PSD, or there was an issue while computing the eigendecomposition of the matrix.

错误信息 (2)：

ValueError: Precomputed metric requires shape (n_queries, n_indexed). Got (50, 14) for 50 indexed.
4

0 回答 0