Python sklearn.decomposition 模块，PCA 实例源码

我们从Python开源项目中，提取了以下50个代码示例，用于说明如何使用sklearn.decomposition.PCA。

项目：blender-scripting 作者：njanakiev | 项目源码 | 文件源码

def PCA(data, num_components=None):
    # mean center the data
    data -= data.mean(axis=0)
    # calculate the covariance matrix
    R = np.cov(data, rowvar=False)
    # calculate eigenvectors & eigenvalues of the covariance matrix
    # use 'eigh' rather than 'eig' since R is symmetric,
    # the performance gain is substantial
    V, E = np.linalg.eigh(R)
    # sort eigenvalue in decreasing order
    idx = np.argsort(V)[::-1]
    E = E[:,idx]
    # sort eigenvectors according to same index
    V = V[idx]
    # select the first n eigenvectors (n is desired dimension
    # of rescaled data array, or dims_rescaled_data)
    E = E[:, :num_components]
    # carry out the transformation on the data using eigenvectors
    # and return the re-scaled data, eigenvalues, and eigenvectors
    return np.dot(E.T, data.T).T, V, E

项目：sakmapper 作者：szairis | 项目源码 | 文件源码

def apply_lens(df, lens='pca', dist='euclidean', n_dim=2, **kwargs):
    """
    input: N x F dataframe of observations
    output: N x n_dim image of input data under lens function
    """
    if n_dim != 2:
        raise 'error: image of data set must be two-dimensional'
    if dist not in ['euclidean', 'correlation']:
        raise 'error: only euclidean and correlation distance metrics are supported'
    if lens == 'pca' and dist != 'euclidean':
        raise 'error: PCA requires the use of euclidean distance metric'

    if lens == 'pca':
        df_lens = pd.DataFrame(decomposition.PCA(n_components=n_dim, **kwargs).fit_transform(df), df.index)
    elif lens == 'mds':
        D = metrics.pairwise.pairwise_distances(df, metric=dist)
        df_lens = pd.DataFrame(manifold.MDS(n_components=n_dim, **kwargs).fit_transform(D), df.index)
    elif lens == 'neighbor':
        D = metrics.pairwise.pairwise_distances(df, metric=dist)
        df_lens = pd.DataFrame(manifold.SpectralEmbedding(n_components=n_dim, **kwargs).fit_transform(D), df.index)
    else:
        raise 'error: only PCA, MDS, neighborhood lenses are supported'

    return df_lens

项目：AutoFolio 作者：mlindauer | 项目源码 | 文件源码

def fit(self, scenario: ASlibScenario, config: Configuration):
        '''
            fit pca object to ASlib scenario data

            Arguments
            ---------
            scenario: data.aslib_scenario.ASlibScenario
                ASlib Scenario with all data in pandas
            config: ConfigSpace.Configuration
                configuration
        '''

        if config.get("pca"):
            self.pca = PCA(n_components=config.get("pca_n_components"))
            self.pca.fit(scenario.feature_data.values)
            self.active = True

项目：AutoFolio 作者：mlindauer | 项目源码 | 文件源码

def transform(self, scenario: ASlibScenario):
        '''
            transform ASLib scenario data

            Arguments
            ---------
            scenario: data.aslib_scenario.ASlibScenario
                ASlib Scenario with all data in pandas

            Returns
            -------
            data.aslib_scenario.ASlibScenario
        '''
        if self.pca:
            self.logger.debug("Applying PCA")
            values = self.pca.transform(
                np.array(scenario.feature_data.values))

            scenario.feature_data = pd.DataFrame(
                data=values, index=scenario.feature_data.index, columns=["f%d" % (i) for i in range(values.shape[1])])

        return scenario

项目：keras-molecules 作者：maxhodak | 项目源码 | 文件源码

def get_arguments():
    parser = argparse.ArgumentParser(description='Molecular autoencoder network')
    parser.add_argument('data', type=str, help='HDF5 file to read input data from.')
    parser.add_argument('model', type=str, help='Trained Keras model to use.')
    parser.add_argument('--save_h5', type=str, help='Name of a file to write HDF5 output to.')
    parser.add_argument('--latent_dim', type=int, metavar='N', default=LATENT_DIM,
                        help='Dimensionality of the latent representation.')
    parser.add_argument('--tsne_lr', metavar='LR', type=float, default=TSNE_LEARNING_RATE,
                        help='Learning to use for t-SNE.')
    parser.add_argument('--tsne_components', metavar='N', type=int, default=TSNE_COMPONENTS,
                        help='Number of components to use for t-SNE.')
    parser.add_argument('--tsne_perplexity', metavar='P', type=float, default=TSNE_PERPLEXITY)
    parser.add_argument('--tsne_iterations', metavar='N', type=int, default=TSNE_ITERATIONS)
    parser.add_argument('--visualize', dest='visualize', action='store_true',
                        help='Fit manifold and render a visualization. If this flag is not used, the sampled data' +
                        ' will simply be returned with no further processing.')
    parser.add_argument('--skip-pca', dest='use_pca', action='store_false',
                        help='Skip PCA preprocessing of data to feed into t-SNE.')
    parser.add_argument('--pca_components', metavar='N', type=int, default=PCA_COMPONENTS,
                        help='Number of components to use for PCA.')
    parser.set_defaults(use_pca = True)
    parser.set_defaults(visualize = False)

    return parser.parse_args()

项目：MultimodalAutoencoder 作者：natashamjaques | 项目源码 | 文件源码

def transform_PCA(X_train,X_all,n_components=100):
    """Given some training data, performs a Principle Components Analysis (PCA)
    and modifies the rest of the data based on the learned PCA.

    Args:
        X_train: A matrix containing training data
        X_all: A matrix containing all the data
        n_components: The number of components to use in the PCA

    Returns:
        The transformed data and the PCA object
    """
    pca = PCA(n_components=n_components)
    pca.fit(X_train)
    print("Total explained variance:", sum(pca.explained_variance_ratio_))

    return pca.transform(X_all),pca