pca

问题 Suppose I have two matrices of PCA loadings loa.orig , and loa.rot , and I know that loa.rot is a rotation (by-hand or otherwise) of loa.orig . ( loa.orig might also have been already orthogonally rotated by varimax or something, but I don't think that matters). I know want to know the angles by which loa.orig has been rotated to arrive at loa.rot . I understand from this comment on another question that "rotations don't commute", and therefore, the order of pair-wise (plane-wise) rotations

问题 I am having issues with princomp , specifically biplot , when I want to use a covariance or correlation matrix not generated by princomp itself. For simplicity I will use a much smaller dataset than the one I am dealing with. cr <- cov.wt(USArrests) biplot(princomp(data = USArrests, covmat = cr)) gives me the error Error in biplot.princomp(princomp(data = USArrests, covmat = cr)) : object 'princomp(data = USArrests, covmat = cr)' has no scores Seems like something simple going on here, but

问题 I am trying to perform the python implementation of PCA using sklearn. I have created the following function: def dimensionality_reduction(train_dataset_mod1, train_dataset_mod2, test_dataset_mod1, test_dataset_mod2): pca = PCA(n_components= 200) pca.fit(train_dataset_mod1.transpose()) mod1_features_train = pca.components_ pca2 = PCA(n_components=200) pca2.fit(train_dataset_mod2.transpose()) mod2_features_train = pca2.components_ mod1_features_test = pca.transform(test_dataset_mod1) mod2

问题 I am trying to use the 2000 topics' top 20 frequency data at https://github.com/wwbp/facebook_topics/tree/master/csv I would like to perform randomizedPCA on the data. From the documentation, X needs to be array-like, shape (n_samples, n_features) . I have imported the file with LDA_topics = pd.read_csv(r'2000topics.top20freqs.keys.csv', header=None, index_col=0, error_bad_lines=False) however this is not the right format for the following line: pca2 = sklearn.decomposition.RandomizedPCA(n

问题 I am trying to do a dimension reduction using PCA from scikit-learn. My data set has around 300 samples and 4096 features. I want to reduce the dimensions to 400 and 40. But when I call the algorithm the resulting data does have at most "number of samples" features. from sklearn.decomposition import PCA pca = PCA(n_components = 400) trainData = pca.fit_transform(trainData) testData = pca.transform(testData) Where initial shape of trainData is 300x4096 and the resulting data shape is 300x300.

问题 I want to build a 3D PCA bi-plot using plotly package because the graph is nice and interactive in html format (something that I need). My difficulty is to add the loading. I want the loading to be presented as straight lines from the point (0,0,0) (i.e. the equivalent to 2D biplots) So all in all I don't know how to add straight lines starting from the centre of the 3D graph. I have calculated the scores and loading using the PCA function; pca1 <- PCA (dat1, graph = F) for scores: ind1 <-

问题 I'm working on a face recognition project in which we are using PCA to reduce feature vector size of an image. The trouble is, during training, I create the PCA object by incorporating all the training images. Now, during testing, I need the PCA object obtained earlier. I cannot seem to figure out how to write the PCA object to a file, so that I can use it during testing. One alternative is that I write it's eigenvectors to the file. But it would be so much more convenient to write the object

问题 From the documentation of sklearn RandomizedPCA, sparse matrices are accepted as input. However when I called it with a sparse matrix, I got a TypeError : > sklearn.__version__ '0.16.1' > pca = RandomizedPCA(n_components=2) > pca.fit(my_sparce_mat) TypeError: A sparse matrix was passed, but dense data is required. Use X.toarray() to convert to a dense numpy array. I obtained the same error using fit_transform . Any suggestion on how to have it work? 回答1: The answer is that it is not possible

问题 In a related question, I have asked why there are differences between stats::varimax and GPArotation::Varimax , both of which psych::principal calls, depending on the option set for rotate = . The differences between these two (see other question) account for some, but not all of the differences from psych::principal . It appears that these differences somehow get exacerbated by psych::principal . (I have a simple theory why, and I'd like to get that confirmed). library(GPArotation) library

问题 I am trying to standardize some data to be able to apply PCA to it. I am using sklearn.preprocessing.StandardScaler. I am having trouble to understand the difference between using "True" or "False" in the parameters "with_mean" and "with_std". Here is the description of the command: https://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.StandardScaler.html Can someone give a more extended explanation? Thank you very much! 回答1: I have provided more details in this post https:/