Questions tagged [pca]

Principal component analysis, a technique for dimensionality reduction.

73 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
3
votes
0answers
344 views

How to use PCA in CNN for image recognition using Keras?

I created a CNN model for image classification and I want to use Principal Component Analysis (PCA) but when I run pca.fit() code, the code still running for hours ...
3
votes
0answers
137 views

PCA and FastICA in scikit-learn giving near identical results

So after importing my data, transforming it, and splitting into training and test sets I tried running this script for PCA: ...
3
votes
0answers
349 views

Examples for predict.FAMD?

I am doing a study on unsupervised data with various categorical variables. So I have found the FactoMineR package to be really handy for this, particularly with the FAMD functions. I can get to a ...
2
votes
1answer
48 views

Interpreting the new dimensions after PCA

I have telecom data with large number of dimentions. Now if I apply dimentionality reduction like PCA then from resulting dimention say PC1, PC2 I would loose the meaning or would not understand what ...
2
votes
0answers
51 views

How to compare Factor and Principal Component Analysis results?

I am currently working on an assignment where I am to perform a comparison of different Dimension Reduction techniques in Python. I am using the Scikit-learn functions to perform PCA and FA. However I ...
2
votes
0answers
136 views

t-SNE on extremely high-dimensional spaces

I successfully applied t-SNE to the number handwriting dataset. n=3823 data points (i.e. handwritten numbers) in an D=64 dimensional space (i.e. 8x8 pixels). Worked great. Now I would like to cluster ...
2
votes
0answers
33 views

I have data of some movies and their subtitles.I want to classify them based on their ratings

I will convert the subtitles into vectors and use them as features to classify the movies into different categories based on their ratings.The problem that I am facing is my feature vector is much ...
2
votes
0answers
66 views

PCA huge parts of missing data filling

I’m performing PCA on different time series’ and then using K Means clustering to try and group together common factors. The issue I’m facing is that some of the factors come in and out of the time ...
2
votes
0answers
682 views

Re-scale data after PCA for an LSTM?

I want to use the result of my PCA as an input for my LSTM model. I began by Applying the MinMaxScaler and then did the PCA, (then I reshaped my data of course) : ...
2
votes
0answers
402 views

How to evaluate the quality of representation for variables and individuals of a PCA in scikit-learn?

I just looked at the PCA in scikit-learn, but I didn't find a way to evaluate the quality of representation for variables and individuals like I usually do using the squared cosine. The squared ...
2
votes
3answers
75 views

What best/correct algorithm/procedure to cluster a dataset with a lot 0's?

I'm new to statistics so sorry any major lack of knowledge in the topic, just doing a project for graduation. I'm trying to cluster a Health dataset containing Diseases(3456) and Symptoms(25) ...
1
vote
1answer
10 views

How to interpret PCA rankings in Weka

I am struggling to understand what the rankings in Weka are representing. I.e. the coefficients for each attribute in the rank. What is the output in the Weka program for PCA telling me with these ...
1
vote
1answer
38 views

Clustering after PCA: Use the standardized data, or take into account the variation explained at each PC?

I am interested in clustering daily gridded data. Because of the many dimensions (gridpoints), I first perform PCA to reduce the dimensionality and keep the n-first PCs that account for at least 85% ...
1
vote
1answer
55 views

Differences and similarities between nonnegative PCA and nonnegative matrix factorization

I have seen references in the literature to nonnegative principal component analysis (nPCA) and nonnegative matrix factorization (NMF). I have tried reading the papers on both of them but it is not ...
1
vote
1answer
529 views

How can I adjust the legend when visualizing clusters in two dimensions?

How can I change the legend as we can see now the legend has some cluster numbers missing. How can I adjust the legend so that it can show all the cluster numbers (such as Cluster 1, Cluster 2 etc, no ...
1
vote
2answers
159 views

Which algorithm can be used to reduce dimension of multiple time series?

In my dataset, a data point is essentially a Time series of 6 feature over a year per month so in all, it results in 6*12=72 features. I need to find class outliers so I perform dimensionality ...
1
vote
1answer
222 views

Kernel PCA and K largest eigenvectors

How can one prove that the optimal kPCA solution $a^*=\{a_1...a_K\}$ are the $k$-largest Eigenvectors of the (centered) kernel matrix $K$? I referred to a lot of resources and couldn't find a proper ...
1
vote
1answer
72 views

Python sklearn PCA transform function output does not match

I am computing PCA on some data using 10 components and using 3 out of 10 as: ...
1
vote
0answers
16 views

Reducing the dimensions of data who's predominant categorical feature, its layer, has depths that overlaps with other samples layer values

I am working with a data set of soil types with multiple layers of varying depths and sizes with multiple features. There are $1-9$ layers each with differing dimensions, for example, a soil type ...
1
vote
0answers
59 views

Model for time series analysis

I'm new to data analysis and ML in general. I'm working with some friends on this problem: We're trying to predict when a component of a machine will stop working properly so the client can change it ...
1
vote
0answers
69 views

Best classification technique for following kind of data set

I have a large table where each record or row represents a single salesperson, and there are 50 columns or dimensions where each column represents one of 50 products potentially sold by any given ...
1
vote
0answers
26 views

PCA on conditional heteroscedastic timeseries

What is the correct method of application of PCA on time series data. Since the time series may exhibit conditional heteroscedasticity, application of normal PCA might be wrong as the variance changes ...
1
vote
0answers
23 views

I need help interpreting this PCA plot

I have a dataset of 116 observations and 10 numeric variables. The dataset contains information about healthy patients and patients attained with breast cancer. I did a PCA plot showing the cluster of ...
1
vote
1answer
344 views

Using PCA to cluster multidimensional data (RFM variables)

So i am performing k-means clustering on RFM variables (Recency, Frequency, Monetary). The RFM variables are in the form of quantiles (1-4). I used PCA and found the PCA components. I then used the ...
1
vote
0answers
58 views

How to read factor vs. factor plots?

How to read factor vs. factor plots? Particularly, what do negative values mean? Also, why is it possible for features to have negative effect on the factors?
1
vote
0answers
78 views

Scripting inverse PCA or MNF in Orange (biolab)

I have a data table with many rows and columns that I have successfully taken through K-means and PCA workflows in Orange. Now I'm trying to calculate the "minimum noise fraction" of the data. This is ...
1
vote
0answers
174 views

Should Principal components be normalized before applying K means on them?

I want to get the Principal components of a dataset and apply K mean clustering on them. Do I need to Normalized the PCA output before applying Kmeans on them ?
1
vote
1answer
108 views

Dataset of extremely low-dimensional images for PCA

I am looking for a public data-set of images that differ from each other only slightly, so that after applying PCA they can be reconstructed with a small error from ...
1
vote
0answers
45 views

PCA Reduction resulted in an elliptical form

I have a dataset with 19 features (columns). I normalized them using sklearn.preprocessing.normalize then I used PCA to reduce them to 2 components for plotting ...
1
vote
0answers
147 views

predict rank from physical measurements with various lengths

I have physical measurements with length 2*n, where the first vector represents a charge or a capacity (in Coulomb) $C$ and the second one is a voltage $V$. Let's call this measurement "forming". A ...
1
vote
0answers
493 views

EOF/PCA/MCA Analysis for a set of data

I have a set of climate data (temperature, pressure and moisture for example), $X$, $Y$, $Z$ which are matricies with dimensions $n \times p$ where $n$ is the number of observations and $p$ is the ...
0
votes
1answer
12 views

Feature relevance in PCA + kmeans algorythm

Working on the World Happiness Report dataset, i have N countries with M features and a happiness score. This is the parameter I built 3 classes from: happy, medium, unhappy (numerical intervals of ...
0
votes
1answer
12 views

Clustering based on missing values

I have a dataframe of the form: ...
0
votes
0answers
14 views

Same values for PCA Loadings results

I've recently performed a Principle component analysis for my masters thesis where I have 25 network datasets, formatted into graphs and applied 5 measurements to each graph. The measurements were ...
0
votes
0answers
9 views

Can we use both ridge-lasso and PCA in the same model for better results?

My question here is if we are using the PCA, the dimensionality is reduced and no question of feature selection is required using ridge & lasso. So should I use ride-lasso followed by PCA or I ...
0
votes
0answers
11 views

PCA and clustering, regression tree with categorical attributes using R

I am trying to analyze a dataset which has 7 categorical attributes out of 9. Can you please help me? I don't know how to find right instructions to do it. I only learnt how to do it with numeric-only ...
0
votes
0answers
7 views

Color overlapping in matplotlib, using PCA

I'm plotting 2d data from PCA, and I tried 2 libraries, matplotlib and seaborn, with seaborn I'm having nice overlapping colors, but in matplotlib it's just random, how would I achieve the color ...
0
votes
0answers
2 views

PCA targeted away from some subspace

Is there an existing technique allowing to do PCA maximizing not the variance per se, but the variance away from some direction? Imagine I have high-dim data with two different labels L1, L2 and I ...
0
votes
0answers
15 views

SGDClassifier and PCA

In here Mentioned: If you apply SGD to features extracted using PCA we found that it is often wise to scale the feature values by some constant c such that the average L2 norm of the training ...
0
votes
1answer
21 views

Why don't get the expected result using a SVM training model?

I want to learn a model for recognizing facial emotions. . I used a dataset with 213 samples. I extract firstly features using the Gabor filter. Then, I reduce the data dimensionality with the PCA and ...
0
votes
0answers
27 views

Training PCA on BERT word embedding: entire training dataset or each document?

I want to reduce the dimensionality of the BERT word embedding to, let's say, 50 dimensions. I am trying with PCA. I will use that for the document classification task. Now for training PCA, should ...
0
votes
0answers
9 views

Supervised dimensionality reduction for multilabel data

re there algorithms for supervised dimensionality reduction like Linear Discriminant Analysis (LDA) for multilabel classification? If I understood it right, the implementation of LDA in scikit-learn ...
0
votes
1answer
24 views

Standardizing features by one specific feature

I am working on a project with a dataset that looks something like the following: ...
0
votes
0answers
11 views

Dimension reduction using non-linear PCA

I am working on an undergraduate astronomy research in which we are analyzing geometrical complexities of different sattelite images of man-made and natural structures on Earth. The different images ...
0
votes
1answer
27 views

How can I normalize my output data for neural network?

I have a dataset consisting of 5 numerical variables, like the sample in the following image: In this dataset the first four variables are the input and the GDP is the output. I am trying to build a ...
0
votes
1answer
34 views

What is the best way to store images in python for machine learning

I am currently working on a classification problem that requires me to classify whether an image contains cancerous tissue cells or not. Each image is 50x50x3 pixels, the 3 is for RGB values. So far ...
0
votes
1answer
22 views

Potential speedup by applying PCA once on dataset with m rows vs. IncrementalPCA to x batches of size m/x?

I've been working on trying to perform dimensionality reduction on high-dimensional, high-volume datasets (with many rows and columns - around 100,000 - 1M rows and ~500 columns). While the size of ...
0
votes
0answers
62 views

(Incremental) PCA for all data

I'm using PCA to find prime components that are covering most of the variance in my dataset. What I usually do is I run a PCA for all components, then see how many components cover most of the ...
0
votes
0answers
24 views

Analogy between Autoencoder and PCA

I know that Autoencoders can be regarded as non-linear generalisations of PCA, but I struggle to understand in depth the analogy between the two. Once PCA has been performed on a function $F(\vec{\...
0
votes
1answer
72 views

comparison of t-SNE and PCA and truncate SVD

How to compare the trucate SVD ,PCA, and T-SNE? What we can say about features if t-SNE and PCA and truncate SVD digaram is in this figure?