the cyclist

Alden Scientific

Last seen: 7 giorni fa | Attivo dal 2011

Followers: 4 Following: 0

Messaggio

Head of Modeling and Statistics at Alden Scientific. Obsessive runner. Professional Interests: Predictive modeling, statistics. (I don't respond to email via author page, but will usually look at a question if you send me a link to it.)

Programming Languages:
Python, R, MATLAB, SQL
Spoken Languages:
English
Pronouns:
He/him

Statistica

All

RANK
15
of 297.613

REPUTAZIONE
15.554

CONTRIBUTI
49 Domande
5.308 Risposte

ACCETTAZIONE DELLE RISPOSTE
73.47%

VOTI RICEVUTI
2.939

Visualizza badge

Feeds

Risposto
Shapley based feature selection
The Shapley values don't require the class labels (i.e. the actual responses) to determine feature importance. The Shapley valu...

16 giorni fa | 1

| accettato

Risposto
Preserving More Decimal Places When Importing Excel Files with readtable in MATLAB
All decimal places are retained for me ... % Change the format format long % Read the file r = readtable("Lab.xlsx"); % H...

2 mesi fa | 0

Risposto
How to get MPE (Mean Percentage Error) with plsregress
The documentation doesn't seem to indicate any way to change the metric that is optimized. (This is unsurprising to me.) I can ...

2 mesi fa | 0

| accettato

Risposto
Why is bootci giving different interval than prctile?
Because your prctile calculation should be ci = prctile(bootstat, [(alpha/2)*100,(1-(alpha/2))*100]);

3 mesi fa | 1

Risposto
Tiling stacks of boxplots. Each stack contains 5 boxplots
Would subplot(2,5,1) ... subplot(2,5,10) do what you want? Also, I would highly recommend using tiledlayout over subplot. It ta...

4 mesi fa | 0

Risposto
how to apply PCA over 6000x82 data
Take a look at this answer of mine which is effectively a tutorial on the MATLAB pca function.

4 mesi fa | 1

| accettato

Risposto
Why is pagemtimes slower than just coding up the matrix multiplication?Especially on GPU.
It seems to me that the two functions are not calculating the same thing, based on the size of their respective outputs: rng ...

5 mesi fa | 1

Risposto
SVM Fitcsvm() thresholds vs ROC curve thresholds
fitcsvm() fits the best possible SVM to the data. That function itself does not make the predictions. The resulting model objec...

5 mesi fa | 0

Risposto
a function slows down my profiler: I would like to speed it up
It won't be a big speedup, but I would expect idx=find(Ntradess(id:-1:1,x)<=a1,1,'first'); to be consistently faster than idx...

5 mesi fa | 0

Risposto
Two lines of plot title with number and date time
Since R2020b, there is a subtitle function. Here is how I would have written your code, incorporating that and some other change...

5 mesi fa | 0

Risposto
Can't open additional instance of MATLAB in release 2024b?
R2024b Update 1 fixed this (presumed) bug.

5 mesi fa | 0

Domanda

Can't open additional instance of MATLAB in release 2024b?
I'm on a Mac (M1), running the latest OSX. I don't seem to be able to open an additional instance of MATLAB by right-clicking o...

5 mesi fa | 3 risposte | 0

3

risposte

Risposto
KS TEST fails at 0.05 but passes at 0.01
R = load('R.txt'); coeff = betafit(R); a_mle = coeff(1); b_mle = coeff(2); [~,x] = ecdf(R); pd_12 = betacdf(x,a_mle,b...

5 mesi fa | 0

| accettato

Risposto
How to create a symmetric 2D distribution from a novel distribution
I agree with @John D'Errico that we need more description. Do you just mean that you want to replicate f across another dimensio...

5 mesi fa | 0

Risposto
Box-Whisker Plot with 5 and 95 percentiles and non-symmetric distributions.
It's a bit kludgy, but here is a way to do it by directly editing the XData and YData of the whiskers and their caps. % Set see...

7 mesi fa | 0

Risposto
How to properly read a csv saved cell array.
@Walter Roberson's answer is the canonical one, to be sure. A csv simply cannot store the cell array as you hoped (and naively c...

7 mesi fa | 1

Risposto
Can MATLAB files that were created in the trial version be used in the full version?
No, there should be nothing different about any MATLAB files created in the trial version. All the happens when a license expire...

7 mesi fa | 1

| accettato

Risposto
How can I replace the upper off diagonal(super diagonal) and lower off diagonal(sub diagonal) of a matrix?
% Arbitrary size N=5; % Example input A = rand(N); % NxN random matrix disp(A) % Vector to set as the sub- or superdiag...

7 mesi fa | 1

Risposto
How to Filter Rows of Cell Array By Date Range
Here is one way: %Date Range MinDate = datetime('14-Jul-2024'); MaxDate = datetime('17-July-2024'); %Cell Array a = cell(...

8 mesi fa | 0

Risposto
Can't click "Roll The Dice!" problem in intro to matlab cody problems therefor cannot earn badge.
I can't say for sure, but I expect that that problem was deleted from Cody (perhaps by the author). Consider contacting support...

8 mesi fa | 0

Risposto
Adjusting Y-Values in Histograms
Your question is not perfectly clear to me. If you don't want the values binned, I think you more likely want to use the bar fun...

8 mesi fa | 0

Risposto
fitlme different to lmer in R
Disclaimer: I don't fully understand the specifics on why you are seeing what you are. Thinking about my comment about being st...

9 mesi fa | 1

Risposto
ylabel changes position with ax.YAxisLocation = 'origin'
It's a bit kludgy, but rng default hold on scatter(-rand(1,10),rand(1,10),120,'or','filled') scatter(rand(1,10),rand(1,10),1...

9 mesi fa | 1

Risposto
How to determine feature importance using gradient boosting?
The model that is output from fitrensemble has a predictorImportance method for global predictor importance. You can also use s...

9 mesi fa | 0

| accettato

Risposto
What happens if I use fitcecoc for a two-class classification, and how is it different from fitcsvm in such a scenario?
Disclaimer: I have not directly tested this idea. The defalt binary learner for fitcecoc is SVM. Therefore, I would expect the ...

9 mesi fa | 0

Risposto
Accessing Fit Coefficients from Curve Fitting
data_fit is a cfit object. You can apply post-processsing steps to this object, as described in this documentation. It sounds l...

9 mesi fa | 0

| accettato

Risposto
"Try the New Desktop" icon persists even after uninstalling the add-on (New Desktop for MATLAB (Beta))
That icon is not related to your use of the beta release from the FEX. The New Desktop is always an option now (presumably until...

9 mesi fa | 2

| accettato

Risposto
"Arrays have incompatible sizes for this operation" error
It's difficult to know for sure, but I'm guessing those are the variables as they exist in the workspace, outside the function. ...

10 mesi fa | 0

Risposto
I run the code below and expect to get a uniform histogram. It's not. I don't understand why not.
It's because of your choice of 100 bins is tuned to the periodicity of your function in a way that makes it the counts chaotic n...

10 mesi fa | 2

| accettato

Risposto
Why I am not getting the same result for an integral of a piecewise function?
You have two mistakes in this code. First, you got the signs wrong on the check. It should be check1 = aux1 - (aux2 + aux3) Se...

10 mesi fa | 1

Carica altro