I have defined a generalised linear model as follows:
glm(formula = ParticleCount ~ ParticlePresent + AlgaePresent +
ParticleTypeSize + ParticlePresent:ParticleTypeSize + AlgaePresent:ParticleTypeSize,
family = poisson(link = "log"), data = PCB)
and I have the below significant interactions
Df Deviance AIC LRT Pr(>Chi)
<none> 666.94 1013.8
ParticlePresent:ParticleTypeSize 6 680.59 1015.4 13.649 0.033818 *
AlgaePresent:ParticleTypeSize 6 687.26 1022.1 20.320 0.002428 **
I am trying to proceed with a posthoc test (Tukey) to compare the interaction of ParticleTypeSize using the lsmeans package. However, I get the following message as soon as I proceed:
library(lsmeans)
leastsquare=lsmeans(glm.particle3,~ParticleTypeSize,adjust ="tukey")
Error in `contrasts<-`(`*tmp*`, value = contrasts.arg[[nn]]) :
contrasts apply only to factors
I've checked whether ParticleTypeSize is a valid factor by applying:
l<-sapply(PCB,function(x)is.factor(x))
l
Sample AlgaePresent ParticlePresent ParticleTypeSize
TRUE FALSE FALSE TRUE
ParticleCount
FALSE
I'm stumped and unsure as to how I can rectify this error message. Any help would be much appreciated!
That error happens when the variable you specify is not a factor. You tested and found that it is, so that's a mystery and all I can guess is that the data changed since you fit the model. So try re-fitting the model with the present dataset.
All that said, I question what you are trying to do. First, you have ParticleTypeSize interacting with two other predictors, which means it is probably not advisable to look at marginal means (lsmeans) for that factor. The fact that there are interactions means that the pattern of those means changes depending on the values of the other variables.
Second, are AlgaePresent and ParticlePresent really numeric variables? By their names, they seem like they ought to be factors. If they are really indicators (0 and 1), that's OK, but it is still cleaner to code them as factors if you are using functions like lsmeans where factors and covariates are treated in distinctly different ways.
BTW, the lsmeans package is being deprecated, and new developments are occurring in its successor, the emmeans package.
Related
I'm a stats newb and was told by my professor to run a MANOVA for something I was checking out. Basically, I wanted to see if there was an interaction between ethnicity and a certain quadrant grouping for a set of outcome variables that are subscales of an overall measure (ders_tot).
An ANCOVA (one DV) already found an interaction between ethnicity and the quadrant grouping for ders_tot.
My MANOVA output is showing me that with Pillai's/Wilks there is no significance (p = .098 for both), but in SPSS there is also a table of between-subjects effects automatically generated that indicates strong interaction significance for one particular outcome variable (p = .003). The other DVs are far from significance (some as high as p = .27 or p = .66).
Is my MANOVA significance (or lack thereof) being seriously skewed by the highly nonsignificant variables? Am I still "allowed" to run analysis on that one particular variable included in the MANOVA that suggests strong significance? I also have data viz/chart output that makes a strong case for analyzing that particular variable.
(EDIT: BELOW PROBLEM HAS BEEN FIXED)
[Also, I've noticed that one of my covariates is always being run in SPSS with 1 df when it should be 2. I've triple checked the variable type and added labels and all that, and can't get it to run appropriately. When I run the same analysis in R, df = 2. This isn't affecting my sig. findings by much, but it's driving me crazy!]
I have a ML.net project and as of right now everything has gone great. I have a motor that collects a power reading 256 times around each rotation and I push that into a model. Right now it determines the state of the motor nearly perfectly. The motor itself only has room for 38 values on it at a time so I have been spending several rotations to collect the full 256 samples for my training data.
I would like to cut the sample size down to 38 so every rotation I can determine its state. If I just evenly space the samples down to 38 my model degrades by a lot. I know I am not feeding the model the features it thinks are most important but just making a guess and randomly selecting data for the model.
Is there a way I can see the importance of each value in the array during the training process? I was thinking I could use IDataView for this and I found the below statement about it (link).
Standard ML schema: The IDataView system does not define, nor prescribe, standard ML schema representation. For example, it does not dictate representation of nor distinction between different semantic interpretations of columns, such as label, feature, score, weight, etc. However, the column metadata support, together with conventions, may be used to represent such interpretations.
Does this mean I can print out such things as weight for each column and how would I do that?
I have actually only been working with ML.net for a couple weeks now so I apologize if the question is naive, I assure you I have googled this as many ways as I can think to. Any advice would be appreciated. Thanks in advance.
EDIT:
Thank you for the answer I was going down a completely useless path. I have been trying to get it to work following the example you linked to. I have 260 columns with numbers and one column with the conditions as one of five text strings. This is the condition I am trying to predict.
The first time I tried it threw an error "expecting single but got string". No problem I used .Append(mlContext.Transforms.Conversion.MapValueToKey("Label", "Label")) to convert to key values and it threw the error expected Single, got Key UInt32. any ideas on how to push that into this function?
At any rate thank you for the reply but I guess my upvotes don't count yet sorry. hopefully I can upvote it later or someone else here can upvote it. Below is the code example.
//Create MLContext
MLContext mlContext = new MLContext();
//Load Data
IDataView data = mlContext.Data.LoadFromTextFile<ModelInput>(TRAIN_DATA_FILEPATH, separatorChar: ',', hasHeader: true);
// 1. Get the column name of input features.
string[] featureColumnNames =
data.Schema
.Select(column => column.Name)
.Where(columnName => columnName != "Label").ToArray();
// 2. Define estimator with data pre-processing steps
IEstimator<ITransformer> dataPrepEstimator =
mlContext.Transforms.Concatenate("Features", featureColumnNames)
.Append(mlContext.Transforms.NormalizeMinMax("Features"))
.Append(mlContext.Transforms.Conversion.MapValueToKey("Label", "Label"));
// 3. Create transformer using the data pre-processing estimator
ITransformer dataPrepTransformer = dataPrepEstimator.Fit(data);//error here
// 4. Pre-process the training data
IDataView preprocessedTrainData = dataPrepTransformer.Transform(data);
// 5. Define Stochastic Dual Coordinate Ascent machine learning estimator
var sdcaEstimator = mlContext.Regression.Trainers.Sdca();
// 6. Train machine learning model
var sdcaModel = sdcaEstimator.Fit(preprocessedTrainData);
ImmutableArray<RegressionMetricsStatistics> permutationFeatureImportance =
mlContext
.Regression
.PermutationFeatureImportance(sdcaModel, preprocessedTrainData, permutationCount: 3);
// Order features by importance
var featureImportanceMetrics =
permutationFeatureImportance
.Select((metric, index) => new { index, metric.RSquared })
.OrderByDescending(myFeatures => Math.Abs(myFeatures.RSquared.Mean));
Console.WriteLine("Feature\tPFI");
foreach (var feature in featureImportanceMetrics)
{
Console.WriteLine($"{featureColumnNames[feature.index],-20}|\t{feature.RSquared.Mean:F6}");
}
I believe what you are looking for is called Permutation Feature Importance. This will tell you which features are most important by changing each feature in isolation, and then measuring how much that change affected the model's performance metrics. You can use this to see which features are the most important to the model.
Interpret model predictions using Permutation Feature Importance is the doc that describes how to use this API in ML.NET.
You can also use an open-source set of packages, they are much more sophisticated than what is found in ML.NET. I have an example on my GitHub how-to use R with advanced explainer packages to explain ML.NET models. You can get local instance as well as global model breakdown/details/diagnostics/feature interactions etc.
https://github.com/bartczernicki/BaseballHOFPredictionWithMlrAndDALEX
I have some features that are zero-centered values and supposed to represent change between a current value and previous value. Generally speaking i believe there should be some symmetry between these values. Ie. there should be roughly the same amount of positive values as negative values and roughly these values should operate on the same scale.
When i try to scale my samples using MaxAbsScaler, i notice that my negative values for this feature get almost completely drowned out by the positive values. And i don't really have any reason to believe my positive values should be that much larger than my negative values.
So what i've noticed is that fundamentally, the magnitude of percentage change values are not symmetrical in scale. For example if i have a value that goes from 50 to 200, that would result in a 300.0% change. If i have a value that goes from 200 to 50 that would result in a -75.0% change. I get there is a reason for this, but in terms of my feature, i don't see a reason why a change of 50 to 100 should be 3x+ more "important" than the same change in value but the opposite direction.
Given this information, i do not believe there would be any reason to want my model to treat a change of 200-50 as a "lesser" change than a change of 50-200. Since i am trying to represent the change of a value over time, i want to abstract this pattern so that my model can "visualize" the change of a value over time that same way a person would.
Right now i am solving this by using this formula
if curr > prev:
return curr / prev - 1
else:
return (prev / curr - 1) * -1
And this does seem to treat changes in value, similarly regardless of the direction. Ie from the example of above 50>200 = 300, 200>50 = -300. Is there a reason why i shouldn't be doing this? Does this accomplish my goal? Has anyone ran into similar dilemmas?
This is a discussion question and it's difficult to know the right answer to it without knowing the physical relevance of your feature. You are calculating a percentage change, and a percent change is dependent on the original value. I am not a big fan of a custom formula only to make percent change symmetric since it adds a layer of complexity when it is unnecessary in my opinion.
If you want change to be symmetric, you can try direct difference or factor change. There's nothing to suggest that difference or factor change are less correct than percent change. So, depending on the physical relevance of your feature, each of the following symmetric measures would be correct ways to measure change -
Difference change -> 50 to 200 yields 150, 200 to 50 yields -150
Factor change with logarithm -> 50 to 200 yields log(4), 200 to 50 yields log(1/4) = -log(4)
You're having trouble because you haven't brought the abstract questions into your paradigm.
"... my model can "visualize" ... same way a person would."
In this paradigm, you need a metric for "same way". There is no such empirical standard. You've dropped both of the simple standards -- relative error and absolute error -- and you posit some inherently "normal" standard that doesn't exist.
Yes, we run into these dilemmas: choosing a success metric. You've chosen a classic example from "How To Lie With Statistics"; depending on the choice of starting and finishing proportions and the error metric, you can "prove" all sorts of things.
This brings us to your central question:
Does this accomplish my goal?
We don't know. First of all, you haven't given us your actual goal. Rather, you've given us an indefinite description and a single example of two data points. Second, you're asking the wrong entity. Make your changes, run the model on your data set, and examine the properties of the resulting predictions. Do those properties satisfy your desired end result?
For instance, given your posted data points, (200, 50) and (50, 200), how would other examples fit in, such as (1, 4), (1000, 10), etc.? If you're simply training on the proportion of change over the full range of values involved in that transaction, your proposal is just what you need: use the higher value as the basis. Since you didn't post any representative data, we have no idea what sort of distribution you have.
I start with a simple Maxima question, the answer to which may provide the answer to the actual problem I'm grappling with.
Related Simple Question:
How can I get maxima to calculate:
bfloat((1+%i)^0.3);
Might there be an option variable that can be set so that this evaluates to a complex number?
Actual Question:
In evaluating approximations for numerical time integration for finite element methods, for this purpose I'm using spectral analysis, which requires the calculation of the eigenvalues of a 4 x 4 matrix. This matrix "cav" is also calculated within maxima, using some of the algebra capabilities of maxima, but sustituting numerical values, so that matrix is entirely numerical, i.e. containing no variables. I've calculated the eigenvalues with Mathematica and it returns 4 real eigenvalues. However Maxima calculates horrenduously complicated expressions for this case, which apparently it does not "know" how to simplify, even numerically as "bigfloat". Perhaps this problem arises because Maxima first approximates the matrix "cac" by rational numbers (i.e. fractions) and then tries to solve the problem fully exactly, instead of simply using numerical "bigfloat" computations throughout. Is there I way I can change this?
Note that if you only change the input value of gzv to say 0.5 it works fine, and returns numerical values of complex eigenvalues.
I include the code below. Note that all of the code up until "cav:subst(vs,ca)$" is just for the definition of the matrix cav and seems to work fine. It is in the few statements thereafter that it fails to calculate numerical values for the eigenvalues.
v1:v0+ (1-gg)*a0+gg*a1$
d1:d0+v0+(1/2-gb)*a0+gb*a1$
obf:a1+(1+ga)*(w^2*d1 + 2*gz*w*(d1-d0)) -
ga *(w^2*d0 + 2*gz*w*(d0-g0))$
obf:expand(obf)$
cd:subst([a1=1,d0=0,v0=0,a0=0,g0=0],obf)$
fd:subst([a1=0,d0=1,v0=0,a0=0,g0=0],obf)$
fv:subst([a1=0,d0=0,v0=1,a0=0,g0=0],obf)$
fa:subst([a1=0,d0=0,v0=0,a0=1,g0=0],obf)$
fg:subst([a1=0,d0=0,v0=0,a0=0,g0=1],obf)$
f:[fd,fv,fa,fg]$
cad1:expand(cd*[1,1,1/2-gb,0] - gb*f)$
cad2:expand(cd*[0,1,1-gg,0] - gg*f)$
cad3:expand(-f)$
cad4:[cd,0,0,0]$
cad:matrix(cad1,cad2,cad3,cad4)$
gav:-0.05$
ggv:1/2-gav$
gbv:(ggv+1/2)^2/4$
gzv:1.1$
dt:0.01$
wv:bfloat(dt*2*%pi)$
vs:[ga=gav,gg=ggv,gb=gbv,gz=gzv,w=wv]$
cav:subst(vs,ca)$
cav:bfloat(cav)$
evam:eigenvalues(cav)$
evam:bfloat(evam)$
eva:evam[1]$
The main problem here is that Maxima tries pretty hard to make computations exact, and it's hard to tell it to ease up and allow inexact results.
Is there a mistake in the code you posted above? You have cav:subst(vs,ca) but ca is not defined. Is that supposed to be cav:subst(vs,cad) ?
For the short problem, usually rectform can simplify complex expressions to something more usable:
(%i58) rectform (bfloat((1+%i)^0.3));
`rat' replaced 1.0B0 by 1/1 = 1.0B0
(%o58) 2.59023849130283b-1 %i + 1.078911979230303b0
About the long problem, if fixed-precision (i.e. ordinary floats, not bigfloats) is acceptable to you, then you can use the LAPACK function dgeev to compute eigenvalues and/or eigenvectors.
(%i51) load (lapack);
<bunch of messages here>
(%o51) /usr/share/maxima/5.39.0/share/lapack/lapack.mac
(%i52) dgeev (cav);
(%o52) [[- 0.02759949957202372, 0.06804641655485913, 0.997993508502892, 0.928429191717788], false, false]
If you really need variable precision, I don't know what to try. In principle it's possible to rework the LAPACK code to work with variable-precision floats, but that's a substantial task and I'm not sure about the details.
everyone. I'm pretty new to R. I've been trying to educate myself about this issue, but I've continued to run into road blocks.
I have a data set with two categorical, independent variables (habitat (1,2,3) and site (1,2,3,4,5). My response variables are the presence or absence of AFLP loci. I have 96 loci, and I want to determine which, if any, of these loci are significantly associated with habitat (site is a random effect). Each of the loci can be assumed to be independent from the others.
As far as relevancy to other researchers, this should be a problem that people trying to analyze molecular data with GLM or LME will begin to run into more.
Here is my code:
##Independent variables
Site=AFLP$Site ##AFLP is my data file
Habitat=AFLP$Habitat
##Dependent variable
Loci=AFLP[,4:99]
##Establishing matrix of variables
mydata <- cbind(Site, Habitat, Loci)
##glm
model1 <- glm(Loci ~ (1|Site)+Habitat, data=mydata, family="binomial")
I get this error:
Error in model.frame.default(formula = Loci ~ (1 | Site) + Habitat, data = mydata, :
invalid type (list) for variable 'Loci'
I know this error is associated with the data type of Loci; however, I've tried a bunch of things and still can't figure out how to correctly address the issue.
My problem seems to be similar to the ones in the below links, but again, I haven't been able to figure out how to apply this information to my data set.
http://stackoverflow.com/questions/18067519/using-r-to-do-a-regression-with-multiple-dependent-and-multiple-independent-vari
https://stats.stackexchange.com/questions/26585/how-to-do-a-generalized-linear-model-with-multiple-dependent-variables-in-r
Thank you in advance. If this turns out to have a simple answer, I apologize for taking up space. I have been Googling and trying to educate myself, and I haven't made any head-way.