I have a list of 282 items that has been classified by 6 independent coders into 20 categories.
The 20 categories are defined by words (example "perceptual", "evaluation" etc).
The 6 coders have different status: 3 of them are experts, 3 are novices.
I calculated all the kappas (and alphas) between each pair of coders, and the overall kappas among the 6 coders, and the kappas between the 3 experts and between the 3 novices.
Now I would like to check whether there is a significant difference between the interrater agreements achieved by the experts vs those achieved by the novices (whose kappa is indeed lower).
How would you approach this question and report the results?
thanks!
You can at least simply obtain the Cohen's Kappa and its sd in R (<- by far the best option in my opinion).
The PresenceAbsence package has a Kappa (see ?Kappa) function.
You can get the package with the regular install.packages("PresenceAbsence"), then pass a confusion matrix, i.e.:
# we load the package
library(PresenceAbsence)
# a dummy confusion matrix
cm <- matrix(round(runif(16, 0, 10)), nrow=4)
Kappa(cm)
you will obtain the Kappa and its sd. As far as I know there are limitations about testing using the Kappa metric (eg see https://en.wikipedia.org/wiki/Cohen's_kappa#Significance_and_magnitude).
hope this helps
Related
Could someone help me to determine the correct random variable structure in my binomial GLMM in lme4?
I will first try to explain my data as best as I can. I have binomial data of seedlings that were eaten (1) or not eaten (0), together with data of vegetation cover. I try to figure out if there is a relationship between vegetation cover and the probability of a tree being eaten, as the other vegetation is a food source that could attract herbivores to a certain forest patch.
The data is collected in ~90 plots scattered over a National Park for 9 years now. Some were measured all years, some were measured only a few years (destroyed/newly added plots). The original datasets is split in 2 (deciduous vs coniferous), both containing ~55.000 entries. Per plot about 100 saplings were measured every time, so the two separate datasets probably contain about 50 trees per plot (though this will not always be the case, since the decid:conif ratio is not always equal). Each plot consists of 4 subplots.
I am aware that there might be spatial autocorrelation due to plot placement, but we will not correct for this, yet.
Every year the vegetation is surveyed in the same period. Vegetation cover is estimated at plot-level, individual trees (binary) are measured at a subplot-level.
All trees are measured, so the amount of responses per subplot will differ between subplots and years, as the forest naturally regenerates.
Unfortunately, I cannot share my original data, but I tried to create an example that captures the essentials:
#set seed for whole procedure
addTaskCallback(function(...) {set.seed(453);TRUE})
# Generate vector containing individual vegetation covers (in %)
cover1vec <- c(sample(0:100,10, replace = TRUE)) #the ',number' is amount of covers generated
# Create dataset
DT <- data.frame(
eaten = sample(c(0,1), 80, replace = TRUE),
plot = as.factor(rep(c(1:5), each = 16)),
subplot = as.factor(rep(c(1:4), each = 2)),
year = as.factor(rep(c(2012,2013), each = 8)),
cover1 = rep(cover1vec, each = 8)
)
Which will generate this dataset:
>DT
eaten plot subplot year cover1
1 0 1 1 2012 4
2 0 1 1 2012 4
3 1 1 2 2012 4
4 1 1 2 2012 4
5 0 1 3 2012 4
6 1 1 3 2012 4
7 0 1 4 2012 4
8 1 1 4 2012 4
9 1 1 1 2013 77
10 0 1 1 2013 77
11 0 1 2 2013 77
12 1 1 2 2013 77
13 1 1 3 2013 77
14 0 1 3 2013 77
15 1 1 4 2013 77
16 0 1 4 2013 77
17 0 2 1 2012 46
18 0 2 1 2012 46
19 0 2 2 2012 46
20 1 2 2 2012 46
....etc....
80 0 5 4 2013 82
Note1: to clarify again, in this example the number of responses is the same for every subplot:year combination, making the data balanced, which is not the case in the original dataset.
Note2: this example can not be run in a GLMM, as I get a singularity warning and all my random effect measurements are zero. Apparently my example is not appropriate to actually use (because using sample() caused the 0 and 1 to be in too even amounts to have large enough effects?).
As you can see from the example, cover data is the same for every plot:year combination.
Plots are measured multiple years (only 2012 and 2013 in the example), so there are repeated measures.
Additionally, a year effect is likely, given the fact that we have e.g. drier/wetter years.
First I thought about the following model structure:
library(lme4)
mod1 <- glmer(eaten ~ cover1 + (1 | year) + (1 | plot), data = DT, family = binomial)
summary(mod1)
Where (1 | year) should correct for differences between years and (1 | plot) should correct for the repeated measures.
But then I started thinking: all trees measured in plot 1, during year 2012 will be more similar to each other than when they are compared with (partially the same) trees from plot 1, during year 2013.
So, I doubt that this random model structure will correct for this within plot temporal effect.
So my best guess is to add another random variable, where this "interaction" is accounted for.
I know of two ways to possibly achieve this:
Method 1.
Adding the random variable " + (1 | year:plot)"
Method 2.
Adding the random variable " + (1 | year/plot)"
From what other people told me, I still do not know the difference between the two.
I saw that Method 2 added an extra random variable (year.1) compared to Method 1, but I do not know how to interpret that extra random variable.
As an example, I added the Random effects summary using Method 2 (zeros due to singularity issues with my example data):
Random effects:
Groups Name Variance Std.Dev.
plot.year (Intercept) 0 0
plot (Intercept) 0 0
year (Intercept) 0 0
year.1 (Intercept) 0 0
Number of obs: 80, groups: plot:year, 10; plot, 5; year, 2
Can someone explain me the actual difference between Method 1 and Method 2?
I am trying to understand what is happening, but cannot grasp it.
I already tried to get advice from a colleague and he mentioned that it is likely more appropriate to use cbind(success, failure) per plot:year combination.
Via this site I found that cbind is used in binomial models when Ntrails > 1, which I think is indeed the case given our sampling procedure.
I wonder, if cbind is already used on a plot:year combination, whether I need to add a plot:year random variable?
When using cbind, the example data would look like this:
>DT3
plot year cover1 Eaten_suc Eaten_fail
8 1 2012 4 4 4
16 1 2013 77 4 4
24 2 2012 46 2 6
32 2 2013 26 6 2
40 3 2012 91 2 6
48 3 2013 40 3 5
56 4 2012 61 5 3
64 4 2013 19 2 6
72 5 2012 19 5 3
80 5 2013 82 2 6
What would be the correct random model structure and why?
I was thinking about:
Possibility A
mod4 <- glmer(cbind(Eaten_suc, Eaten_fail) ~ cover1 + (1 | year) + (1 | plot),
data = DT3, family = binomial)
Possibility B
mod5 <- glmer(cbind(Eaten_suc, Eaten_fail) ~ cover1 + (1 | year) + (1 | plot) + (1 | year:plot),
data = DT3, family = binomial)
But doesn't cbind(success, failure) already correct for the year:plot dependence?
Possibility C
mod6 <- glmer(cbind(Eaten_suc, Eaten_fail) ~ cover1 + (1 | year) + (1 | plot) + (1 | year/plot),
data = DT3, family = binomial)
As I do not yet understand the difference between year:plot and year/plot
Thus: Is it indeed more appropriate to use the cbind-method than the raw binary data? And what random model structure would be necessary to prevent pseudoreplication and other dependencies?
Thank you in advance for your time and input!
EDIT 7/12/20: I added some extra information about the original data
You are asking quite a few questions in your question. I'll try to cover them all, but I do suggest reading the documentation and vignette from lme4 and the glmmFAQ page for more information. Also I'd highly recommend searching for these topics on google scholar, as they are fairly well covered.
I'll start somewhere simple
Note 2 (why is my model singular?)
Your model is highly singular, because the way you are simulating your data does not indicate any dependency between the data itself. If you wanted to simulate a binomial model you would use g(eta) = X %*% beta to simulate your linear predictor and thus the probability for success. One can then use this probability for simulating the your binary outcome. This would thus be a 2 step process, first using some known X or randomly simulated X given some prior distribution of our choosing. In the second step we would then use rbinom to simulate binary outcome while keeping it dependent on our predictor X.
In your example you are simulating independent X and a y where the probability is independent of X as well. Thus, when we look at the outcome y the probability of success is equal to p=c for all subgroup for some constant c.
Can someone explain me the actual difference between Method 1 and Method 2? ((1| year:plot) vs (1|year/plot))
This is explained in the package vignette fitting linear mixed effects models with lme4 in the table on page 7.
(1|year/plot) indicates that we have 2 mixed intercept effects, year and plot and plot is nested within year.
(1|year:plot) indicates a single mixed intercept effect, plot nested within year. Eg. we do not include the main effect of year. It would be somewhat similar to having a model without intercept (although less drastic, and interpretation is not destroyed).
It is more common to see the first rather than the second, but we could write the first as a function of the second (1|year) + (1|year:plot).
Thus: Is it indeed more appropriate to use the cbind-method than the raw binary data?
cbind in a formula is used for binomial data (or multivariate analysis), while for binary data we use the raw vector or 0/1 indicating success/failure, eg. aggregate binary data (similar to how we'd use glm). If you are uninterested in the random/fixed effect of subplot, you might be able to aggregate your data across plots, and then it would likely make sense. Otherwise stay with you 0/1 outcome vector indicating either success or failures.
What would be the correct random model structure and why?
This is a topic that is extremely hard to give a definitive answer to, and one that is still actively researched. Depending on your statistical paradigm opinions differ greatly.
Method 1: The classic approach
Classic mixed modelling is based upon knowledge of the data you are working with. In general there are several "rules of thumb" for choosing these parameters. I've gone through a few in my answer here. In general if you are "not interested" in the systematic effect and it can be thought of as a random sample of some population, then it could be a random effect. If it is the population, eg. samples do not change if the process is repeated, then it likely shouldn't.
This approach often yields "decent" choices for those who are new to mixed effect models, but is highly criticized by authors who tend towards methods similar to those we'd use in non-mixed models (eg. visualizing to base our choice and testing for significance).
Method 2: Using visualization
If you are able to split your data into independent subgroups and keeping the fixed effect structure a reasonable approach for checking potential random effects is the estimate marginal models (eg. using glm) across these subgroups and seeing if the fixed effects are "normally distributed" between these observations. The function lmList (in lme4) is designed for this specific approach. In linear models we would indeed expect these to be normally distributed, and thus we can get an indication whether a specific grouping "might" be a valid random effect structure. I believe the same is approximately true in the case of generalized linear models, but I lack references. I know that Ben Bolker have advocated for this approach in a prior article of his (the first reference below) that I used during my thesis. However this is only a valid approach for strictly separable data, and the implementation is not robust in the case where factor levels are not shared across all groups.
So in short: If you have the right data, this approach is simple, fast and seemingly highly reliable.
Method 3: Fitting maximal/minimal models and decreasing/expanding model based on AIC or AICc (or p-value tests or alternative metrics)
Finally an alternative to use a "step-wise"-like procedure. There are advocates of both starting with maximal and minimal models (I'm certain at least one of my references below talk about problems with both, otherwise check glmmFAQ) and then testing your random effects for their validity. Just like classic regression this is somewhat of a double-edged sword. The reason is both extremely simple to understand and amazingly complex to comprehend.
For this method to be successful you'd have to perform cross-validation or out-of-sample validation to avoid selection bias just like standard models, but unlike standard models sampling becomes complicated because:
The fixed effects are conditional on the random structure.
You will need your training and testing samples to be independent
As this is dependent on your random structure, and this is chosen in a step-wise approach it is hard to avoid information leakage in some of your models.
The only certain way to avoid problems here is to define the space
that you will be testing and selecting samples based on the most
restrictive model definition.
Next we also have problems with choice of metrics for evaluation. If one is interested in the random effects it makes sense to use AICc (AIC estimate of the conditional model) while for fixed effects it might make more sense to optimize AIC (AIC estimate of the marginal model). I'd suggest checking references to AIC and AICc on glmmFAQ, and be wary since the large-sample results for these may be uncertain outside a very reestrictive set of mixed models (namely "enough independent samples over random effects").
Another approach here is to use p-values instead of some metric for the procedure. But one should likely be even more wary of test on random effects. Even using a Bayesian approach or bootstrapping with incredibly high number of resamples sometimes these are just not very good. Again we need "enough independent samples over random effects" to ensure the accuracy.
The DHARMA provides some very interesting testing methods for mixed effects that might be better suited. While I was working in the area the author was still (seemingly) developing an article documenting the validity of their chosen method. Even if one does not use it for initial selection I can only recommend checking it out and deciding upon whether one believes in their methods. It is by far the most simple approach for a visual test with simple interpretation (eg. almost no prior knowledge is needed to interpret the plots).
A final note on this method would thus be: It is indeed an approach, but one I would personally not recommend. It requires either extreme care or the author accepting ignorance of model assumptions.
Conclusion
Mixed effect parameter selection is something that is difficult. My experience tells me that mostly a combination of method 1 and 2 are used, while method 3 seems to be used mostly by newer authors and these tend to ignore either out-of-sample error (measure model metrics based on the data used for training), ignore independence of samples problems when fitting random effects or restrict themselves to only using this method for testing fixed effect parameters. All 3 do however have some validity. I myself tend to be in the first group, and base my decision upon my "experience" within the field, rule-of-thumbs and the restrictions of my data.
Your specific problem.
Given your specific problem I would assume a mixed effect structure of (1|year/plot/subplot) would be the correct structure. If you add autoregressive (time-spatial) effects likely year disappears. The reason for this structure is that in geo-analysis and analysis of land plots the classic approach is to include an effect for each plot. If each plot can then further be indexed into subplot it is natural to think of "subplot" to be nested in "plot". Assuming you do not model autoregressive effects I would think of time as random for reasons that you already stated. Some years we'll have more dry and hotter weather than others. As the plots measured will have to be present in a given year, these would be nested in year.
This is what I'd call the maximal model and it might not be feasible depending on your amount of data. In this case I would try using (1|time) + (1|plot/subplot). If both are feasible I would compare these models, either using bootstrapping methods or approximate LRT tests.
Note: It seems not unlikely that (1|time/plot/subplot) would result in "individual level effects". Eg 1 random effect per row in your data. For reasons that I have long since forgotten (but once read) it is not plausible to have individual (also called subject-level) effects in binary mixed models. In this case It might also make sense to use the alternative approach or test whether your model assumptions are kept when withholding subplot from your random effects.
Below I've added some useful references, some of which are directly relevant to the question. In addition check out the glmmFAQ site by Ben Bolker and more.
References
Bolker, B. et al. (2009). „Generalized linear mixed models: a practical guide for ecology and evolution“. In: Trends in ecology & evolution 24.3, p. 127–135.
Bolker, B. et al. (2011). „GLMMs in action: gene-by-environment interaction in total fruit production of wild populations of Arabidopsis thaliana“. In: Revised version, part 1 1, p. 127–135.
Eager, C. og J. Roy (2017). „Mixed effects models are sometimes terrible“. In: arXiv preprint arXiv:1701.04858. url: https://arxiv.org/abs/1701.04858 (last seen 19.09.2019).
Feng, Cindy et al. (2017). „Randomized quantile residuals: an omnibus model diagnostic tool with unified reference distribution“. In: arXiv preprint arXiv:1708.08527. (last seen 19.09.2019).
Gelman, A. og Jennifer Hill (2007). Data Analysis Using Regression and Multilevel/Hierarchical Models. Cambridge University Press.
Hartig, F. (2019). DHARMa: Residual Diagnostics for Hierarchical (Multi-Level / Mixed) Regression Models. R package version 0.2.4. url: http://florianhartig.github.io/DHARMa/ (last seen 19.09.2019).
Lee, Y. og J. A. Nelder (2004). „Conditional and Marginal Models: Another View“. In: Statistical Science 19.2, p. 219–238.
doi: 10.1214/088342304000000305. url: https://doi.org/10.1214/088342304000000305
Lin, D. Y. et al. (2002). „Model-checking techniques based on cumulative residuals“. In: Biometrics 58.1, p. 1–12. (last seen 19.09.2019).
Lin, X. (1997). „Variance Component Testing in Generalised Linear Models with Random Effects“. In: Biometrika 84.2, p. 309–326. issn: 00063444. url: http://www.jstor.org/stable/2337459
(last seen 19.09.2019).
Stiratelli, R. et al. (1984). „Random-effects models for serial observations with binary response“. In:
Biometrics, p. 961–971.
I've used mclust to find clusters in a dataset. Now I want to implement these findings into external non-r software (predict.Mclust is thus not an option as has been suggested in previous similar Questions) to classify new observations. I need to know how mclust classifies observations.
Since mclust outputs a center and a covariance matrix for each cluster it felt reasonable to calculate mahalanobis distance for every observation and for every cluster. Observations could then be classified to the mahalonobi-nearest cluster. It seems not not to work fully however.
Example code with simulated data (in this example I only use one dataset, d, and try to obtain the same classification as mclust does by the mahalanobi approach outlined above):
set.seed(123)
c1<-mvrnorm(100,mu=c(0,0),Sigma=matrix(c(2,0,0,2),ncol=2))
c2<-mvrnorm(200,mu=c(3,3),Sigma=matrix(c(3,0,0,3),ncol=2))
d<-rbind(c1,c2)
m<-Mclust(d)
int_class<-m$classification
clust1_cov<-m$parameters$variance$sigma[,,1]
clust1_center<-m$parameters$mean[,1]
clust2_cov<-m$parameters$variance$sigma[,,2]
clust2_center<-m$parameters$mean[,2]
mahal_clust1<-mahalanobis(d,cov=clust1_cov,center=clust1_center)
mahal_clust2<-mahalanobis(d,cov=clust2_cov,center=clust2_center)
mahal_clust_dist<-cbind(mahal_clust1,mahal_clust2)
mahal_classification<-apply(mahal_clust_dist,1,function(x){
match(min(x),x)
})
table(int_class,mahal_classification)
#List mahalanobis distance for miss-classified observations:
mahal_clust_dist[mahal_classification!=int_class,]
plot(m,what="classification")
#Indicate miss-classified observations:
points(d[mahal_classification!=int_class,],pch="X")
#Results:
> table(int_class,mahal_classification)
mahal_classification
int_class 1 2
1 124 0
2 5 171
> mahal_clust_dist[mahal_classification!=int_class,]
mahal_clust1 mahal_clust2
[1,] 1.340450 1.978224
[2,] 1.607045 1.717490
[3,] 3.545037 3.938316
[4,] 4.647557 5.081306
[5,] 1.570491 2.193004
Five observations are classified differently between the mahalanobi approach and mclust. In the plots they are intermediate points between the two clusters. Could someone tell me why it does not work and how I could mimic the internal classification of mclust and predict.Mclust?
After formulating the above question I did some additional research (thx LoBu) and found that the key was to calculate the posterior probability (pp) for an observation to belong to a certain cluster and classify according to maximal pp. The following works:
denom<-rep(0,nrow(d))
pp_matrix<-matrix(rep(NA,nrow(d)*2),nrow=nrow(d))
for(i in 1:2){
denom<-denom+m$parameters$pro[i]*dmvnorm(d,m$parameters$mean[,i],m$parameters$variance$sigma[,,i])
}
for(i in 1:2){
pp_matrix[,i]<-m$parameters$pro[i]*dmvnorm(d,m$parameters$mean[,i],m$parameters$variance$sigma[,,i]) / denom
}
pp_class<-apply(pp_matrix,1,function(x){
match(max(x),x)
})
table(pp_class,m$classification)
#Result:
pp_class 1 2
1 124 0
2 0 176
But if someone in layman terms could explain the difference between the mahalanobi and pp approach I would be greatful. What do the "mixing probabilities" (m$parameters$pro) signify?
In addition to Mahalanobis distance, you also need to take the cluster weight into account.
These weight the relative importance of clusters when they overlap.
I know one formula to calculate classification accuracy is X = t / n * 100 (where t is the number of correct classification and n is the total number of samples. )
But, let's say we have total 100 samples, 80 in class A, 10 in class B, 10 in class C.
Scenario 1: All 100 samples were assigned to class A, by using the formula, we got accuracy equals 80%.
Scenario 2: 10 samples belong to B were correctly assigned to class B ;10 samples belong to C were correctly assigned to class C as well; 30 samples belong to A correctly assigned to class A; the rest 50 samples belong to A were incorrectly assigned to C. By using the formula, we got accuracy of 50%.
My question is:
1: Can we say scenario 1 has a higher accuracy rate then scenario 2?
2: Is there any way to calculate accuracy rate for classification problem?
Many thanks ahead!
Classification accuracy is defined as "percentage of correct predictions". That is the case regardless of the number of classes. Thus, scenario 1 has a higher classification accuracy than scenario 2.
However, it sounds like what you are really asking is for an alternative evaluation metric or process that "rewards" scenario 2 for only making certain types of mistakes. I have two suggestions:
Create a confusion matrix: It describes the performance of a classifier so that you can see what types of errors your classifier is making.
Calculate the precision, recall, and F1 score for each class. The average F1 score might be the single-number metric you are looking for.
The Classification metrics section of the scikit-learn documentation has lots of good information about classifier evaluation, even if you are not a scikit-learn user.
I am a bit confuse of how to use a cut-off score to improve a precision of my predictive model.
here is a sample of data:
I have a dataset (matrix) which looks like:
> data_test
1 2 3 4 5 6
KRT6B 0.807688 1.097187 -0.390313 0.644938 -0.187188 1.200688
CXCL1 0.255250 -0.134917 1.886083 0.433417 0.267583 0.996583
S100A8 -1.694800 0.012900 -0.314800 -0.368600 -0.750100 2.864700
S100A7 -0.417500 0.989000 -0.887000 -0.914500 -0.909000 4.485000
HORMAD1 -0.124750 -0.304083 -0.911050 5.426917 0.042250 6.490917
CLCA2 4.243417 0.032583 -1.750917 -1.551250 1.249917 1.494417
the colnames are samples and rownames are Genes.
so to find a cut-off point I generate a score for the cut-offs by adding up the expression of each column and assign it to predictor:
predictor <- colSums(data_test)
> predictor
1 2 3 4 5 6
3.069305 1.692670 -2.367997 3.670922 -0.286538 17.532305
and the response for it:
> response
[1] norm high norm low norm high
Levels: high norm low
I used pROC package to generate a ROC curve and find the optimised cut-off (with youden index value/ J statistic):
library(pROC)
rocobj <- roc(response,predictor)
cutpoint <- coords(rocobj,x='best',input='threshold',best.method = 'youden')
threshold specificity sensitivity
0.7030660 1.0000000 0.6666667
So, now I have my optimised cut-off point but I cannot understand how can I use this optimised cut-off (sort of a score!) to improve the precision of my predictive model.
In several papers they've used this approach and at the end they've shown that the similarity level of the predictive model has been improved by using the new cut-off point. I tried to understand but I am stock here cause I don't get it! (I mean the next step!). They didn't mention how they checked the similarity or how they implement the new cut-off point in my case the score to improve their method.
Could someone give me a good explanation for the next step?
Thanks in advance and sorry for my messy explanation.
I'm working on a very big data-set.(csv)
The data set is composed from both numeric and categorical columns.
One of the columns is my "target column" , meaning i want to use the other columns to determine which value (out of 3 possible known values) is likely to be in the "target column". In the end check my classification vs the real data.
My question:
I'm using R.
I am trying to find a way to select the subset of features which give the best classifiation.
going over all the subsets is impossible.
Does anyone know an algorithm or can think of a way do it on R?
This seems to be a classification problem. Without knowing the amount of covariates you have for your target, can't be sure, but wouldn't a neural network solve your problem?
You could use the nnet package, which uses a Feed-forward neural network and works with multiple classes. Having categorical columns is not a problem since you could just use factors.
Without a datasample I can only explain it just a bit, but mainly using the function:
newNet<-nnet(targetColumn~ . ,data=yourDataset, subset=yourDataSubset [..and more values]..)
You obtain a trained neural net. What is also important here is the size of the hidden layer which is a tricky thing to get right. As a rule of thumb it should be roughly 2/3 of the amount of imputs + amount of outputs (3 in your case).
Then with:
myPrediction <- predict(newNet, newdata=yourDataset(with the other subset))
You obtain the predicted values. About how to evaluate them, I use the ROCR package but currently only supports binary classification, I guess a google search will show some help.
If you are adamant about eliminate some of the covariates, using the cor() function may help you to identify the less caracteristic ones.
Edit for a step by step guide:
Lets say we have this dataframe:
str(df)
'data.frame': 5 obs. of 3 variables:
$ a: num 1 2 3 4 5
$ b: num 1 1.5 2 2.5 3
$ c: Factor w/ 3 levels "blue","red","yellow": 2 2 1 2 3
The column c has 3 levels, that is, 3 type of values it can take. This is something done by default by a dataframe when a column has strings instead of numerical values.
Now, using the columns a and b we want to predict which value c is going to be. Using a neural network. The nnet package is simple enough for this example. If you don't have it installed, use:
install.packages("nnet")
Then, to load it:
require(nnet)
after this, lets train the neural network with a sample of the data, for that, the function
portion<-sample(1:nrow(df),0.7*nrow(df))
will store in portion, 70% of the rows from the dataframe. Now, let's train that net! I recommend you to check the documentation for the nnet package with ?nnet for a deeper knowledge. Using only basics:
myNet<-nnet( c~ a+b,data=df,subset=portion,size=1)
c~ a+b is the formula for the prediction. You want to predict the column c using the columns a and b
data= means the data origin, in this case, the dataframe df
subset= self explanatory
size= the size of the hidden layer, as I said, use about 2/3 of the total columns(a+b) + total outputs(1)
We have trained net now, lets use it.
Using predict you will use the trained net for new values.
newPredictedValues<-predict(myNet,newdata=df[-portion,])
After that, newPredictedValues will have the predictions.
Since you have both numerical and categorical data, then you may try SVM.
I am using SVM and KNN on my numerical data and I also tried to apply DNN. DNN is pretty slow for training especially big data in R. KNN does not need to be trained, but is used for numerical data. And the following is what I am using. Maybe you can have a look at it.
#Train the model
y_train<-data[,1] #first col is response variable
x_train<-subset(data,select=-1)
train_df<-data.frame(x=x_train,y=y_train)
svm_model<-svm(y~.,data=train_df,type="C")
#Test
y_test<-testdata[,1]
x_test<-subset(testdata,select=-1)
pred<-predict(svm_model,newdata = x_test)
svm_t<-table(pred,y_test)
sum(diag(svm_t))/sum(svm_t) #accuracy