search for: misclassifying

Dear experts, I'm new in R and trying to learn by writing a version of the Perceptron Algorithm. How can I tell in the code below to stop the iteration when the condition in the "for loop" is not satisfied for all training examples? Thanks in advance for your help! ## Generate a linearly separable data set in R2 sample <- as.data.frame(cbind(runif(n=100),runif(n=100)))

Greetings R world, I know some version of the this question has been asked before, but i need to save the output of a loop into a data frame to eventually be written to a postgres data base with dbWriteTable. Some background. I have developed classifications models to help identify problem accounts. The logic is this, if the model classifies the record as including variable X and it turns out

...A. (I have an equal number of examples of each, so p(class) = 0.5.) One way of seeing how well this does is to compute the error rate on the test set, i.e. if f(x)>0.5 call it A, and see how many times I misclassify an item. That's what MASS does. But we should be able to do better: misclassifying should be more of a problem if the regression is confident then if it isn't. How can I show that my f(x) = P(x is in class A) does better than chance? Thanks, Martin

...ode the penalty function L[i,j] in which 0 <= L[i,j] <= 1 for j > i. It gives an example that if we have an ordered response with 4 categories, then we might wish to penalise larger misclassifications more - so there is (for example) 0 penalty for correct classifications, 0.25 penalty for misclassifying by one category, 0.5 penalty for misclassifying by two categories and 1.0 penalty for misclassifying by 3 categories. I wanted to use this sort of penalty - but with equal distances between the 4 categories (0, 1/3, 2/3, 1). But, I found that if I simply re-scale the penalty matrix, while maintaini...

Hello I want to build a classification tree for a binary response variable while the condition for the final tree should be : The total misclassification for each group (zero or one) will be less then 10% . for example: if I have in the root 100 observations, 90 from group 0 and 10 from group 1, I want that in the final tree a maximum of 9 and 1 observations out of group 0 and 1, respectively,

I use sieve-filter for postprocessing misclassified mail. For false positives I use the following script: require [ "variables", "include", "fileinto" ]; global [ "FORCENOSPAM", "ext", "ext1" ]; set "FORCENOSPAM" "YES"; fileinto "JUNK-PRENOUCE"; if header :matches "Delivered-To"

Dear friends, I have several sets of points in a transformed environmental space. Each set of points can be represented as a cloud in the environmental space. This space is spanned by n coordinates, corresponding to the first n PCs of 36 PCs of some environmental variables (12 monthly minimum temperatures, 12 monthly maximum temperature, 12 monthly precipitations). I would like to calculate

Hello, When I plot or look at the error rate vector for a random forest (rf$err.rate) it looks like a descending function except for a few first points of the vector with error rates values lower(sometimes much lower) than the general level of error rates for a forest with such number of trees when the error rates stop descending. Does it mean that there is a tree(s) (that is built the first in

Op 8/13/2015 om 4:33 PM schreef Jost Krieger: > I use sieve-filter for postprocessing misclassified mail. > For false positives I use the following script: > > require [ "variables", "include", "fileinto" ]; > > global [ "FORCENOSPAM", "ext", "ext1" ]; > > set "FORCENOSPAM" "YES"; > >

Now available on CRAN. Package: mspath Title: Multi-state Path-Dependent Models in Discrete Time Description: Functions for fitting path-dependent (non-Markov) multi-state models to categorical processes observed at arbitrary times, optionally with misclassified responses, and covariates on transition or misclassification rates. Uses discrete-time approximation. Based on the Jackson's

Hello, I need to draw a vertical line on my plot, the uncertainty segment (which is a vertical segment on every point of my plot so I can have an idea about the probability that a point is misclassified.... clustering problem.....) I remember I have done it a long time ago in Splus using a function called "segment" to which we give the extrem point of the segment , I didn't find

...es? Breiman et al. suggest some possibilities, but, of course, do not say how rpart does it. 2) In the loss matrix, which direction (column or row) is 'truth' and which 'output of program'? e.g., if you have a 3 level DV (say the levels are A, B, C) and you want a higher cost for misclassifying as later in the alphabet, would it be 0 3 5 1 0 2 2 1 0 or 0 1 2 3 0 1 5 2 0 Thanks in advance Peter

Dear R users, Usually the variance-inflation factor, which is based on R^2, is used as a measure for multicollinearity. But, in contrast to OLS regression there is no robust R^2 available for MM-regressions in R. Do you know if an equivalent or an alternative nmeasure of multicollinearity is available for MM-regression in R? With best regards, Carsten Colombier Dr. Carsten Colombier Economist

Hello I am using support vector machine (from package kernlab) for a classification task (with RBF-Kernel). My data has dozens of variables and I need to identify which variables contribute most to the classification performance. What I did so far is comparing the classification performance (measured for example with the proportion of misclassified cases) of different sets of variables with

Now available on CRAN. Package: mspath Title: Multi-state Path-Dependent Models in Discrete Time Description: Functions for fitting path-dependent (non-Markov) multi-state models to categorical processes observed at arbitrary times, optionally with misclassified responses, and covariates on transition or misclassification rates. Uses discrete-time approximation. Based on the Jackson's

Hi, I am trying to model credit risk data using decision trees. Since the number of defaulters is less compared to non-defaulters (defaulters around 10%), we have the class imbalance problem. Consequently, the confusion matrix shows that the number of misclassified non-defaulters is large. Classifying a defaulter as non-defaulter is more expensive. How does one include this information

Dear friends, I'm examining the characteristics of two models that both fit the sodium concentration in 16 pigs quite well under treatment or control conditions. The more complicated model is by anova better than the less complicated model. To take it further I have generated replicate data using the independent variables and parameter estimates under the two models. A clinically

I (finally) moved over to Maildir storage here and would like to implement some "scripts" to manage taking actions on emails manually identified as misclassified as spam/ham. After reading through the Dovecot 2 description of how it works to try to see how it interacts with other processes changing the files. I'm concerned that I would be corrupting the message indexes if I just

We're using Dovecot 1.0.3, and I'm setting up some shared IMAP folders. The eventual goal is to do the standard "learn as spam" / "learn as ham" type of setup, with some cron jobs to do the message extractions. But there's one minor twist: the "learn as ham" folder will need to be write-only for users. (I'll either create a fake user with read

Greetings list, We have an issue with call quality at 2 sites where the users (4 Elmeg IP290s at one site, 2 SPA942s at the other) do not have an asterisk box on-site. Each site has an 8mb down/448k up ADSL connection and the phones connect via SIP to an asterisk box in a datacentre using g729. The asterisk box in the datacentre connects to our other asterisk boxes providing pstn connectivity