I extracting splitting rules from Greg Ridgeway's GBM 1.6-3.2 in R 2.15.2, so I
can run classification in a production system outside of R. I have it working
and verified for a dummy data set with all variable types (numeric, factor,
ordered) and missing values, but in the titanic survivors
The mailing list ate the attachments, so here they are again.
R code
https://gist.github.com/4270628
Log
http://pastebin.com/0e49CTsL
Andrew
-Original Message-
From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] On
Behalf Of Andrew Ziem
Sent: Wednesday
It sounds like you want to do supervised classification, so maybe a supervised
classification algorithm would be more appropriate? Consider logistic
regression, rpart, ctree, earth, etc.
Andrew
-Original Message-
From: r-help-boun...@r-project.org
Try the fork() function in the package multicore (if your system supports it)
Andrew
-Original Message-
From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] On
Behalf Of PALMIER Patrick (Responsable de groupe) - CETE NP/TM/ST
Sent: Monday, November 07, 2011 3:49 AM
aajit75 aajit75 at yahoo.co.in writes:
fit - rpart(decile ~., method=class,
control=rpart.control(minsplit=min_obs_split, cp=c_c_factor),
data=dtm_ip)
In A and B target variable 'segment' is from the clustering data using same
set of input variables , while in C target
Does caret have a bug calculating ROC with earth? When using caret and earth
on any of my data sets, caret's ROC never varies. This could mean earth is
finding the same model (for example, because of using an nprune parameter that
is too high). However, if that were true, sensitivity and
In addition's to Max's suggestion about caret, look at ROCR which visualizes
ROC charts for any binary classifier. I have an example of e1071::SVN and ROCR
here
https://heuristically.wordpress.com/2009/12/23/compare-performance-machine-learning-classifiers-r/
-Original Message-
Try the function ctree() in the package party or earth() in earth. You can
use factor variable as is, or you can transform the factor to binary variables
(i.e., is_P is 0 or 1, is_D is 0 or 1). In the second case, you can use any
algorithm, and earth() automatically transforms factors to
After ctree builds a tree, how would I determine the direction missing values
follow by examining the BinaryTree-class object? For instance in the example
below Bare.nuclei has 16 missing values and is used for the first split, but
the missing values are not listed in either set of factors.
Like earth can be trained simultaneously for degree and nprune, is there a way
to train ctree simultaneously for mincriterion and maxdepth?
Also, I notice there are separate methods ctree and ctree2, and if both options
are attempted to tune with one method, the summary averages the option it
Hello Petr,
Thank you. That works beautifully. I searched for a way to transpose
a data frame, but you are right: barplot() wants a matrix.
Andrew
On Wed, Mar 4, 2009 at 1:49 AM, Petr PIKAL petr.pi...@precheza.cz wrote:
Read what barplot does and look to your plot.
If you want each row to
What is the best way to produce a barplot from my data? I would like
the barplot to show each person with the values stacked
val1+val2+val3, so there is one bar for each person When I use
barplot(data.matrix(realdata)), it shows one bar for each value
instead.
To post here, I created an
This is a working example of how to merge records with a SQL database
given the constraints
1. The database is too large to pull all the records
2. The database permissions don't allow creating a table for
temporarily storing identifiers
3. The R database driver doesn't allow creating temporary
Creating a temp table isn't completely intuitive with MySQL 5 and R
2.8..1, but it can be done.
library(RMySQL)
Loading required package: DBI
con - dbConnect(dbDriver(MySQL), dbname = foo,
user=me,password=secret)
x- data.frame(1:10)
colnames(x) -c(x)
dbWriteTable(con, #x, x,
I can create a temp table with MySQL and R DBI[1], but I don't see how
to do the same with Microsoft SQL 2005 and RODBC. R 2.8.1 creates the
table, but then it can never see it. I'm looking to avoid replacing
the convenience functions like sqlSave().
[1]
I want to find the last record for each person_id in a data frame
(from a SQL database) ordered by date. Is there a better way than
this for loop?
for (i in 2:length(history[,1])) {
if (history[i, person_id] == history[i - 1, person_id])
history[i, order] = history[i - 1, order] + 1 #
On Fri, Feb 27, 2009 at 2:10 PM, William Dunlap wdun...@tibco.com wrote:
Andrew, it makes it easier to help if you supply a typical
input and expected output along with your code. I tried
your code with the following input:
I'll be careful to avoid these mistakes. Also, I should not have
17 matches
Mail list logo