Search Results

Search found 14 results on 1 pages for 'al3xa'.

Page 1/1 | 1 

• Strange stuff in apache log

  - by aL3xa

  Hi lads, I'm building some kind of webapp, and currently the whole thing runs on my machine. I was combing down my logs, and found several "strange" log entries that made me a bit paranoid. Here goes: ***.***.***.** - - [19/Dec/2010:19:47:47 +0100] "\x99\x91g\xca\xa8" 501 1054 **.***.***.** - - [19/Dec/2010:20:14:58 +0100] "<}\xdbe\x86E\x18\xe7\x8b" 501 1054 **.**.***.*** - - [21/Dec/2010:15:28:14 +0100] "J\xaa\x9f\xa3\xdd\x9c\x81\\\xbd\xb3\xbe\xf7\xa6A\x92g'\x039\x97\xac,vC\x8d\x12\xec\x80\x06\x10\x8e\xab7e\xa9\x98\x10\xa7" 501 1054 Bloody hell... what is this?!

  Read the article

• Preview colours in Emacs-ESS

  - by aL3xa

  I accidentally managed to get colour names, #HEX, and a colour preview in Emacs-ESS. Don't have a bloody idea how, must've pressed some keybinding or menu item... But, now I can't seem to find where's that feature... I'm quite sure I wasn't hallucinating, so it's gotta be there, under some keystroke that I can't reproduce!!! =) Thanks in advance!

  Read the article

• Homoscedascity test for Two-Way ANOVA

  - by aL3xa

  I've been using var.test and bartlett.test to check basic ANOVA assumptions, among others, homoscedascity (homogeniety, equality of variances). Procedure is quite simple for One-Way ANOVA: bartlett.test(x ~ g) # where x is numeric, and g is a factor var.test(x ~ g) But, for 2x2 tables, i.e. Two-Way ANOVA's, I want to do something like this: bartlett.test(x ~ c(g1, g2)) # or with list; see latter: var.test(x ~ list(g1, g2)) Of course, ANOVA assumptions can be checked with graphical procedures, but what about "an arithmetic option"? Is that manageable? How do you test homoscedascity in Two-Way ANOVA?

  Read the article

• Homoscedascity test for Two-Way ANOVA

  - by aL3xa

  I've been using var.test and bartlett.test to check basic ANOVA assumptions, among others, homoscedascity (homogeniety, equality of variances). Procedure is quite simple for One-Way ANOVA: bartlett.test(x ~ g) # where x is numeric, and g is a factor var.test(x ~ g) But, for 2x2 tables, i.e. Two-Way ANOVA's, I want to do something like this: bartlett.test(x ~ c(g1, g2)) # or with list; see latter: var.test(x ~ list(g1, g2)) Of course, ANOVA assumptions can be checked with graphical procedures, but what about "an arithmetic option"? Is that, at all, manageable? How do you test homoscedascity in Two-Way ANOVA?

  Read the article

• Show frequencies along with barplot in ggplot2

  - by aL3xa

  I'm trying to display frequencies within barplot ... well, I want them somewhere in the graph: under the bars, within bars, above bars or in the legend area. And I recall (I may be wrong) that it can be done in ggplot2. This is probably an easy one... at least it seems easy. Here's the code: p <- ggplot(mtcars) p + aes(factor(cyl)) + geom_bar() Is there any chance that I can get frequencies embedded in the graph?

  Read the article

• Subset a data.frame by list and apply function on each part, by rows

  - by aL3xa

  This may seem as a typical plyr problem, but I have something different in mind. Here's the function that I want to optimize (skip the for loop). # dummy data set.seed(1985) lst <- list(a=1:10, b=11:15, c=16:20) m <- matrix(round(runif(200, 1, 7)), 10) m <- as.data.frame(m) dfsub <- function(dt, lst, fun) { # check whether dt is `data.frame` stopifnot (is.data.frame(dt)) # check if vectors in lst are "whole" / integer # vector elements should be column indexes is.wholenumber <- function(x, tol = .Machine$double.eps^0.5) abs(x - round(x)) < tol # fall if any non-integers in list idx <- rapply(lst, is.wholenumber) stopifnot(idx) # check for list length stopifnot(ncol(dt) == length(idx)) # subset the data subs <- list() for (i in 1:length(lst)) { # apply function on each part, by row subs[[i]] <- apply(dt[ , lst[[i]]], 1, fun) } # preserve names names(subs) <- names(lst) # convert to data.frame subs <- as.data.frame(subs) # guess what =) return(subs) } And now a short demonstration... actually, I'm about to explain what I primarily intended to do. I wanted to subset a data.frame by vectors gathered in list object. Since this is a part of code from a function that accompanies data manipulation in psychological research, you can consider m as a results from personality questionnaire (10 subjects, 20 vars). Vectors in list hold column indexes that define questionnaire subscales (e.g. personality traits). Each subscale is defined by several items (columns in data.frame). If we presuppose that the score on each subscale is nothing more than sum (or some other function) of row values (results on that part of questionnaire for each subject), you could run: > dfsub(m, lst, sum) a b c 1 46 20 24 2 41 24 21 3 41 13 12 4 37 14 18 5 57 18 25 6 27 18 18 7 28 17 20 8 31 18 23 9 38 14 15 10 41 14 22 I took a glance at this function and I must admit that this little loop isn't spoiling the code at all... BUT, if there's an easier/efficient way of doing this, please, let me know!

  Read the article

• Rreport / LaTeX quality output package

  - by aL3xa

  I'm looking for some LaTeX template for creating quality output. On R-bloggers I've bumped on Frank Harrel's Rreport package. Due to my, quite modest LaTeX abilities, only user-friendly (and noob-friendly) interface should suffice. Here's a link to an official website. I'm following the instructions, but I cannot manage to install an app. I use Ubuntu 9.10, R version is 2.10.1 (updated regularly from UCLA's CRAN server)... of course, cvs is installed on my sistem. Now, I'd like to know is there some user-friendly LaTeX template package (Sweave is still to advanced/spartan for me). I'm aware that my question is quite confounding, but brief glance on examples on Rreport page should give you a hint. I'm aware that LaTeX skills are a must, but just for now I need something that will suite my needs (as a psychological researcher). Is there any pandan for Rreport package?

  Read the article

• Eta/Eta-squared routines in R

  - by aL3xa

  Apart from graphical estimation of linearity (gaze-at-scatterplot method), which is utilized before applying some technique from GLM family, there are several ways to do this estimation arithmetically (i.e. without graphs). Right now, I'll focus on Fisher's eta-squared - correlation ratio: arithmetically, it's equal to squared Pearson's r (coef. of determination: R2) if relationship between two variables is linear. Hence, you can compare values of eta and r and make an assessment about type of relation (linear or not). It provides an information about percent of variance in the dependent variable explained (linearly or not) by the independent variable. Therefore, you can apply it when linearity assumptions are not met. Simply stated: is there a routine for eta/eta-squared in R?

  Read the article

• ESS/AucTeX/Sweave integration

  - by aL3xa

  I'm using GNU/Linux distro (Arch, if that's relevant), Emacs v23.2.1, ESS v5.9 and AucTeX v11.86. I want to setup AucTeX to recognize .Rnw files, so I can run LaTeX on .Rnw files with C-c C-c and get .dvi file automatically. I reckon it's quite manageable by editing .emacs file, but I still haven't got a firm grasp on Elisp. Yet another problem is quite annoying - somehow, LaTeX is not recognizing \usepackage{Sweave} in preambule, so I actually need to copy Sweave.sty file (in my case located in /usr/share/R/texmf/Sweave.sty) to directory where .Rnw file is located (and I'm getting more frustrated with the fact that this is common bug on Windows platforms!) My question boils down to two problems: how to make LaTeX recognize \usepackage{Sweave} (without copying Sweave.sty to "home" folder each time) how to setup AucTeX to compile .Rnw files to .dvi

  Read the article

• Return call from ggplot object

  - by aL3xa

  I've been using ggplot2 for a while now, and I can't find a way to get formula from ggplot object. Though I can get basic info with summary(<ggplot_object>), in order to get complete formula, usually I was combing up and down through .Rhistory file. And this becomes frustrating when you experiment with new graphs, especially when code gets a bit lengthy... so searching through history file isn't quite convenient way of doing this... Is there a more efficient way of doing this? Just an illustration: p <- qplot(data = mtcars, x = factor(cyl), geom = "bar", fill = factor(cyl)) + scale_fill_manual(name = "Cylinders", value = c("firebrick3", "gold2", "chartreuse3")) + stat_bin(aes(label = ..count..), vjust = -0.2, geom = "text", position = "identity") + xlab("# of cylinders") + ylab("Frequency") + opts(title = "Barplot: # of cylinders") I can get some basic info with summary: > summary(p) data: mpg, cyl, disp, hp, drat, wt, qsec, vs, am, gear, carb [32x11] mapping: fill = factor(cyl), x = factor(cyl) scales: fill faceting: facet_grid(. ~ ., FALSE) ----------------------------------- geom_bar: stat_bin: position_stack: (width = NULL, height = NULL) mapping: label = ..count.. geom_text: vjust = -0.2 stat_bin: width = 0.9, drop = TRUE, right = TRUE position_identity: (width = NULL, height = NULL) But I want to get code I typed in to get the graph. I reckon that I'm missing something essential here... it's seems impossible that there's no way to get call from ggplot object!

  Read the article

• Suggestion for R/LaTeX table creation package

  - by aL3xa

  I've been using xtable package for a long time, and looking forward to writting my first package in R... so I reckon that if I have some "cool" idea that's worth carying out, there's a great chance that somebody got there before me... =) I'm interested in functions/packages specialized for LaTeX table creation (through R, of course). I bumped on quantreg package which has latex.table function. Any suggestion for similar function(s)/package(s)? P.S. I'm thinking about building a webapp in which users can define their own presets/templates of tables, choose style, statistics, etc. It's an early thought, though... =)

  Read the article

• Screening (multi)collinearity in a regression model

  - by aL3xa

  I hope that this one is not going to be "ask-and-answer" question... here goes: (multi)collinearity refers to extremely high correlations between predictors in the regression model. How to cure them... well, sometimes you don't need to "cure" collinearity, since it doesn't affect regression model itself, but interpretation of an effect of individual predictors. One way to spot collinearity is to put each predictor as a dependent variable, and other predictors as independent variables, determine R2, and if it's larger than .9 (or .95), we can consider predictor redundant. This is one "method"... what about other approaches? Some of them are time consuming, like excluding predictors from model and watching for b-coefficient changes - they should be noticeably different. Of course, we must always bare in mind specific context/goal of analysis... Sometimes, only remedy is to repeat a research, but right now, I'm interested in various ways of screening redundant predictors when (multi)collinearity occurs in a regression model.

  Read the article

• Non-graphical linearity estimation

  - by aL3xa

  In my previous post, I was looking for correlation ratio (η or η2) routines in R. I was surprised by the fact that no one uses η for linearity checking in the GLM procedures. Let's start form a simple example: how do you check linearity of bivariate correlation? Solely with scatterplot? There are several ways of doing this, one way is to compare linear and non-linear model R2, then to apply F test to seek for significant difference between them. Finally, the question is: How do you check linearity, the "non-grafical" way?

  Read the article

• Screening (multi)collinearity in a reggresion model

  - by aL3xa

  I hope that this one is not going to be "ask-and-answer" question... here goes: (multi)collinearity refers to extremely high correlations between predictors in the regression model. How to cure them... well, sometimes you don't need to "cure" collinearity, since it doesn't affect regression model itself, but interpretation of an effect of individual predictors. One way to spot collinearity is to put each predictor as a dependent variable, and other predictors as independent variables, determine R2, and if it's larger than .9 (or .95), we can consider predictor redundant. This is one "method"... what about other approaches? Some of them are time consuming, like excluding predictors from model and watching for b-coefficient changes - they should be noticeably different. Of course, we must always bare in mind specific context/goal of analysis... Sometimes, only remedy is to repeat a research, but right now, I'm interested in various ways of screening redundant predictors when (multi)collinearity occurs in a regression model.

  Read the article

1