similar to: Partial Dependence and RandomForest

Hello, I am running randomForest models on a number of species. I would like to be able to automate the printing of dependence plots for the most important variables in each model, but I am unable to figure out how to enter the variable names into my code. I had originally thought to extract them from the $importance matrix after sorting by metric (e.g. %IncMSE), but the importance matrix is n

Hi, I'm trying to make a partial plot with package randomForest in R. After I perform my random forest object I type partialPlot(data.rforest, pred.data=act2, x.var=centroid, "C") where data.rforest is my randomforest object, act2 is the original dataset, centroid is one of the predictor and C is one of the classes in my response variable. Whatever predictor or response class I

Hello, I need to draw a partial dependence bar graph. My the my predictor vectors are continous and so is the response variable. Iam using the partialPlot function of the randomForest package. I get a line graph. How can I edit it to get a bar graph instead? (partialPlot(randomForest object ,data-matrix, number of predictor vectors, "Temp")) -- Daudi Jjingo [[alternative HTML

Help, I've been having a difficult time trying to create 3d partial dependence plots using "rgl". It looks like this question has been asked a couple times, but I'm unable to find a clear answer googling. I've tried creating x, y, and z variables by extracting them from the partialPlot output to no avail. I've seen these plots used several times in articles, and I

I'm having trouble calling randomForest::partialPlot programmatically. It tries to use name of the (R) variable as the data column name. Example: library(randomForest) iris.rf <- randomForest(Species ~ ., data=iris, importance=TRUE, proximity=TRUE) partialPlot(iris.rf, iris, Sepal.Width) # works partialPlot(iris.rf, iris, "Sepal.Width") # works (function(var.name)

Hola erreros. A ver si alguien podría decirme qué son los dos ejes del plot que resulta de aplicar partialPlot en un Randomforest. Encuentro que: Partial dependence plot gives a graphical depiction of the marginal effect of a variable on the class probability (classification) or response (regression) que nos indica como varía la VR en función de la variable considerada, manteniendo el

Muchas gracias Carlos; ¡tu siempre al pié del cañón! (lo puse el día de reyes a la 1.20h y me contestas a las 2.45h) Una cosa más: si el eje y es la probabilidad ¿por qué va de 0 a 10? En un RF para clasificación me da valores parecidos a los de tu ejemplo, y en otro para regresión, valores de y entre 45 y 55. Para regresión, el último parámetro no puede ser una categoría, como

Dear R Group I had an observation that in some cases, when I use the randomForest model to create partialPlot in R using the package "randomForest" the y-axis displays values that are more than -1! It is a classification problem that i was trying to address. Any insights as to how the y axis can display value more than -1 for some variables? Am i missing something! Thanks Regards

Dear R Users, I'm using the randomForest package and would like to generate partial dependence plots, one after another, for a variety of variables: m <- randomForest( s, ... ) varnames <- c( "var1", "var2", "var3", "var4" ) # var1..4 are all in data frame s for( v in varnames ) { partialPlot( x=m, pred.data=s, x.var=v ) } ...but this

Greg, Two thoughts: 1. It might be possible that 'vars' is a reserved word of sorts and if you change the name of your vector RF might be happier 2. A way that works for me is to call importance as follows: sel.imp <- importance(sel.rf, class=NULL, scale=TRUE, type=NULL) and then use the 'names' of the imp data frame to be absolutely clear to RF you are talking about the

Hello ALL, I'm unsure how to interpret partial dependence plots and had 2 questions: Does the randomForest library scale partial dependence plots such that zero on the y axis is mean(y)? I am also unclear as to why the range of y on these plots is smaller than what is in the dataset. Also I have noticed that partial dependence plots cluster around the mean response. That is, if I'm

No no, eso lo he sacaod, es decir, tengo la matriz de confusión para las OK/NOK, lo que no entiendo es como extraer las conclusiones sobre el modelo, de cara a como afectan las variables. He seguido dos estrategias: 1-Crear arboles de clasificacion con las variables más importantes del random Forest, pero el modelo se empobrece bastante. 2- Sacar los partialPlot, para ver la influencia de cada

Mi matriz de datos inicial estaba muy desbalanceada (5% de la clase minoritaria), por lo que he creado con el algoritmo SMOTE un dataset balanceado con el que he creado el modelo, y luego sobre ese modelo he creado la matriz de confusión con los datos originales. Respecto a lo que me comentas, Carlos, creo que además de todo lo que comentas, que está bien, en micaso es necesario también saber no

Hi, everyone, I haven't found anything similar in the forum, so here's my problem (I'm no expert in R nor statistics): I have a data set of 59.000 cases with 9 variables each (fractional coverage of 9 different plant types, such as deciduous broad-leaved temperate trees or evergreen tropical trees etc.), which was generated by a vegetation model. In order to evaluate the quality of

Gracias por la pronta respuesta, pero tras leer la contestación de la gente, sigo sin entender muy bien la explicación. Le responden lo siguiente: "Each point on the partial dependence plot is the average vote percentage in favor of the "Yes trees" class across all observations, given a fixed level of TRI. It's not a probability of correct classification. It has absolutely

I am trying to run a partialPlot with Random Forest (as I have done many times before). First I run my forest... Cell is a 6 level factor that is the dependent variable - all other variables are predictors, most of these are factors as well. predCell<-randomForest(x=tempdata[-match("Cell",names(tempdata))],y=tempdata$Cell,importance=T) Then I try my partial plot to look at the

Hi everybody, I used random forest regression to explain the patterns of species richness and a bunch of climate variables (e.g. Temperature, precipitation, etc.) All are continuos variables. My results are really interesting and my model explained 96,7% of the variance. Now I am trying to take advantage of the importance variable function and depicts the observed patterns using partial

Hi, i try several possibilities adn looking in the archive, but didn't getting success to install j.lindsey's usefuel "library repeated" on my linux (suse9.0 with kernel 2.6.7,R.1.9.1) P.S. Windows, works fine Many thanks for help Christian chris at linux:/space/downs> R CMD INSTALL - l /usr/lib/R/library repeated WARNING: invalid package '-' WARNING:

All, I'm trying to set up a function which calls the partialPlot function but am getting an error that I can't seem to solve. Here's a simplified version of the function and error... > pplot <- function(rf,pred.var){partialPlot(x=rf,pred.data=acoust,x.var=pred.var)} > > attach(acoust) > acoust.rf <-

Hello, I was wondering if anyone knew of an R function/R code to plot bivariate (3 dimensional) partial dependence plots in random forests (randomForest package). It is apparently possible using the rgl package (http://esapubs.org/archive/ecol/E088/173/appendix-C.htm) or there may be a more direct function such as the pairplot() in MART (multiple additive regression trees)? Many