Comments for blog.RDataMining.com

Comment on An Example of Social Network Analysis with R using Package igraph by Yanchang Zhao

Yanchang Zhao — Wed, 22 May 2013 09:04:29 +0000

First, create a data frame with 2 columns: food and ingredient, You might use stack() or unstack() for that. In you case, the data frame will look like:
Column1 Column2
Food1 ingredient1
Food1 ingredient2
Food1 ingredient3
Food2 ingredient2
Food2 ingredient3
…

Second, convert it to graph with graph.data.frame(YourDataFrame)

For future questions, please post them to my RDataMining group on LinkedIn at http://group.rdatamining.com/

Comment on An Example of Social Network Analysis with R using Package igraph by Asif

Asif — Wed, 22 May 2013 03:28:53 +0000

Hi ,
I want to create a network data file for further analysis using igraph.
I want to create a network of ingredients.
The current data format that I have looks like this :
Column1 Column2
Food1 ingredient1, ingredient2 , ingredient3
Food2 ingredient2, ingredeint3
Food3 ingredeint3, ingredeint4

From this file I want to create an adjacency matrix of ingredients . My final goal is to find out
which ingredients go together.
Could you please give me suggestion how to create adjacency matrix from the above datafile.
Thanks

Comment on Using Text Mining to Find Out What @RDataMining Tweets are About by CASEN survey – text mining after Social Network Analysis // Encuesta CASEN – mineria de texto despues del analisis de redes sociales | Kawin project

Tue, 21 May 2013 16:13:21 +0000

[…] For this post, I relied heavily on this post http://rdatamining.wordpress.com/2011/11/09/using-text-mining-to-find-out-what-rdatamining-tweets-ar… […]

Comment on Using Text Mining to Find Out What @RDataMining Tweets are About by Yanchang Zhao

Yanchang Zhao — Sat, 18 May 2013 05:44:27 +0000

Seems that you haven’t install package twitteR. Please install it first and then try the code again.

Comment on Using Text Mining to Find Out What @RDataMining Tweets are About by David

David — Thu, 16 May 2013 21:24:07 +0000

Hi, I’m completely new to R, but everything works fine until I get to this line:
df <- do.call(“rbind”, lapply(rdmTweets, as.data.frame))

I get this error:
Error in as.data.frame.default(X[[1L]], …) :
cannot coerce class "structure("status", package = "twitteR")" to a data.frame

Any idea why? I can't find anyone else with my problem via Google.
Thanks for any help.

Comment on Time Series Analysis and Mining with R by huiseguiji

huiseguiji — Tue, 23 Apr 2013 03:08:28 +0000

I think the data sample2 have some NA values, hava a look at your sample2 data!

Comment on Time Series Analysis and Mining with R by Julian Hagenauer

Julian Hagenauer — Mon, 15 Apr 2013 09:43:16 +0000

Thank you for pointing this out!

Comment on Using Text Mining to Find Out What @RDataMining Tweets are About by Ganttic

Ganttic — Fri, 05 Apr 2013 15:09:43 +0000

Thank you very much for sharing this informative post. I have learned a lot from here. I hope that there will be an update soon. Keep up the good work!

Comment on R Code Examples on Graphics by incataloguevn

incataloguevn — Thu, 21 Mar 2013 09:05:00 +0000

thanks

Comment on Time Series Analysis and Mining with R by Emmanuel

Emmanuel — Tue, 19 Mar 2013 11:47:26 +0000

Dear Yanchang,
As a follow up to my previous request on how to merge data from different stations where you suggested using “d <- merge(stn12, stn14, by="vehicleId")", I would like to ask for your assistance once again.
At this stage, I am trying to work with data from many stations stored as a list which requires writing a loop that will merge all the stations together and and give the output of the individual merge data set. I have tried a couple of solutions based on my Fortran knowledge but to no avail.
Here is a brief breakdown of what I have tried:
# mdata is a list of the files to be merged
# merging more than 2 files using a loop function
mdata <- all
i<-0
i2<-0
mgr<- function(mdata){
l <- length(mdata)
for(i in mdata){
i <- i+1
i2 <- i+1
mdat[[i]] <- merge(mdata[[i]], mdata[[i2]], by = "VehicleId", sort=T,all = FALSE)[mdata[[i]],
!=mdata[[i2]]]
}
return(mdat)
}
mg <- mgr(mdata)

### another trier
i<-0
i2<-0
mdata <- all
mgr = function(mdata){
for(i in 1:length(mdata)){
i <- i+1
i2 <- i+1
mdat[[i]] <- merge(mdata[[i]], mdata[[i2]], by = "VehicleId", sort=TRUE,
all = FALSE)
}
return(mdat[[i]])
}
mg <- lapply(mdata,mgr)

However, if I run the following for any combination of two files, it will give me the output as desired.
mdat <- merge(mdata[[1]], mdata[[2]], by = "VehicleId", sort=TRUE,all = FALSE)

Any help will be highly appreciated. Thank you for your usual cooperation