I am using WEKA 3.7.11. I am using the J4.8 classification method with the 10-fold cross validation option. Is there a way to export/save the datasets produced by the cross validation in order to use them as input to other methods?
If you wish have data set containing columns with predictions of your model have a look here:
http://weka.wikispaces.com/Making+predictions
Good luck..
I think Weka allows you to save the results for the datasets (10 sets of results for 10 fold CV) but not the datasets themselves. In order to have your datasets in hand, you can first create them according to my video tutorial Here. Then you need to use the k datasets you produce to simulate a k-fold CV. I know it is not a good solution, but still this is the way that solved my problems.
Related
Good day everyone, this is my first time posting here but I'd like some help with a recent issue.
So, I'm working on a small React app just for fun and to keep practising, in it I made a few constants for different datasets (each with varying data fields), that is, I have various kinds of records categorized in said constants, since some records use 2+ rows and some need only one row.
Initially I was going to share the app's code, but the datasets are a tad... large, so reading the tips I thought I'd instead create an online sandbox to illustrate with a much simpler and smaller scenario of what I managed to do: [link to the sandbox].
However, looking around and trying different stuff I found out about react-table, which is what I needed due to its useful features and how lightweight it is. I mainly need it for filtering records but I want to try some other features as well.
All this brings me to my problem: I want to populate a table in react-table with the multiple datasets together and their own ways their data is placed on the JSX code, however, I can't figure out what to do and my app's code is getting messy in the process, so I thought I'd ask here to see what I can do, using the code in the sandbox as base, then I can edit my app accordingly if there's a solution for this, otherwise I guess I can maybe make one table for each dataset or just use good ol' HTML+JS+CSS? But neither are the results I'm aiming for.
I'm in no rush for answers since this is just a project for fun and to practise, however, any help is appreciated, thanks in advance.
my .pbix is an import and I'm trying to take to simple text fields and create a DAX measure that concatenates 2 fields.
My DAX functions work on numbers and values, but when I try DAX functions on text fields like concatenate or concatenateX or combinevalues, none of these work
When I start building the simple formula, my power BI doesn't recognize the fields , despite the data imported into my PBIX.
Has anyone experienced this before and if so how did you resolve it? I've tried creating the fields in power Query with no issues, but my plan was to make conditional measures with my DAX concatenate measures.
I was able to create a really nice dashboard, but being able create additional functions, would be to take my report/dashboard to the next level. and I've been able to create plenty of DAKS measures using number values , but for some reason I can't seem to make measures out of text.
Help(!) Is appreciated!!!
I am new to BigQuery and not familiar with dealing with tables that have repeated rows. I am aware that in Standard SQL in BigQuery that it will automatically handle the repeated rows, and I have seen how that works. However, I am trying to bring the data into a visualization tool that isn't able to handle tables with repeated rows.
What I am trying to do is run a query that is going to save the data in a view with the data flatten (legacy language)/unnested (standard language). All I am trying to include in the result of the query is the fields:
id
itemizations (this is the repeated field)
Could you give me some input on how to accomplish this or what other information you might need to help provide an answer to this? Thank you in advance.
I'm really new to Prometheus and for the moment I want to do some tests with the query to be a bit more familiar with it.
So with the query container_last_seen[10s] it returns me an array :
container_last_seen{container_label_com_docker_compose_config_hash="dc8a2ab1347ad16ab37ff0ad03f3a00f86b381ea2d85d45a11367331526c3640",container_label_com_docker_compose_container_number="1",container_label_com_docker_compose_oneoff="False",container_label_com_docker_compose_project="dockprom",container_label_com_docker_compose_service="cadvisor",container_label_com_docker_compose_version="1.10.0",container_label_org_label_schema_group="monitoring",id="/docker/2b448d19a33b50411941a55435b03f5a4af19e3b3e9581054a67e4da3363ef19",image="google/cadvisor:v0.24.1",instance="cadvisor:8080",job="cadvisor",name="cadvisor"}
And I want to get only the attribute name.
So my idea was to do something like this:
container_last_seen[10s][name]
But I have a parse error. So how can I make this query ?
It may seem a little counterintuitive for this purpose, but the aggregation operators allow reducing labels with the by and without clauses.
sum by(name) (container_last_seen{..criteria..})
should get you closer to what you are wanting by returning objects with only the name key.
I think you want a little further though - you don't want values and you don't want the object part - you just want strings. Unfortunately Prometheus deals with numeric metrics that can have labels, and specifically not string metrics.
While it requires additional software, it is officially recommended by Prometheus so I will mention it here as it gets you very close to what I believe is your desired solution:
If you were to chart that query in Grafana, either with all the keys or just the name key, the legend format {{name}} should get you exactly what you want. Grafana also provides label_values to help with this purpose in regards to filtering.
Lastly if this is not the right direction for you, for intensive string-based metrics ELK/EFK stack may be a better fit. There are projects like prometheus-es-exporter that can report the results from ElasticSearch queries as metrics.
This is not possible as labels like 'name' are separate to the metric value. You should look at the JSON the query and query_range endpoints return to see how this is exposed.
I want to code Excel-like behaviour in my MEAN Application. What I mean with excel-like behaviour that is having cells and columns and rows (I have that in Angular already) and now I want to enable users to select e.g. 2 columns and let a self-defined calculation run over it.
Now storing User-defined Functions in MongoDB sounds like a very bad idea, since a user could drop the database.
The Stack
[User Input]
[Calculations/Functions]
[Controller]
[Middleware]
[API+Server]
[DB]
I discussed how to achieve this with MEAN here: Convert JSON String to Objects however I highly doubt this will be secure. Any idea how to achieve this in a solid fashion?