Be sure to review our Idea Submission Guidelines for more information!
Submission GuidelinesHello,
After used the new "Image Recognition Tool" a few days, I think you could improve it :
> by adding the dimensional constraints in front of each of the pre-trained models,
> by adding a true tool to divide the training data correctly (in order to have an equivalent number of images for each of the labels)
> at least, allow the tool to use black & white images (I wanted to test it on the MNIST, but the tool tells me that it necessarily needs RGB images) ?
Question : do you in the future allow the user to choose between CPU or GPU usage ?
In any case, thank you again for this new tool, it is certainly perfectible, but very simple to use, and I sincerely think that it will allow a greater number of people to understand the many use cases made possible thanks to image recognition.
Thank you again
Kévin VANCAPPEL (France ;-))
Thank you again.
Kévin VANCAPPEL
Our DAT file structure is as follows:
The first line of the .DAT file must be a header row identifying the field neames.
The .DAT file must use the following Concordance default delimiters:
Comma ASCII character (020)
Quote ASCII character (254)
Newline ASCII character (174)
Thank you,
Pete Vara
When a workflow has run it has it's final message.
It would be great to have a datetime stamp included in the file message. When running multiple jobs and editing multiple workflows it would be great to be able to check the last runtime so you know when each job had finished. As I often flip between multiple workflows during development and can working on up to 10 or more at any one time
Hi,
I think that the sample tool should have a T or F port.
Lets say I want to keep first N records but would like to stream the rest of the data (the not sampled one) somewhere else in my workflow, its possible but it would be easier to have that in the sampler.
Simon
Korem
I am trying to run batch regressions on a pretty sizable set of data. About ~1M distinct groups of data, each wtih 30-500 x,y pairs.
A batch macro with a linear regression works ok - but it is really slow. Started at about 2-3s per regression. After stripping out bunch or reporting from the macro, I am down to ~2s. This is still feels quite slow compared to something purpose built.
Has anyone experimented with higher speed versions that just dump out m,b, & r2?
Hi - I miss the functionality in 9.5 of being able to set a default tool in a tab and then drag in tools from the tab. This seems to be gone in 10. Is there any possibility of it coming back?
Many thanks - Nathalie
Currently only DateTime based functions are available, Time based functions should be introduced. like TimeAdd(), TimeDiff() etc.
This will help users a lot to calculate different aspects of time based calculations...
Ashok Bhatt
At the moment, we are not able to use input data field names and its values in Output tool, mainly in the Pre-SQL and Post-SQL statement. I see some discussions on this in the community and in many scenarios we require that. It will be great if we have this option.
There is a web hosted trial that anyone can have a hands on experiance with alteryx tutorials without even downoading the tool.
That's awesome... http://goo.gl/dpSoe2
It may be a nice idea to;
1) either start seperate "Alteryx-kaggle" instances with data sets specific to each kaggle competition so that anyone want to try out may have a go with those well known examples thru the Alteryx site,
2) Or even better have a partnership with kaggle so that anyone can just have it's own Alteryx trial per specific competition on the kaggle website...
I'm sure this will draw a lot of attention...
Rationale;
You'll immediately have a greater reach in Kaggle community, some data hobbiyists and cs, ie students and acedemics (which will eventually end up doing lot's of data blending when ther are going to be hired by top notch firms...
Idea:
As a method of deploying preprocessing and ML models it would be awesome to be able to convert a workflow to java...
Rationale:
models are needed to be deployed into Complex event processes or decision systems. Even for SAS there is a need to implement the datastep algorithms and procs to run in JVM.
Quickwin:
It is possible to convert a workflow into a PMML file and then use JMML package to convert that to Java. Yet the full workflow with all preprocessing alternatives and a series of ML methods may not be captured fully.
Competitor example:
For SAS case here is a similar solution: http://www.dullesresearch.com/carolina-features/
Idea:
In forecasting and in commercial/sme risk scoring there is a need for trying vast number of algebraic equations which is a very cumbersome prosess. Let's add symbolic regression as a new competitive capability.
Rationale:
Summations, ratios, power transforms and all combinations of a like are needed to be tested as new variables for a forecasting or prediction model. Doing this by hand manually is a though and long business... And there is always a possibility for one to skip a valuable combination.
Symbolic regression is a novel techinique for automatically generating algebraic equations with use of genetic programming,
In every evolution a variable is selected checked if the equation is discriminatitive of the target variable at hand. In every next step frequently observed variables will be selected more likely.
SR comparison with linear regression neural nets and random forests
Benefit for clients:
This method produces variables mainly with nonlinear relationships. It is a technique that will help in corporate/commercial/sme risk modelling, such that powerful risk models are generated from a hort list of B/S and P/L based algebraic equations.
There is potential use cases in algorithmic trading as well...
There are 3 very interesting world problems solved with symbolic regression here.
A very relevant thesis by sean Wouter is attached as a pdf document for your reading pleasure...
R side of things:
I've found Rgp package for genetic programming, here is a link.
Competition:
I haven't seen something similar in SAS, SPSS but there is this; http://www.nutonian.com/products/eureqa/
Also there is Bruce Ratner's page
Is it possible to add some color coding to the InDB tool. I am building out models InDB and I end up with a sea of navy blue icons. Maybe they could generally correspond to the other tools. For example the summary would be orange. Etc Formula Lime Green.
It would be great if I could save a tool and its configuration for future use. I'm sure this could be done now with a macro, and that's possibly how I'll do it.
The scenario is that we have numerous data inputs that require some finessing to import. Because the field headers are not in the first row, they aren't recognized accurately as comma delimited. But some of our fields also contain commas within the field, so the solution is to add a multi-field formula to replace things like ", Inc." with " Inc." and ", Ltd." with " Ltd."
But on occasion I find new text strings that need to be added to the formula, like ", Inc" (without the period) for instance.
I use this replacement technique with several workflows, so it would be great to change it just one time and have the other instances updated automatically.
Maybe in addition to our Favorites toolbar we could have a Custom or User toolbar where we could save tools along with their configuration.
When using ./*.csv for an input (relative path and wildcard), a preview does not show in the Properties area of the input tool. Can this be added?
I have the Show Properties Window selected, but it is not showing up on my screen. At first I thought it was just hidden and that I could just pull it back from being hidden, but I can't find it anywhere.
Thanks!
User | Likes Count |
---|---|
8 | |
6 | |
6 | |
5 | |
5 |