Solved: Re: Can't continue on trial

Q: How does DataRobot select the right blueprint for a given problem?

DataRobot doesn't "select" blueprints it creates them dynamically based on the dataset that you give it and the target you specify. Data scientists at DataRobot have spent over 7 years embedding their data science knowledge and best practices into this blueprint development process. Roughly hundreds of blueprints are created for each project. For most data science problems, you can come up with multiple viable approaches without knowing which ones will perform the best. DataRobot uses the Leaderboard to compare blueprints and identify the best ones.

Q: Can I see the effect of some of the DataRobot-created features?

DataRobot shows the effect of some of the engineered variables through the Insights tab. Both the Tree-Based Variable Importance as well as the Variable Effects sections show the engineered variables used by the models.

Q: Is it possible for users to change the preprocessing method?

Yes, you can change some of the preprocessing methods used within DataRobot on the Advanced Tuning tab of each model. If you have a custom preprocessing step that you want to include, you could do it outside of DataRobot and load in the processed dataset. This becomes seamless when using the DataRobot R/Python clients.

Q: What do asterisks on the Leaderboard metrics mean?

The asterisks indicate that the scores are computed from in-sample training data.

Q: What does a snowflake icon mean near a model in the Leaderboard?

This indicates a frozen run. A frozen run of a model is a retrained version of another model, where hyperparameters from the other model are frozen and the model is simply retrained on more observations.

Q: What does a snowflake icon mean near a model in the Leaderboard?

This indicates a frozen run. A frozen run of a model is a retrained version of another model, where hyperparameters from the other model are frozen and the model is simply retrained on more observations.

Q: Why didn't cross-validation automatically run on my dataset?

Cross-validation has a hard cutoff at 50,000 rows; if the dataset is greater than or equal to 50,000 rows, DataRobot does not run cross-validation automatically. If you require automatic cross-validation, use a dataset with fewer than 50,000 rows. If you need to get cross-validation values for a specific model, on the Leaderboard for that model click Run (under the Cross Validation column). If the dataset is larger than 800MB, DataRobot will use TVH. (Cross-validation is generally useful for smaller datasets where you would not otherwise have enough useful data using TVH.)

Abdulkadir

Hi, In the ML Development part of trial, I uploaded my data and selected the prediction column. When I press the Start button it directs me to partitioning part of advanced options. Even I tried many other options I can not continue on trial. Is it about some restrictions on demo platform? Could you help me?

lhaviland

Hi Abdulkadir - sorry you're having problems! A couple of quick questions while we figure this out:

- do you see any messages while doing this? If yes, what is shown?

- have you tried the datasets provided with the in-app use cases? Do those work for you? If you haven't, could you try one out and let us know?

Abdulkadir

Hi, There is no message, just directing me to advanced options->Partitioning part of the screen and Partitioning is highlighted in red. I also tried other datasets provided.like Detect Credit Card Transaction Fraud which uses Pathfinder_Training_Transaction-Fraud.csv. But the result is the same. Thanks

jeetu.kukreja1

Hi,

Once you click the Start button, do you see the activity on the right panel regarding analysis of the dataset and progress of the model ranking process?

Would be very helpful if you could attach some screenshots of the pages that you are seeing.

Thanks!

Abdulkadir

Hi,

When I click the start button there is no activity on the right panel.
I've uploaded my screen video.

Thanks..

jeetu.kukreja1

Thanks. That is weird. I was able to click start on that same dataset without issues. Could you try a couple of things

1. creating a fresh project via the ML Development option

2. Opening the Developer Tools for your browser and sharing what you see in the Console logs (in case there are any errors)

3. Trying this scenario from an Incognito mode browser window to eliminate any issues due to browser side UI caching

Abdulkadir

Thanks @jeetu.kukreja1

In developer tools console log there were some errors. I tried it on another browser and it worked.

lhaviland

@Abdulkadir oh! what browser were you using, and what are you using now? in general, DataRobot should be run on Chrome; were you not on Chrome?

Abdulkadir

I was working on chrome. Then I switched to Edge and it worked.