Hi, While building MLmodels, is it possible to alter feature importance? I know the feature importance will be calculated internally and the charts can be viewed but for experimentation purpose I want to add in custom importance and see how the model output varies
Collaborating as a team while coding recipes is complex since there is only one branch per project in Dataiku flow. Operating system used: windows Operating system used: windows
i have to delete data in a data set based on some conditions. I want to achieve this via a auto trigger scenario maybe once in a day. Do you think this will be able to achieve in dataiku? Pls let me know
Hello everyone, I'm currently working with Dataiku version 12.6, and I'm looking to perform Principal Component Analysis (PCA) using the visual recipe available in the platform. My goal is to reduce my data to three principal components, but so far, I've only found the option to create a PCA with two components. Could…
Hello guys, I hope you're doing well. I need help with a situation. I created a timestamp with: asDate(now()) then I format the date to yyyy-MM-dd HH:mm:ss.SSSZ, and default timezone, that one I need. Then I parse the date to change from string to date with the same format and timezone. This still gives me UTC, when the…
I'm currently working with Dataiku version 12.6, and I'm looking to perform Principal Component Analysis (PCA) using the visual recipe available in the platform. My goal is to reduce my data to three principal components, but so far, I've only found the option to create a PCA with two components. Could someone guide me on…
Hi all - Is there a way to retain the exact formatting of fields in Dataiku when you export the data to excel? For example, I have a field called "Cost" and am using the format function to give it two decimal places, like 25.00. However, when I run the Prepare recipe and export it to Excel, the value is only showing up as…
I have a simple dataset containing 1 row and about 20 columns. Each column represents a Boolean value of whether or not a particular threshold has been breached. If the result is true for any of the 20 columns, then a message is sent to a designated MS Teams Channel that a breach has occurred. I would like to supplement…
Hello community, I have a SQL query; it is working fine. I have 2 inputs with redshift tables. I have added 2 more columns in one of the table. Now, when I try to add those into the query, I am getting validation error and saying those columns are not available in the table. In fact, they are. The schema is consistent.…
Hi, I am working on building a prediction model in Dataiku. I am building models in the lab, and I'm trying to build a dashboard that can compare different versions of the model in LAB. I'm accessing different versions of the model and comparing the different aspects of the model. I'm accessing the Lab model as follows.…
Create an account to contribute great content, engage with others, and show your appreciation.
