-
PythonノートブックからカスタムLightGBM（5-Fold）モデルをSaved Modelに登録する際のエラーについて
Dataikuコミュニティの皆様、こんにちは。 現在、Jupyter Notebook（Pythonコードレシピ）で作成したカスタムのLightGBMモデルを、Dataikuの「Saved Model（保存済みモデル）」としてフローに登録し、ScoreレシピやEvaluateレシピと連携させようとしています。 予測時（推論時）のカテゴリ型のマッピングのズレ防止、および5つのFoldのアンサンブル（平均）予測を内包させるため、MLflowの mlflow.pyfunc.PythonModel を使用して以下のようなカスタムラッパークラスを実装しました。 1. 参考にしたドキュメント 公式チュートリアルの「Step 3: ML Deploy…
-
Dark mode UI
Please introduce a dark mode for the entire DSS UI. It would help people with photosensitive eyes. Here is a render of how it can look. Hoping to hear from dataiku team soon. Cheers.
-
Dataiku GCP installation question(s)
Hello, newbie question regarding Dataiku GCP installation. Reference architecture states: https://doc.dataiku.com/dss/latest/cloud/gcp/reference-architectures/gke-gcs.html and https://github.com/sudsk/dataiku/blob/main/README.md Setup an AlmaLinux 8 GCE machine and make sure that: - you select the right Service Account -…
-
Timezone trigger using Python API deployment
Hi, I'm using the Dataiku API to deploy parameters in my scenario. My question is about the timezone in the scenario trigger. In my custom python, I specify, timezone : "Europe/Paris" and the dataiku front took this parameter like we saw on the second screenshot. I want to launch my scenario at 1:00 in the timezone…
-
Add a dataset from a data collection in Python
Hi, Is it possible in Dataiku to import a dataset from a Data Collection into a project, using the Python API ? (I mean from a recipe in the target project, not in the source project). I am looking for a way to do this via a Python recipe or through the Dataiku Python API client, without having to do it manually through…
-
Allow nested flow zones
Hi, I use flow zones a lot and appreciate the value. Why not extend the capability and allow nested flow zones, i.e. a flow zone within a flow zone? thx
-
Unexpected prediction behavior in API Designer Test Queries with missing feature values
Hello, I am currently testing an API endpoint created with Dataiku API Designer and noticed some prediction behaviors that I do not fully understand. Environment Dataiku DSS API Designer LightGBM prediction model Approximately 48 input features Observation I expected the API to return an error when required feature values…
-
Deep Learning Feature Importance
I'm using v13.3.2, and notice Feature Importance is not available for DL models … it that available in v14 ? Dataiku version used: 13.3.2
-
jobId from scenario execution
Hi. I created a scenario that executes a python recipe and builds a dataset. I tried to exact jobId within the recipe using get_custom_variables.get("jobId"). However, the approach is unreliable, as the code returns a value and times and sometimes it doesn't. The scenario is run using a time-based trigger. Could someone…
-
Oncrawl - Leveraging Dataiku for Predictive SEO as a Product Strategy
Team members: Vincent Terrasi, Product Director Elodie Mondon, Data Engineer Damien Garaud, Data Scientist Country: France Organization: Oncrawl Description: Enterprise SEO platform powered by the industry-leading SEO Crawler and Log Analyzer. Combine the power of technical SEO, machine learning and data science for…