-
時系列データの品質確認について
dataikuの時系列予測で、波形パターンを学習してモデル生成し、 テストデータとして波形データを入力して、そのテストデータにノイズが乗っているか否かを判定する、というようなことは可能でしょうか。 テストデータとして入力した波形が使えるデータか否かを判定する、データクレンジング的なことをやることが目的です。 可能な場合、手順をご教示頂けると助かります。 宜しくお願い致します。
-
Sampling Techniques for AutoML Lab Recipe
Hi - I am new to using the Dataiku modeling interface. I am looking to create a two class classification algorithm using the 'AutoML' feature in the Visual ML lab section. The data I am using has a large class imbalance (80% negative & 20% positive). Where/ how can I make sure the data is being rebalanced correctly? i.e.…
-
problem web logs analysis
Hello. I have a problem in the formation : the course ask us to do that * Cleaning * Remove four columns: br_width, br_height, sc_width and sc_height * Rename the column client_addr to ip_address * Clear invalid cells in the ip_address column for the IP address meaning * Rename the column location to url How I make those…
-
Error while redeploying model from a notebook
I am trying to build an adjusting model in Dataiku. I want to leverage the APIs to do the same. I already have a model deployed in the flow. After each data refresh, I want to check the model's performance, and if it is below a threshold, I want to retrain the model. Below is the code I am using if trained_model_MAPE >…
-
when training a model with a visual recipe, does dataiku fit the model on the entire dataset?
Context: * I have deployed a model to the flow * I want to retrain that model with its associated "train" recipe * I understand that the model's performance is evaluated using a test set or K-folds under a cross-validation strategy My question: after retraining the model using the "train" recipe, is the resulting new…
-
Load from Oracle to Vertica
Hi everyone, How can I load data from an Oracle database to Vertica without drop the destiny table each time that I run the process? Because I try to use the sync recipe but each time that I run the flow, dataiku recreate the table in Vertica instead of append the new rows. I already try with the configurations of free…
-
R recipe dkuWriteDataset "Missing Activity ID" Error
Hello, I am using R recipe on Dataiku v12.5.1. At the end of the code block I am using dkuWriteDataset function to write results to dataset. I am getting error below. [17:50:01] [INFO] [dku.utils] - > dkuWriteDataset(All_preds_cutoff_Final,"sow_output_deneme") [17:50:01] [INFO] [dku.utils] - Start writing table to file ...…
-
Ml Model Training Failed
Hello, I attempted to execute a partitioned XGBoost model using a Python 3.8 coding environment. The log files containing the details are enclosed in the attached .txt file. and also the train diagnosis in a zip file. Could you assist me in comprehending the underlying cause and suggest potential solutions to address this…
-
Incremental Load in Dataiku
Hi everyone, I want to create an incremental load in dataiku. For example, I have a transactional DB and need to move data in an ETL process to an Analytical DB, but I just want to read from de transactional DB the rows based on the Last_modified Date field. I don't want to read the entire Database each time that I run de…
-
API Python endpoint : can we call another endpoint part of another API service ?
My question is related to the use of the API python endpoint in the API Designer. Scenario : we have one API service 'service_A' in a DSS Project A and one API service 'service_B' in a DSS project B. service_A includes a python endpoint 'endpoint_A'. service_B includes a python endpoint 'endpoint_B'. Please, could you…
