Upon accessing the project, your initial task is to upload pertinent data sets. These may encompass data utilized for training, testing, validation, production, or any other data integral to your project's scope and requirements.

Data upload

To upload data, we need to pass the file path and Tag.

To upload data to the project, you have the option to either directly provide a file path or pass a Pandas DataFrame.

If you are uploading data for the first time, it's necessary to configure the project details in the 'Project config'. This config will be used for all further Operations and cannot be changed once set.

You can achieve this and upload data through our SDK by utilizing the following commands:

config = {
            "project_type": "classification",  # The Prediction Type of your project (classification / regression)
            "unique_identifier": "id", # unique identifier for your project
            "true_label": "loan_status", # Target label
            "pred_label": "", # Define predicted value if you are looking to use Surrogate models for explainability.
            "feature_exclude": [],  # feature you are not using in your model or in the XAI model.
            "drop_duplicate_uid": True
        }

Tag = 'Training'  # Data is diffrentiated using Tag

‍

To upload the data into the project. This will also build the initial ML model.

NOTE: To upload model we first need to make sure the features going into model are already uploaded using data upload.

‍

project.upload_data('file_path','tag', config)

#Help on method upload_data
help(project.upload_data)

‍

Data can be uploaded to the project either directly with file or by passing Pandas DataFrame. 

‍

To see uploaded model info.:

project.models()

‍

Once the data is uploaded, you can also view the files, and file info through SDK. 

#Check the files that are uploaded in the project.
project.files()

Some additional functions:

#fetch the detailed analytics of each uploaded files individually
project.file_summary()

# fetch the list of uploaded files and data
project.files()

‍

NOTE: Above config function may throw error until Explainbility is generated, so please wait until the config() works.

‍

Once uploaded you can see your Project Config. Check feature exclude and include and match with your setting.

Additionally, AryaXAI AutoML framework may choose to remove additional columns if the missing values are greater than 30%. You can override this in the AutoML model settings and retrain the model

#To know all the settings: Data, Data Encoding & Model params
project.config()

‍

Once the initial data configuration is completed, you can upload additional data sets, such as testing, validation data, or you can add with your own tag without needing to reconfigure the settings.

Additionally, you can also delete the uploaded file:

#project.delete_file('file_name')

‍

To fetch all tags which user has uploaded

project.tags()

#you can view the data using:
project.tag_data('XGBoost_default_testdata')

‍

NOTE: "_test" are the tags generated automatically by AryaXAI post running the respective model on 'Test' data.