Python Guide

This is our Python Guide for ML development. See Tables. Below


Table 1. vai_toolkit.client()

Method Description
client.create_organization() This method is used to create organization for user.
client.update_name() This method is used to update user's first name and last name.
client.update_password() This method is used to update user password.


Table 2. vai_toolkit.pipeline()

Method Description
pipeline.create() This method is used to create pipeline of provided user.
pipeline.create_alert() This method is used to create alert for given pipeline of user.
pipeline.create_table() This method is used to create table for given pipeline of user.
pipeline.delete_pipeline() This method is used to delete pipeline when there is no dataset in pipeline.
pipeline.delete_table() This method is used to delete table for given pipeline of user.
pipeline.get_table() This method is used to get tables of given pipeline of user.
pipeline.list_alerts() This method is used to get the list of alerts for given pipeline of user.
pipeline.set_default_table() This method is used to set default table for given pipeline of user.
pipeline.update_table() This method is used to update table name for given pipeline of user.



Table 3. vai_toolkit.data()

Method Description
data.delete_data() This method is used to delete dataset data for given range in pipeline of user.
data.download_csvs() This method is used to download dataset for given pipeline of user.
data.list_labels() This method is used to get labels for given pipeline of user.
data.set_labels() This method is used to set labels for given pipeline of user.
data.set_relations() This method is used to set relations between tables of given pipeline of user.
data.upload_csv() This method is used to upload csv for given pipeline of user
data.upload_data() This method is used to upload data for given pipeline of user.



Table 4. vai_toolkit.model()

Method Description
model.explain() This method is used to get explanability values of specific record for given pipeline of user with options "NEXT_SERIES" or "MIXED" or "NEXT_LINK", if "NEXT_SERIES" then get explanability values of specific record with timeseries on for given pipeline of user and if "MIXED" then get explanability values of specific record with timeseries off for given pipeline of user.
model.history() This method is used to get history of given model.
model.predict() This method is used to get prediction of table count with different model two options available "NEXT_SERIES" and "NEXT_LINK".
model.train() This method is used to train model with options "NEXT_SERIES", "MIXED" and "NEXT_LINK", if "NEXT_SERIES" then model will be trained with timeseries on for given pipeline of user and if "MIXED" then model will be trained with timeseries off for given pipeline of user.
model.delete() This method is used to delete given model.
model.retrain() This method is used to retrain given model.


vai_toolkit.client

create_organization(user_secret, name, users)

This method is used to create organization for user.

Parameters:
  • user_secret ({string}) –

    It is the user secret key.

  • name ({string}) –

    It is name of organization to create

  • users ({obj}) –

    It is the object consisting of keys as the emails and values as the role to be assigned to that specific email. Eg., { "john.deo@gmail.com" :"ADMIN" }
Returns:
  • type( object ) –

    Created organization object.
Example 





from vai_toolkit import client 

org_name  = "ORGANIZATION_NAME"
users = { 'john.deo@gmail.com' : 'ADMIN' }
user_secret = 'USER_SECRET_KEY'

res = client.create_organization(user_secret, org_name, users)
print(res)
Output 
{
    "user": "61efccd707170700131a87v2",
    "name": "ORGANIZATION_NAME",
    "datasetS3TotalSize": 0,
    "isDeleted": false,
    "createdAt": "2023-07-19T05:34:13.391Z",
    "updatedAt": "2023-07-19T05:34:13.391Z",
    "_id": "64b775d5f0a90246a2a2c31cd"
}

update_name(user_secret, first_name, last_name)

This method is used to update user's first name and last name.

Parameters:
  • user_secret ({string}) –

    It is the user secret key.

  • first_name ({string}) –

    User first name value

  • last_name ({string}) –

    User last name value
Returns:
  • type( object ) –

    User object with updated name.
Example 





from vai_toolkit import client 

user_secret = 'USER_SECRET_KEY'
first_name = 'John'
last_name = 'Deo'

updated_pass = client.update_name(user_secret ,first_name ,last_name )
print(updated_pass)
Output 
{
    "email": "john.deo@gmail.com",
    "_id": "61efccd707170700131a87c2",
    "firstName": "John",
    "lastName": "Deo",
}

update_password(user_secret, new_password)

This method is used to update user password.

Parameters:
  • user_secret ({string}) –

    It is the user secret key.

  • new_password ({string}) –

    User new password value
Returns:
  • type( object ) –

    Response object.
Example 





from vai_toolkit import client 
user_secret = 'USER_SECRET_KEY'
new_password = 'NEW_SECURE_PASSWORD'

res = client.update_password(user_secret, password)

print(res)
Output 
{
    "message": "Password changed successfully!.."
}



vai_toolkit.pipeline

create(user_secret, title, type)

This method is used to create pipeline of provided user.

Parameters:
  • user_secret ({string}) –

    It is the user secret key.

  • title ({string}) –

    It is the name of pipeline to assign.

  • type ({string}) –

    It is the type of pipeline. it could be only 'TABULAR' or 'GRAPH'
Returns:
  • type( object ) –

    Created pipeline response object.
Example 





from vai_toolkit import pipeline

title  = "Tabular data"
type = "TABULAR"
user_secret  =  'USER_SECRET_KEY'

res = pipeline.create(user_secret, title, type)
print(res)
Output 
{
    '_id': '65017bdc104c04cd9663ba05', 
    'title': 'Tabular data', 
    'apiKey': 'd2159682-aecc-49cf-ba7d-a8bfcc828d5e-1694596060912'
}

create_alert(user_secret, pipeline_key, settings)

This method is used to create alert for given pipeline of user.

Parameters:
  • user_secret ({string}) –

    It is the user secret key.

  • pipeline_key ({string}) –

    It is the pipeline key.

  • settings ({obj}) –

    It is data object to create alerts.
Returns:
  • type( object ) –

    Created alert response object.
Example 





from vai_toolkit import pipeline

user_secret  =  'USER_SECRET_KEY'
pipeline_key =  'PIPELINE_KEY'
data ={
    "name":"test",
    "type":"DATASET",
    "from": "1/1/2023", 
    "to": "12/31/2023",
    "columnFields": ["race",  "hours-per-week", "age"],
    "week": 2,  
    "thresholdLimit": 49
}

res = pipeline.create_alert(user_secret, pipeline_key ,data)
print(res)
Output 
{
    'name': 'test', 
    'type': 'DATASET', 
    'pipelineId': '65017bdc104c04cd9663ba05', 
    'modelId': None, 
    'creator': '62c56baeb4fbc200139daed0', 
    'from': '1/1/2023', 
    'to': '12/31/2023', 
    'columnFields': ['race', 'hours-per-week', 'age'], 
    'week': 2, 
    'thresholdLimit': 49, 
    'timeWindow': {
        'window': None, 
        'startTime': None, 
        'endTime': None, 
        'column': None, 
        'dates': [], 
        'times': [], 
        'isHoliday': None, 
        'holidays': [], 
        'step': None
    }, 
    'createdAt': '2023-09-13T09:13:10.080Z', 
    'updatedAt': '2023-09-13T09:13:10.080Z', 
    '_id': '65017d26104c04cd9663c23e'}

create_table(user_secret, pipeline_key, name)

This method is used to create table for given pipeline of user.

Parameters:
  • user_secret ({string}) –

    It is the user secret key.

  • pipeline_key ({string}) –

    It is the pipeline key.

  • name ({string}) –

    It is the name of table.
Returns:
  • type( object ) –

    Created alert response object.
Example 





from vai_toolkit import pipeline

user_secret  =  'USER_SECRET_KEY'
pipeline_key =  'PIPELINE_KEY'
name = 'TABLE NAME'

res = pipeline.create_table(user_secret, pipeline_key ,data)
print(res)
Output 
{
        'success': True,
        'table': {'name': 'Table Name','pipeline': 'Pipeline id', '_id': 'Table Id'}
    }

delete_pipeline(user_secret, pipeline_key)

This method is used to delete pipeline when there is no dataset in pipeline

Parameters:
  • user_secret ({string}) –

    It is the user secret key.

  • pipeline_key ({string}) –

    It is the pipeline key.
Returns:
  • type( object ) –

    Created alert response object.
Example 





from vai_toolkit import pipeline

user_secret  =  'USER_SECRET_KEY'
pipeline_key =  'PIPELINE_KEY'

res = pipeline.delete_pipeline(user_secret, pipeline_key )
print(res)
Output 
{
        message: "Pipeline deleted successfully!.."
}

delete_table(user_secret, pipeline_key, name)

This method is used to delete table for given pipeline of user.

Parameters:
  • user_secret ({string}) –

    It is the user secret key.

  • pipeline_key ({string}) –

    It is the pipeline key.

  • name ({string}) –

    It is the name of table.
Returns:
  • type( str ) –

    Created alert response object.
Example 





from vai_toolkit import pipeline

user_secret  =  'USER_SECRET_KEY'
pipeline_key =  'PIPELINE_KEY'
name = 'TABLE NAME TO DELETE'

res = pipeline.delete_table(user_secret, pipeline_key ,name)
print(res)
Output 
Table deleted successfully.

get_table(user_secret, pipeline_key)

This method is used to get tables of given pipeline of user.

Parameters:
  • user_secret ({string}) –

    It is the user secret key.

  • pipeline_key ({string}) –

    It is the pipeline key.
Returns:
  • type( object ) –

    Created alert response object.
Example 





from vai_toolkit import pipeline

user_secret  =  'USER_SECRET_KEY'
pipeline_key =  'PIPELINE_KEY'

res = pipeline.get_table(user_secret, pipeline_key )
print(res)
Output 
[
    {
        name : 'TABLE NAME',
        _id : 'Table id',
        pipeline : 'Pipeline id'
    },
    {
        name : 'TABLE NAME 2',
        _id : 'Table id',
        pipeline : 'Pipeline id'
    },
]

list_alerts(user_secret, pipeline_key)

This method is used to get the list of alerts for given pipeline of user.

Parameters:
  • user_secret ({string}) –

    It is the user secret key.

  • pipeline_key ({string}) –

    It is the pipeline key.
Returns:
  • type( list ) –

    List of all alerts objects.
Example 





from vai_toolkit import pipeline

user_secret  =  'USER_SECRET_KEY'
pipeline_key =  'PIPELINE_KEY'

res = pipeline.list_alerts(user_secret, pipeline_key)
print(res)
Output 
[
    {
        'timeWindow': {
            'window': None, 
            'startTime': None, 
            'endTime': None, 
            'column': None, 
            'dates': [], 
            'times': [], 
            'isHoliday': None, 
            'holidays': [], 
            'step': None
            }, 
            '_id': '65017d26104c04cd9663c23e', 
            'name': 'test', 
            'type': 'DATASET', 
            'pipelineId': '65017bdc104c04cd9663ba05', 
            'modelId': None, 
            'creator': '62c56baeb4fbc200139daed0', 
            'from': '1/1/2023', 
            'to': '12/31/2023', 
            'columnFields': ['race', 'hours-per-week', 'age'], 
            'week': 2, 
            'thresholdLimit': 49, 
            'createdAt': '2023-09-13T09:13:10.080Z', 
            'updatedAt': '2023-09-13T09:13:10.080Z'
    }
]

set_default_table(user_secret, pipeline_key, name)

This method is used to set default table for given pipeline of user.

Parameters:
  • user_secret ({string}) –

    It is the user secret key.

  • pipeline_key ({string}) –

    It is the pipeline key.

  • name ({string}) –

    It is the name of table.
Returns:
  • type( str ) –

    Created alert response object.
Example 





from vai_toolkit import pipeline

user_secret  =  'USER_SECRET_KEY'
pipeline_key =  'PIPELINE_KEY'
name = 'TABLE NAME TO SET DEFAULT'

res = pipeline.set_default_table(user_secret, pipeline_key ,name)
print(res)
Output 
Default table successfully.

update_table(user_secret, pipeline_key, old_name, new_name)

This method is used to update table name for given pipeline of user.

Parameters:
  • user_secret ({string}) –

    It is the user secret key.

  • pipeline_key ({string}) –

    It is the pipeline key.

  • old_name ({string}) –

    It is the name of current name of table.

  • new_name ({string}) –

    It is the new name of table to update.
Returns:
  • type( str ) –

    Created alert response object.
Example 





from vai_toolkit import pipeline

user_secret  =  'USER_SECRET_KEY'
pipeline_key =  'PIPELINE_KEY'
old_name = 'TABLE NAME'
new_name = 'NEW TABLE NAME'

res = pipeline.update_table(user_secret, pipeline_key ,old_name, new_name)
print(res)
Output 
Name updated successfully.


vai_toolkit.data

delete_data(user_secret, pipeline_key, from_date, to_date, table_name='')

This method is used to delete dataset data for given range in pipeline of user.

Parameters:
  • user_secret ({string}) –

    It is the user secret key.

  • pipeline_key ({string}) –

    It is the pipeline key.

  • from_date ({string}) –

    It is from date value in 'MM-DD-YYYY' format.

  • to_date ({string}) –

    It is to date value in 'MM-DD-YYYY' format.

  • table_name ({string}, default: '' ) –

    It is name of table to delete data.
Returns:
  • type( object ) –

    Get response message
Example 





from vai_toolkit import data

user_secret  =  'USER_SECRET_KEY'
pipeline_key =  'PIPELINE_KEY'
from_date = "09/06/2023" # From Date
to_date = "09/06/2023" # From Date
table='Table 2'

res = data.delete_data(user_secret, pipeline_key,  from_date, to_date, table )

print(res)
Output 
{
    "message": "Deleted successfully!.."
}

download_csvs(user_secret, pipeline_key, to_file, from_date='', to_date='', table_name='')

This method is used to download dataset for given pipeline and table of user.

Parameters:
  • user_secret ({string}) –

    It is the user secret key.

  • pipeline_key ({string}) –

    It is the pipeline key.

  • to_file ({string}) –

    It is file path in which store all csvs.

  • from_date ({string}, default: '' ) –

    It is from date value in 'MM-DD-YYYY' format.

  • to_date ({string}, default: '' ) –

    It is to date value in 'MM-DD-YYYY' format.

  • table_name ({string}, default: '' ) –

    It is name of table to download data.
Returns:
  • type( object ) –

    Response message.
Example 





from vai_toolkit import data

user_secret  =  'USER_SECRET_KEY'
pipeline_key =  'PIPELINE_KEY'
from_date = "09/01/2023" # From Date
to_date = "09/11/2023" # From Date
path = "./new2.zip" #Path
table='Table 2'

res = data.download_csvs(user_secret, pipeline_key, path, from_date=from_date, to_date=to_date,table_name=table)

print(res)

list_labels(user_secret, pipeline_key, table_name='')

This method is used to get labels for given pipeline and table of user.

Parameters:
  • user_secret ({string}) –

    It is the user secret key.

  • pipeline_key ({string}) –

    It is the pipeline key.

  • table_name ({string}, default: '' ) –

    It is name of table to download data.
Returns:
  • type( object ) –

    List of all labels.
Example 





from vai_toolkit import data

user_secret  =  'USER_SECRET_KEY'
pipeline_key =  'PIPELINE_KEY'

table_name = 'Table 2'
res = data.list_labels(user_secret, pipeline_key,table_name =table_name  )

print(res)
Output 
{
    'success': True, 
    'details': {
        'Table Name': 'Table 2', 
        'Column Names': ['id', 'Capital Gain'], 
        'Column Types': ['CATEGORY', 'CATEGORY'], 
        'Column Labels': [None, None]
    }
}

set_labels(user_secret, pipeline_key, labels, d_types, table_name='')

This method is used to set labels for given pipeline and table of user.

Parameters:
  • user_secret ({string}) –

    It is the user secret key.

  • pipeline_key ({string}) –

    It is the pipeline key.

  • labels ({object}) –

    It is dictionary containing the keys as the column of provided pipeline and values are Input, Protected and Output of that column as column label.

  • d_types ({object}) –

    It is dictionary containing the keys as the column of provided pipeline and values are NUMBER, STRING, and CATEGORICAL of that column as column type.

  • table_name ({string}, default: '' ) –

    It is name of table to download data.
Returns:
  • type( object ) –

    Get response with added labels.
Example 





from vai_toolkit import data

user_secret  =  'USER_SECRET_KEY'
pipeline_key =  'PIPELINE_KEY'
columnLabels = { "id" : 'Input' ,"Capital Gain" : 'Output'  } # Column Labels
columnTypes ={ "id" : 'CATEGORY',"Capital Gain" : 'CATEGORY' } # Column Types
table_name = 'Table 2'

res = data.set_labels(user_secret, pipeline_key, columnLabels, columnTypes,table_name)
print(res)
Output 
{
    'tableName': 'dim_item',
    'columnLabels': [None, 'Output', None, None, 'Input', None, None, None, None],
    'columnNames': ['A1', 'DimItemkey', 'RestaurantCustomerName', 'PLU', 'ItemDescription', 'ItemSubcategory', 'ItemCategory', 'ItemReportingCategory', 'ItemFNBCategory'],
    'columnTypes': ['CATEGORY', 'CATEGORY', 'CATEGORY', 'CATEGORY', 'STRING', 'CATEGORY', 'CATEGORY', 'CATEGORY', 'CATEGORY'],
    'pipeline': 'pipeline id',
    '_id': 'Table id'
}

set_relations(user_secret, pipeline_key, primary_keys_obj, to_table, relation_array)

This method is used to set relations between tables of given pipeline of user.

Parameters:
  • user_secret ({string}) –

    It is the user secret key.

  • pipeline_key ({string}) –

    It is the pipeline key.

  • primary_keys_obj ({string}) –

    It is an object where key represents the name of table, and it's value is considered as primary key column.

  • to_table ({string}) –

    It is the table name of which you want to set main table to bind other tables.

  • relation_array ({array}) –

    It is an array consists of relation object, where object is { "from":"From table name", "toColumn": "Where column of to table want to bind"}.
Returns:
  • type( object ) –

    Get response message
Example 





from vai_toolkit import data

user_secret  =  'USER_SECRET_KEY'
pipeline_key =  'PIPELINE_KEY'
primary_keys_obj = {
    "dim_item": "PLU",
    "check": "CheckKey",
    "check_item": "CheckItemKey"
}
to_table =  "check_item"
relation_array =  [
    {
        "from": "dim_item",
        "toColumn": "ItemNumber"
    },
    {
        "from": "check",
        "toColumn": "CheckKey"
    }
]
res = data.set_relations(user_secret, pipeline_key, primary_keys_obj, to_table, relation_array)

print(res)
Output 
{
    "message": "Updated successfully."
}

upload_csv(user_secret, pipeline_key, path, table_name)

This method is used to upload csv for given pipeline and table of user.

Parameters:
  • user_secret ({string}) –

    It is the user secret key.

  • pipeline_key ({string}) –

    It is the pipeline key.

  • path ({string}) –

    It is the path value of csv file.

  • table_name ({string}) –

    It is name of table in which you want to upload.
Returns:
  • type( object ) –

    Response message.
Example 





from vai_toolkit import data

user_secret  =  'USER_SECRET_KEY'
pipeline_key =  'PIPELINE_KEY'
table_name = 'Table 1'

res = data.upload_csv(user_secret, pipeline_key, "./09-11-2023.csv", table_name)
print(res)
Output 
Dataset uploaded succesfully.

upload_data(user_secret, pipeline_key, data, date, time, new_columns=False, duplicates=False, new_categories=False, table_name='')

This method is used to upload data for given pipeline and table of user.

Parameters:
  • user_secret ({string}) –

    It is the user secret key.

  • pipeline_key ({string}) –

    It is the pipeline key.

  • data ({obj}) –

    It is data object to upload data.

  • date ({array}) –

    It is list of dates value in 'MM-DD-YYYY' format.

  • time ({array}) –

    It is list of time value in 'HH:MM:SS' format.

  • new_columns ({boolean}, default: False ) –

    It is boolean value for add new columns either 'True' or 'False'.

  • duplicates ({boolean}, default: False ) –

    It is boolean value either 'True' or 'False'.

  • new_categories ({boolean}, default: False ) –

    It is boolean value for add new categories either 'True' or 'False'.

  • table_name ({string}, default: '' ) –

    It is name of table.
Returns:
  • type( object ) –

    Uploaded data object in response.
Example 





from vai_toolkit import data

user_secret  =  'USER_SECRET_KEY'
pipeline_key =  'PIPELINE_KEY'
uploadData = { "id": [11111, 1], "Capital Gain": [10000, 15000] }   # Columns data
dates = ["09-06-2023", "09-06-2023"]  # Dates
times = ["11:08:50", "11:09:50" ]  # Times
table_name =  'Table 2'

res = data.upload_data(user_secret, pipeline_key, uploadData, dates, times, new_columns = True, duplicates = True,new_categories =  True ,table_name=table_name)
print(res)
Output 
{
    'success': True, 
    'data': '{
        "dates":["09-06-2023"]
    }', 
    'warning': 'We insert the duplicate data if we found.'}


vai_toolkit.model

delete(user_secret, pipeline_key, model_key)

This method is used to delete model of provided pipeline.

Parameters:
  • user_secret ({string}) –

    It is the user secret key.

  • pipeline_key ({string}) –

    It is the pipeline key.

  • model_key ({string}) –

    It is the model key.
Returns:
  • type( object ) –

    Success response message.
Example 





from vai_toolkit import pipeline

user_secret  =  'USER_SECRET_KEY'
pipeline_key =  'PIPELINE_KEY'
model_key = 'MODEL_KEY'

res = model.delete(user_secret, pipeline_key ,model_key)
print(res)
Output 
Model deleted successfully.

explain(user_secret, pipeline_key, model_key, datasetData=None, dataset=None, from_date=None, to_date=None, config=None, option='')

This method is used to get explanability values of specific record for given pipeline of user with two options "NEXT_SERIES" or "MIXED", if "NEXT_SERIES" then get explanability values of specific record with timeseries on for given pipeline of user and if "MIXED" then get explanability values of specific record with timeseries off for given pipeline of user.

Parameters:
  • user_secret ({string}) –

    It is the user secret key.

  • pipeline_key ({string}) –

    It is the pipeline key.

  • model_key ({string}) –

    It is model key.
Other parameters:
  • datasetData ({string}) –

    It is dataset data value passed if the option is "MIXED" only.

  • dataset ({string}) –

    It is dataset value passed if the option is "MIXED" only.

  • from_date ({string}) –

    It is from date string passed if the option is "NEXT_SERIES" only.

  • to_date ({string}) –

    It is to date string passed if the option is "NEXT_SERIES" only.

  • config ({object}) –

    It is the config object if the option is "NEXT_LINK" only..

  • option ({string}) –

    It could be only "NEXT_SERIES" or "MIXED".
Returns:
  • type( object ) –

    Response message.
Example 





from vai_toolkit import model

user_secret = 'USER_SECRET_KEY'
pipeline_key = 'PIPELINE_KEY'
model_key ='MODEL_KEY'

from_date = '03/01/2023'
to_date = '05/31/2023'
option='NEXT_SERIES'

res = model.explain(user_secret, pipeline_key, model_key ,from_date=from_date,to_date=to_date,option=option)
print(res)




from vai_toolkit import model

user_secret = 'USER_SECRET_KEY'
pipeline_key = 'PIPELINE_KEY'
model_key ='MODEL_KEY'

datasetData ={
    "hours-per-week": 35,
    "age" : 40,
    "loan-approved":0,
    "capital-gain": 0,
    "capital-loss": 0,
    "education": "HS-grad",
    "education-num": 9,
    "marital-status": "Never-married",
    "native-country": "United-States",
    "occupation": "Transport-moving",
    "race": "Non-white",
    "relationship": "Not-in-family",
    "sex": "Male",
    "workclass": "Private"
}
dataset ="08-31-2023"

res = model.explain(user_secret, pipeline_key,model_key, datasetData=datasetData,dataset=dataset, option="MIXED" )
print(res)



from vai_toolkit import model

user_secret = 'USER_SECRET_KEY'
pipeline_key = 'PIPELINE_KEY'
model_key ='MODEL_KEY'
config ={
        "seedNodeNameCol" : 'ItemDescription',
        "prediction" : 10,
        "seedNodeNames" : ["1","2"],
        "refNodeDict" : {
            "GuestCount" :0,
            "CheckOpen" : "2023-09-08T05:14:05.283Z",
}}
option ='NEXT_LINK'

res = model.explain(user_secret, pipeline_key, model_key, config=config, option=option)
print(res)
Output 
{
    "data": {
        "errorMessage": "",
        "traceback": "",
        "data": {
            "y": [
                {
                    "date": "01-16-2022",
                    "counts": "[{"tableCount":22.3249225616,"time":11},{"tableCount":15.3308525085,"time":12},{"tableCount":6.0051803589,"time":13},{"tableCount":6.4271569252,"time":14},{"tableCount":3.3630287647,"time":15},{"tableCount":2.7648005486,"time":16},{"tableCount":5.4221305847,"time":17},{"tableCount":21.0307579041,"time":18},{"tableCount":17.9799308777,"time":19},{"tableCount":11.0987033844,"time":20},{"tableCount":7.7918105125,"time":21}]"
                },
                {
                    "date": "01-17-2022",
                    "counts": "[{"tableCount":4.3347301483,"time":11},{"tableCount":13.7139158249,"time":12},{"tableCount":22.5580196381,"time":13},{"tableCount":17.7829666138,"time":14},{"tableCount":10.4020938873,"time":15},{"tableCount":2.7406756878,"time":16},{"tableCount":4.4894299507,"time":17},{"tableCount":3.9393897057,"time":18},{"tableCount":2.5602560043,"time":19},{"tableCount":5.2975172997,"time":20},{"tableCount":24.4320220947,"time":21}]"
                },
                {
                    "date": "01-18-2022",
                    "counts": "[{"tableCount":25.5556297302,"time":11},{"tableCount":21.6066265106,"time":12},{"tableCount":16.9466266632,"time":13},{"tableCount":13.0571289062,"time":14},{"tableCount":22.881313324,"time":15},{"tableCount":34.0851211548,"time":16},{"tableCount":28.8900508881,"time":17},{"tableCount":23.1612758636,"time":18},{"tableCount":13.7236795425,"time":19},{"tableCount":12.1094703674,"time":20},{"tableCount":8.7841835022,"time":21}]"
                },
                {
                    "date": "01-19-2022",
                    "counts": "[{"tableCount":6.8754734993,"time":11},{"tableCount":9.8974742889,"time":12},{"tableCount":29.4479675293,"time":13},{"tableCount":33.2332077026,"time":14},{"tableCount":26.8839187622,"time":15},{"tableCount":22.5158405304,"time":16},{"tableCount":21.4588184357,"time":17},{"tableCount":31.3786964417,"time":18},{"tableCount":41.555103302,"time":19},{"tableCount":38.0847129822,"time":20},{"tableCount":33.7989006042,"time":21}]"
                },
                {
                    "date": "01-20-2022",
                    "counts": "[{"tableCount":21.2980632782,"time":11},{"tableCount":16.9026260376,"time":12},{"tableCount":9.3885774612,"time":13},{"tableCount":5.1352725029,"time":14},{"tableCount":8.3074045181,"time":15},{"tableCount":26.5341453552,"time":16},{"tableCount":32.1234817505,"time":17},{"tableCount":29.40417099,"time":18},{"tableCount":25.5267181396,"time":19},{"tableCount":18.9728393555,"time":20},{"tableCount":21.9795360565,"time":21}]"
                },
                {
                    "date": "01-21-2022",
                    "counts": "[{"tableCount":26.9185009003,"time":11},{"tableCount":23.7499847412,"time":12},{"tableCount":19.7978839874,"time":13},{"tableCount":10.8758878708,"time":14},{"tableCount":9.7679300308,"time":15},{"tableCount":4.2197132111,"time":16},{"tableCount":0.0849183798,"time":17},{"tableCount":2.3076190948,"time":18},{"tableCount":18.9048557281,"time":19},{"tableCount":22.7209529877,"time":20},{"tableCount":19.5034141541,"time":21}]"
                },
                {
                    "date": "01-22-2022",
                    "counts": "[{"tableCount":16.1986370087,"time":11},{"tableCount":9.5400733948,"time":12},{"tableCount":11.5875263214,"time":13},{"tableCount":16.3533973694,"time":14},{"tableCount":13.4710626602,"time":15},{"tableCount":9.5767259598,"time":16},{"tableCount":3.3179194927,"time":17},{"tableCount":6.832379818,"time":18},{"tableCount":5.7702031136,"time":19},{"tableCount":3.5545077324,"time":20},{"tableCount":4.9158325195,"time":21}]"
                }
            ],
            "x": "",
            "note": "predicting without explanation"
        }
    }
}

 {
    "success": true,
    "output": {
        "loan-approved": {
            "inputs": {
                "age": [
                    0.056
                ],
                "capital-loss": [
                    0
                ],
                "education": [
                    -0.037
                ],
                "education-num": [
                    -0.008
                ],
                "hours-per-week": [
                    0.113
                ],
                "native-country": [
                    -0.006
                ],
                "occupation": [
                    -0.019
                ],
                "relationship": [
                    0.05
                ],
                "workclass": [
                    -0.011
                ]
            },
            "outputs": [
                0.138
            ]
        }
    },
    "payload": {
        "model": "dev/models/5e99761f522f057aeb4ed3c4/64412fa37a5a840c036a3fce/64a526df900b514e57881ef5_0.1_100_1000_1_17",
        "x": {
            "age": {
                "type": "NUMBER",
                "values": [
                    48
                ]
            },
            "capital-loss": {
                "type": "CATEGORY",
                "values": [
                    0
                ]
            },
            "hours-per-week": {
                "type": "NUMBER",
                "values": [
                    60
                ]
            },
            "workclass": {
                "type": "CATEGORY",
                "values": [
                    "Self-emp-not-inc"
                ]
            },
            "education": {
                "type": "CATEGORY",
                "values": [
                    "HS-grad"
                ]
            },
            "education-num": {
                "type": "CATEGORY",
                "values": [
                    9
                ]
            },
            "occupation": {
                "type": "CATEGORY",
                "values": [
                    "Craft-repair"
                ]
            },
            "relationship": {
                "type": "CATEGORY",
                "values": [
                    "Husband"
                ]
            },
            "native-country": {
                "type": "CATEGORY",
                "values": [
                    "England"
                ]
            }
        },
        "y": {
            "loan-approved": {
                "type": "CATEGORY"
            }
        },
        "file_paths": [
            "dev/dataset-files/5e99761f522f057aeb4ed3c4/64412fa37a5a840c036a3fce/64412fd67a5a840c036a40fd/04-14-2023.csv"
        ]
    },
    "response": {
        "StatusCode": 200,
        "ExecutedVersion": "$LATEST",
        "Payload": "{"errorMessage": "", "traceback": "", "data": {"loan-approved": {"inputs": {"age": [0.056], "capital-loss": [0.0], "education": [-0.037], "education-num": [-0.008], "hours-per-week": [0.113], "native-country": [-0.006], "occupation": [-0.019], "relationship": [0.05], "workclass": [-0.011]}, "outputs": [0.138]}}}"
    }
}

history(user_secret, pipeline_key, model_key, limit=5)

This method is used to get history of given model.

Parameters:
  • user_secret ({string}) –

    It is the user secret key.

  • pipeline_key ({string}) –

    It is the pipeline key.

  • model_key ({string}) –

    It is the model key.

  • limit ({number}, default: 5 ) –

    It is limit used to specify a particular constraint for retrieving history data.
Returns:
  • type( object ) –

    Get response containing input and output.
Example 





from vai_toolkit import model

user_secret = 'USER_SECRET_KEY'
pipeline_key = 'PIPELINE_KEY'
model_key = 'MODEL_KEY'
limit = 5

res= model.history( user_secret, pipeline_key, model_key, limit)
print(res)
Output 
[
    {
        "id": "65260a39bb6b899f4d789222",
        "input": {
            "fromDate": "12/21/2022",
            "toDate": "12/31/2022"
        },
        "output": {
            "data": {
                "errorMessage": "",
                "traceback": "",
                "data": {
                    "y": [
                        {
                          "date": "01-01-2023",
                          "counts": "[{"tableCount":8.1729021072,"time":11},{"tableCount":9.2272834778,"time":12},{"tableCount":8.7410840988,"time":13},{"tableCount":7.2610864639,"time":14},{"tableCount":4.7990121841,"time":15},{"tableCount":4.9796061516,"time":16},{"tableCount":5.1875333786,"time":17},{"tableCount":6.0545682907,"time":18},{"tableCount":6.2240757942,"time":19},{"tableCount":6.6397485733,"time":20},{"tableCount":6.5043768883,"time":21}]"
                        },
                        {
                          "date": "01-02-2023",
                          "counts": "[{"tableCount":5.9584774971,"time":11},{"tableCount":4.71900177,"time":12},{"tableCount":5.23458004,"time":13},{"tableCount":5.9814653397,"time":14},{"tableCount":5.5183796883,"time":15},{"tableCount":6.3703117371,"time":16},{"tableCount":3.9970772266,"time":17},{"tableCount":1.6930608749,"time":18},{"tableCount":2.1605021954,"time":19},{"tableCount":2.2661693096,"time":20},{"tableCount":4.5692014694,"time":21}]"
                        },
                        {
                          "date": "01-03-2023",
                          "counts": "[{"tableCount":4.8561573029,"time":11},{"tableCount":5.6609015465,"time":12},{"tableCount":3.6423728466,"time":13},{"tableCount":4.340628624,"time":14},{"tableCount":7.3471589088,"time":15},{"tableCount":8.417137146,"time":16},{"tableCount":11.6935253143,"time":17},{"tableCount":13.3711690903,"time":18},{"tableCount":12.0397434235,"time":19},{"tableCount":9.6431388855,"time":20},{"tableCount":10.8736925125,"time":21}]"
                        },
                        {
                          "date": "01-04-2023",
                          "counts": "[{"tableCount":9.326757431,"time":11},{"tableCount":9.4327068329,"time":12},{"tableCount":8.0079860687,"time":13},{"tableCount":5.2251749039,"time":14},{"tableCount":2.5511522293,"time":15},{"tableCount":2.8028771877,"time":16},{"tableCount":2.1789927483,"time":17},{"tableCount":3.3140306473,"time":18},{"tableCount":2.8704621792,"time":19},{"tableCount":3.9721398354,"time":20},{"tableCount":7.6661634445,"time":21}]"
                        },
                        {
                          "date": "01-05-2023",
                          "counts": "[{"tableCount":7.1075911522,"time":11},{"tableCount":5.5151014328,"time":12},{"tableCount":8.0471925735,"time":13},{"tableCount":6.7182812691,"time":14},{"tableCount":8.4082269669,"time":15},{"tableCount":9.8997507095,"time":16},{"tableCount":7.8638906479,"time":17},{"tableCount":9.3877916336,"time":18},{"tableCount":10.8658905029,"time":19},{"tableCount":10.8907938004,"time":20},{"tableCount":8.6171550751,"time":21}]"
                        },
                        {
                          "date": "01-06-2023",
                          "counts": "[{"tableCount":10.2738752365,"time":11},{"tableCount":11.7885751724,"time":12},{"tableCount":14.5384082794,"time":13},{"tableCount":13.7233953476,"time":14},{"tableCount":10.7814865112,"time":15},{"tableCount":10.6480283737,"time":16},{"tableCount":11.9552650452,"time":17},{"tableCount":12.1137609482,"time":18},{"tableCount":9.6347846985,"time":19},{"tableCount":9.3301410675,"time":20},{"tableCount":8.0276508331,"time":21}]"
                        },
                        {
                          "date": "01-07-2023",
                          "counts": "[{"tableCount":9.2904233932,"time":11},{"tableCount":10.0985774994,"time":12},{"tableCount":8.670334816,"time":13},{"tableCount":9.018081665,"time":14},{"tableCount":10.2240543365,"time":15},{"tableCount":12.6987085342,"time":16},{"tableCount":10.0400686264,"time":17},{"tableCount":6.4473996162,"time":18},{"tableCount":8.7904291153,"time":19},{"tableCount":9.4310073853,"time":20},{"tableCount":9.7929801941,"time":21}]"
                        }
                    ],
                 "x": "",
                "note": "predicting without explanation"
            }
        }
     }
},
{
    "id": "65260a39bb6b899f4d789223",
    "input": {
        "fromDate": "12/21/2022",
        "toDate": "12/31/2022"
    },
    "output": {
        "data": {
            "errorMessage": "",
            "traceback": "",
            "data": {
                "y": [
                    {
                        "date": "01-01-2023",
                        "counts": "[{"tableCount":8.1729021072,"time":11},{"tableCount":9.2272834778,"time":12},{"tableCount":8.7410840988,"time":13},{"tableCount":7.2610864639,"time":14},{"tableCount":4.7990121841,"time":15},{"tableCount":4.9796061516,"time":16},{"tableCount":5.1875333786,"time":17},{"tableCount":6.0545682907,"time":18},{"tableCount":6.2240757942,"time":19},{"tableCount":6.6397485733,"time":20},{"tableCount":6.5043768883,"time":21}]"
                    },
                    {
                        "date": "01-02-2023",
                        "counts": "[{"tableCount":5.9584774971,"time":11},{"tableCount":4.71900177,"time":12},{"tableCount":5.23458004,"time":13},{"tableCount":5.9814653397,"time":14},{"tableCount":5.5183796883,"time":15},{"tableCount":6.3703117371,"time":16},{"tableCount":3.9970772266,"time":17},{"tableCount":1.6930608749,"time":18},{"tableCount":2.1605021954,"time":19},{"tableCount":2.2661693096,"time":20},{"tableCount":4.5692014694,"time":21}]"
                    },
                    {
                        "date": "01-03-2023",
                        "counts": "[{"tableCount":4.8561573029,"time":11},{"tableCount":5.6609015465,"time":12},{"tableCount":3.6423728466,"time":13},{"tableCount":4.340628624,"time":14},{"tableCount":7.3471589088,"time":15},{"tableCount":8.417137146,"time":16},{"tableCount":11.6935253143,"time":17},{"tableCount":13.3711690903,"time":18},{"tableCount":12.0397434235,"time":19},{"tableCount":9.6431388855,"time":20},{"tableCount":10.8736925125,"time":21}]"
                    },
                    {
                        "date": "01-04-2023",
                        "counts": "[{"tableCount":9.326757431,"time":11},{"tableCount":9.4327068329,"time":12},{"tableCount":8.0079860687,"time":13},{"tableCount":5.2251749039,"time":14},{"tableCount":2.5511522293,"time":15},{"tableCount":2.8028771877,"time":16},{"tableCount":2.1789927483,"time":17},{"tableCount":3.3140306473,"time":18},{"tableCount":2.8704621792,"time":19},{"tableCount":3.9721398354,"time":20},{"tableCount":7.6661634445,"time":21}]"
                    },
                    {
                        "date": "01-05-2023",
                        "counts": "[{"tableCount":7.1075911522,"time":11},{"tableCount":5.5151014328,"time":12},{"tableCount":8.0471925735,"time":13},{"tableCount":6.7182812691,"time":14},{"tableCount":8.4082269669,"time":15},{"tableCount":9.8997507095,"time":16},{"tableCount":7.8638906479,"time":17},{"tableCount":9.3877916336,"time":18},{"tableCount":10.8658905029,"time":19},{"tableCount":10.8907938004,"time":20},{"tableCount":8.6171550751,"time":21}]"
                    },
                    {
                        "date": "01-06-2023",
                        "counts": "[{"tableCount":10.2738752365,"time":11},{"tableCount":11.7885751724,"time":12},{"tableCount":14.5384082794,"time":13},{"tableCount":13.7233953476,"time":14},{"tableCount":10.7814865112,"time":15},{"tableCount":10.6480283737,"time":16},{"tableCount":11.9552650452,"time":17},{"tableCount":12.1137609482,"time":18},{"tableCount":9.6347846985,"time":19},{"tableCount":9.3301410675,"time":20},{"tableCount":8.0276508331,"time":21}]"
                    },
                    {
                        "date": "01-07-2023",
                        "counts": "[{"tableCount":9.2904233932,"time":11},{"tableCount":10.0985774994,"time":12},{"tableCount":8.670334816,"time":13},{"tableCount":9.018081665,"time":14},{"tableCount":10.2240543365,"time":15},{"tableCount":12.6987085342,"time":16},{"tableCount":10.0400686264,"time":17},{"tableCount":6.4473996162,"time":18},{"tableCount":8.7904291153,"time":19},{"tableCount":9.4310073853,"time":20},{"tableCount":9.7929801941,"time":21}]"
                    }
                ],
                "x": "",
                "note": "predicting without explanation"
            }
        }
     }
  }               
]

predict(user_secret, pipeline_key, model_key, from_date, to_date, config, option)

This method is used to get prediction of table count with different model two options available "NEXT_SERIES" and "NEXT_LINK".

Parameters:
  • user_secret ({string}) –

    It is the user secret key.

  • pipeline_key ({string}) –

    It is the pipeline key.

  • model_key ({string}) –

    It is model key.

  • from_date ({string}) –

    It is the date of dataset in pipeline from which model will create in 'MM-DD-YYYY' format, passed if the option is "NEXT_SERIES" only.

  • to_date ({string}) –

    It is the date of dataset in pipeline to which model will create in 'MM_DD_YYYY' format, passed if the option is "NEXT_SERIES" only.

  • config ({object}) –

    It is the config object, passed if the option is "NEXT_LINK" only.

  • option ({string}) –

    It could be only "NEXT_SERIES" or "NEXT_LINK".
Returns:
  • type( object ) –

    Response message.
Example 





from vai_toolkit import model

user_secret='USER_SECRET_KEY'
pipeline_key = 'PIPELINE_KEY'
model_key = 'MODEL_KEY' 

from_date = '03/01/2023'
to_date = '05/31/2023'
option = 'NEXT_SERIES'

res = model.predict(user_secret, pipeline_key, model_key ,from_date,to_date,None,option)
print(res)



from vai_toolkit import model

user_secret = 'USER_SECRET_KEY'
pipeline_key = 'PIPELINE_KEY'
model_key ='MODEL_KEY'
config ={
        "seedNodeNameCol" : 'ItemDescription',
        "prediction" : 10,
        "seedNodeNames" : ["1","2"],
        "refNodeDict" : {
            "GuestCount" :0,
            "CheckOpen" : "2023-09-08T05:14:05.283Z",
}}
option ='NEXT_LINK'

res = model.predict(user_secret, pipeline_key, model_key, None,None, config, option)
print(res)
Output 
{
    {
        'data': {
            'errorMessage': '', 
            'traceback': '', 
            'data': {
                'y': [
                        {'date': '05-31-2023', 'counts': '[{"tableCount":281.7903747559,"time":11},{"tableCount":221.9609527588,"time":12},{"tableCount":136.3621520996,"time":13},{"tableCount":88.3298797607,"time":14}, {"tableCount":66.8720169067,"time":15},{"tableCount":53.803276062,"time":16},{"tableCount":84.1227493286,"time":17},{"tableCount":159.0596923828,"time":18},{"tableCount":186.9671936035,"time":19},{"tableCount":188.2597351074,"time":20},{"tableCount":192.5038146973,"time":21}]'},
                        {'date': '06-01-2023', 'counts': '[{"tableCount":221.7015228271,"time":11},{"tableCount":249.4067230225,"time":12},{"tableCount":262.0877990723,"time":13},{"tableCount":227.6030883789,"time":14},{"tableCount":163.640625,"time":15},{"tableCount":81.578666687,"time":16},{"tableCount":35.5799293518,"time":17},{"tableCount":25.2485866547,"time":18},{"tableCount":16.2483539581,"time":19},{"tableCount":56.0276679993,"time":20},{"tableCount":127.5245361328,"time":21}]'},
                        {'date': '06-02-2023', 'counts': '[{"tableCount":151.8760070801,"time":11},{"tableCount":149.3125305176,"time":12},{"tableCount":136.9319000244,"time":13},{"tableCount":138.5372772217,"time":14},{"tableCount":149.87840271,"time":15},{"tableCount":159.7752838135,"time":16},{"tableCount":138.3939819336,"time":17},{"tableCount":101.8885879517,"time":18},{"tableCount":51.3734474182,"time":19},{"tableCount":26.7129077911,"time":20},{"tableCount":25.0917453766,"time":21}]'}, 
                        {'date': '06-03-2023', 'counts': '[{"tableCount":15.0687656403,"time":11},{"tableCount":40.74168396,"time":12},{"tableCount":89.7492446899,"time":13},{"tableCount":101.6272888184,"time":14},{"tableCount":98.6197280884,"time":15},{"tableCount":94.0878372192,"time":16},{"tableCount":106.0318145752,"time":17},{"tableCount":128.7826690674,"time":18},{"tableCount":150.5857696533,"time":19},{"tableCount":137.3954925537,"time":20},{"tableCount":107.9107666016,"time":21}]'},
                        {'date': '06-04-2023', 'counts': '[{"tableCount":69.9748687744,"time":11},{"tableCount":48.4622573853,"time":12},{"tableCount":38.2721862793,"time":13},{"tableCount":23.1030216217,"time":14},{"tableCount":40.9192276001,"time":15},{"tableCount":80.6420669556,"time":16},{"tableCount":88.2661819458,"time":17},{"tableCount":88.1396331787,"time":18},{"tableCount":92.166053772,"time":19},{"tableCount":116.6257400513,"time":20},{"tableCount":148.4887084961,"time":21}]'}, 
                        {'date': '06-05-2023', 'counts': '[{"tableCount":169.0198364258,"time":11},{"tableCount":147.4364776611,"time":12},{"tableCount":108.4352493286,"time":13},{"tableCount":58.7132301331,"time":14},{"tableCount":31.183631897,"time":15},{"tableCount":28.5562381744,"time":16},{"tableCount":17.1293258667,"time":17},{"tableCount":44.2518920898,"time":18},{"tableCount":96.2329483032,"time":19},{"tableCount":95.2348632812,"time":20},{"tableCount":85.2216186523,"time":21}]'}, 
                        {'date': '06-06-2023', 'counts': '[{"tableCount":89.2415390015,"time":11},{"tableCount":117.0859832764,"time":12},{"tableCount":144.4945983887,"time":13},{"tableCount":158.9694213867,"time":14},{"tableCount":136.0721588135,"time":15},{"tableCount":91.8300094604,"time":16},{"tableCount":37.7490653992,"time":17},{"tableCount":20.4870605469,"time":18},{"tableCount":29.0067577362,"time":19},{"tableCount":17.4881305695,"time":20},{"tableCount":52.84141922,"time":21}]'}
                    ], 
                'x': '', 
                'note': 'predicting without explanation'
        }
    }
}

retrain(user_secret, pipeline_key, model_key)

This method is used to delete model of provided pipeline.

Parameters:
  • user_secret ({string}) –

    It is the user secret key.

  • pipeline_key ({string}) –

    It is the pipeline key.

  • model_key ({string}) –

    It is the model key.
Returns:
  • type( object ) –

    Success response message.
Example 





from vai_toolkit import pipeline

user_secret  =  'USER_SECRET_KEY'
pipeline_key =  'PIPELINE_KEY'
model_key = 'MODEL_KEY'

res = model.retrain(user_secret, pipeline_key ,model_key)
print(res)
Output 
Model retrained successfully.

train(user_secret, pipeline_key, title, from_date, to_date, settings, option, table_name='')

This method is used to train model with options "NEXT_SERIES", "MIXED" and "NEXT_LINK", if "NEXT_SERIES" then model will be trained with timeseries on for given pipeline of user and if "MIXED" then model will be trained with timeseries off for given pipeline of user.

Parameters:
  • user_secret ({string}) –

    It is the user secret key.

  • pipeline_key ({string}) –

    It is the pipeline key.

  • title ({string}) –

    It is the name of model you want to give

  • from_date ({string}) –

    It is the date of dataset in pipeline from which model will create in 'MM-DD-YYYY' format, passed if the option is "NEXT_SERIES" and "MIXED" only.

  • to_date ({string}) –

    It is the date of dataset in pipeline to which model will create in 'MM_DD_YYYY' format, passed if the option is "NEXT_SERIES" and "MIXED" only.

  • settings ({object}) –

    It is a settings object passed if the option is "NEXT_LINK" only, object with required fields - dates, trainNodeType, dummyNodeType, seedNodeType and in dates field, add keys as column_names with its object values, for Ex. see below example of "NEXT_LINK" option.

  • option ({string}) –

    It could be only "NEXT_SERIES", "MIXED" and "NEXT_LINK".

  • table_name ({string}, default: '' ) –

    It is the name of table of which data needs to consider while creating model.
Returns:
  • type( object ) –

    Response message.
Example 





from vai_toolkit import model

user_secret = 'USER_SECRET_KEY'
pipeline_key = 'PIPELINE_KEY'
title = 'MODEL_TITLE'
from_date = '01/01/2022'
to_date = '05/30/2023'
option='NEXT_SERIES' 
table_name='Table 1'

res= model.train( user_secret,pipeline_key,title, from_date,to_date, None, option , table_name =table_name)
print(res)



# train mixed model

from vai_toolkit import model

user_secret = 'USER_SECRET_KEY'
pipeline_key = 'PIPELINE_KEY'
title = 'MODEL_TITLE'
from_date = '08/31/2023'
to_date = '09/11/2023'
option='MIXED' 
table_name='Table 1'


res= model.train( user_secret,pipeline_key,title, from_date,to_date, None,option , table_name =table_name)
print(res)




from vai_toolkit import model

user_secret = 'USER_SECRET_KEY'
pipeline_key = 'PIPELINE_KEY'
title = 'MODEL_TITLE'

option  = 'NEXT_LINK'
settings  = {
    "dates": {
        "dim_item": {
            "from": "01-01-2023",
            "to": "12-31-2023",
            "allDate": False
        },
        "check": {
            "from": "01-01-2023",
            "to": "12-31-2023",
            "allDate": False 
        },
        "check_item": {
            "from": "01-01-2023",
            "to": "12-31-2023",
            "allDate": False
        }
    },
    "trainNodeType": "check",
    "dummyNodeType": "check",
    "seedNodeType": "dim_item"
}

res= model.train( user_secret,pipeline_key,title,None,None,settings,option)
print(res)
Output 
{
    "status": "In progress", 
    "model Id": "Model Id", 
    "apiKey": "Model api key."
}

{
    "status": "In progress", 
    "model Id": "Model Id", 
    "apiKey": "Model api key."
}

{
    "status": "In progress", 
    "model Id": "Model Id", 
    "apiKey": "Model api key."
}