Skip to main content

​
Endpoint

POST /train
Trains a new fraud detection model using training data from the specified folder path. This endpoint triggers the complete training workflow including data validation, preprocessing, and model training.

​
Request Body

The request must be sent as JSON with the following parameter:
​
folderPath
string
required
The file system path to the folder containing training data files. This folder should contain properly formatted CSV files with transaction data for model training.

​
Request Format

{
  "folderPath": "/path/to/training/data"
}

​
Training Workflow

When the /train endpoint is called, the following process is executed:
  1. Validation - The train_validation object validates the training data structure and format
  2. Data Processing - Training data is validated and inserted into the database
  3. Model Training - The trainModel object trains the fraud detection model using the validated data
train_valObj = train_validation(path)
train_valObj.train_validation()

trainModelObj = trainModel()
trainModelObj.trainingModel()

​
Response

​
success
string
Returns a success message when training completes successfully.

​
Success Response

Training successfull!!

​
Error Responses

​
error
string
Returns an error message if training fails.
Possible error responses: 
Error Occurred! <class 'ValueError'>
Error Occurred! <class 'KeyError'>
Error Occurred! {exception_message}

​
Example Request

​
cURL

curl -X POST http://127.0.0.1:5001/train \
  -H "Content-Type: application/json" \
  -d '{
    "folderPath": "/home/user/fraud_detection/training_data"
  }'

​
Python (requests)

import requests

url = "http://127.0.0.1:5001/train"
payload = {
    "folderPath": "/home/user/fraud_detection/training_data"
}

response = requests.post(url, json=payload)
print(response.text)

​
JavaScript (fetch)

fetch('http://127.0.0.1:5001/train', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    folderPath: '/home/user/fraud_detection/training_data'
  })
})
.then(response => response.text())
.then(data => console.log(data));

​
Error Handling

The endpoint handles the following error cases:
Raised when the provided folder path or data format is invalid.
Error Occurred! <class 'ValueError'>
Raised when the required folderPath parameter is missing from the request body.
Error Occurred! <class 'KeyError'>
Catches any other exceptions during the training process and returns the specific error message.
Error Occurred! {specific_error_message}

​
Implementation Details

The endpoint implementation from main.py:64-92: 
@app.route("/train", methods=['POST'])
@cross_origin()
def trainRouteClient():
    try:
        if request.json['folderPath'] is not None:
            path = request.json['folderPath']
            train_valObj = train_validation(path)
            train_valObj.train_validation()
            
            trainModelObj = trainModel()
            trainModelObj.trainingModel()

    except ValueError:
        return Response("Error Occurred! %s" % ValueError)
    except KeyError:
        return Response("Error Occurred! %s" % KeyError)
    except Exception as e:
        return Response("Error Occurred! %s" % e)
        
    return Response("Training successfull!!")

Build docs developers (and LLMs) love

Get started for freeTalk to us