utils/handle.py

import json
import os

import pandas as pd
from fastapi import UploadFile

import tasks.data.dataAugmentation as da
import tasks.data.dataEngineering as de
import tasks.data.utility as util
import tasks.training.handle_train as trainingPipeline


def augmentDataUsingVectorSpaceAlgorithm(file: UploadFile, savePath: str):
    try:
        os.makedirs(os.path.dirname(savePath), exist_ok=True)
        data = pd.read_csv(file.file)
        df = da.augmentDataWithVectorSpaceAlgorithm(data)
        df.to_csv(savePath, index=False, encoding='utf-8')
        
        return {
            "success": True,
            "message": "Training data augmented successfully",
            "data": df.head(5).to_dict()
        }
    except Exception as error:
        return {
            "success": False,
            "message": f"Training data augmentation failed. {error}",
            "data": None
        }


def getSymptomsCausesAndDiseaseNameFromJSON(file: UploadFile, savePath: str):
    try:
        os.makedirs(os.path.dirname(savePath), exist_ok=True)
        data = pd.read_csv(file.file)
        
        diseaseDict = util.getSymptomsCausesAndDiseaseNameFromJSON(data)
        
        json.dump(diseaseDict, open(savePath, 'w', encoding='utf-8'), ensure_ascii=False)
        
        return {
            "success": True,
            "message": "Symptoms, causes and disease name extracted successfully",
            "data": None
        }
    except Exception as error:
        return {
            "success": False,
            "message": f"Symptoms, causes and disease name extraction failed. {error}",
            "data": None
        }


def trainingDataFromUTagsJSON(file: UploadFile, savePath: str):
    try:
        os.makedirs(os.path.dirname(savePath), exist_ok=True)
        data = json.loads(file.file.read())
        df = de.trainingDataFromUTagsJSON(data)
        df.to_csv(savePath, index=False, encoding='utf-8')
        
        return {
            "success": True,
            "message": "Training data generated successfully",
            "data": df.head(5).to_dict()
        }
    except Exception as error:
        return {
            "success": False,
            "message": f"Training data generation failed. {error}",
            "data": None
        }


def trainingDataFromPromptsForBERT(file: UploadFile, savePath: str):
    try:
        os.makedirs(os.path.dirname(savePath), exist_ok=True)
        data = json.loads(file.file.read())
        df = de.trainingDataFromPromptsForBERT(data)
        df.to_csv(savePath, index=False, encoding='utf-8')
        
        return {
            "success": True,
            "message": "Training data generated successfully",
            "data": df.head(5).to_dict()
        }
    except Exception as error:
        return {
            "success": False,
            "message": f"Training data generation failed. {error}",
            "data": None
        }
    

def trainModelOnSageMaker(trainDataPath: str, testDataPath: str, file: UploadFile | None = None):
    try:
        hyperparameters = None
        if file is not None:
            hyperparameters = json.loads(file.file.read())
        
        trainingPipeline.train(trainDataPath, testDataPath, hyperparameters)
        
        return {
            "success": True,
            "message": "Model trained successfully",
            "data": None
        }
    except Exception as error:
        return {
            "success": False,
            "message": f"Model training failed. {error}",
            "data": None
        }