src/components/data_ingestion.py

import os
import sys
from src.exception import CustomException
from src.logger import logging

import pandas as pd
from sklearn.model_selection import train_test_split
from dataclasses import dataclass

from src.components.data_transformation import DataTransformation,DataTransformationConfig

from src.components.model_trainer import ModelTrainerConfig,ModelTrainer

@dataclass
class DataIngestionConfig:
    train_data_path: str=os.path.join('artifacts','train.csv')
    test_data_path: str = os.path.join('artifacts','test.csv')
    raw_data_path: str = os.path.join('artifacts','data.csv')


class DataIngestion:
    def __init__(self):
        self.ingestion_config = DataIngestionConfig()
        
    def intiate_data_ingestion(self):
        logging.info("Entered the data ingestion method or component")
        try:
            df=pd.read_csv('notebook/data/stud.csv')
            logging.info('read the dataset as dataframe')

            ## make dir
            os.makedirs(os.path.dirname(self.ingestion_config.train_data_path),exist_ok=True)
             
            ## save raw data
            df.to_csv(self.ingestion_config.raw_data_path,index=False,header=True)

            ## train test split
            logging.info('Train test split initiated')
            train_set, test_set = train_test_split(df, test_size=0.2, random_state=42)

            train_set.to_csv(self.ingestion_config.train_data_path,index=False,header=True)

            test_set.to_csv(self.ingestion_config.test_data_path,index=False, header=True)

            logging.info("ingestion of data completed")

            return (
                self.ingestion_config.train_data_path,
                self.ingestion_config.test_data_path,
            )
        except Exception as e:
            raise CustomException(e,sys)

if __name__ == '__main__':
    obj=DataIngestion()
    train_data_path, test_data_path = obj.intiate_data_ingestion()

    data_transformation = DataTransformation()
    train_arr, test_arr,_ = data_transformation.initiate_data_tranformation(train_data_path,test_data_path)


    modelTrainer=ModelTrainer()

    print(modelTrainer.initiate_model_trainer(train_array=train_arr,test_array=test_arr))