data ingestion

.gitignore

@@ -1 +1,2 @@
-venv/
+venv/
+artifacts/

logs/09_08_2023_20_06_15.log/09_08_2023_20_06_15.log

@@ -0,0 +1,3 @@
+[ 2023-09-08 20:06:18,654 ] 22 root - INFO - Entered the data ingestion method or component 
+[ 2023-09-08 20:06:18,658 ] 25 root - INFO - read the dataset as dataframe 
+[ 2023-09-08 20:06:18,662 ] 34 root - INFO - Train test split initiated 

logs/09_08_2023_20_10_02.log/09_08_2023_20_10_02.log

@@ -0,0 +1,3 @@
+[ 2023-09-08 20:10:03,099 ] 22 root - INFO - Entered the data ingestion method or component 
+[ 2023-09-08 20:10:03,102 ] 25 root - INFO - read the dataset as dataframe 
+[ 2023-09-08 20:10:03,104 ] 34 root - INFO - Train test split initiated 

logs/09_08_2023_20_11_36.log/09_08_2023_20_11_36.log

@@ -0,0 +1,4 @@
+[ 2023-09-08 20:11:36,808 ] 22 root - INFO - Entered the data ingestion method or component 
+[ 2023-09-08 20:11:36,812 ] 25 root - INFO - read the dataset as dataframe 
+[ 2023-09-08 20:11:36,814 ] 34 root - INFO - Train test split initiated 
+[ 2023-09-08 20:11:36,817 ] 41 root - INFO - ingestion of data completed 

src/components/data_ingestion.py

@@ -0,0 +1,52 @@
+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
+
+@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()
+    obj.intiate_data_ingestion()