split added

src/data/process_data.py

@@ -12,7 +12,7 @@ def process_data(split='train'):
     df.columns = ['Unnamed: 0', 'input_text', 'output_text']
     df = df.sample(frac=params['split'], replace=True, random_state=1)
     if os.path.exists("data/raw/{}.csv"):
-        os.remove("data/raw/{}.csv")
+        os.remove("data/raw/{}.csv".format(split))
     df.to_csv('data/processed/{}.csv'.format(split))
 
 

src/models/evaluate_model.py

@@ -1,7 +1,7 @@
 import dagshub
 import yaml
 
-from src.models.model import Summarization
+from .model import Summarization
 import pandas as pd
 
 

src/models/train_model.py

@@ -1,6 +1,6 @@
 import yaml
 
-from src.models.model import Summarization
+from .model import Summarization
 import pandas as pd