updates

dvc.yaml

@@ -9,6 +9,7 @@ stages:
   process_data:
     cmd: python src/data/process_data.py
     deps:
+      - data/raw
       - src/data/process_data.py
     outs:
       - data/processed/test.csv:

src/data/process_data.py

@@ -4,7 +4,7 @@ import pandas as pd
 def process_data(split='train'):
     df = pd.read_csv('C:/Users/gbhat/Documents/GitHub/summarization/data/raw/{}.csv'.format(split))
     df.rename(columns={"article": "input_text", "highlights": "output_text"})
-    print(df.shape)
+    print(df.shape())
     df.to_csv('C:/Users/gbhat/Documents/GitHub/summarization/data/processed/{}.csv'.format(split))