Update process_data.py

src/data/process_data.py

@@ -9,7 +9,7 @@ def process_data(split="train"):
 
     df = pd.read_csv("data/raw/{}.csv".format(split))
     df.columns = ["Unnamed: 0", "input_text", "output_text"]
-    df = df.sample(frac=params["split"], replace=True, random_state=1)
+    df = df.sample(frac=float(params["split"]), replace=True, random_state=1)
     df.to_csv("data/processed/{}.csv".format(split))