changing parameter name

src/data_preprocessing.py

@@ -2,11 +2,11 @@ from datasets import Dataset, DatasetDict
 import pandas as pd
 
 
-def process_ChatDoctor_data(data_path: str, headers: list, hf_data_path=None):
+def process_ChatDoctor_data(data_path: str, header: list, hf_data_path=None):
     """
     converting ChatDoctor data to hugging face Dataset
     :param data_path:
-    :param headers: a list of header names
+    :param header: a list of header names
     :param hf_data_path:
     :return:
     """
@@ -27,7 +27,7 @@ def process_ChatDoctor_data(data_path: str, headers: list, hf_data_path=None):
                 if line.strip() in ['[', '{', ']']:
                     continue
                 if line.strip() in ["},", "}"]:
-                    if len(buffer) == len(headers):
+                    if len(buffer) == len(header):
                         rows.append(buffer)
                     buffer = []
                 else:
@@ -35,7 +35,7 @@ def process_ChatDoctor_data(data_path: str, headers: list, hf_data_path=None):
             except Exception as e:
                 print("Error in processing line. Detail: {}".format(e))
                 errors += 1
-    df_train = pd.DataFrame(rows, columns=headers)
+    df_train = pd.DataFrame(rows, columns=header)
     hf_data_train = Dataset.from_pandas(df_train)
     hf_data = DatasetDict({'train': hf_data_train})
 

tests/test_data_conversion.py

@@ -15,7 +15,7 @@ class TestMethods(unittest.TestCase):
                      "iCliniq.json": ["input", "answer_icliniq", "answer_chatgpt", "answer_chatdoctor"]
                      }
         for data_name, headers in data_dict.items():
-            process_ChatDoctor_data(data_path + data_name, headers=headers)
+            process_ChatDoctor_data(data_path + data_name, header=headers)
 
 
 if __name__ == '__main__':