diff --git a/efo/efo_data_cleanup.py b/efo/efo_data_cleanup.py
index 82149f0..d54e3e0 100644
--- a/efo/efo_data_cleanup.py
+++ b/efo/efo_data_cleanup.py
@@ -7,12 +7,13 @@
 
 # input csv files
 data_dir = "/Users/morteza/workspace/notebooks/efo/data/"
-csv_path = f"{data_dir}efo_pubmed_hits.v2.csv"
-tasks_csv_path = f"{data_dir}efo_pubmed_tasks_hits.v2.csv"
-concepts_csv_path = f"{data_dir}efo_pubmed_concepts_hits.v2.csv"
+data_version = "20200114"
+csv_path = f"{data_dir}efo_pubmed_hits.{data_version}.csv"
+tasks_csv_path = f"{data_dir}efo_pubmed_tasks_hits.{data_version}.csv"
+concepts_csv_path = f"{data_dir}efo_pubmed_concepts_hits.{data_version}.csv"
 
 # output csv file
-output_csv_path = f"{data_dir}efo_pubmed_hits.v2_cleaned.csv"
+output_csv_path = f"{data_dir}efo_pubmed_hits_preproc.{data_version}.csv"
 
 def merge_csv_files(tasks_concepts_hits_csv, concepts_hits_csv, tasks_hits_csv):
   """merge tasks, concepts, and tasks-concepts hits data files"""
@@ -26,7 +27,7 @@
 
   # drop backup columns
   to_drop_cols = df.filter(like = '_original').columns
-  df.drop(to_drop_cols, axis='columns', inplace=True)
+  #df.drop(to_drop_cols, axis='columns', inplace=True)
 
   return df
 
@@ -46,11 +47,11 @@
     df['task_suffixgame_concept_hits']
   )
 
-  to_drop_cols = df.filter(like = ['suffixtest','suffixtask','suffixgame').columns
-  df.drop(to_drop_cols, axis='columns', inplace=True)
+  to_drop_cols = df.filter(like = ['suffixtest','suffixtask','suffixgame']).columns
+  #df.drop(to_drop_cols, axis='columns', inplace=True)
 
   return df
 
 
-merge_csv_files(csv_path, concepts_csv_path, tasks_csv_path, output_csv_path).to_csv(output_csv_path)
+merge_csv_files(csv_path, concepts_csv_path, tasks_csv_path).to_csv(output_csv_path)
 #WARNING combine_hits(output_csv_path).to_csv(output_csv_path)
\ No newline at end of file