update azure collector fix regioin column

ddps-lab · Oct 17, 2023 · ba2a005 · ba2a005
1 parent 6862679
commit ba2a005
Show file tree

Hide file tree

Showing 2 changed files with 2 additions and 2 deletions.
diff --git a/collector/spot-dataset/azure/lambda/current_collector/load_price.py b/collector/spot-dataset/azure/lambda/current_collector/load_price.py
@@ -137,6 +137,6 @@ def collect_price_with_multithreading():
 
     price_df = pd.DataFrame(price_list)
     savings_df = preprocessing_price(price_df)
-    savings_df = savings_df.drop_duplicates(subset=['InstanceTier', 'InstanceType', 'Region'], keep='first')
+    savings_df = savings_df.drop_duplicates(subset=['InstanceTier', 'InstanceType', 'Region'], keep='first', inplace=True)
 
     return savings_df
diff --git a/collector/spot-dataset/azure/lambda/current_collector/upload_data.py b/collector/spot-dataset/azure/lambda/current_collector/upload_data.py
@@ -111,7 +111,7 @@ def update_latest(data, timestamp):
 # Save raw data in S3
 def save_raw(data, timestamp):
     data['Time'] = timestamp.strftime("%Y-%m-%d %H:%M:%S")
-    data = data[['Time','InstanceTier','InstanceType','OndemandPrice','SpotPrice', 'IF', 'Savings']]
+    data = data[['Time','InstanceTier','InstanceType', 'Region', 'OndemandPrice','SpotPrice', 'IF', 'Savings']]
 
     data.to_csv(f"{AZURE_CONST.SERVER_SAVE_DIR}/{timestamp}.csv.gz", index=False, compression="gzip")