Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

add id column in latest data json file #210

Merged
merged 4 commits into from
Sep 30, 2022
Merged

add id column in latest data json file #210

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
f5902c3
add id column in latest data json file
chris0765 Sep 26, 2022
57026c8
update latest columns and rows'
chris0765 Sep 28, 2022
71f9655
use to_json with orient='records'
chris0765 Sep 29, 2022
1ce685e
Change the NA value to fill with -1, not zero
chris0765 Sep 30, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion collection/aws/ec2_collector/aws_collect.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,7 +51,7 @@

current_df = build_join_df(spot_price_df, ondemand_price_df, spotinfo_df, sps_df)

update_latest(current_df) # upload current data to S3
update_latest(current_df, timestamp) # upload current data to S3
save_raw(current_df, timestamp)

if 'latest_df.pkl' not in os.listdir(f'{LOCAL_PATH}/'):
Expand Down
10 changes: 5 additions & 5 deletions collection/aws/ec2_collector/join_data.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,11 +21,11 @@ def build_join_df(spot_price_df, ondemand_price_df, spotinfo_df, sps_df):
join_df = pd.merge(join_df, spotinfo_df, how="outer")

join_df['Savings'] = 100.0 - (join_df['SpotPrice'] * 100 / join_df['OndemandPrice'])
join_df['Savings'] = join_df['Savings'].fillna(0)
join_df['SPS'] = join_df['SPS'].fillna(0)
join_df['SpotPrice'] = join_df['SpotPrice'].fillna(0)
join_df['OndemandPrice'] = join_df['OndemandPrice'].fillna(0)
join_df['IF'] = join_df['IF'].fillna(0)
join_df['Savings'] = join_df['Savings'].fillna(-1)
join_df['SPS'] = join_df['SPS'].fillna(-1)
join_df['SpotPrice'] = join_df['SpotPrice'].fillna(-1)
join_df['OndemandPrice'] = join_df['OndemandPrice'].fillna(-1)
join_df['IF'] = join_df['IF'].fillna(-1)

join_df['Savings'] = join_df['Savings'].astype('int')
join_df['SPS'] = join_df['SPS'].astype('int')
Expand Down
7 changes: 5 additions & 2 deletions collection/aws/ec2_collector/upload_data.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -71,9 +71,12 @@ def upload_timestream(data, timestamp):
print(f"end : {counter}")


def update_latest(data):
def update_latest(data, timestamp):
filename = 'latest_aws.json'
result = data.to_json(f"{LOCAL_PATH}/{filename}")
data = data.drop(data[(data['AZ'].isna()) | (data['Region'].isna()) | (data['InstanceType'].isna())].index)
data['time'] = timestamp.strftime("%Y-%m-%d %H:%M:%S")
data['id'] = data.index+1
result = data.to_json(f"{LOCAL_PATH}/{filename}", orient="records")
s3_path = f'latest_data/{filename}'
session = boto3.Session()
s3 = session.client('s3')
Expand Down