Skip to content

Use total_power_draw for energy calculations #12

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

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Use total_power_draw for energy calculations #12

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
22 changes: 19 additions & 3 deletions process_experiment_data.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,9 +18,25 @@ def read_csv(file_path):
def merge_data(main_df, additional_df, on='timestamp', tolerance=MERGE_TOLERANCE):
"""Merge dataframes based on the closest preceding timestamp with a tolerance."""
additional_df['timestamp'] = pd.to_datetime(additional_df['timestamp'])
merged_df = pd.merge_asof(main_df.sort_values('timestamp'),
additional_df.sort_values('timestamp'),
on='timestamp', direction='backward', tolerance=tolerance)
merged_df = pd.merge_asof(
main_df.sort_values('timestamp'),
additional_df.sort_values('timestamp'),
on='timestamp',
direction='backward',
tolerance=tolerance,
suffixes=('', '_extra'),
)

# Preserve total_power_draw if present in either dataframe
if 'total_power_draw_extra' in merged_df.columns:
if 'total_power_draw' not in merged_df.columns:
merged_df.rename(columns={'total_power_draw_extra': 'total_power_draw'}, inplace=True)
else:
merged_df['total_power_draw'] = merged_df['total_power_draw'].fillna(merged_df['total_power_draw_extra'])
merged_df.drop(columns=['total_power_draw_extra'], inplace=True)
elif 'total_power_draw' not in merged_df.columns and 'power_draw' in merged_df.columns:
merged_df['total_power_draw'] = merged_df['power_draw']

return merged_df

def process_inference_data(experiment_log, inference_stats, gpu_metrics):
Expand Down
12 changes: 9 additions & 3 deletions recommend.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,11 +10,17 @@

# Function to calculate summary statistics
def calculate_summary(data):
numeric_data = data.select_dtypes(include='number')
numeric_data = data.select_dtypes(include='number').copy()
numeric_data['max_watt'] = data['max_watt']
grouped = numeric_data.groupby('max_watt').mean() # Use mean instead of median
grouped['total_time_min'] = data.groupby('max_watt').apply(lambda x: (x['timestamp'].max() - x['timestamp'].min()).total_seconds() / 60.0)
grouped['energy_consumption_watt_min'] = grouped['power_draw'] * grouped['total_time_min']
grouped['total_time_min'] = (
data.groupby('max_watt').apply(
lambda x: (x['timestamp'].max() - x['timestamp'].min()).total_seconds() / 60.0
)
)

power_col = 'total_power_draw' if 'total_power_draw' in grouped.columns else 'power_draw'
grouped['energy_consumption_watt_min'] = grouped[power_col] * grouped['total_time_min']
return grouped

# Function to recommend sweet spot
Expand Down