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

Jump to bottom

Produce output csv with aggregate results #150

Merged
merged 1 commit into from
Apr 15, 2024
Merged

Produce output csv with aggregate results #150

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: 20 additions & 2 deletions consensus_decentralization/analyze.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,16 +21,23 @@ def analyze(projects, aggregated_data_filename, output_dir):
"""
logging.info('Calculating metrics on aggregated data..')
metrics = hlp.get_metrics_config()
metric_names = list(metrics.keys())

aggregate_output = {}

csv_contents = {}
for metric in metrics.keys():
for metric in metric_names:
# Each metric list is of the form [['<timeframe>', '<comma-separated values for different projects']].
# The special entry ['timeframe', '<comma-separated names of projects>'] is for the csv header
csv_contents[metric] = [['timeframe'] + projects]

for column_index, project in enumerate(projects):
aggregate_output[project] = {}
aggregated_data_dir = output_dir / project / 'blocks_per_entity'
time_chunks, blocks_per_entity = hlp.get_blocks_per_entity_from_file(aggregated_data_dir / aggregated_data_filename)
for time_chunk in time_chunks:
aggregate_output[project][time_chunk] = {}

chunks_with_blocks = set()
for block_values in blocks_per_entity.values():
for tchunk, nblocks in block_values.items():
Expand All @@ -51,10 +58,21 @@ def analyze(projects, aggregated_data_filename, output_dir):
result = func(time_chunk_blocks_per_entity, **args_dict) if args_dict else func(
time_chunk_blocks_per_entity)
csv_contents[metric][row_index + 1].append(result)
aggregate_output[project][time_chunk][metric] = result

for metric in metrics.keys():
with open(output_dir / f'{metric}.csv', 'w') as f:
csv_writer = csv.writer(f)
csv_writer.writerows(csv_contents[metric])

return list(metrics.keys())
aggregate_csv_output = [['ledger', 'snapshot date'] + metric_names]
for project, timeframes in aggregate_output.items():
for time_chunk, results in timeframes.items():
aggregate_csv_output.append([project, time_chunk])
for metric in metric_names:
aggregate_csv_output[-1].append(results[metric])
with open(output_dir / 'output.csv', 'w') as f:
csv_writer = csv.writer(f)
csv_writer.writerows(aggregate_csv_output)

return metric_names
Loading