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

feat: add rank into report (mle_summary) #665

Merged
merged 3 commits into from
Mar 10, 2025
Merged

feat: add rank into report (mle_summary) #665

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
dfe640d
add rank into report (mle_summary)
WinstonLiyt Mar 10, 2025
3b645d1
fix CI
WinstonLiyt Mar 10, 2025
42a24df
fix
WinstonLiyt Mar 10, 2025
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
11 changes: 11 additions & 0 deletions rdagent/log/mle_summary.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,7 @@
from rdagent.core.proposal import ExperimentFeedback
from rdagent.log.storage import FileStorage
from rdagent.scenarios.data_science.experiment.experiment import DSExperiment
from rdagent.scenarios.kaggle.kaggle_crawler import score_rank
from rdagent.utils.env import DockerEnv, MLEBDockerConf

mle_de_conf = MLEBDockerConf()
Expand Down Expand Up @@ -67,6 +68,7 @@ def summarize_folder(log_folder: Path):
silver_num = 0
gold_num = 0
test_scores = {}
test_ranks = {}
valid_scores = {}
bronze_threshold = 0.0
silver_threshold = 0.0
Expand All @@ -76,6 +78,7 @@ def summarize_folder(log_folder: Path):

sota_exp_stat = ""
sota_exp_score = None
sota_exp_rank = None
grade_output = None
for msg in FileStorage(log_trace_path).iter_msg(): # messages in log trace
if msg.tag and "llm" not in msg.tag and "session" not in msg.tag:
Expand Down Expand Up @@ -114,6 +117,9 @@ def summarize_folder(log_folder: Path):
if grade_output:
if grade_output["score"] is not None:
test_scores[loop_num - 1] = grade_output["score"]
_, test_ranks[loop_num - 1] = score_rank(
stat[log_trace_path.name]["competition"], grade_output["score"]
)
if grade_output["valid_submission"]:
valid_submission_num += 1
if grade_output["above_median"]:
Expand Down Expand Up @@ -146,6 +152,9 @@ def summarize_folder(log_folder: Path):
sota_exp_stat = "made_submission"
if grade_output["score"] is not None:
sota_exp_score = grade_output["score"]
_, sota_exp_rank = score_rank(
stat[log_trace_path.name]["competition"], grade_output["score"]
)

stat[log_trace_path.name].update(
{
Expand All @@ -158,10 +167,12 @@ def summarize_folder(log_folder: Path):
"silver_num": silver_num,
"gold_num": gold_num,
"test_scores": test_scores,
"test_ranks": test_ranks,
"valid_scores": valid_scores,
"success_loop_num": success_loop_num,
"sota_exp_stat": sota_exp_stat,
"sota_exp_score": sota_exp_score,
"sota_exp_rank": sota_exp_rank,
"bronze_threshold": bronze_threshold,
"silver_threshold": silver_threshold,
"gold_threshold": gold_threshold,
Expand Down