From 1250732addcfb6f1f890e67116ba7c8358830612 Mon Sep 17 00:00:00 2001 From: yangdsh Date: Thu, 5 Dec 2019 06:20:33 +0000 Subject: [PATCH] resolve conflicts --- server/analysis/ddpg/ddpg.py | 2 +- server/website/website/settings/constants.py | 4 ++-- server/website/website/tasks/async_tasks.py | 5 +++-- 3 files changed, 6 insertions(+), 5 deletions(-) diff --git a/server/analysis/ddpg/ddpg.py b/server/analysis/ddpg/ddpg.py index c8bc14a..9b6d77b 100644 --- a/server/analysis/ddpg/ddpg.py +++ b/server/analysis/ddpg/ddpg.py @@ -3,7 +3,7 @@ # # Copyright (c) 2017-18, Carnegie Mellon University Database Group # -# from: https://github.com/KqSMea8/use_default +# from: https://github.com/KqSMea8/CDBTune # Zhang, Ji, et al. "An end-to-end automatic cloud database tuning system using # deep reinforcement learning." Proceedings of the 2019 International Conference # on Management of Data. ACM, 2019 diff --git a/server/website/website/settings/constants.py b/server/website/website/settings/constants.py index f2c1cab..f00becd 100644 --- a/server/website/website/settings/constants.py +++ b/server/website/website/settings/constants.py @@ -52,11 +52,11 @@ DEFAULT_LEARNING_RATE = 0.01 # a small bias when using training data points as starting points. GPR_EPS = 0.001 -DEFAULT_RIDGE = 0.01 +DEFAULT_RIDGE = 1.00 DEFAULT_EPSILON = 1e-6 -DEFAULT_SIGMA_MULTIPLIER = 3.0 +DEFAULT_SIGMA_MULTIPLIER = 1.0 DEFAULT_MU_MULTIPLIER = 1.0 diff --git a/server/website/website/tasks/async_tasks.py b/server/website/website/tasks/async_tasks.py index 366a5db..5743007 100644 --- a/server/website/website/tasks/async_tasks.py +++ b/server/website/website/tasks/async_tasks.py @@ -670,8 +670,9 @@ def configuration_recommendation(recommendation_input): epsilon=DEFAULT_EPSILON, max_iter=MAX_ITER, sigma_multiplier=DEFAULT_SIGMA_MULTIPLIER, - mu_multiplier=DEFAULT_MU_MULTIPLIER) - model.fit(X_scaled, y_scaled, X_min, X_max, ridge=DEFAULT_RIDGE) + mu_multiplier=DEFAULT_MU_MULTIPLIER, + ridge=DEFAULT_RIDGE) + model.fit(X_scaled, y_scaled, X_min, X_max) res = model.predict(X_samples, constraint_helper=constraint_helper) best_config_idx = np.argmin(res.minl.ravel())