public
/
ottertune
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

disable dummy encoder in knob identification

This commit is contained in:
bohanjason 2019-12-14 23:41:58 -05:00 committed by Dana Van Aken
parent 1994a09a6e
commit d5f7ae65eb
2 changed files with 17 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
server/website/website/tasks/async_tasks.py
View File

@ -482,6 +482,8 @@ def configuration_recommendation(recommendation_input):
workload=mapped_workload,
task_type=PipelineTaskType.RANKED_KNOBS)
ranked_knobs = JSONUtil.loads(ranked_knobs.data)[:IMPORTANT_KNOB_NUMBER]
# Sort the important knobs to fix the columns of input X
ranked_knobs = sorted(ranked_knobs)
ranked_knob_idxs = [i for i, cl in enumerate(X_columnlabels) if cl in ranked_knobs]
X_workload = X_workload[:, ranked_knob_idxs]
X_target = X_target[:, ranked_knob_idxs]

27
server/website/website/tasks/periodic_tasks.py
View File

@ -18,7 +18,7 @@ from analysis.preprocessing import (Bin, get_shuffle_indices,
DummyEncoder,
consolidate_columnlabels)
from website.models import PipelineData, PipelineRun, Result, Workload
from website.settings import RUN_EVERY
from website.settings import RUN_EVERY, ENABLE_DUMMY_ENCODER
from website.types import PipelineTaskType, WorkloadStatusType
from website.utils import DataUtil, JSONUtil
@ -296,18 +296,21 @@ def run_knob_identification(knob_data, metric_data, dbms):
nonconst_metric_columnlabels.append(cl)
nonconst_metric_matrix = np.hstack(nonconst_metric_matrix)
# determine which knobs need encoding (enums with >2 possible values)
if ENABLE_DUMMY_ENCODER:
# determine which knobs need encoding (enums with >2 possible values)
categorical_info = DataUtil.dummy_encoder_helper(nonconst_knob_columnlabels,
dbms)
# encode categorical variable first (at least, before standardize)
dummy_encoder = DummyEncoder(categorical_info['n_values'],
categorical_info['categorical_features'],
categorical_info['cat_columnlabels'],
categorical_info['noncat_columnlabels'])
encoded_knob_matrix = dummy_encoder.fit_transform(
nonconst_knob_matrix)
encoded_knob_columnlabels = dummy_encoder.new_labels
categorical_info = DataUtil.dummy_encoder_helper(nonconst_knob_columnlabels,
dbms)
# encode categorical variable first (at least, before standardize)
dummy_encoder = DummyEncoder(categorical_info['n_values'],
categorical_info['categorical_features'],
categorical_info['cat_columnlabels'],
categorical_info['noncat_columnlabels'])
encoded_knob_matrix = dummy_encoder.fit_transform(
nonconst_knob_matrix)
encoded_knob_columnlabels = dummy_encoder.new_labels
else:
encoded_knob_columnlabels = nonconst_knob_columnlabels
# standardize values in each column to N(0, 1)
standardizer = StandardScaler()