clean metrics for DDPG

server/website/website/settings/constants.py

@@ -32,3 +32,9 @@ VIEWS_FOR_PRUNING = {
     DBMSType.ORACLE: ['dba_hist_osstat', 'dba_hist_sysstat', 'dba_hist_system_event',
                       'dba_workload_replays', 'dba_hist_sys_time_model'],
 }
+
+# The views used for DDPG
+# WARNING: modifying this parameter will cause all existing DDPG sessions broken
+VIEWS_FOR_DDPG = {
+    DBMSType.ORACLE: ['dba_hist_sys_time_model'],
+}

server/website/website/tasks/async_tasks.py

@@ -34,7 +34,7 @@ from website.models import (PipelineData, PipelineRun, Result, Workload, Session
 from website import db
 from website.types import PipelineTaskType, AlgorithmType, VarType
 from website.utils import DataUtil, JSONUtil
-from website.settings import ENABLE_DUMMY_ENCODER, TIME_ZONE
+from website.settings import ENABLE_DUMMY_ENCODER, TIME_ZONE, VIEWS_FOR_DDPG
 
 
 LOG = get_task_logger(__name__)
@@ -420,6 +420,7 @@ def train_ddpg(train_ddpg_input):
     result_id, algorithm, target_data = train_ddpg_input
     result = Result.objects.get(pk=result_id)
     session = result.session
+    dbms = session.dbms
     task_name = _get_task_name(session, result_id)
 
     # If the preprocessing method has already generated a config, bypass this method.
@@ -480,13 +481,14 @@ def train_ddpg(train_ddpg_input):
     prev_objective = prev_metric_data[target_obj_idx]
 
     # Clean metric data
+    views = VIEWS_FOR_DDPG.get(dbms.type, None)
     metric_data, _ = DataUtil.clean_metric_data(agg_data['y_matrix'],
-                                                agg_data['y_columnlabels'], session)
+                                                agg_data['y_columnlabels'], views)
     metric_data = metric_data.flatten()
     metric_scalar = MinMaxScaler().fit(metric_data.reshape(1, -1))
     normalized_metric_data = metric_scalar.transform(metric_data.reshape(1, -1))[0]
     prev_metric_data, _ = DataUtil.clean_metric_data(prev_agg_data['y_matrix'],
-                                                     prev_agg_data['y_columnlabels'], session)
+                                                     prev_agg_data['y_columnlabels'], views)
     prev_metric_data = prev_metric_data.flatten()
     prev_metric_scalar = MinMaxScaler().fit(prev_metric_data.reshape(1, -1))
     prev_normalized_metric_data = prev_metric_scalar.transform(prev_metric_data.reshape(1, -1))[0]
@@ -597,6 +599,7 @@ def configuration_recommendation_ddpg(recommendation_ddpg_input):  # pylint: dis
     result_list = Result.objects.filter(pk=result_id)
     result = result_list.first()
     session = result.session
+    dbms = session.dbms
     task_name = _get_task_name(session, result_id)
 
     early_return, target_data_res = check_early_return(target_data, algorithm)
@@ -609,8 +612,9 @@ def configuration_recommendation_ddpg(recommendation_ddpg_input):  # pylint: dis
 
     params = JSONUtil.loads(session.hyperparameters)
     agg_data = DataUtil.aggregate_data(result_list)
+    views = VIEWS_FOR_DDPG.get(dbms.type, None)
     metric_data, _ = DataUtil.clean_metric_data(agg_data['y_matrix'],
-                                                agg_data['y_columnlabels'], session)
+                                                agg_data['y_columnlabels'], views)
     metric_data = metric_data.flatten()
     metric_scalar = MinMaxScaler().fit(metric_data.reshape(1, -1))
     normalized_metric_data = metric_scalar.transform(metric_data.reshape(1, -1))[0]

server/website/website/tasks/periodic_tasks.py

@@ -269,16 +269,8 @@ def run_workload_characterization(metric_data, dbms=None):
     LOG.debug("Workload characterization ~ initial data size: %s", matrix.shape)
 
     views = None if dbms is None else VIEWS_FOR_PRUNING.get(dbms.type, None)
-    if views is not None:
-        useful_labels = []
-        for label in columnlabels:
-            for view in views:
-                if view in label:
-                    useful_labels.append(label)
-                    break
-        matrix, columnlabels = DataUtil.clean_metric_data(matrix, columnlabels, None,
-                                                          useful_labels)
-        LOG.debug("Workload characterization ~ cleaned data size: %s", matrix.shape)
+    matrix, columnlabels = DataUtil.clean_metric_data(matrix, columnlabels, views)
+    LOG.debug("Workload characterization ~ cleaned data size: %s", matrix.shape)
 
     # Bin each column (metric) in the matrix by its decile
     binner = Bin(bin_start=1, axis=0)

server/website/website/utils.py

@@ -212,33 +212,35 @@ class DataUtil(object):
         return X_unique, y_unique, rowlabels_unique
 
     @staticmethod
-    def clean_metric_data(metric_matrix, metric_labels, session, useful_labels=None):
-        # Make metric_labels identical to useful_labels (if given)
-        # If useful_labels is not given, let it to be all metrics in the catalog.
-        if useful_labels is None:
-            metric_objs = MetricCatalog.objects.filter(dbms=session.dbms)
-            metric_cat = [session.target_objective]
-            for metric_obj in metric_objs:
-                metric_cat.append(metric_obj.name)
-        else:
-            metric_cat = useful_labels
-        missing_columns = sorted(set(metric_cat) - set(metric_labels))
-        unused_columns = set(metric_labels) - set(metric_cat)
+    def clean_metric_data(metric_matrix, metric_labels, useful_views):
+        # Make metric_labels identical to useful_labels (if not None)
+        if useful_views is None:
+            return metric_matrix, metric_labels
+
+        useful_labels = []
+        for label in metric_labels:
+            for view in useful_views:
+                if view in label:
+                    useful_labels.append(label)
+                    break
+
+        missing_columns = sorted(set(useful_labels) - set(metric_labels))
+        unused_columns = set(metric_labels) - set(useful_labels)
         LOG.debug("clean_metric_data: added %d metrics and removed %d metric.",
                   len(missing_columns), len(unused_columns))
         default_val = 0
-        metric_cat_size = len(metric_cat)
-        matrix = np.ones((len(metric_matrix), metric_cat_size)) * default_val
+        useful_labels_size = len(useful_labels)
+        matrix = np.ones((len(metric_matrix), useful_labels_size)) * default_val
         metric_labels_dict = {n: i for i, n in enumerate(metric_labels)}
-        # column labels in matrix has the same order as ones in metric catalog
+        # column labels in matrix has the same order as ones in useful_labels
         # missing values are filled with default_val
-        for i, metric_name in enumerate(metric_cat):
+        for i, metric_name in enumerate(useful_labels):
             if metric_name in metric_labels_dict:
                 index = metric_labels_dict[metric_name]
                 matrix[:, i] = metric_matrix[:, index]
         LOG.debug("clean_metric_data: final ~ matrix: %s, labels: %s", matrix.shape,
-                  len(metric_cat))
-        return matrix, metric_cat
+                  useful_labels_size)
+        return matrix, useful_labels
 
     @staticmethod
     def clean_knob_data(knob_matrix, knob_labels, sessions):