support enum/boolean in GPR/DNN

client/driver/fabfile.py

@@ -425,13 +425,17 @@ def upload_batch(result_dir=None, sort=True, upload_code=None):
         upload_result(result_dir=result_dir, prefix=prefix, upload_code=upload_code)
         LOG.info('Uploaded result %d/%d: %s__*.json', i + 1, count, prefix)
 
-
 @task
 def dump_database():
     dumpfile = os.path.join(dconf.DB_DUMP_DIR, dconf.DB_NAME + '.dump')
-    if not dconf.ORACLE_FLASH_BACK and file_exists(dumpfile):
+    if dconf.DB_TYPE == 'oracle':
-        LOG.info('%s already exists ! ', dumpfile)
+        if not dconf.ORACLE_FLASH_BACK and file_exists(dumpfile):
-        return False
+            LOG.info('%s already exists ! ', dumpfile)
+            return False
+    else:
+        if file_exists(dumpfile):
+            LOG.info('%s already exists ! ', dumpfile)
+            return False
 
     if dconf.ORACLE_FLASH_BACK:
         LOG.info('create restore point %s for database %s in %s', dconf.RESTORE_POINT,
@@ -582,7 +586,7 @@ def loop(i):
 
 
 @task
-def run_loops(max_iter=1):
+def run_loops(max_iter=10):
     # dump database if it's not done before.
     dump = dump_database()
 

server/website/website/set_default_knobs.py

@@ -14,8 +14,8 @@ LOG = logging.getLogger(__name__)
 # tunable knobs in the KnobCatalog will be used instead.
 DEFAULT_TUNABLE_KNOBS = {
     DBMSType.POSTGRES: {
-        "global.checkpoint_completion_target",
+        "global.autovacuum",
-        "global.default_statistics_target",
+        "global.archive_mode",
         "global.effective_cache_size",
         "global.maintenance_work_mem",
         "global.max_wal_size",
@@ -59,7 +59,7 @@ STORAGE_PERCENT = 0.8
 SESSION_NUM = 50.0
 
 
-def set_default_knobs(session):
+def set_default_knobs(session, cascade=True):
     dbtype = session.dbms.type
     default_tunable_knobs = DEFAULT_TUNABLE_KNOBS.get(dbtype)
 
@@ -71,7 +71,19 @@ def set_default_knobs(session):
         tunable = knob.name in default_tunable_knobs
         minval = knob.minval
 
-        if knob.vartype in (VarType.INTEGER, VarType.REAL):
+        # set session knob tunable in knob catalog
+        if tunable and cascade:
+            knob.tunable = True
+            knob.save()
+
+        if knob.vartype is VarType.ENUM:
+            enumvals = knob.enumvals.split(',')
+            minval = 0
+            maxval = len(enumvals) - 1
+        elif knob.vartype is VarType.BOOL:
+            minval = 0
+            maxval = 1
+        elif knob.vartype in (VarType.INTEGER, VarType.REAL):
             vtype = int if knob.vartype == VarType.INTEGER else float
 
             minval = vtype(minval) if minval is not None else MINVAL

server/website/website/settings/constants.py

@@ -19,6 +19,9 @@ TOP_NUM_CONFIG = 10
 
 # ---CONSTRAINTS CONSTANTS---
 
+# address categorical knobs (enum, boolean)
+ENABLE_DUMMY_ENCODER = False
+
 #  Initial probability to flip categorical feature in apply_constraints
 #  server/analysis/constraints.py
 INIT_FLIP_PROB = 0.3

server/website/website/tasks/async_tasks.py

@@ -43,7 +43,7 @@ from website.settings import (USE_GPFLOW, DEFAULT_LENGTH_SCALE, DEFAULT_MAGNITUD
                               DNN_TRAIN_ITER, DNN_EXPLORE, DNN_EXPLORE_ITER,
                               DNN_NOISE_SCALE_BEGIN, DNN_NOISE_SCALE_END,
                               DNN_DEBUG, DNN_DEBUG_INTERVAL, GPR_DEBUG, UCB_BETA,
-                              GPR_MODEL_NAME)
+                              GPR_MODEL_NAME, ENABLE_DUMMY_ENCODER)
 
 from website.settings import INIT_FLIP_PROB, FLIP_PROB_DECAY
 from website.types import VarType
@@ -526,17 +526,23 @@ def configuration_recommendation(recommendation_input):
     X_matrix = np.vstack([X_target, X_workload])
 
     # Dummy encode categorial variables
-    categorical_info = DataUtil.dummy_encoder_helper(X_columnlabels,
+    if ENABLE_DUMMY_ENCODER:
-                                                     mapped_workload.dbms)
+        categorical_info = DataUtil.dummy_encoder_helper(X_columnlabels,
-    dummy_encoder = DummyEncoder(categorical_info['n_values'],
+                                                         mapped_workload.dbms)
-                                 categorical_info['categorical_features'],
+        dummy_encoder = DummyEncoder(categorical_info['n_values'],
-                                 categorical_info['cat_columnlabels'],
+                                     categorical_info['categorical_features'],
-                                 categorical_info['noncat_columnlabels'])
+                                     categorical_info['cat_columnlabels'],
-    X_matrix = dummy_encoder.fit_transform(X_matrix)
+                                     categorical_info['noncat_columnlabels'])
-
+        X_matrix = dummy_encoder.fit_transform(X_matrix)
-    # below two variables are needed for correctly determing max/min on dummies
+        binary_encoder = categorical_info['binary_vars']
-    binary_index_set = set(categorical_info['binary_vars'])
+        # below two variables are needed for correctly determing max/min on dummies
-    total_dummies = dummy_encoder.total_dummies()
+        binary_index_set = set(categorical_info['binary_vars'])
+        total_dummies = dummy_encoder.total_dummies()
+    else:
+        dummy_encoder = None
+        binary_encoder = None
+        binary_index_set = []
+        total_dummies = 0
 
     # Scale to N(0, 1)
     X_scaler = StandardScaler()
@@ -566,7 +572,7 @@ def configuration_recommendation(recommendation_input):
     # Set up constraint helper
     constraint_helper = ParamConstraintHelper(scaler=X_scaler,
                                               encoder=dummy_encoder,
-                                              binary_vars=categorical_info['binary_vars'],
+                                              binary_vars=binary_encoder,
                                               init_flip_prob=INIT_FLIP_PROB,
                                               flip_prob_decay=FLIP_PROB_DECAY)
 
@@ -686,8 +692,10 @@ def configuration_recommendation(recommendation_input):
     best_config_idx = np.argmin(res.minl.ravel())
     best_config = res.minl_conf[best_config_idx, :]
     best_config = X_scaler.inverse_transform(best_config)
-    # Decode one-hot encoding into categorical knobs
+
-    best_config = dummy_encoder.inverse_transform(best_config)
+    if ENABLE_DUMMY_ENCODER:
+        # Decode one-hot encoding into categorical knobs
+        best_config = dummy_encoder.inverse_transform(best_config)
 
     # Although we have max/min limits in the GPRGD training session, it may
     # lose some precisions. e.g. 0.99..99 >= 1.0 may be True on the scaled data,