Advitya17 commented on a change in pull request #518:
URL: https://github.com/apache/madlib/pull/518#discussion_r493918741
##########
File path: src/ports/postgres/modules/deep_learning/madlib_keras_automl.py_in
##########
@@ -291,9 +338,100 @@ class KerasAutoML():
(self.metrics_compute_frequency >= 1 and \
self.metrics_compute_frequency <= num_iterations)
+ def print_best_so_far(self):
+ """
+ Prints mst keys with best train/val losses at a given point.
+ """
+ best_so_far = '\n'
+ best_so_far += self.print_best_helper('training')
+ if self.validation_table:
+ best_so_far += self.print_best_helper('validation')
+ plpy.info(best_so_far)
+
+ def print_best_helper(self, keyword):
+ """
+ Helper function to Prints mst keys with best train/val losses at a
given point.
+ :param keyword: column prefix ('training' or 'validation')
+ :return:
+ """
+ metrics_word, loss_word = keyword + '_metrics_final', keyword +
'_loss_final'
+
+ res_str = 'Best {keyword} loss so far:\n'.format(keyword=keyword)
+ best_value = plpy.execute("SELECT {ModelSelectionSchema.MST_KEY},
{metrics_word}, " \
+ "{loss_word} FROM {self.model_info_table}
ORDER BY " \
+ "{loss_word} LIMIT 1".format(self=self,
ModelSelectionSchema=ModelSelectionSchema,
+
metrics_word=metrics_word, loss_word=loss_word))[0]
+ mst_key_value, metric_value, loss_value =
best_value[ModelSelectionSchema.MST_KEY], \
+ best_value[metrics_word],
best_value[loss_word]
+ res_str += ModelSelectionSchema.MST_KEY + '=' + str(mst_key_value) +
': metric=' + str(metric_value) + \
+ ', loss=' + str(loss_value) + '\n'
+ return res_str
+
+ def get_current_timestamp(self):
+ """for start and end times for the chosen AutoML algorithm. Showcased
in the output summary table"""
+ return datetime.fromtimestamp(time()).strftime('%Y-%m-%d %H:%M:%S')
+
+ def remove_temp_tables(self, model_training):
+ """
+ Remove all intermediate tables created for AutoML runs/updates.
+ :param model_training: Fit Multiple function call object.
+ """
+ drop_tables([model_training.original_model_output_table,
model_training.model_info_table,
+ model_training.model_summary_table,
AutoMLSchema.TEMP_MST_TABLE,
+ AutoMLSchema.TEMP_MST_SUMMARY_TABLE])
+
+# @MinWarning("warning")
+class AutoMLHyperband(KerasAutoML):
+ """
+ This class implements Hyperband, an infinite-arm bandit based algorithm
that speeds up random search
+ through adaptive resource allocation, successive halving (SHA) and early
stopping.
+
+ This class showcases and novel hyperband implementation by executing the
hyperband rounds 'diagonally'
Review comment:
I think I just need to add a comma like this: `through adaptive resource
allocation, successive halving (SHA), and early stopping`
##########
File path: src/ports/postgres/modules/deep_learning/madlib_keras_automl.py_in
##########
@@ -404,24 +544,30 @@ class KerasAutoML():
model_id=ModelSelectionSchema.MODEL_ID,
compile_params=ModelSelectionSchema.COMPILE_PARAMS,
fit_params=ModelSelectionSchema.FIT_PARAMS)
- with MinWarning('warning'):
- plpy.execute(create_query)
+ # with MinWarning('warning'):
Review comment:
See above
##########
File path: src/ports/postgres/modules/deep_learning/madlib_keras_automl.py_in
##########
@@ -500,63 +648,432 @@ class KerasAutoML():
"b (key integer, s_val integer, i_val integer) WHERE
t.mst_key=b.key".format(self=self, l=l)
plpy.execute(query)
- def update_model_selection_table(self):
+# @MinWarning("warning")
+class AutoMLHyperopt(KerasAutoML):
+ """
+ This class implements Hyperopt, another automl method that explores
awkward search spaces using
+ Random Search, Tree-structured Parzen Estimator (TPE), or Adaptive TPE.
+
+ This function executes hyperopt on top of our multiple model training
infrastructure powered with
+ Model hOpper Parallelism (MOP), a hybrid of data and task parallelism.
+
+ This automl method inherits qualities from the automl class.
+ """
+ def __init__(self, schema_madlib, source_table, model_output_table,
model_arch_table, model_selection_table,
+ model_id_list, compile_params_grid, fit_params_grid,
automl_method='hyperopt',
+ automl_params='num_models=20, num_iters=5, algorithm=tpe',
random_state=None, object_table=None,
+ use_gpus=False, validation_table=None,
metrics_compute_frequency=None,
+ name=None, description=None, **kwargs):
+ KerasAutoML.__init__(self, schema_madlib, source_table,
model_output_table, model_arch_table,
+ model_selection_table, model_id_list,
compile_params_grid, fit_params_grid,
+ automl_method, automl_params, random_state,
object_table, use_gpus,
+ validation_table, metrics_compute_frequency,
name, description, **kwargs)
+ self.compile_params_grid = self.compile_params_grid.replace('\n',
'').replace(' ', '')
+ self.fit_params_grid = self.fit_params_grid.replace('\n',
'').replace(' ', '')
+ try:
+ self.compile_params_grid = literal_eval(self.compile_params_grid)
+
+ except:
+ plpy.error("Invalid syntax in 'compile_params_dict'")
+ try:
+ self.fit_params_grid = literal_eval(self.fit_params_grid)
+ except:
+ plpy.error("Invalid syntax in 'fit_params_dict'")
+ self.validate_and_define_inputs()
+
+ self.num_workers = get_seg_number() * get_segments_per_host()
+
+ self.create_model_output_table()
+ self.create_model_output_info_table()
+ self.find_hyperopt_config()
+
+ def validate_and_define_inputs(self):
+ automl_params_dict = extract_keyvalue_params(self.automl_params,
+
default_values={'num_models': 20,
+
'num_iters': 5,
+
'algorithm': 'tpe'},
+ lower_case_names=True)
+ # casting relevant values to int
+ for i in automl_params_dict:
+ try:
+ automl_params_dict[i] = int(automl_params_dict[i])
+ except ValueError:
+ pass
+ _assert(len(automl_params_dict) >= 1 and len(automl_params_dict) <= 3,
+ "DL: Only num_models, num_iters, and algorithm may be
specified")
+ for i in automl_params_dict:
+ if i == AutoMLSchema.NUM_MODELS:
+ self.num_models = automl_params_dict[AutoMLSchema.NUM_MODELS]
+ elif i == AutoMLSchema.NUM_ITERS:
+ self.num_iters = automl_params_dict[AutoMLSchema.NUM_ITERS]
+ elif i == AutoMLSchema.ALGORITHM:
+ if automl_params_dict[AutoMLSchema.ALGORITHM].lower() ==
'rand':
+ self.algorithm = rand
+ elif automl_params_dict[AutoMLSchema.ALGORITHM].lower() ==
'tpe':
+ self.algorithm = tpe
+ # elif automl_params_dict[AutoMLSchema.ALGORITHM].lower() ==
'atpe':
+ # self.algorithm = atpe
+ # uncomment the above lines after atpe works
+ else:
+ plpy.error("DL: algorithm in 'automl_params' must be
'rand', 'tpe'") # , or 'atpe'
+ else:
+ plpy.error("DL: {0} is an invalid automl param".format(i))
+ _assert(self.num_models > 0 and self.num_iters > 0, "DL: num_models
and num_iters in 'automl_params' "
+ "must be positive")
+ _assert(self._is_valid_metrics_compute_frequency(self.num_iters), "DL:
'metrics_compute_frequency' "
+ "out
of iteration range")
+
+ def find_hyperopt_config(self):
"""
- Drops and re-create the mst table to only include the best performing
model configuration.
+ Executes hyperopt on top of MOP.
"""
- drop_tables([self.model_selection_table])
- # only retaining best performing config
- plpy.execute("CREATE TABLE {self.model_selection_table} AS SELECT
mst_key, model_id, compile_params, " \
- "fit_params FROM {self.model_info_table} " \
- "ORDER BY {AutoMLSchema.LOSS_METRIC} LIMIT
1".format(self=self, AutoMLSchema=AutoMLSchema))
+ make_mst_summary = True
+ trials = Trials()
+ domain = Domain(None, self.get_search_space())
+ rand_state = np.random.RandomState(self.random_state)
+ configs_lst = self.get_configs_list()
- def generate_model_output_summary_table(self, model_training):
+ self.start_training_time = self.get_current_timestamp()
+ for low, high in configs_lst:
+ i, n = low, high - low + 1
+
+ # Using HyperOpt TPE/ATPE to generate parameters
+ hyperopt_params = []
+ sampled_params = []
+ for j in range(i, i + n):
+ new_param = self.algorithm.suggest([j], domain, trials,
rand_state.randint(0, 2 ** 31 - 1))
+ new_param[0]['status'] = STATUS_RUNNING
+
+ trials.insert_trial_docs(new_param)
+ trials.refresh()
+ hyperopt_params.append(new_param[0])
+ sampled_params.append(new_param[0]['misc']['vals'])
+
+ model_id_list, compile_params, fit_params =
self.extract_param_vals(sampled_params)
+ msts_list = self.generate_msts(model_id_list, compile_params,
fit_params)
+ try:
+ self.remove_temp_tables(model_training)
+ except:
+ pass
+ self.populate_temp_mst_table(i, msts_list)
+
+ plpy.info("***Evaluating {n} newly suggested model
configurations***".format(n=n))
+ model_training = FitMultipleModel(self.schema_madlib,
self.source_table, AutoMLSchema.TEMP_OUTPUT_TABLE,
+ AutoMLSchema.TEMP_MST_TABLE, self.num_iters,
self.use_gpus, self.validation_table,
+ self.metrics_compute_frequency, False, self.name,
self.description)
+ if make_mst_summary:
+
self.generate_mst_summary_table(self.model_selection_summary_table)
+ make_mst_summary = False
+
+ # HyperOpt TPE update
+ for k, hyperopt_param in enumerate(hyperopt_params, i):
+ loss_val = plpy.execute("SELECT {AutoMLSchema.LOSS_METRIC}
FROM {model_training.model_info_table} " \
+ "WHERE
{ModelSelectionSchema.MST_KEY}={k}".format(AutoMLSchema=AutoMLSchema,
+
ModelSelectionSchema=ModelSelectionSchema,
+
**locals()))[0][AutoMLSchema.LOSS_METRIC]
+
+ hyperopt_param['status'] = STATUS_OK
Review comment:
Yeah it's apparently used internally by the hyperopt module during
`refresh`.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
