change categorical with integer

Author: jrzaurin

initialize.py

@@ -61,13 +61,13 @@ def create_model():
 	print("creating model...")
 	init_dataprocessor = 'dataprocessor_0_.p'
 	dtrain = pickle.load(open(DATAPROCESSORS_PATH/init_dataprocessor, 'rb'))
-	# LGBOpt = LGBOptimizer(dtrain, MODELS_PATH)
-	# LGBOpt.optimize(maxevals=10)
-	LGBOpt = LGBOptimizer(dtrain, str(MODELS_PATH))
-	LGBOpt.optimize('f1_score', StratifiedKFold, n_splits=3, maxevals=10)
+	LGBOpt = LGBOptimizer(dtrain, MODELS_PATH)
+	LGBOpt.optimize(maxevals=10)
+	# LGBOpt = LGBOptimizer(dtrain, str(MODELS_PATH))
+	# LGBOpt.optimize('f1_score', StratifiedKFold, n_splits=3, maxevals=10)
 
 if __name__ == '__main__':
-	create_folders()
-	download_data()
+	# create_folders()
+	# download_data()
 	create_data_processor()
-	create_model()
+	# create_model()

train/train_hyperopt_mlflow.py

@@ -117,9 +117,11 @@ def optimize(self, maxevals=50, model_id=0):
 		else:
 			client = MlflowClient()
 			n_experiments = len(client.list_experiments())
-			client.create_experiment(name=str(n_experiments))
+			experiment_name = 'experiment_' + str(n_experiments)
+			client.create_experiment(name=experiment_name)
 		experiments = client.list_experiments()
 		with mlflow.start_run(experiment_id=experiments[-1].experiment_id) as run:
+		# with mlflow.start_run() as run:
 			model = lgb.LGBMClassifier(**best)
 			model.fit(self.lgtrain.data,
 				self.lgtrain.label,
@@ -164,7 +166,7 @@ def objective(params):
 				stratified=True,
 				early_stopping_rounds=20)
 			self.early_stop_dict[objective.i] = len(cv_result['binary_logloss-mean'])
-			error = round(cv_result['binary_logloss-mean'][-1], 4)
+			error = cv_result['binary_logloss-mean'][-1]
 			objective.i+=1
 			return error
 
@@ -175,7 +177,7 @@ def hyperparameter_space(self, param_space=None):
 		space = {
 			'learning_rate': hp.uniform('learning_rate', 0.01, 0.2),
 			'num_boost_round': hp.quniform('num_boost_round', 50, 500, 20),
-			'num_leaves': hp.quniform('num_leaves', 31, 255, 4),
+			'num_leaves': hp.quniform('num_leaves', 31, 256, 4),
 		    'min_child_weight': hp.uniform('min_child_weight', 0.1, 10),
 		    'colsample_bytree': hp.uniform('colsample_bytree', 0.5, 1.),
 		    'subsample': hp.uniform('subsample', 0.5, 1.),

train/train_hyperparameterhunter_mlfow.py

@@ -113,8 +113,8 @@ def hyperparameter_space(self, param_space=None):
         space = dict(
                 is_unbalance = True,
                 learning_rate = Real(0.01, 0.3),
-                num_boost_round=Categorical(np.arange(50, 500, 20)),
-                num_leaves=Categorical(np.arange(31, 256, 4)),
+                num_boost_round=Integer(50, 500),
+                num_leaves=Integer(31, 255),
                 min_child_weight = Real(0.1, 10),
                 colsample_bytree= Real(0.5, 1.),
                 subsample=Real(0.5, 1.),