edit-baseline-experimenter

metagpt/ext/sela/experimenter/aide.py

@@ -1,11 +1,15 @@
-import aide
 import os
 import time
 
+import aide
+
 os.environ["OPENAI_API_KEY"] = "sk-xxx"
 os.environ["OPENAI_BASE_URL"] = "your url"
+
 start_time = time.time()
+
 data_dir = "xxx/data/titanic"
+
 goal = f"""
 # User requirement
 ({data_dir}, 'This is a 04_titanic dataset. Your goal is to predict the target column `Survived`.\nPerform data analysis, data preprocessing, feature engineering, and modeling to predict the target. \nReport f1 on the eval data. Do not plot or make any visualizations.\n')
@@ -28,4 +32,4 @@ print(f"Best solution code: {best_solution.code}")
 end_time = time.time()
 execution_time = end_time - start_time
 
-print(f"run time : {execution_time} seconds")
+print(f"run time : {execution_time} seconds")

metagpt/ext/sela/experimenter/autogluon.py

@@ -1,8 +1,10 @@
-from datetime import datetime
-from metagpt.ext.sela.experimenter.custom import CustomExperimenter
 import os
+from datetime import datetime
+
 import pandas as pd
 
+from metagpt.ext.sela.experimenter.custom import CustomExperimenter
+
 
 class AGRunner:
     def __init__(self, state=None):
@@ -11,6 +13,7 @@ class AGRunner:
 
     def run(self):
         from autogluon.tabular import TabularDataset, TabularPredictor
+
         train_path = self.datasets["train"]
         dev_path = self.datasets["dev"]
         dev_wo_target_path = self.datasets["dev_wo_target"]
@@ -32,6 +35,7 @@ class AGRunner:
 
     def run_multimodal(self):
         from autogluon.multimodal import MultiModalPredictor
+
         target_col = self.state["dataset_config"]["target_col"]
         train_path = self.datasets["train"]
         dev_path = self.datasets["dev"]
@@ -56,10 +60,7 @@ class AGRunner:
         test_preds = predictor.predict(test_data)
 
         # Return predictions for dev and test datasets
-        return {
-            "dev_preds": dev_preds,
-            "test_preds": test_preds
-        }
+        return {"dev_preds": dev_preds, "test_preds": test_preds}
 
     def load_split_dataset(self, train_path, dev_path, dev_wo_target_path, test_wo_target_path):
         """
@@ -94,7 +95,8 @@ class AGRunner:
         train_data[image_column] = train_data[image_column].apply(lambda x: os.path.join(root_folder, x))
         dev_data[image_column] = dev_data[image_column].apply(lambda x: os.path.join(root_folder, x))
         dev_wo_target_data[image_column] = dev_wo_target_data[image_column].apply(
-            lambda x: os.path.join(root_folder, x))
+            lambda x: os.path.join(root_folder, x)
+        )
         test_data[image_column] = test_data[image_column].apply(lambda x: os.path.join(root_folder, x))
 
         return train_data, dev_data, dev_wo_target_data, test_data
@@ -106,7 +108,7 @@ class GluonExperimenter(CustomExperimenter):
     def __init__(self, args, **kwargs):
         super().__init__(args, **kwargs)
         self.framework = AGRunner(self.state)
-        self.is_multimodal = args.is_multimodal if hasattr(args, 'is_multimodal') else False
+        self.is_multimodal = args.is_multimodal if hasattr(args, "is_multimodal") else False
 
     async def run_experiment(self):
         if not self.is_multimodal:

metagpt/ext/sela/experimenter/autosklearn.py

@@ -1,9 +1,11 @@
 from datetime import datetime
-import pandas as pd
-from metagpt.ext.sela.experimenter.custom import CustomExperimenter
-from metagpt.ext.sela.evaluation.evaluation import evaluate_score
 from functools import partial
 
+import pandas as pd
+
+from metagpt.ext.sela.evaluation.evaluation import evaluate_score
+from metagpt.ext.sela.experimenter.custom import CustomExperimenter
+
 
 def custom_scorer(y_true, y_pred, metric_name):
     return evaluate_score(y_pred, y_true, metric_name)
@@ -19,9 +21,7 @@ class ASRunner:
     def create_autosklearn_scorer(self, metric_name):
         from autosklearn.metrics import make_scorer
 
-        return make_scorer(
-            name=metric_name, score_func=partial(custom_scorer, metric_name=metric_name)
-        )
+        return make_scorer(name=metric_name, score_func=partial(custom_scorer, metric_name=metric_name))
 
     def run(self):
         import autosklearn.classification