style: format code with Autopep8, isort and Ruff Formatter

src/everyai/classfier/classfy.py

@@ -13,9 +13,16 @@
 from sklearn.ensemble import RandomForestClassifier
 from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer
 from sklearn.linear_model import LogisticRegression
-from sklearn.metrics import (accuracy_score, auc, confusion_matrix, f1_score,
-                             precision_recall_curve, precision_score,
-                             recall_score, roc_curve)
+from sklearn.metrics import (
+    accuracy_score,
+    auc,
+    confusion_matrix,
+    f1_score,
+    precision_recall_curve,
+    precision_score,
+    recall_score,
+    roc_curve,
+)
 from sklearn.model_selection import train_test_split
 from sklearn.pipeline import make_pipeline
 from sklearn.svm import SVC
@@ -168,8 +175,7 @@ def __init__(
         )
         self.model_config = None
         self.model_path = (
-            MODEL_PATH
-            / f"{self.model_name}_{self.tokenizer_name}_{self.data_name}.pkl"
+            MODEL_PATH / f"{self.model_name}_{self.tokenizer_name}_{self.data_name}.pkl"
         )
         self.pipeline = pipeline if pipeline is not None else None
 
@@ -179,15 +185,13 @@ def load_data(self, texts, labels, data_name):
             raise ValueError("Length of texts and labels should be same")
         self.texts = texts
         self.labels = labels
-        logging.info(
-            f"Loading data: {data_name} to classfier {self.model_name}"
-        )
+        logging.info(f"Loading data: {data_name} to classfier {self.model_name}")
         self.data_name = data_name
         self.classfier_name = (
             f"{self.model_name}_{self.tokenizer_name}_{self.data_name}"
         )
         return self.texts, self.labels, self.data_name
-    
+
     def show_score(self):
         self.score = evaluate_classification_model(
             self.data.y_test,
@@ -257,9 +261,7 @@ def __init__(self, **classfiy_config):
         else:
             logging.warning("Split size not provided or not valid")
         if self.texts is None or self.labels is None or self.data_name is None:
-            logging.warning(
-                "Data not provided, please use the load_data method"
-            )
+            logging.warning("Data not provided, please use the load_data method")
         if "device" in classfiy_config and classfiy_config["device"] == "cuda":
             logging.warning(
                 "Cuda is not supported in sklearn and setting device to cpu"
@@ -334,8 +336,7 @@ def _split_data(self, x, y):
                 x_train,
                 y_train,
                 train_indices,
-                test_size=self.valid_size
-                / (self.train_size + self.valid_size),
+                test_size=self.valid_size / (self.train_size + self.valid_size),
                 random_state=42,
             )
         )
@@ -424,4 +425,4 @@ def __init__(
             device,
             model,
             tokenizer,
-        )
+        )

src/everyai/data_loader/data_load.py

@@ -77,7 +77,11 @@ def load_data2list(self, max_count: int = None):
         return data[["question", "answer"]].to_dict(orient="records")
 
     def apply_filter(self, orginal_data: pd.DataFrame) -> pd.DataFrame:
-        return orginal_data if self.filter is None else orginal_data[orginal_data.apply(self.filter, axis=1)]
+        return (
+            orginal_data
+            if self.filter is None
+            else orginal_data[orginal_data.apply(self.filter, axis=1)]
+        )
 
 
 if __name__ == "__main__":

src/everyai/main.py

@@ -39,16 +39,12 @@ def generate():
                 file_path=data_config["file_path"],
                 data_type=data_config["data_type"],
             )
-            qa_datas = data_loader.load_data2list(
-                max_count=data_config["max_count"]
-            )
+            qa_datas = data_loader.load_data2list(max_count=data_config["max_count"])
             everyai_dataset = EveryaiDataset(
                 dataname=data_config["data_name"],
                 ai_list=[generate_config["model_name"]],
             )
-            for data in tqdm(
-                qa_datas, desc="Generating data", total=len(qa_datas)
-            ):
+            for data in tqdm(qa_datas, desc="Generating data", total=len(qa_datas)):
                 ai_response: str = generator.generate(data["question"])
                 everyai_dataset.insert_ai_response(
                     question=data["question"],
@@ -106,9 +102,7 @@ def classfiy():
         )
         everyai_dataset.load(format="mongodb")
         logging.info(f"Loaded data: {everyai_dataset.data_name}")
-        texts, labels = everyai_dataset.get_records_with_1ai(
-            ["THUDM/glm-4-9b-chat-hf"]
-        )
+        texts, labels = everyai_dataset.get_records_with_1ai(["THUDM/glm-4-9b-chat-hf"])
         for classfiy_config in get_config(file_path=CLASSFIY_CONFIG_PATH)[
             "classfier_list"
         ]:
@@ -119,9 +113,7 @@ def classfiy():
                     )
                 case _:
                     raise ValueError("Classfier type not supported")
-            text_classfier.load_data(
-                texts, labels, data_name=everyai_dataset.data_name
-            )
+            text_classfier.load_data(texts, labels, data_name=everyai_dataset.data_name)
             text_classfier.train()
             text_classfier.test()
             text_classfier.save_model()