Update backend/core/model_factory.py

backend/core/model_factory.py

@@ -1,40 +1,40 @@
-import os
-from sklearn.model_selection import train_test_split
-from ..tabular.pipelines import build_preprocessing_pipeline
-from ..tabular.trainers import train_model
-from ..tabular.evaluators import evaluate_model
-from ..nlp.trainers import TextClassifier
-from ..nlp.evaluators import evaluate_nlp_model
-from ..utils.model_io import ModelIO
-
-class ModelFactory:
-    def __init__(self):
-        self.model_io = ModelIO()
-
-    def build_and_train(self, df, target_column, dataset_info, problem_type, strategy):
-        if dataset_info["small_data"]:
-            raise ValueError("Dataset is too small for training. Minimum 1200 rows required.")
-
-        if problem_type == "nlp":
-            raise ValueError("NLP functionality is not supported in this version.")
-        else:
-            # Tabular
-            X = df.drop(columns=[target_column])
-            y = df[target_column]
-
-            X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
-
-            pipeline = build_preprocessing_pipeline(dataset_info["numeric_cols"], dataset_info["categorical_cols"])
-            pipeline.fit(X_train, y_train)
-
-            model = train_model(pipeline, X_train, y_train, problem_type, strategy)
-            metrics = evaluate_model(model, X_test, y_test, problem_type)
-
-            # Save model
-            self.model_io.save(model, "exports/models/trained_model.pkl")
-
-            return model, metrics
-
-
-
-
+import os
+from sklearn.model_selection import train_test_split
+from ..tabular.pipelines import build_preprocessing_pipeline
+from ..tabular.trainers import train_model
+from ..tabular.evaluators import evaluate_model
+#from ..nlp.trainers import TextClassifier
+#from ..nlp.evaluators import evaluate_nlp_model
+from ..utils.model_io import ModelIO
+
+class ModelFactory:
+    def __init__(self):
+        self.model_io = ModelIO()
+
+    def build_and_train(self, df, target_column, dataset_info, problem_type, strategy):
+        if dataset_info["small_data"]:
+            raise ValueError("Dataset is too small for training. Minimum 1200 rows required.")
+
+        if problem_type == "nlp":
+            raise ValueError("NLP functionality is not supported in this version.")
+        else:
+            # Tabular
+            X = df.drop(columns=[target_column])
+            y = df[target_column]
+
+            X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+            pipeline = build_preprocessing_pipeline(dataset_info["numeric_cols"], dataset_info["categorical_cols"])
+            pipeline.fit(X_train, y_train)
+
+            model = train_model(pipeline, X_train, y_train, problem_type, strategy)
+            metrics = evaluate_model(model, X_test, y_test, problem_type)
+
+            # Save model
+            self.model_io.save(model, "exports/models/trained_model.pkl")
+
+            return model, metrics
+
+
+
+