Content based recommender completed

.gitignore

@@ -1,8 +1,6 @@
-ars/
-
+ars/ 
 .env
 Artifacts/
 logs/
-__pycache__/
-
+__pycache__/ 
 model_trainer/

anime_recommender/entity/artifact_entity.py

@@ -5,6 +5,14 @@ from typing import Optional
 class DataIngestionArtifact: 
     feature_store_anime_file_path:str
     feature_store_userrating_file_path:str
+
 @dataclass
 class DataTransformationArtifact:
-    merged_file_path:str
+    merged_file_path:str
+
+
+    
+
+@dataclass
+class ContentBasedModelArtifact:
+    cosine_similarity_model_file_path:str

anime_recommender/entity/config_entity.py

@@ -40,3 +40,15 @@ class DataTransformationConfig:
         """
         self.data_transformation_dir:str = os.path.join(training_pipeline_config.artifact_dir,DATA_TRANSFORMATION_DIR)
         self.merged_file_path:str = os.path.join(self.data_transformation_dir,DATA_TRANSFORMATION_TRANSFORMED_DATA_DIR,MERGED_FILE_NAME)
+
+
+class ContentBasedModelConfig:
+    """
+    Configuration for model training, including paths for trained models.
+    """
+    def __init__(self,training_pipeline_config:TrainingPipelineConfig):
+        """
+        Initialize model trainer paths.
+        """
+        self.model_trainer_dir:str = os.path.join(training_pipeline_config.artifact_dir,MODEL_TRAINER_DIR_NAME)
+        self.cosine_similarity_model_file_path:str = os.path.join(self.model_trainer_dir,MODEL_TRAINER_CON_TRAINED_MODEL_DIR,MODEL_TRAINER_COSINESIMILARITY_MODEL_NAME)

anime_recommender/source/content_based_recommender.py

@@ -0,0 +1,43 @@
+import sys
+from anime_recommender.loggers.logging import logging
+from anime_recommender.exception.exception import AnimeRecommendorException
+from anime_recommender.entity.config_entity import ContentBasedModelConfig
+from anime_recommender.entity.artifact_entity import ContentBasedModelArtifact, DataIngestionArtifact
+from anime_recommender.utils.main_utils.utils import load_csv_data
+from anime_recommender.model_trainer.content_filtering import ContentBasedRecommender
+from anime_recommender.constant import *
+ 
+class ContentBasedModelTrainer:
+    """Class to train the model, track metrics, and save the trained model."""
+
+    def __init__(self, content_based_model_trainer_config: ContentBasedModelConfig, data_ingestion_artifact: DataIngestionArtifact):
+        try:
+            self.content_based_model_trainer_config = content_based_model_trainer_config
+            self.data_ingestion_artifact = data_ingestion_artifact
+        except Exception as e:
+            raise AnimeRecommendorException(e, sys)
+
+    def initiate_model_trainer(self) -> ContentBasedModelArtifact:
+        try:
+            logging.info("Loading ingested data...")
+            df = load_csv_data(self.data_ingestion_artifact.feature_store_anime_file_path)
+            logging.info("Training ContentBasedRecommender model...")
+            
+            # Initialize and train the model
+            recommender = ContentBasedRecommender(df=df )
+            
+            # Save the model (TF-IDF and cosine similarity matrix)
+            recommender.save_model(self.content_based_model_trainer_config.cosine_similarity_model_file_path)
+            logging.info("Model saved successfully.")
+            
+            logging.info("Loading saved model to get recommendations...")
+            cosine_recommendations = recommender.get_rec_cosine(title="One Piece", model_path=self.content_based_model_trainer_config.cosine_similarity_model_file_path, n_recommendations=10)
+            logging.info(f"Cosine similarity recommendations: {cosine_recommendations}")
+            
+            # Return artifact with saved model path
+            content_model_trainer_artifact = ContentBasedModelArtifact(
+                cosine_similarity_model_file_path=self.content_based_model_trainer_config.cosine_similarity_model_file_path
+            )
+            return content_model_trainer_artifact
+        except Exception as e:
+            raise AnimeRecommendorException(f"Error in ContentBasedModelTrainer: {str(e)}", sys)

run_pipeline.py

@@ -2,11 +2,11 @@ import sys
 from anime_recommender.loggers.logging import logging
 from anime_recommender.exception.exception import AnimeRecommendorException
 from anime_recommender.source.data_ingestion import DataIngestion
-from anime_recommender.entity.config_entity import TrainingPipelineConfig,DataIngestionConfig,DataTransformationConfig
-# ,DataTransformationConfig,CollaborativeModelConfig,ContentBasedModelConfig
+from anime_recommender.entity.config_entity import TrainingPipelineConfig,DataIngestionConfig,DataTransformationConfig,ContentBasedModelConfig
+# ,DataTransformationConfig,CollaborativeModelConfig
 from anime_recommender.source.data_transformation import DataTransformation
 # from anime_recommender.source.collaborative_recommenders import CollaborativeModelTrainer
-# from anime_recommender.source.content_based_recommenders import ContentBasedModelTrainer 
+from anime_recommender.source.content_based_recommender import ContentBasedModelTrainer 
 # from anime_recommender.source.popularity_based_recommenders import PopularityBasedRecommendor
 
 if __name__ == "__main__":
@@ -35,13 +35,13 @@ if __name__ == "__main__":
         # logging.info("Collaborative Model training completed.")
         # print(collaborative_model_trainer_artifact)
 
-        # # Content Based Model Training
-        # content_based_model_trainer_config = ContentBasedModelConfig(training_pipeline_config)
-        # content_based_model_trainer = ContentBasedModelTrainer(content_based_model_trainer_config=content_based_model_trainer_config,data_ingestion_artifact=data_ingestion_artifact)
-        # logging.info("Initiating Content Based Model training.")
-        # content_based_model_trainer_artifact = content_based_model_trainer.initiate_model_trainer()
-        # logging.info("Content Based Model training completed.")
-        # print(content_based_model_trainer_artifact)
+        # Content Based Model Training
+        content_based_model_trainer_config = ContentBasedModelConfig(training_pipeline_config)
+        content_based_model_trainer = ContentBasedModelTrainer(content_based_model_trainer_config=content_based_model_trainer_config,data_ingestion_artifact=data_ingestion_artifact)
+        logging.info("Initiating Content Based Model training.")
+        content_based_model_trainer_artifact = content_based_model_trainer.initiate_model_trainer()
+        logging.info("Content Based Model training completed.")
+        print(content_based_model_trainer_artifact)
 
         # # Popularity Based Filtering
         # logging.info("Initiating Popularity based filtering.")