Spaces:

krishnaveni76
/

Anime-Recommendation-System

Running

App Files Files Community

krishnaveni76 commited on Feb 8

Commit

c3c7748

1 Parent(s): ab6b19a

Final changes

Browse files

Files changed (13) hide show

.gitattributes +2 -1
README.md +152 -152
anime_recommender/components/collaborative_recommender.py +58 -53
anime_recommender/components/content_based_recommender.py +7 -2
anime_recommender/constant/__init__.py +1 -2
anime_recommender/exception/exception.py +2 -2
anime_recommender/pipelines/training_pipeline.py +1 -2
anime_recommender/utils/main_utils/utils.py +23 -0
app.py +241 -241
logs/{02_03_2025_11_40_31.log → 02_08_2025_12_23_10.log} +119 -73
notebooks/EDA.ipynb +0 -0
notebooks/final_ARS.ipynb +0 -0
run_pipeline.py +4 -1

.gitattributes CHANGED Viewed

@@ -32,4 +32,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.xz filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text assets/project_architecture.gif filter=lfs diff=lfs merge=lfs -text

 *.xz filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+assets/project_architecture.gif filter=lfs diff=lfs merge=lfs -text

README.md CHANGED Viewed

@@ -1,153 +1,153 @@
----
-title: Anime Recommendation System
-emoji: 📚
-colorFrom: purple
-colorTo: yellow
-sdk: streamlit
-sdk_version: 1.41.1
-app_file: app.py
-pinned: false
-license: apache-2.0
----
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
-# Anime Recommendation system
-This is an **Anime Recommendation System** that combines multiple recommendation techniques such as **Collaborative Filtering**, **Content-Based Filtering**, and **Popularity-Based Filtering**. We used the **AnimeList 2023 dataset**, but to optimize computational cost and storage, we included only animes with an average rating above **6.0**. The system is designed for **continuous data ingestion and transformation** and is fully **dockerized** for seamless deployment.
-The system is hosted on **Hugging Face Spaces** and fetches datasets and pre-trained models from **Hugging Face Hub** to generate **personalized anime recommendations** based on user preferences and anime features.
-![assets/animes.jpg](assets/animes.jpg)
-## Live Demo 🤗
-[Anime Recommendation System App](https://huggingface.co/spaces/krishnaveni76/Anime-Recommendation-System)
-## Tech Stacks 🛠️
-- **Python**: Main programming language used for building recommendation algorithms and Streamlit app.
-- **Docker**: Containerizes the application to ensure a consistent environment across different platforms.
-- **Streamlit**: For building and deploying the web app that serves the recommendations.
-- **Hugging Face Spaces**: Hosts the Streamlit-based recommendation system.
-- **Hugging Face Datasets**: Stores and retrieves anime datasets for processing.
-- **Hugging Face Models**: Stores the pre-trained recommendation models for inference.
-## Pipeline 🚀
-![assets/project_architecture.gif](assets/project_architecture.gif)
-The pipeline follows a structured sequence of steps to build an **Anime Recommendation System**, including data ingestion, transformation, and multiple recommendation models.
-### 1. Data Ingestion 📥
-- Initiates the **data ingestion process**, where anime data is loaded from Hugging Face datasets.
-- The ingested data is saved as artifacts in a local folder for further processing.
-### 2. Data Transformation 🔄
-- Cleans, transforms, and processes the raw data into a structured format.
-- Extracts important features required for **Content-Based Filtering** and prepares data for **Collaborative Filtering**.
-### 3. Collaborative Filtering 🤝
-- Implements **three collaborative filtering models** to recommend anime based on user preferences:
-  - **Singular Value Decomposition (SVD)**: Factorizes the user-item interaction matrix to make personalized recommendations.
-  - **Item-Based K-Nearest Neighbors (Item-KNN)**: Recommends anime similar to a given anime based on user ratings.
-  - **User-Based K-Nearest Neighbors (User-KNN)**: Suggests anime that users with similar preferences have liked.
-- The chosen model is trained using **transformed data**, and the final trained model is stored as an artifact.
-- Once trained, it can generate recommendations for users or anime titles.
-![assets/collaborative and contentbased filtering.png](assets/collaborative_and_contentbased_filtering.png)
-### 4. Content-Based Filtering 🎭
-- Uses extracted anime features like genres to train a **Content-Based Recommendation Model**.
-- This model recommends anime similar to those a user has watched or liked.
-### 5. Popularity-Based Filtering ⭐
-This recommendation system ranks anime based on various **popularity metrics**, making it ideal for users who want to discover trending or highly-rated shows **without needing personalized preferences**.
-The system applies different filters to sort anime based on:
-- **Most Popular** 🎭: Anime ranked by **popularity score**, highlighting the most widely recognized titles.
-- **Top Ranked** 🏆: Highest-rated anime, based on **official ranking metrics**.
-- **Overall Top Rated** ⭐: Best-rated anime, sorted by **average user ratings**.
-- **Most Favorited** ❤️: Anime with the highest number of **favorites**, indicating strong fan appreciation.
-- **Highest Member Count** 👥: Anime with the largest **viewer base**, showing widespread appeal.
-- **Popular Among Members** 🔥: Anime with a **high number of members and strong ratings**, making them community favorites.
-- **Highest Average Rating** 🎖️: Shows that have the **best average rating** after handling missing values.
-## Artifacts Storage 📂
-All intermediate and final outputs, including processed datasets and trained models, are first saved locally in the **Artifacts** folder. These artifacts are then uploaded to **Hugging Face** for efficient storage and easy access.
-When building the **Streamlit** app, these datasets and trained models are retrieved directly from **Hugging Face**, ensuring seamless integration and scalability.
-![assets/Artifacts.png](assets/artifacts.png)
-- The datasets used in this project are available at:
-    - [Anime and User Ratings](https://www.kaggle.com/datasets/krishnaveniponna/anime-and-ratings-list-dataset-2023)
-- You can find the Artifacts of trained models here:
-    - [Pre-trained Models](https://huggingface.co/krishnaveni76/anime-recommendation-models)
-## Deployment on Hugging Face Spaces 🚀
-This project is deployed using **Hugging Face Spaces**, which provides a seamless way to host **Streamlit applications**. The application pulls the datasets and trained models from Hugging Face and runs inside a **Docker container**.
-### Pre-requisites
-- Docker
-- Hugging Face (for datasets and trained models)
-- Python 3.8+
-- Hugging Face Spaces account
-### Local step 🔧
-1. **Clone the repository**
-```bash
-   git clone https://huggingface.co/spaces/krishnaveni76/Anime-Recommendation-System
-   cd Anime-Recommendation-System
-```
-2. **Set Up a Virtual Environment**:
-```bash
-# For macOS and Linux:
-python3 -m venv venv
-# For Windows:
-python -m venv venv
-```
-3. **Activate the Virtual Environment**:
-```bash
-# For macOS and Linux:
-source venv/bin/activate
-# For Windows:
-.\venv\Scripts\activate
-```
-4. **Install Required Dependencies**:
-```bash
-pip install -r requirements.txt
-```
-### Running the Pipeline 🔄
-To process the data and train the recommendation models, run the following command:
-```bash
-python run_pipeline.py
-```
-This will execute the pipeline, ingest and transform data, and train the models before making recommendations.
-### Running with Docker 🚀
-To run the application inside a Docker container, follow these steps:
-1. Build the Docker Image
-```bash
-docker build -t anime-recommendation-system .
-```
-2. Run the Docker Container
-```bash
-docker run -p 8501:8501 anime-recommendation-system
-```
-This will start the Streamlit application, which can be accessed at `http://localhost:8501`.
-### Contact 📫
-For any questions, suggestions, or collaboration opportunities, feel free to reach out:
-📧Email: [email protected]
-🌐 LinkedIn: [Krishnaveni Ponna](https://www.linkedin.com/in/krishnaveni-ponna-28ab93239)
 🐦 Twitter: [@Krishnaveni076](https://x.com/Krishnaveni076)

+---
+title: Anime Recommendation System
+emoji: 📚
+colorFrom: purple
+colorTo: yellow
+sdk: streamlit
+sdk_version: 1.41.1
+app_file: app.py
+pinned: false
+license: apache-2.0
+---
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Anime Recommendation system
+This is an **Anime Recommendation System** that combines multiple recommendation techniques such as **Collaborative Filtering**, **Content-Based Filtering**, and **Popularity-Based Filtering**. We used the **AnimeList 2023 dataset**, but to optimize computational cost and storage, we included only animes with an average rating above **6.0**. The system is designed for **continuous data ingestion and transformation** and is fully **dockerized** for seamless deployment.
+The system is hosted on **Hugging Face Spaces** and fetches datasets and pre-trained models from **Hugging Face Hub** to generate **personalized anime recommendations** based on user preferences and anime features.
+![assets/animes.jpg](assets/animes.jpg)
+## Live Demo 🤗
+[Anime Recommendation System App](https://huggingface.co/spaces/krishnaveni76/Anime-Recommendation-System)
+## Tech Stacks 🛠️
+- **Python**: Main programming language used for building recommendation algorithms and Streamlit app.
+- **Docker**: Containerizes the application to ensure a consistent environment across different platforms.
+- **Streamlit**: For building and deploying the web app that serves the recommendations.
+- **Hugging Face Spaces**: Hosts the Streamlit-based recommendation system.
+- **Hugging Face Datasets**: Stores and retrieves anime datasets for processing.
+- **Hugging Face Models**: Stores the pre-trained recommendation models for inference.
+## Pipeline 🚀
+![assets/project_architecture.gif](assets/project_architecture.gif)
+The pipeline follows a structured sequence of steps to build an **Anime Recommendation System**, including data ingestion, transformation, and multiple recommendation models.
+### 1. Data Ingestion 📥
+- Initiates the **data ingestion process**, where anime data is loaded from Hugging Face datasets.
+- The ingested data is saved as artifacts in a local folder for further processing.
+### 2. Data Transformation 🔄
+- Cleans, transforms, and processes the raw data into a structured format.
+- Extracts important features required for **Content-Based Filtering** and prepares data for **Collaborative Filtering**.
+### 3. Collaborative Filtering 🤝
+- Implements **three collaborative filtering models** to recommend anime based on user preferences:
+  - **Singular Value Decomposition (SVD)**: Factorizes the user-item interaction matrix to make personalized recommendations.
+  - **Item-Based K-Nearest Neighbors (Item-KNN)**: Recommends anime similar to a given anime based on user ratings.
+  - **User-Based K-Nearest Neighbors (User-KNN)**: Suggests anime that users with similar preferences have liked.
+- The chosen model is trained using **transformed data**, and the final trained model is stored as an artifact.
+- Once trained, it can generate recommendations for users or anime titles.
+![assets/collaborative and contentbased filtering.png](assets/collaborative_and_contentbased_filtering.png)
+### 4. Content-Based Filtering 🎭
+- Uses extracted anime features like genres to train a **Content-Based Recommendation Model**.
+- This model recommends anime similar to those a user has watched or liked.
+### 5. Popularity-Based Filtering ⭐
+This recommendation system ranks anime based on various **popularity metrics**, making it ideal for users who want to discover trending or highly-rated shows **without needing personalized preferences**.
+The system applies different filters to sort anime based on:
+- **Most Popular** 🎭: Anime ranked by **popularity score**, highlighting the most widely recognized titles.
+- **Top Ranked** 🏆: Highest-rated anime, based on **official ranking metrics**.
+- **Overall Top Rated** ⭐: Best-rated anime, sorted by **average user ratings**.
+- **Most Favorited** ❤️: Anime with the highest number of **favorites**, indicating strong fan appreciation.
+- **Highest Member Count** 👥: Anime with the largest **viewer base**, showing widespread appeal.
+- **Popular Among Members** 🔥: Anime with a **high number of members and strong ratings**, making them community favorites.
+- **Highest Average Rating** 🎖️: Shows that have the **best average rating** after handling missing values.
+## Artifacts Storage 📂
+All intermediate and final outputs, including processed datasets and trained models, are first saved locally in the **Artifacts** folder. These artifacts are then uploaded to **Hugging Face** for efficient storage and easy access.
+When building the **Streamlit** app, these datasets and trained models are retrieved directly from **Hugging Face**, ensuring seamless integration and scalability.
+![assets/Artifacts.png](assets/artifacts.png)
+- The datasets used in this project are available at:
+    - [Anime and User Ratings](https://www.kaggle.com/datasets/krishnaveniponna/anime-and-ratings-list-dataset-2023)
+- You can find the Artifacts of trained models here:
+    - [Pre-trained Models](https://huggingface.co/krishnaveni76/anime-recommendation-models)
+## Deployment on Hugging Face Spaces 🚀
+This project is deployed using **Hugging Face Spaces**, which provides a seamless way to host **Streamlit applications**. The application pulls the datasets and trained models from Hugging Face and runs inside a **Docker container**.
+### Pre-requisites
+- Docker
+- Hugging Face (for datasets and trained models)
+- Python 3.8+
+- Hugging Face Spaces account
+### Local step 🔧
+1. **Clone the repository**
+```bash
+   git clone https://huggingface.co/spaces/krishnaveni76/Anime-Recommendation-System
+   cd Anime-Recommendation-System
+```
+2. **Set Up a Virtual Environment**:
+```bash
+# For macOS and Linux:
+python3 -m venv venv
+# For Windows:
+python -m venv venv
+```
+3. **Activate the Virtual Environment**:
+```bash
+# For macOS and Linux:
+source venv/bin/activate
+# For Windows:
+.\venv\Scripts\activate
+```
+4. **Install Required Dependencies**:
+```bash
+pip install -r requirements.txt
+```
+### Running the Pipeline 🔄
+To process the data and train the recommendation models, run the following command:
+```bash
+python run_pipeline.py
+```
+This will execute the pipeline, ingest and transform data, and train the models before making recommendations.
+### Running with Docker 🚀
+To run the application inside a Docker container, follow these steps:
+1. Build the Docker Image
+```bash
+docker build -t anime-recommendation-system .
+```
+2. Run the Docker Container
+```bash
+docker run -p 8501:8501 anime-recommendation-system
+```
+This will start the Streamlit application, which can be accessed at `http://localhost:8501`.
+### Contact 📫
+For any questions, suggestions, or collaboration opportunities, feel free to reach out:
+📧Email: [email protected]
+🌐 LinkedIn: [Krishnaveni Ponna](https://www.linkedin.com/in/krishnaveni-ponna-28ab93239)
 🐦 Twitter: [@Krishnaveni076](https://x.com/Krishnaveni076)

anime_recommender/components/collaborative_recommender.py CHANGED Viewed

@@ -3,9 +3,10 @@ from anime_recommender.loggers.logging import logging
 from anime_recommender.exception.exception import AnimeRecommendorException
 from anime_recommender.entity.config_entity import CollaborativeModelConfig
 from anime_recommender.entity.artifact_entity import DataTransformationArtifact, CollaborativeModelArtifact
-from anime_recommender.utils.main_utils.utils import load_csv_data, save_model, load_object
 from anime_recommender.model_trainer.collaborative_modelling import CollaborativeAnimeRecommender
 class CollaborativeModelTrainer:
     """
     Trains and saves collaborative filtering recommendation models.
@@ -29,63 +30,67 @@ class CollaborativeModelTrainer:
         except Exception as e:
             raise AnimeRecommendorException(e, sys)
-    def initiate_model_trainer(self, model_type: str) -> CollaborativeModelArtifact:
         """
-        Trains and saves the specified collaborative filtering model.
-        Args:
-            model_type (str): The type of model to train.
-                              Choices: 'svd', 'item_knn', 'user_knn'.
         Returns:
-            CollaborativeModelArtifact: Object containing the file path of the trained model.
         """
         try:
             logging.info("Loading transformed data...")
             df = load_csv_data(self.data_transformation_artifact.merged_file_path)
-            recommender = CollaborativeAnimeRecommender(df)
-            if model_type == 'svd':
-                logging.info("Training and saving SVD model...")
-                recommender.train_svd()
-                save_model(recommender.svd, self.collaborative_model_trainer_config.svd_trained_model_file_path)
-                logging.info("Loading pre-trained SVD model...")
-                svd_model = load_object(self.collaborative_model_trainer_config.svd_trained_model_file_path)
-                svd_recommendations = recommender.get_svd_recommendations(user_id=436, n=10, svd_model=svd_model)
-                logging.info(f"SVD recommendations: {svd_recommendations}")
-                return CollaborativeModelArtifact(
-                    svd_file_path=self.collaborative_model_trainer_config.svd_trained_model_file_path
-                )
-            elif model_type == 'item_knn':
-                logging.info("Training and saving KNN item-based model...")
-                recommender.train_knn_item_based()
-                save_model(recommender.knn_item_based, self.collaborative_model_trainer_config.item_knn_trained_model_file_path)
-                logging.info("Loading pre-trained item-based KNN model...")
-                item_knn_model = load_object(self.collaborative_model_trainer_config.item_knn_trained_model_file_path)
-                item_based_recommendations = recommender.get_item_based_recommendations(
-                    anime_name='One Piece', n_recommendations=10, knn_item_model=item_knn_model
-                )
-                logging.info(f"Item Based recommendations: {item_based_recommendations}")
-                return CollaborativeModelArtifact(
-                    item_based_knn_file_path=self.collaborative_model_trainer_config.item_knn_trained_model_file_path
-                )
-            elif model_type == 'user_knn':
-                logging.info("Training and saving KNN user-based model...")
-                recommender.train_knn_user_based()
-                save_model(recommender.knn_user_based, self.collaborative_model_trainer_config.user_knn_trained_model_file_path)
-                logging.info("Loading pre-trained user-based KNN model...")
-                user_knn_model = load_object(self.collaborative_model_trainer_config.user_knn_trained_model_file_path)
-                user_based_recommendations = recommender.get_user_based_recommendations(
-                    user_id=817, n_recommendations=10, knn_user_model=user_knn_model
-                )
-                logging.info(f"User Based recommendations: {user_based_recommendations}")
-                return CollaborativeModelArtifact(
-                    user_based_knn_file_path=self.collaborative_model_trainer_config.user_knn_trained_model_file_path
-                )
-            else:
-                raise ValueError("Invalid model_type. Choose from 'svd', 'item_knn', or 'user_knn'.")
         except Exception as e:
-            raise AnimeRecommendorException(f"Error in CollaborativeModelTrainer: {str(e)}", sys)

 from anime_recommender.exception.exception import AnimeRecommendorException
 from anime_recommender.entity.config_entity import CollaborativeModelConfig
 from anime_recommender.entity.artifact_entity import DataTransformationArtifact, CollaborativeModelArtifact
+from anime_recommender.utils.main_utils.utils import load_csv_data, save_model, load_object, upload_model_to_huggingface
 from anime_recommender.model_trainer.collaborative_modelling import CollaborativeAnimeRecommender
+from anime_recommender.constant import *
 class CollaborativeModelTrainer:
     """
     Trains and saves collaborative filtering recommendation models.
         except Exception as e:
             raise AnimeRecommendorException(e, sys)
+    def initiate_model_trainer(self) -> CollaborativeModelArtifact:
         """
+        Trains and saves all collaborative filtering models.
         Returns:
+            CollaborativeModelArtifact: Object containing file paths of all trained models.
         """
         try:
             logging.info("Loading transformed data...")
             df = load_csv_data(self.data_transformation_artifact.merged_file_path)
+            recommender = CollaborativeAnimeRecommender(df)
+            # Train and save SVD model
+            logging.info("Training and saving SVD model...")
+            recommender.train_svd()
+            save_model(model=recommender.svd,file_path= self.collaborative_model_trainer_config.svd_trained_model_file_path)
+            upload_model_to_huggingface(
+                model_path=self.collaborative_model_trainer_config.svd_trained_model_file_path,
+                repo_id=MODELS_FILEPATH,
+                filename=MODEL_TRAINER_SVD_TRAINED_MODEL_NAME
+            )
+            logging.info("Loading pre-trained SVD model...")
+            svd_model = load_object(self.collaborative_model_trainer_config.svd_trained_model_file_path)
+            svd_recommendations = recommender.get_svd_recommendations(user_id=436, n=10, svd_model=svd_model)
+            logging.info(f"SVD recommendations: {svd_recommendations}")
+            # Train and save Item-Based KNN model
+            logging.info("Training and saving KNN item-based model...")
+            recommender.train_knn_item_based()
+            save_model(model=recommender.knn_item_based, file_path=self.collaborative_model_trainer_config.item_knn_trained_model_file_path)
+            upload_model_to_huggingface(
+                model_path=self.collaborative_model_trainer_config.item_knn_trained_model_file_path,
+                repo_id=MODELS_FILEPATH,
+                filename=MODEL_TRAINER_ITEM_KNN_TRAINED_MODEL_NAME
+            )
+            logging.info("Loading pre-trained item-based KNN model...")
+            item_knn_model = load_object(self.collaborative_model_trainer_config.item_knn_trained_model_file_path)
+            item_based_recommendations = recommender.get_item_based_recommendations(
+                anime_name='One Piece', n_recommendations=10, knn_item_model=item_knn_model
+            )
+            logging.info(f"Item Based recommendations: {item_based_recommendations}")
+            # Train and save User-Based KNN model
+            logging.info("Training and saving KNN user-based model...")
+            recommender.train_knn_user_based()
+            save_model(model=recommender.knn_user_based,file_path= self.collaborative_model_trainer_config.user_knn_trained_model_file_path)
+            upload_model_to_huggingface(
+                model_path=self.collaborative_model_trainer_config.user_knn_trained_model_file_path,
+                repo_id=MODELS_FILEPATH,
+                filename=MODEL_TRAINER_USER_KNN_TRAINED_MODEL_NAME
+            )
+            logging.info("Loading pre-trained user-based KNN model...")
+            user_knn_model = load_object(self.collaborative_model_trainer_config.user_knn_trained_model_file_path)
+            user_based_recommendations = recommender.get_user_based_recommendations(
+                user_id=817, n_recommendations=10, knn_user_model=user_knn_model
+            )
+            logging.info(f"User Based recommendations: {user_based_recommendations}")
+            return CollaborativeModelArtifact(
+                svd_file_path=self.collaborative_model_trainer_config.svd_trained_model_file_path,
+                item_based_knn_file_path=self.collaborative_model_trainer_config.item_knn_trained_model_file_path,
+                user_based_knn_file_path=self.collaborative_model_trainer_config.user_knn_trained_model_file_path
+            )
         except Exception as e:
+            raise AnimeRecommendorException(f"Error in CollaborativeModelTrainer: {str(e)}", sys)

anime_recommender/components/content_based_recommender.py CHANGED Viewed

@@ -3,7 +3,7 @@ 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_based_modelling import ContentBasedRecommender
 from anime_recommender.constant import *
@@ -42,7 +42,12 @@ class ContentBasedModelTrainer:
             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...")

 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, upload_model_to_huggingface
 from anime_recommender.model_trainer.content_based_modelling import ContentBasedRecommender
 from anime_recommender.constant import *
             recommender = ContentBasedRecommender(df=df )
             # Save the model (TF-IDF and cosine similarity matrix)
+            recommender.save_model(model_path=self.content_based_model_trainer_config.cosine_similarity_model_file_path)
+            upload_model_to_huggingface(
+                model_path=self.content_based_model_trainer_config.cosine_similarity_model_file_path,
+                repo_id=MODELS_FILEPATH,
+                filename=MODEL_TRAINER_COSINESIMILARITY_MODEL_NAME
+            )
             logging.info("Model saved successfully.")
             logging.info("Loading saved model to get recommendations...")

anime_recommender/constant/__init__.py CHANGED Viewed

@@ -36,5 +36,4 @@ MODEL_TRAINER_ITEM_KNN_TRAINED_MODEL_NAME: str = "itembasedknn.pkl"
 MODEL_TRAINER_USER_KNN_TRAINED_MODEL_NAME: str = "userbasedknn.pkl"
 MODEL_TRAINER_CON_TRAINED_MODEL_DIR:str = "content_based_recommenders"
-MODEL_TRAINER_COSINESIMILARITY_MODEL_NAME:str = "cosine_similarity.pkl"

 MODEL_TRAINER_USER_KNN_TRAINED_MODEL_NAME: str = "userbasedknn.pkl"
 MODEL_TRAINER_CON_TRAINED_MODEL_DIR:str = "content_based_recommenders"
+MODEL_TRAINER_COSINESIMILARITY_MODEL_NAME:str = "cosine_similarity.pkl"

anime_recommender/exception/exception.py CHANGED Viewed

@@ -2,14 +2,14 @@ import sys
 class AnimeRecommendorException(Exception):
     """
-    Custom exception class for handling errors in the Energy Generation Prediction project.
     This class captures the error message, file name, and line number where an exception occurred.
     It is useful for debugging and identifying the source of the error in a structured way.
     """
     def __init__(self,error_message, error_details:sys):
         """
-        Initialize the EnergyGenerationException instance.
         Args:
             error_message (str): The error message describing the exception.

 class AnimeRecommendorException(Exception):
     """
+    Custom exception class for handling errors in the Anime Recommendation project.
     This class captures the error message, file name, and line number where an exception occurred.
     It is useful for debugging and identifying the source of the error in a structured way.
     """
     def __init__(self,error_message, error_details:sys):
         """
+        Initialize the AnimeRecommendorException instance.
         Args:
             error_message (str): The error message describing the exception.

anime_recommender/pipelines/training_pipeline.py CHANGED Viewed

@@ -1,7 +1,6 @@
 import sys
 from anime_recommender.loggers.logging import logging
 from anime_recommender.exception.exception import AnimeRecommendorException
 from anime_recommender.components.data_ingestion import DataIngestion
 from anime_recommender.components.data_transformation import DataTransformation
 from anime_recommender.components.collaborative_recommender import CollaborativeModelTrainer
@@ -80,7 +79,7 @@ class TrainingPipeline:
                 collaborative_model_trainer_config=collaborative_model_config,
                 data_transformation_artifact=data_transformation_artifact
             )
-            collaborative_model_trainer_artifact = collaborative_model_trainer.initiate_model_trainer(model_type='user_knn')
             logging.info(f"Collaborative Model Training completed: {collaborative_model_trainer_artifact}")
             return collaborative_model_trainer_artifact
         except Exception as e:

 import sys
 from anime_recommender.loggers.logging import logging
 from anime_recommender.exception.exception import AnimeRecommendorException
 from anime_recommender.components.data_ingestion import DataIngestion
 from anime_recommender.components.data_transformation import DataTransformation
 from anime_recommender.components.collaborative_recommender import CollaborativeModelTrainer
                 collaborative_model_trainer_config=collaborative_model_config,
                 data_transformation_artifact=data_transformation_artifact
             )
+            collaborative_model_trainer_artifact = collaborative_model_trainer.initiate_model_trainer()
             logging.info(f"Collaborative Model Training completed: {collaborative_model_trainer_artifact}")
             return collaborative_model_trainer_artifact
         except Exception as e:

anime_recommender/utils/main_utils/utils.py CHANGED Viewed

@@ -5,6 +5,7 @@ import joblib
 from anime_recommender.loggers.logging import logging
 from anime_recommender.exception.exception import AnimeRecommendorException
 from anime_recommender.constant import *
 def export_data_to_dataframe(dataframe: pd.DataFrame, file_path: str) -> pd.DataFrame:
     """
@@ -86,4 +87,26 @@ def load_object(file_path: str) -> object:
             return joblib.load(file_obj)
     except Exception as e:
         logging.error(f"Error loading object from {file_path}: {e}")
         raise AnimeRecommendorException(e, sys) from e

 from anime_recommender.loggers.logging import logging
 from anime_recommender.exception.exception import AnimeRecommendorException
 from anime_recommender.constant import *
+from huggingface_hub import HfApi, HfFolder
 def export_data_to_dataframe(dataframe: pd.DataFrame, file_path: str) -> pd.DataFrame:
     """
             return joblib.load(file_obj)
     except Exception as e:
         logging.error(f"Error loading object from {file_path}: {e}")
+        raise AnimeRecommendorException(e, sys) from e
+def upload_model_to_huggingface(model_path: str, repo_id: str, filename: str):
+    """
+    Uploads a trained model file to the specified Hugging Face repository.
+    Args:
+        model_path (str): Local path of the trained model file.
+        repo_id (str): Hugging Face repository ID (e.g., 'krishnaveni76/anime-recommendation-models').
+        filename (str): Name of the file when uploaded to Hugging Face.
+    """
+    try:
+        api = HfApi()
+        api.upload_file(
+            path_or_fileobj=model_path,
+            path_in_repo=filename,
+            repo_id=repo_id,
+            repo_type="model"
+        )
+        logging.info(f"Successfully uploaded {filename} to Hugging Face: {repo_id}")
+    except Exception as e:
+        logging.info(f"Error uploading model to Hugging Face: {str(e)}")
         raise AnimeRecommendorException(e, sys) from e

app.py CHANGED Viewed

@@ -1,242 +1,242 @@
-import pandas as pd
-import streamlit as st
-from anime_recommender.model_trainer.content_based_modelling import ContentBasedRecommender
-from anime_recommender.model_trainer.collaborative_modelling import CollaborativeAnimeRecommender
-from anime_recommender.model_trainer.top_anime_filtering import PopularityBasedFiltering
-import joblib
-from anime_recommender.constant import *
-from huggingface_hub import hf_hub_download
-from datasets import load_dataset
-def run_app():
-    """
-    Initializes the Streamlit app, loads necessary datasets and models,
-    and provides a UI for anime recommendations based on three methods:
-    Content-Based, Collaborative, and Popularity-Based Filtering. 🎬🎮
-    """
-    # Set page configuration
-    st.set_page_config(page_title="Anime Recommendation System", layout="wide")
-    # Load datasets if not present in session state
-    if "anime_data" not in st.session_state or "anime_user_ratings" not in st.session_state:
-        # Load datasets from Hugging Face (assuming no splits)
-        animedataset = load_dataset(ANIME_FILE_PATH, split=None)
-        mergeddataset = load_dataset(ANIMEUSERRATINGS_FILE_PATH, split=None)
-        # Convert the dataset to Pandas DataFrame
-        st.session_state.anime_data = pd.DataFrame(animedataset["train"])
-        st.session_state.anime_user_ratings = pd.DataFrame(mergeddataset["train"])
-    # Load models only once
-    if "models_loaded" not in st.session_state:
-        st.session_state.models_loaded = {}
-        # Load models
-        st.session_state.models_loaded["cosine_similarity_model"] = hf_hub_download(MODELS_FILEPATH, MODEL_TRAINER_COSINESIMILARITY_MODEL_NAME)
-        st.session_state.models_loaded["item_based_knn_model_path"] = hf_hub_download(MODELS_FILEPATH, MODEL_TRAINER_ITEM_KNN_TRAINED_MODEL_NAME)
-        st.session_state.models_loaded["user_based_knn_model_path"] = hf_hub_download(MODELS_FILEPATH, MODEL_TRAINER_USER_KNN_TRAINED_MODEL_NAME)
-        st.session_state.models_loaded["svd_model_path"] = hf_hub_download(MODELS_FILEPATH, MODEL_TRAINER_SVD_TRAINED_MODEL_NAME)
-        # Load the models using joblib
-        with open(st.session_state.models_loaded["item_based_knn_model_path"], "rb") as f:
-            st.session_state.models_loaded["item_based_knn_model"] = joblib.load(f)
-        with open(st.session_state.models_loaded["user_based_knn_model_path"], "rb") as f:
-            st.session_state.models_loaded["user_based_knn_model"] = joblib.load(f)
-        with open(st.session_state.models_loaded["svd_model_path"], "rb") as f:
-            st.session_state.models_loaded["svd_model"] = joblib.load(f)
-        print("Models loaded successfully!")
-    # Access the data from session state
-    anime_data = st.session_state.anime_data
-    anime_user_ratings = st.session_state.anime_user_ratings
-    # # Display dataset info
-    # st.write("Anime Data:")
-    # st.dataframe(anime_data.head())
-    # st.write("Anime User Ratings Data:")
-    # st.dataframe(anime_user_ratings.head())
-    # Access the models from session state
-    cosine_similarity_model_path = hf_hub_download(MODELS_FILEPATH, MODEL_TRAINER_COSINESIMILARITY_MODEL_NAME)
-    item_based_knn_model = st.session_state.models_loaded["item_based_knn_model"]
-    user_based_knn_model = st.session_state.models_loaded["user_based_knn_model"]
-    svd_model = st.session_state.models_loaded["svd_model"]
-    print("Models loaded successfully!")
-    # Streamlit UI
-    app_selector = st.sidebar.radio(
-        "Select App", ("Content-Based Recommender", "Collaborative Recommender", "Top Anime Recommender")
-    )
-    # Content-Based Recommender App
-    if app_selector == "Content-Based Recommender":
-        st.title("Content-Based Recommendation System")
-        try:
-            anime_list = anime_data["name"].tolist()
-            anime_name = st.selectbox("Pick an anime..unlock similar anime recommendations..", anime_list)
-            # Set number of recommendations
-            max_recommendations = min(len(anime_data), 100)
-            n_recommendations = st.slider("Number of Recommendations", 1, max_recommendations, 10)
-            # Inject custom CSS for anime name font size
-            st.markdown(
-                """
-                <style>
-                .anime-title {
-                    font-size: 14px !important;
-                    font-weight: bold;
-                    text-align: center;
-                    margin-top: 5px;
-                }
-                </style>
-                """,
-                unsafe_allow_html=True,
-            )
-            # Get Recommendations
-            if st.button("Get Recommendations"):
-                try:
-                    recommender = ContentBasedRecommender(anime_data)
-                    recommendations = recommender.get_rec_cosine(anime_name, n_recommendations=n_recommendations,model_path=cosine_similarity_model_path)
-                    if isinstance(recommendations, str):
-                        st.warning(recommendations)
-                    elif recommendations.empty:
-                        st.warning("No recommendations found.🧐")
-                    else:
-                        st.write(f"Here are the Content-based Recommendations for {anime_name}:")
-                        cols = st.columns(5)
-                        for i, row in enumerate(recommendations.iterrows()):
-                            col = cols[i % 5]
-                            with col:
-                                st.image(row[1]['Image URL'], use_container_width=True)
-                                st.markdown(
-                                    f"<div class='anime-title'>{row[1]['Anime name']}</div>",
-                                    unsafe_allow_html=True,
-                                )
-                                st.caption(f"Genres: {row[1]['Genres']} | Rating: {row[1]['Rating']}")
-                except Exception as e:
-                    st.error(f"Unexpected error: {str(e)}")
-        except Exception as e:
-            st.error(f"Unexpected error: {str(e)}")
-    elif app_selector == "Collaborative Recommender":
-        st.title("Collaborative Recommender System 🧑‍🤝‍🧑💬")
-        try:
-            # Sidebar for choosing the collaborative filtering method
-            collaborative_method = st.sidebar.selectbox(
-                "Choose a collaborative filtering method:",
-                ["SVD Collaborative Filtering", "User-Based Collaborative Filtering", "Anime-Based KNN Collaborative Filtering"]
-            )
-            # User input
-            if collaborative_method == "SVD Collaborative Filtering" or collaborative_method == "User-Based Collaborative Filtering":
-                user_ids = anime_user_ratings['user_id'].unique()
-                user_id = st.selectbox("Select your MyAnimeList user ID to get anime recommendations based on similar users", user_ids)
-                n_recommendations = st.slider("Number of Recommendations:", min_value=1, max_value=50, value=10)
-            elif collaborative_method == "Anime-Based KNN Collaborative Filtering":
-                anime_list = anime_user_ratings["name"].dropna().unique().tolist()
-                anime_name = st.selectbox("Pick an anime, and we'll suggest more titles you'll love", anime_list)
-                n_recommendations = st.slider("Number of Recommendations:", min_value=1, max_value=50, value=10)
-            # Get recommendations
-            if st.button("Get Recommendations"):
-                # Load the recommender
-                recommender = CollaborativeAnimeRecommender(anime_user_ratings)
-                if collaborative_method == "SVD Collaborative Filtering":
-                    recommendations = recommender.get_svd_recommendations(user_id, n=n_recommendations, svd_model=svd_model)
-                elif collaborative_method == "User-Based Collaborative Filtering":
-                    recommendations = recommender.get_user_based_recommendations(user_id, n_recommendations=n_recommendations, knn_user_model=user_based_knn_model)
-                elif collaborative_method == "Anime-Based KNN Collaborative Filtering":
-                    if anime_name:
-                        recommendations = recommender.get_item_based_recommendations(anime_name, n_recommendations=n_recommendations, knn_item_model=item_based_knn_model)
-                    else:
-                        st.error("Invalid Anime Name. Please enter a valid anime title.")
-                if isinstance(recommendations, pd.DataFrame) and not recommendations.empty:
-                    if len(recommendations) < n_recommendations:
-                        st.warning(f"Oops...Only {len(recommendations)} recommendations available, fewer than the requested {n_recommendations}.")
-                    st.write(f"Here are the {collaborative_method} Recommendations:")
-                    cols = st.columns(5)
-                    for i, row in enumerate(recommendations.iterrows()):
-                        col = cols[i % 5]
-                        with col:
-                            st.image(row[1]['Image URL'], use_container_width=True)
-                            st.markdown(
-                                f"<div class='anime-title'>{row[1]['Anime Name']}</div>",
-                                unsafe_allow_html=True,
-                            )
-                            st.caption(f"Genres: {row[1]['Genres']} | Rating: {row[1]['Rating']}")
-                else:
-                    st.error("No recommendations found.")
-        except Exception as e:
-            st.error(f"An error occurred: {e}")
-    elif app_selector == "Top Anime Recommender":
-        st.title("Top Anime Recommender System 🔥")
-        try:
-            popularity_method = st.sidebar.selectbox(
-                "Choose a Popularity-Based Filtering method:",
-                [
-                    "Popular Animes",
-                    "Top Ranked Animes",
-                    "Overall Top Rated Animes",
-                    "Favorite Animes",
-                    "Top Animes by Members",
-                    "Popular Anime Among Members",
-                    "Top Average Rated Animes",
-                ]
-            )
-            n_recommendations = st.slider("Number of Recommendations:", min_value=1, max_value=500 , value=10)
-            if st.button("Get Recommendations"):
-                recommender = PopularityBasedFiltering(anime_data)
-                # Get recommendations based on selected method
-                if popularity_method == "Popular Animes":
-                    recommendations = recommender.popular_animes(n=n_recommendations)
-                elif popularity_method == "Top Ranked Animes":
-                    recommendations = recommender.top_ranked_animes(n=n_recommendations)
-                elif popularity_method == "Overall Top Rated Animes":
-                    recommendations = recommender.overall_top_rated_animes(n=n_recommendations)
-                elif popularity_method == "Favorite Animes":
-                    recommendations = recommender.favorite_animes(n=n_recommendations)
-                elif popularity_method == "Top Animes by Members":
-                    recommendations = recommender.top_animes_members(n=n_recommendations)
-                elif popularity_method == "Popular Anime Among Members":
-                    recommendations = recommender.popular_anime_among_members(n=n_recommendations)
-                elif popularity_method == "Top Average Rated Animes":
-                    recommendations = recommender.top_avg_rated(n=n_recommendations)
-                else:
-                    st.error("Invalid selection. Please choose a valid method.")
-                    recommendations = None
-                # Display recommendations
-                if isinstance(recommendations, pd.DataFrame) and not recommendations.empty:
-                    st.write(f" Here are the Recommendations:")
-                    cols = st.columns(5)
-                    for i, row in recommendations.iterrows():
-                        col = cols[i % 5]
-                        with col:
-                            st.image(row['Image URL'], use_container_width=True)
-                            st.markdown(
-                                f"<div class='anime-title'>{row['Anime name']}</div>",
-                                unsafe_allow_html=True,
-                            )
-                            st.caption(f"Genres: {row['Genres']} | Rating: {row['Rating']}")
-                else:
-                    st.error("No recommendations found.")
-        except Exception as e:
-            st.error(f"An error occurred: {e}")
-if __name__ == "__main__":
     run_app()

+import pandas as pd
+import streamlit as st
+from anime_recommender.model_trainer.content_based_modelling import ContentBasedRecommender
+from anime_recommender.model_trainer.collaborative_modelling import CollaborativeAnimeRecommender
+from anime_recommender.model_trainer.top_anime_filtering import PopularityBasedFiltering
+import joblib
+from anime_recommender.constant import *
+from huggingface_hub import hf_hub_download
+from datasets import load_dataset
+def run_app():
+    """
+    Initializes the Streamlit app, loads necessary datasets and models,
+    and provides a UI for anime recommendations based on three methods:
+    Content-Based, Collaborative, and Popularity-Based Filtering. 🎬🎮
+    """
+    # Set page configuration
+    st.set_page_config(page_title="Anime Recommendation System", layout="wide")
+    # Load datasets if not present in session state
+    if "anime_data" not in st.session_state or "anime_user_ratings" not in st.session_state:
+        # Load datasets from Hugging Face (assuming no splits)
+        animedataset = load_dataset(ANIME_FILE_PATH, split=None)
+        mergeddataset = load_dataset(ANIMEUSERRATINGS_FILE_PATH, split=None)
+        # Convert the dataset to Pandas DataFrame
+        st.session_state.anime_data = pd.DataFrame(animedataset["train"])
+        st.session_state.anime_user_ratings = pd.DataFrame(mergeddataset["train"])
+    # Load models only once
+    if "models_loaded" not in st.session_state:
+        st.session_state.models_loaded = {}
+        # Load models
+        st.session_state.models_loaded["cosine_similarity_model"] = hf_hub_download(MODELS_FILEPATH, MODEL_TRAINER_COSINESIMILARITY_MODEL_NAME)
+        st.session_state.models_loaded["item_based_knn_model_path"] = hf_hub_download(MODELS_FILEPATH, MODEL_TRAINER_ITEM_KNN_TRAINED_MODEL_NAME)
+        st.session_state.models_loaded["user_based_knn_model_path"] = hf_hub_download(MODELS_FILEPATH, MODEL_TRAINER_USER_KNN_TRAINED_MODEL_NAME)
+        st.session_state.models_loaded["svd_model_path"] = hf_hub_download(MODELS_FILEPATH, MODEL_TRAINER_SVD_TRAINED_MODEL_NAME)
+        # Load the models using joblib
+        with open(st.session_state.models_loaded["item_based_knn_model_path"], "rb") as f:
+            st.session_state.models_loaded["item_based_knn_model"] = joblib.load(f)
+        with open(st.session_state.models_loaded["user_based_knn_model_path"], "rb") as f:
+            st.session_state.models_loaded["user_based_knn_model"] = joblib.load(f)
+        with open(st.session_state.models_loaded["svd_model_path"], "rb") as f:
+            st.session_state.models_loaded["svd_model"] = joblib.load(f)
+        print("Models loaded successfully!")
+    # Access the data from session state
+    anime_data = st.session_state.anime_data
+    anime_user_ratings = st.session_state.anime_user_ratings
+    # # Display dataset info
+    # st.write("Anime Data:")
+    # st.dataframe(anime_data.head())
+    # st.write("Anime User Ratings Data:")
+    # st.dataframe(anime_user_ratings.head())
+    # Access the models from session state
+    cosine_similarity_model_path = hf_hub_download(MODELS_FILEPATH, MODEL_TRAINER_COSINESIMILARITY_MODEL_NAME)
+    item_based_knn_model = st.session_state.models_loaded["item_based_knn_model"]
+    user_based_knn_model = st.session_state.models_loaded["user_based_knn_model"]
+    svd_model = st.session_state.models_loaded["svd_model"]
+    print("Models loaded successfully!")
+    # Streamlit UI
+    app_selector = st.sidebar.radio(
+        "Select App", ("Content-Based Recommender", "Collaborative Recommender", "Top Anime Recommender")
+    )
+    # Content-Based Recommender App
+    if app_selector == "Content-Based Recommender":
+        st.title("Content-Based Recommendation System")
+        try:
+            anime_list = anime_data["name"].tolist()
+            anime_name = st.selectbox("Pick an anime..unlock similar anime recommendations..", anime_list)
+            # Set number of recommendations
+            max_recommendations = min(len(anime_data), 100)
+            n_recommendations = st.slider("Number of Recommendations", 1, max_recommendations, 10)
+            # Inject custom CSS for anime name font size
+            st.markdown(
+                """
+                <style>
+                .anime-title {
+                    font-size: 14px !important;
+                    font-weight: bold;
+                    text-align: center;
+                    margin-top: 5px;
+                }
+                </style>
+                """,
+                unsafe_allow_html=True,
+            )
+            # Get Recommendations
+            if st.button("Get Recommendations"):
+                try:
+                    recommender = ContentBasedRecommender(anime_data)
+                    recommendations = recommender.get_rec_cosine(anime_name, n_recommendations=n_recommendations,model_path=cosine_similarity_model_path)
+                    if isinstance(recommendations, str):
+                        st.warning(recommendations)
+                    elif recommendations.empty:
+                        st.warning("No recommendations found.🧐")
+                    else:
+                        st.write(f"Here are the Content-based Recommendations for {anime_name}:")
+                        cols = st.columns(5)
+                        for i, row in enumerate(recommendations.iterrows()):
+                            col = cols[i % 5]
+                            with col:
+                                st.image(row[1]['Image URL'], use_container_width=True)
+                                st.markdown(
+                                    f"<div class='anime-title'>{row[1]['Anime name']}</div>",
+                                    unsafe_allow_html=True,
+                                )
+                                st.caption(f"Genres: {row[1]['Genres']} | Rating: {row[1]['Rating']}")
+                except Exception as e:
+                    st.error(f"Unexpected error: {str(e)}")
+        except Exception as e:
+            st.error(f"Unexpected error: {str(e)}")
+    elif app_selector == "Collaborative Recommender":
+        st.title("Collaborative Recommender System 🧑‍🤝‍🧑💬")
+        try:
+            # Sidebar for choosing the collaborative filtering method
+            collaborative_method = st.sidebar.selectbox(
+                "Choose a collaborative filtering method:",
+                ["SVD Collaborative Filtering", "User-Based Collaborative Filtering", "Anime-Based KNN Collaborative Filtering"]
+            )
+            # User input
+            if collaborative_method == "SVD Collaborative Filtering" or collaborative_method == "User-Based Collaborative Filtering":
+                user_ids = anime_user_ratings['user_id'].unique()
+                user_id = st.selectbox("Select your MyAnimeList user ID to get anime recommendations based on similar users", user_ids)
+                n_recommendations = st.slider("Number of Recommendations:", min_value=1, max_value=50, value=10)
+            elif collaborative_method == "Anime-Based KNN Collaborative Filtering":
+                anime_list = anime_user_ratings["name"].dropna().unique().tolist()
+                anime_name = st.selectbox("Pick an anime, and we'll suggest more titles you'll love", anime_list)
+                n_recommendations = st.slider("Number of Recommendations:", min_value=1, max_value=50, value=10)
+            # Get recommendations
+            if st.button("Get Recommendations"):
+                # Load the recommender
+                recommender = CollaborativeAnimeRecommender(anime_user_ratings)
+                if collaborative_method == "SVD Collaborative Filtering":
+                    recommendations = recommender.get_svd_recommendations(user_id, n=n_recommendations, svd_model=svd_model)
+                elif collaborative_method == "User-Based Collaborative Filtering":
+                    recommendations = recommender.get_user_based_recommendations(user_id, n_recommendations=n_recommendations, knn_user_model=user_based_knn_model)
+                elif collaborative_method == "Anime-Based KNN Collaborative Filtering":
+                    if anime_name:
+                        recommendations = recommender.get_item_based_recommendations(anime_name, n_recommendations=n_recommendations, knn_item_model=item_based_knn_model)
+                    else:
+                        st.error("Invalid Anime Name. Please enter a valid anime title.")
+                if isinstance(recommendations, pd.DataFrame) and not recommendations.empty:
+                    if len(recommendations) < n_recommendations:
+                        st.warning(f"Oops...Only {len(recommendations)} recommendations available, fewer than the requested {n_recommendations}.")
+                    st.write(f"Here are the {collaborative_method} Recommendations:")
+                    cols = st.columns(5)
+                    for i, row in enumerate(recommendations.iterrows()):
+                        col = cols[i % 5]
+                        with col:
+                            st.image(row[1]['Image URL'], use_container_width=True)
+                            st.markdown(
+                                f"<div class='anime-title'>{row[1]['Anime Name']}</div>",
+                                unsafe_allow_html=True,
+                            )
+                            st.caption(f"Genres: {row[1]['Genres']} | Rating: {row[1]['Rating']}")
+                else:
+                    st.error("No recommendations found.")
+        except Exception as e:
+            st.error(f"An error occurred: {e}")
+    elif app_selector == "Top Anime Recommender":
+        st.title("Top Anime Recommender System 🔥")
+        try:
+            popularity_method = st.sidebar.selectbox(
+                "Choose a Popularity-Based Filtering method:",
+                [
+                    "Popular Animes",
+                    "Top Ranked Animes",
+                    "Overall Top Rated Animes",
+                    "Favorite Animes",
+                    "Top Animes by Members",
+                    "Popular Anime Among Members",
+                    "Top Average Rated Animes",
+                ]
+            )
+            n_recommendations = st.slider("Number of Recommendations:", min_value=1, max_value=500 , value=10)
+            if st.button("Get Recommendations"):
+                recommender = PopularityBasedFiltering(anime_data)
+                # Get recommendations based on selected method
+                if popularity_method == "Popular Animes":
+                    recommendations = recommender.popular_animes(n=n_recommendations)
+                elif popularity_method == "Top Ranked Animes":
+                    recommendations = recommender.top_ranked_animes(n=n_recommendations)
+                elif popularity_method == "Overall Top Rated Animes":
+                    recommendations = recommender.overall_top_rated_animes(n=n_recommendations)
+                elif popularity_method == "Favorite Animes":
+                    recommendations = recommender.favorite_animes(n=n_recommendations)
+                elif popularity_method == "Top Animes by Members":
+                    recommendations = recommender.top_animes_members(n=n_recommendations)
+                elif popularity_method == "Popular Anime Among Members":
+                    recommendations = recommender.popular_anime_among_members(n=n_recommendations)
+                elif popularity_method == "Top Average Rated Animes":
+                    recommendations = recommender.top_avg_rated(n=n_recommendations)
+                else:
+                    st.error("Invalid selection. Please choose a valid method.")
+                    recommendations = None
+                # Display recommendations
+                if isinstance(recommendations, pd.DataFrame) and not recommendations.empty:
+                    st.write(f" Here are the Recommendations:")
+                    cols = st.columns(5)
+                    for i, row in recommendations.iterrows():
+                        col = cols[i % 5]
+                        with col:
+                            st.image(row['Image URL'], use_container_width=True)
+                            st.markdown(
+                                f"<div class='anime-title'>{row['Anime name']}</div>",
+                                unsafe_allow_html=True,
+                            )
+                            st.caption(f"Genres: {row['Genres']} | Rating: {row['Rating']}")
+                else:
+                    st.error("No recommendations found.")
+        except Exception as e:
+            st.error(f"An error occurred: {e}")
+if __name__ == "__main__":
     run_app()

logs/{02_03_2025_11_40_31.log → 02_08_2025_12_23_10.log} RENAMED Viewed

@@ -1,51 +1,51 @@
-[ 2025-02-03 11:40:38,249 ] 8 root - INFO - Starting the Anime Recommendation System Training Pipeline...
-[ 2025-02-03 11:40:38,249 ] 42 root - INFO - Initiating Data Ingestion...
-[ 2025-02-03 11:40:38,249 ] 40 root - INFO - Fetching data from Hugging Face dataset: krishnaveni76/Animes
-[ 2025-02-03 11:40:50,688 ] 48 root - INFO - Shape of the dataframe: (12194, 18)
-[ 2025-02-03 11:40:50,689 ] 49 root - INFO - Column names: Index(['anime_id', 'genres', 'name', 'average_rating', 'overview', 'type',
        'episodes', 'producers', 'licensors', 'studios', 'source',
        'anime_rating', 'rank', 'popularity', 'favorites', 'scored by',
        'members', 'image url'],
       dtype='object')
-[ 2025-02-03 11:40:50,718 ] 50 root - INFO - Preview of the DataFrame:
-   anime_id                                             genres                              name  ... scored by  members                                          image url
-0     32281               Drama, Romance, School, Supernatural                    Kimi no Na wa.  ...   1807089  2597495  https://cdn.myanimelist.net/images/anime/5/870...
-1      5114  Action, Adventure, Drama, Fantasy, Magic, Mili...  Fullmetal Alchemist: Brotherhood  ...   2020030  3176556  https://cdn.myanimelist.net/images/anime/1208/...
-2     28977  Action, Comedy, Historical, Parody, Samurai, S...                          Gintama°  ...    237957   595767  https://cdn.myanimelist.net/images/anime/3/720...
-3      9253                                   Sci-Fi, Thriller                       Steins;Gate  ...   1336233  2440369  https://cdn.myanimelist.net/images/anime/1935/...
-4      9969  Action, Comedy, Historical, Parody, Samurai, S...                          Gintama'  ...    226175   525688  https://cdn.myanimelist.net/images/anime/4/503...
 [5 rows x 18 columns]
-[ 2025-02-03 11:40:50,718 ] 51 root - INFO - Data fetched successfully from Hugging Face.
-[ 2025-02-03 11:40:50,719 ] 40 root - INFO - Fetching data from Hugging Face dataset: krishnaveni76/UserRatings
-[ 2025-02-03 11:42:21,881 ] 48 root - INFO - Shape of the dataframe: (1112830, 4)
-[ 2025-02-03 11:42:21,881 ] 49 root - INFO - Column names: Index(['user_id', 'username', 'anime_id', 'rating'], dtype='object')
-[ 2025-02-03 11:42:21,889 ] 50 root - INFO - Preview of the DataFrame:
    user_id username  anime_id  rating
 0      357   zhambi     35427       5
 1      357   zhambi     28391       6
 2      357   zhambi     36649       7
 3      357   zhambi       530       6
 4      357   zhambi     37451       7
-[ 2025-02-03 11:42:21,889 ] 51 root - INFO - Data fetched successfully from Hugging Face.
-[ 2025-02-03 11:42:21,894 ] 21 root - INFO - Saving DataFrame to file: Artifacts/02_03_2025_11_40_35/data_ingestion/feature_store/Animes.csv
-[ 2025-02-03 11:42:22,227 ] 25 root - INFO - DataFrame saved successfully to Artifacts/02_03_2025_11_40_35/data_ingestion/feature_store/Animes.csv.
-[ 2025-02-03 11:42:22,227 ] 21 root - INFO - Saving DataFrame to file: Artifacts/02_03_2025_11_40_35/data_ingestion/feature_store/UserRatings.csv
-[ 2025-02-03 11:42:24,690 ] 25 root - INFO - DataFrame saved successfully to Artifacts/02_03_2025_11_40_35/data_ingestion/feature_store/UserRatings.csv.
-[ 2025-02-03 11:42:24,820 ] 46 root - INFO - Data Ingestion completed: DataIngestionArtifact(feature_store_anime_file_path='Artifacts/02_03_2025_11_40_35/data_ingestion/feature_store/Animes.csv', feature_store_userrating_file_path='Artifacts/02_03_2025_11_40_35/data_ingestion/feature_store/UserRatings.csv')
-[ 2025-02-03 11:42:24,820 ] 58 root - INFO - Initiating Data Transformation...
-[ 2025-02-03 11:42:24,821 ] 95 root - INFO - Entering initiate_data_transformation method of DataTransformation class.
-[ 2025-02-03 11:42:29,247 ] 54 root - INFO - Shape of the Merged dataframe:(916416, 21)
-[ 2025-02-03 11:42:29,247 ] 55 root - INFO - Column names: Index(['user_id', 'username', 'anime_id', 'rating', 'genres', 'name',
        'average_rating', 'overview', 'type', 'episodes', 'producers',
        'licensors', 'studios', 'source', 'anime_rating', 'rank', 'popularity',
        'favorites', 'scored by', 'members', 'image url'],
       dtype='object')
-[ 2025-02-03 11:42:31,342 ] 81 root - INFO - Shape of the Merged dataframe:(862804, 8)
-[ 2025-02-03 11:42:31,342 ] 82 root - INFO - Column names: Index(['user_id', 'anime_id', 'rating', 'genres', 'name', 'average_rating',
        'anime_rating', 'image url'],
       dtype='object')
-[ 2025-02-03 11:42:31,361 ] 83 root - INFO - Preview of the merged DataFrame:
    user_id  anime_id  rating  ... average_rating               anime_rating                                          image url
 0      357     28391       6  ...           6.65  PG-13 - Teens 13 or older  https://cdn.myanimelist.net/images/anime/9/778...
 1      357       530       6  ...           7.73  PG-13 - Teens 13 or older  https://cdn.myanimelist.net/images/anime/1440/...
@@ -54,25 +54,70 @@
 5      357     31798       9  ...           7.38  PG-13 - Teens 13 or older  https://cdn.myanimelist.net/images/anime/6/784...
 [5 rows x 8 columns]
-[ 2025-02-03 11:42:31,399 ] 21 root - INFO - Saving DataFrame to file: Artifacts/02_03_2025_11_40_35/data_transformation/transformed/Anime_UserRatings.csv
-[ 2025-02-03 11:42:38,424 ] 25 root - INFO - DataFrame saved successfully to Artifacts/02_03_2025_11_40_35/data_transformation/transformed/Anime_UserRatings.csv.
-[ 2025-02-03 11:42:38,583 ] 65 root - INFO - Data Transformation completed: DataTransformationArtifact(merged_file_path='Artifacts/02_03_2025_11_40_35/data_transformation/transformed/Anime_UserRatings.csv')
-[ 2025-02-03 11:42:38,584 ] 77 root - INFO - Initiating Collaborative Model Training...
-[ 2025-02-03 11:42:38,584 ] 42 root - INFO - Loading transformed data...
-[ 2025-02-03 11:42:38,585 ] 42 root - INFO - Loading CSV data from file: Artifacts/02_03_2025_11_40_35/data_transformation/transformed/Anime_UserRatings.csv
-[ 2025-02-03 11:42:40,977 ] 44 root - INFO - CSV file loaded successfully.
-[ 2025-02-03 11:42:40,979 ] 26 root - INFO - Initializing CollaborativeAnimeRecommender
-[ 2025-02-03 11:42:44,796 ] 45 root - INFO - Data preparation completed...
-[ 2025-02-03 11:42:44,796 ] 75 root - INFO - Training and saving KNN user-based model...
-[ 2025-02-03 11:42:44,797 ] 78 root - INFO - Training KNN model
-[ 2025-02-03 11:42:44,987 ] 82 root - INFO - KNN model training completed
-[ 2025-02-03 11:42:44,988 ] 59 root - INFO - Entered the save_model method.
-[ 2025-02-03 11:42:45,031 ] 63 root - INFO - Model saved successfully to Artifacts/02_03_2025_11_40_35/trained_models/collaborative_recommenders/userbasedknn.pkl.
-[ 2025-02-03 11:42:45,031 ] 79 root - INFO - Loading pre-trained user-based KNN model...
-[ 2025-02-03 11:42:45,031 ] 79 root - INFO - Attempting to load object from Artifacts/02_03_2025_11_40_35/trained_models/collaborative_recommenders/userbasedknn.pkl
-[ 2025-02-03 11:42:45,031 ] 85 root - INFO - Object loaded successfully.
-[ 2025-02-03 11:42:45,157 ] 253 root - INFO - Shape of filtered df: (10, 8)
-[ 2025-02-03 11:42:45,171 ] 84 root - INFO - User Based recommendations:                                   Anime Name                                          Image URL                                             Genres  Rating
 0                    Little Busters! Refrain  https://cdn.myanimelist.net/images/anime/10/55...  Comedy, Drama, Romance, School, Slice of Life,...    8.19
 1         Chuunibyou demo Koi ga Shitai! Ren  https://cdn.myanimelist.net/images/anime/7/566...      Comedy, Drama, Romance, School, Slice of Life    7.55
 2  Clannad: Mou Hitotsu no Sekai, Tomoyo-hen  https://cdn.myanimelist.net/images/anime/12/19...              Drama, Romance, School, Slice of Life    7.93
@@ -83,20 +128,21 @@
 7                           Motto To LOVE-Ru  https://cdn.myanimelist.net/images/anime/4/598...      Comedy, Ecchi, Harem, School, Sci-Fi, Shounen    7.28
 8                                   Overlord  https://cdn.myanimelist.net/images/anime/7/880...  Action, Adventure, Fantasy, Game, Magic, Super...    7.91
 9                                       No.6  https://cdn.myanimelist.net/images/anime/1474/...                                     Action, Sci-Fi    7.56
-[ 2025-02-03 11:42:45,315 ] 84 root - INFO - Collaborative Model Training completed: CollaborativeModelArtifact(svd_file_path=None, item_based_knn_file_path=None, user_based_knn_file_path='Artifacts/02_03_2025_11_40_35/trained_models/collaborative_recommenders/userbasedknn.pkl')
-[ 2025-02-03 11:42:45,315 ] 96 root - INFO - Initiating Content-Based Model Training...
-[ 2025-02-03 11:42:45,316 ] 37 root - INFO - Loading ingested data...
-[ 2025-02-03 11:42:45,316 ] 42 root - INFO - Loading CSV data from file: Artifacts/02_03_2025_11_40_35/data_ingestion/feature_store/Animes.csv
-[ 2025-02-03 11:42:45,499 ] 44 root - INFO - CSV file loaded successfully.
-[ 2025-02-03 11:42:45,500 ] 39 root - INFO - Training ContentBasedRecommender model...
-[ 2025-02-03 11:43:06,457 ] 35 root - INFO - Saving model to Artifacts/02_03_2025_11_40_35/trained_models/content_based_recommenders/cosine_similarity.pkl
-[ 2025-02-03 11:43:41,225 ] 39 root - INFO - Content recommender Model saved successfully
-[ 2025-02-03 11:43:41,244 ] 46 root - INFO - Model saved successfully.
-[ 2025-02-03 11:43:41,245 ] 48 root - INFO - Loading saved model to get recommendations...
-[ 2025-02-03 11:43:41,250 ] 46 root - INFO - Loading model from Artifacts/02_03_2025_11_40_35/trained_models/content_based_recommenders/cosine_similarity.pkl
-[ 2025-02-03 11:44:23,930 ] 50 root - INFO - Model loaded successfully
-[ 2025-02-03 11:44:24,814 ] 64 root - INFO - Recommendations generated successfully
-[ 2025-02-03 11:44:27,761 ] 50 root - INFO - Cosine similarity recommendations:                                           Anime name                                          Image URL                                             Genres Rating
 0  One Piece: Episode of Merry - Mou Hitori no Na...  https://cdn.myanimelist.net/images/anime/9/610...  Action, Adventure, Comedy, Drama, Fantasy, Sho...   8.19
 1  One Piece: Episode of Nami - Koukaishi no Nami...  https://cdn.myanimelist.net/images/anime/5/414...  Action, Adventure, Comedy, Drama, Fantasy, Sho...   8.12
 2  One Piece: Episode of Sabo - 3 Kyoudai no Kizu...  https://cdn.myanimelist.net/images/anime/1373/...  Action, Adventure, Comedy, Drama, Fantasy, Sho...   7.71
@@ -107,14 +153,14 @@
 7                                   Digimon Frontier  https://cdn.myanimelist.net/images/anime/1048/...  Action, Adventure, Comedy, Drama, Fantasy, Sho...   7.15
 8                                     Digimon Tamers  https://cdn.myanimelist.net/images/anime/7/736...         Adventure, Comedy, Drama, Fantasy, Shounen   7.63
 9                                     Digimon Savers  https://cdn.myanimelist.net/images/anime/1415/...         Adventure, Comedy, Drama, Fantasy, Shounen   6.95
-[ 2025-02-03 11:44:29,361 ] 103 root - INFO - Content-Based Model Training completed: ContentBasedModelArtifact(cosine_similarity_model_file_path='Artifacts/02_03_2025_11_40_35/trained_models/content_based_recommenders/cosine_similarity.pkl')
-[ 2025-02-03 11:44:29,366 ] 113 root - INFO - Initiating Popularity-Based Filtering...
-[ 2025-02-03 11:44:29,371 ] 41 root - INFO - Loading transformed data...
-[ 2025-02-03 11:44:29,376 ] 42 root - INFO - Loading CSV data from file: Artifacts/02_03_2025_11_40_35/data_ingestion/feature_store/Animes.csv
-[ 2025-02-03 11:44:30,775 ] 44 root - INFO - CSV file loaded successfully.
-[ 2025-02-03 11:44:30,776 ] 17 root - INFO - Initializing PopularityBasedFiltering class
-[ 2025-02-03 11:44:30,905 ] 29 root - INFO - Fetching top 10 most popular animes
-[ 2025-02-03 11:44:31,089 ] 48 root - INFO - Popular Anime recommendations:                          Anime name                                          Image URL                                             Genres  Rating
 0                Shingeki no Kyojin  https://cdn.myanimelist.net/images/anime/10/47...       Action, Drama, Fantasy, Shounen, Super Power    8.54
 1                        Death Note  https://cdn.myanimelist.net/images/anime/9/945...  Mystery, Police, Psychological, Supernatural, ...    8.62
 2  Fullmetal Alchemist: Brotherhood  https://cdn.myanimelist.net/images/anime/1208/...  Action, Adventure, Drama, Fantasy, Magic, Mili...    9.10
@@ -125,5 +171,5 @@
 7                       Tokyo Ghoul  https://cdn.myanimelist.net/images/anime/1498/...  Action, Drama, Horror, Mystery, Psychological,...    7.79
 8            Hunter x Hunter (2011)  https://cdn.myanimelist.net/images/anime/1337/...            Action, Adventure, Shounen, Super Power    9.04
 9                    Kimi no Na wa.  https://cdn.myanimelist.net/images/anime/5/870...               Drama, Romance, School, Supernatural    8.85
-[ 2025-02-03 11:44:31,094 ] 116 root - INFO - Popularity-Based Filtering completed.
-[ 2025-02-03 11:44:31,094 ] 141 root - INFO - Training Pipeline executed successfully.

+[ 2025-02-08 12:23:14,445 ] 8 root - INFO - Starting the Anime Recommendation System Training Pipeline...
+[ 2025-02-08 12:23:14,445 ] 41 root - INFO - Initiating Data Ingestion...
+[ 2025-02-08 12:23:14,445 ] 40 root - INFO - Fetching data from Hugging Face dataset: krishnaveni76/Animes
+[ 2025-02-08 12:23:20,052 ] 48 root - INFO - Shape of the dataframe: (12194, 18)
+[ 2025-02-08 12:23:20,052 ] 49 root - INFO - Column names: Index(['anime_id', 'genres', 'name', 'average_rating', 'overview', 'type',
        'episodes', 'producers', 'licensors', 'studios', 'source',
        'anime_rating', 'rank', 'popularity', 'favorites', 'scored by',
        'members', 'image url'],
       dtype='object')
+[ 2025-02-08 12:23:20,072 ] 50 root - INFO - Preview of the DataFrame:
+   anime_id                                             genres  ...  members                                          image url
+0     32281               Drama, Romance, School, Supernatural  ...  2597495  https://cdn.myanimelist.net/images/anime/5/870...
+1      5114  Action, Adventure, Drama, Fantasy, Magic, Mili...  ...  3176556  https://cdn.myanimelist.net/images/anime/1208/...
+2     28977  Action, Comedy, Historical, Parody, Samurai, S...  ...   595767  https://cdn.myanimelist.net/images/anime/3/720...
+3      9253                                   Sci-Fi, Thriller  ...  2440369  https://cdn.myanimelist.net/images/anime/1935/...
+4      9969  Action, Comedy, Historical, Parody, Samurai, S...  ...   525688  https://cdn.myanimelist.net/images/anime/4/503...
 [5 rows x 18 columns]
+[ 2025-02-08 12:23:20,072 ] 51 root - INFO - Data fetched successfully from Hugging Face.
+[ 2025-02-08 12:23:20,073 ] 40 root - INFO - Fetching data from Hugging Face dataset: krishnaveni76/UserRatings
+[ 2025-02-08 12:24:00,180 ] 48 root - INFO - Shape of the dataframe: (1112830, 4)
+[ 2025-02-08 12:24:00,181 ] 49 root - INFO - Column names: Index(['user_id', 'username', 'anime_id', 'rating'], dtype='object')
+[ 2025-02-08 12:24:00,184 ] 50 root - INFO - Preview of the DataFrame:
    user_id username  anime_id  rating
 0      357   zhambi     35427       5
 1      357   zhambi     28391       6
 2      357   zhambi     36649       7
 3      357   zhambi       530       6
 4      357   zhambi     37451       7
+[ 2025-02-08 12:24:00,184 ] 51 root - INFO - Data fetched successfully from Hugging Face.
+[ 2025-02-08 12:24:00,187 ] 22 root - INFO - Saving DataFrame to file: Artifacts/02_08_2025_12_23_12/data_ingestion/feature_store/Animes.csv
+[ 2025-02-08 12:24:00,356 ] 26 root - INFO - DataFrame saved successfully to Artifacts/02_08_2025_12_23_12/data_ingestion/feature_store/Animes.csv.
+[ 2025-02-08 12:24:00,356 ] 22 root - INFO - Saving DataFrame to file: Artifacts/02_08_2025_12_23_12/data_ingestion/feature_store/UserRatings.csv
+[ 2025-02-08 12:24:01,514 ] 26 root - INFO - DataFrame saved successfully to Artifacts/02_08_2025_12_23_12/data_ingestion/feature_store/UserRatings.csv.
+[ 2025-02-08 12:24:01,581 ] 45 root - INFO - Data Ingestion completed: DataIngestionArtifact(feature_store_anime_file_path='Artifacts/02_08_2025_12_23_12/data_ingestion/feature_store/Animes.csv', feature_store_userrating_file_path='Artifacts/02_08_2025_12_23_12/data_ingestion/feature_store/UserRatings.csv')
+[ 2025-02-08 12:24:01,582 ] 57 root - INFO - Initiating Data Transformation...
+[ 2025-02-08 12:24:01,582 ] 95 root - INFO - Entering initiate_data_transformation method of DataTransformation class.
+[ 2025-02-08 12:24:02,365 ] 54 root - INFO - Shape of the Merged dataframe:(916416, 21)
+[ 2025-02-08 12:24:02,366 ] 55 root - INFO - Column names: Index(['user_id', 'username', 'anime_id', 'rating', 'genres', 'name',
        'average_rating', 'overview', 'type', 'episodes', 'producers',
        'licensors', 'studios', 'source', 'anime_rating', 'rank', 'popularity',
        'favorites', 'scored by', 'members', 'image url'],
       dtype='object')
+[ 2025-02-08 12:24:03,520 ] 81 root - INFO - Shape of the Merged dataframe:(862804, 8)
+[ 2025-02-08 12:24:03,520 ] 82 root - INFO - Column names: Index(['user_id', 'anime_id', 'rating', 'genres', 'name', 'average_rating',
        'anime_rating', 'image url'],
       dtype='object')
+[ 2025-02-08 12:24:03,526 ] 83 root - INFO - Preview of the merged DataFrame:
    user_id  anime_id  rating  ... average_rating               anime_rating                                          image url
 0      357     28391       6  ...           6.65  PG-13 - Teens 13 or older  https://cdn.myanimelist.net/images/anime/9/778...
 1      357       530       6  ...           7.73  PG-13 - Teens 13 or older  https://cdn.myanimelist.net/images/anime/1440/...
 5      357     31798       9  ...           7.38  PG-13 - Teens 13 or older  https://cdn.myanimelist.net/images/anime/6/784...
 [5 rows x 8 columns]
+[ 2025-02-08 12:24:03,549 ] 22 root - INFO - Saving DataFrame to file: Artifacts/02_08_2025_12_23_12/data_transformation/transformed/Anime_UserRatings.csv
+[ 2025-02-08 12:24:07,286 ] 26 root - INFO - DataFrame saved successfully to Artifacts/02_08_2025_12_23_12/data_transformation/transformed/Anime_UserRatings.csv.
+[ 2025-02-08 12:24:07,400 ] 64 root - INFO - Data Transformation completed: DataTransformationArtifact(merged_file_path='Artifacts/02_08_2025_12_23_12/data_transformation/transformed/Anime_UserRatings.csv')
+[ 2025-02-08 12:24:07,401 ] 76 root - INFO - Initiating Collaborative Model Training...
+[ 2025-02-08 12:24:07,401 ] 41 root - INFO - Loading transformed data...
+[ 2025-02-08 12:24:07,401 ] 43 root - INFO - Loading CSV data from file: Artifacts/02_08_2025_12_23_12/data_transformation/transformed/Anime_UserRatings.csv
+[ 2025-02-08 12:24:08,571 ] 45 root - INFO - CSV file loaded successfully.
+[ 2025-02-08 12:24:08,572 ] 26 root - INFO - Initializing CollaborativeAnimeRecommender
+[ 2025-02-08 12:24:10,797 ] 45 root - INFO - Data preparation completed...
+[ 2025-02-08 12:24:10,797 ] 46 root - INFO - Training and saving SVD model...
+[ 2025-02-08 12:24:10,797 ] 54 root - INFO - Training SVD model
+[ 2025-02-08 12:25:13,802 ] 59 root - INFO - SVD model training completed
+[ 2025-02-08 12:25:13,803 ] 60 root - INFO - Entered the save_model method.
+[ 2025-02-08 12:25:23,132 ] 64 root - INFO - Model saved successfully to Artifacts/02_08_2025_12_23_12/trained_models/collaborative_recommenders/svd.pkl.
+[ 2025-02-08 12:25:31,079 ] 109 root - INFO - Successfully uploaded svd.pkl to Hugging Face: krishnaveni76/anime-recommendation-models
+[ 2025-02-08 12:25:31,079 ] 54 root - INFO - Loading pre-trained SVD model...
+[ 2025-02-08 12:25:31,079 ] 80 root - INFO - Attempting to load object from Artifacts/02_08_2025_12_23_12/trained_models/collaborative_recommenders/svd.pkl
+[ 2025-02-08 12:25:31,079 ] 86 root - INFO - Object loaded successfully.
+[ 2025-02-08 12:25:35,137 ] 134 root - INFO - Shape of recommended_anime: (10, 8)
+[ 2025-02-08 12:25:35,142 ] 57 root - INFO - SVD recommendations:                                           Anime Name                                             Genres                                          Image URL  Rating
+0                               Clannad: After Story  Drama, Fantasy, Romance, Slice of Life, Supern...  https://cdn.myanimelist.net/images/anime/1299/...    8.93
+1                               Fate/Zero 2nd Season            Action, Fantasy, Supernatural, Thriller  https://cdn.myanimelist.net/images/anime/1522/...    8.55
+2                   Fullmetal Alchemist: Brotherhood  Action, Adventure, Drama, Fantasy, Magic, Mili...  https://cdn.myanimelist.net/images/anime/1208/...    9.10
+3                                           Mushishi  Adventure, Fantasy, Historical, Mystery, Seine...  https://cdn.myanimelist.net/images/anime/2/738...    8.66
+4                         Tengen Toppa Gurren Lagann           Action, Adventure, Comedy, Mecha, Sci-Fi  https://cdn.myanimelist.net/images/anime/4/512...    8.63
+5              Evangelion: 2.0 You Can (Not) Advance                              Action, Mecha, Sci-Fi  https://cdn.myanimelist.net/images/anime/5/749...    8.31
+6                             Hunter x Hunter (2011)            Action, Adventure, Shounen, Super Power  https://cdn.myanimelist.net/images/anime/1337/...    9.04
+7               Kara no Kyoukai Movie 5: Mujun Rasen  Action, Drama, Mystery, Romance, Supernatural,...  https://cdn.myanimelist.net/images/anime/1574/...    8.53
+8  Rurouni Kenshin: Meiji Kenkaku Romantan - Tsui...  Action, Drama, Historical, Martial Arts, Roman...  https://cdn.myanimelist.net/images/anime/1391/...    8.71
+9                               Ginga Eiyuu Densetsu                     Drama, Military, Sci-Fi, Space  https://cdn.myanimelist.net/images/anime/13/13...    9.02
+[ 2025-02-08 12:25:35,142 ] 60 root - INFO - Training and saving KNN item-based model...
+[ 2025-02-08 12:25:35,142 ] 68 root - INFO - Training KNN model
+[ 2025-02-08 12:25:35,219 ] 60 root - INFO - Entered the save_model method.
+[ 2025-02-08 12:25:35,245 ] 64 root - INFO - Model saved successfully to Artifacts/02_08_2025_12_23_12/trained_models/collaborative_recommenders/itembasedknn.pkl.
+[ 2025-02-08 12:25:36,067 ] 4009 huggingface_hub.hf_api - WARNING - No files have been modified since last commit. Skipping to prevent empty commit.
+[ 2025-02-08 12:25:36,344 ] 109 root - INFO - Successfully uploaded itembasedknn.pkl to Hugging Face: krishnaveni76/anime-recommendation-models
+[ 2025-02-08 12:25:36,344 ] 68 root - INFO - Loading pre-trained item-based KNN model...
+[ 2025-02-08 12:25:36,344 ] 80 root - INFO - Attempting to load object from Artifacts/02_08_2025_12_23_12/trained_models/collaborative_recommenders/itembasedknn.pkl
+[ 2025-02-08 12:25:36,345 ] 86 root - INFO - Object loaded successfully.
+[ 2025-02-08 12:25:36,373 ] 185 root - INFO - Top 10 recommendations: ['Bleach', 'Naruto', 'One Piece Film: Strong World', 'Fairy Tail', 'Soul Eater', 'Death Note', 'Code Geass: Hangyaku no Lelouch', 'Naruto: Shippuuden', 'Code Geass: Hangyaku no Lelouch R2', 'Fullmetal Alchemist: Brotherhood']
+[ 2025-02-08 12:25:36,408 ] 187 root - INFO - Shape of filtered df: (10, 8)
+[ 2025-02-08 12:25:36,412 ] 73 root - INFO - Item Based recommendations:                            Anime Name                                          Image URL                                             Genres  Rating
+0     Code Geass: Hangyaku no Lelouch  https://cdn.myanimelist.net/images/anime/1032/...  Action, Mecha, Military, School, Sci-Fi, Super...    8.70
+1  Code Geass: Hangyaku no Lelouch R2  https://cdn.myanimelist.net/images/anime/1088/...  Action, Drama, Mecha, Military, Sci-Fi, Super ...    8.91
+2    Fullmetal Alchemist: Brotherhood  https://cdn.myanimelist.net/images/anime/1208/...  Action, Adventure, Drama, Fantasy, Magic, Mili...    9.10
+3                          Soul Eater  https://cdn.myanimelist.net/images/anime/9/780...  Action, Adventure, Comedy, Fantasy, Shounen, S...    7.84
+4                              Bleach  https://cdn.myanimelist.net/images/anime/3/404...  Action, Comedy, Shounen, Super Power, Supernat...    7.92
+5                          Death Note  https://cdn.myanimelist.net/images/anime/9/945...  Mystery, Police, Psychological, Supernatural, ...    8.62
+6                              Naruto  https://cdn.myanimelist.net/images/anime/13/17...  Action, Comedy, Martial Arts, Shounen, Super P...    7.99
+7                  Naruto: Shippuuden  https://cdn.myanimelist.net/images/anime/1565/...  Action, Comedy, Martial Arts, Shounen, Super P...    8.26
+8                          Fairy Tail  https://cdn.myanimelist.net/images/anime/5/181...  Action, Adventure, Comedy, Fantasy, Magic, Sho...    7.57
+9        One Piece Film: Strong World  https://cdn.myanimelist.net/images/anime/1192/...  Action, Adventure, Comedy, Drama, Fantasy, Sho...    8.08
+[ 2025-02-08 12:25:36,412 ] 76 root - INFO - Training and saving KNN user-based model...
+[ 2025-02-08 12:25:36,412 ] 78 root - INFO - Training KNN model
+[ 2025-02-08 12:25:36,535 ] 82 root - INFO - KNN model training completed
+[ 2025-02-08 12:25:36,535 ] 60 root - INFO - Entered the save_model method.
+[ 2025-02-08 12:25:36,558 ] 64 root - INFO - Model saved successfully to Artifacts/02_08_2025_12_23_12/trained_models/collaborative_recommenders/userbasedknn.pkl.
+[ 2025-02-08 12:25:37,249 ] 4009 huggingface_hub.hf_api - WARNING - No files have been modified since last commit. Skipping to prevent empty commit.
+[ 2025-02-08 12:25:37,598 ] 109 root - INFO - Successfully uploaded userbasedknn.pkl to Hugging Face: krishnaveni76/anime-recommendation-models
+[ 2025-02-08 12:25:37,598 ] 84 root - INFO - Loading pre-trained user-based KNN model...
+[ 2025-02-08 12:25:37,598 ] 80 root - INFO - Attempting to load object from Artifacts/02_08_2025_12_23_12/trained_models/collaborative_recommenders/userbasedknn.pkl
+[ 2025-02-08 12:25:37,598 ] 86 root - INFO - Object loaded successfully.
+[ 2025-02-08 12:25:37,649 ] 253 root - INFO - Shape of filtered df: (10, 8)
+[ 2025-02-08 12:25:37,654 ] 89 root - INFO - User Based recommendations:                                   Anime Name                                          Image URL                                             Genres  Rating
 0                    Little Busters! Refrain  https://cdn.myanimelist.net/images/anime/10/55...  Comedy, Drama, Romance, School, Slice of Life,...    8.19
 1         Chuunibyou demo Koi ga Shitai! Ren  https://cdn.myanimelist.net/images/anime/7/566...      Comedy, Drama, Romance, School, Slice of Life    7.55
 2  Clannad: Mou Hitotsu no Sekai, Tomoyo-hen  https://cdn.myanimelist.net/images/anime/12/19...              Drama, Romance, School, Slice of Life    7.93
 7                           Motto To LOVE-Ru  https://cdn.myanimelist.net/images/anime/4/598...      Comedy, Ecchi, Harem, School, Sci-Fi, Shounen    7.28
 8                                   Overlord  https://cdn.myanimelist.net/images/anime/7/880...  Action, Adventure, Fantasy, Game, Magic, Super...    7.91
 9                                       No.6  https://cdn.myanimelist.net/images/anime/1474/...                                     Action, Sci-Fi    7.56
+[ 2025-02-08 12:25:38,100 ] 83 root - INFO - Collaborative Model Training completed: CollaborativeModelArtifact(svd_file_path='Artifacts/02_08_2025_12_23_12/trained_models/collaborative_recommenders/svd.pkl', item_based_knn_file_path='Artifacts/02_08_2025_12_23_12/trained_models/collaborative_recommenders/itembasedknn.pkl', user_based_knn_file_path='Artifacts/02_08_2025_12_23_12/trained_models/collaborative_recommenders/userbasedknn.pkl')
+[ 2025-02-08 12:25:38,100 ] 95 root - INFO - Initiating Content-Based Model Training...
+[ 2025-02-08 12:25:38,100 ] 37 root - INFO - Loading ingested data...
+[ 2025-02-08 12:25:38,100 ] 43 root - INFO - Loading CSV data from file: Artifacts/02_08_2025_12_23_12/data_ingestion/feature_store/Animes.csv
+[ 2025-02-08 12:25:38,208 ] 45 root - INFO - CSV file loaded successfully.
+[ 2025-02-08 12:25:38,209 ] 39 root - INFO - Training ContentBasedRecommender model...
+[ 2025-02-08 12:25:52,919 ] 35 root - INFO - Saving model to Artifacts/02_08_2025_12_23_12/trained_models/content_based_recommenders/cosine_similarity.pkl
+[ 2025-02-08 12:26:00,731 ] 39 root - INFO - Content recommender Model saved successfully
+[ 2025-02-08 12:28:18,967 ] 109 root - INFO - Successfully uploaded cosine_similarity.pkl to Hugging Face: krishnaveni76/anime-recommendation-models
+[ 2025-02-08 12:28:18,969 ] 51 root - INFO - Model saved successfully.
+[ 2025-02-08 12:28:18,969 ] 53 root - INFO - Loading saved model to get recommendations...
+[ 2025-02-08 12:28:18,972 ] 46 root - INFO - Loading model from Artifacts/02_08_2025_12_23_12/trained_models/content_based_recommenders/cosine_similarity.pkl
+[ 2025-02-08 12:28:28,483 ] 50 root - INFO - Model loaded successfully
+[ 2025-02-08 12:28:28,626 ] 64 root - INFO - Recommendations generated successfully
+[ 2025-02-08 12:28:28,804 ] 55 root - INFO - Cosine similarity recommendations:                                           Anime name                                          Image URL                                             Genres Rating
 0  One Piece: Episode of Merry - Mou Hitori no Na...  https://cdn.myanimelist.net/images/anime/9/610...  Action, Adventure, Comedy, Drama, Fantasy, Sho...   8.19
 1  One Piece: Episode of Nami - Koukaishi no Nami...  https://cdn.myanimelist.net/images/anime/5/414...  Action, Adventure, Comedy, Drama, Fantasy, Sho...   8.12
 2  One Piece: Episode of Sabo - 3 Kyoudai no Kizu...  https://cdn.myanimelist.net/images/anime/1373/...  Action, Adventure, Comedy, Drama, Fantasy, Sho...   7.71
 7                                   Digimon Frontier  https://cdn.myanimelist.net/images/anime/1048/...  Action, Adventure, Comedy, Drama, Fantasy, Sho...   7.15
 8                                     Digimon Tamers  https://cdn.myanimelist.net/images/anime/7/736...         Adventure, Comedy, Drama, Fantasy, Shounen   7.63
 9                                     Digimon Savers  https://cdn.myanimelist.net/images/anime/1415/...         Adventure, Comedy, Drama, Fantasy, Shounen   6.95
+[ 2025-02-08 12:28:29,200 ] 102 root - INFO - Content-Based Model Training completed: ContentBasedModelArtifact(cosine_similarity_model_file_path='Artifacts/02_08_2025_12_23_12/trained_models/content_based_recommenders/cosine_similarity.pkl')
+[ 2025-02-08 12:28:29,201 ] 112 root - INFO - Initiating Popularity-Based Filtering...
+[ 2025-02-08 12:28:29,205 ] 41 root - INFO - Loading transformed data...
+[ 2025-02-08 12:28:29,206 ] 43 root - INFO - Loading CSV data from file: Artifacts/02_08_2025_12_23_12/data_ingestion/feature_store/Animes.csv
+[ 2025-02-08 12:28:29,762 ] 45 root - INFO - CSV file loaded successfully.
+[ 2025-02-08 12:28:29,765 ] 17 root - INFO - Initializing PopularityBasedFiltering class
+[ 2025-02-08 12:28:29,820 ] 29 root - INFO - Fetching top 10 most popular animes
+[ 2025-02-08 12:28:29,873 ] 48 root - INFO - Popular Anime recommendations:                          Anime name                                          Image URL                                             Genres  Rating
 0                Shingeki no Kyojin  https://cdn.myanimelist.net/images/anime/10/47...       Action, Drama, Fantasy, Shounen, Super Power    8.54
 1                        Death Note  https://cdn.myanimelist.net/images/anime/9/945...  Mystery, Police, Psychological, Supernatural, ...    8.62
 2  Fullmetal Alchemist: Brotherhood  https://cdn.myanimelist.net/images/anime/1208/...  Action, Adventure, Drama, Fantasy, Magic, Mili...    9.10
 7                       Tokyo Ghoul  https://cdn.myanimelist.net/images/anime/1498/...  Action, Drama, Horror, Mystery, Psychological,...    7.79
 8            Hunter x Hunter (2011)  https://cdn.myanimelist.net/images/anime/1337/...            Action, Adventure, Shounen, Super Power    9.04
 9                    Kimi no Na wa.  https://cdn.myanimelist.net/images/anime/5/870...               Drama, Romance, School, Supernatural    8.85
+[ 2025-02-08 12:28:29,877 ] 115 root - INFO - Popularity-Based Filtering completed.
+[ 2025-02-08 12:28:29,877 ] 140 root - INFO - Training Pipeline executed successfully.

notebooks/EDA.ipynb CHANGED Viewed

The diff for this file is too large to render. See raw diff

notebooks/final_ARS.ipynb CHANGED Viewed

The diff for this file is too large to render. See raw diff

run_pipeline.py CHANGED Viewed

@@ -13,6 +13,9 @@ if __name__ == "__main__":
         raise AnimeRecommendorException(e, sys)
 # import sys
 # from anime_recommender.loggers.logging import logging
 # from anime_recommender.exception.exception import AnimeRecommendorException
@@ -46,7 +49,7 @@ if __name__ == "__main__":
 #         collaborative_model_trainer_config = CollaborativeModelConfig(training_pipeline_config)
 #         collaborative_model_trainer = CollaborativeModelTrainer(collaborative_model_trainer_config= collaborative_model_trainer_config,data_transformation_artifact=data_transformation_artifact)
 #         logging.info("Initiating Collaborative Model training.")
-#         collaborative_model_trainer_artifact = collaborative_model_trainer.initiate_model_trainer(model_type='user_knn')
 #         logging.info("Collaborative Model training completed.")
 #         print(collaborative_model_trainer_artifact)

         raise AnimeRecommendorException(e, sys)
 # import sys
 # from anime_recommender.loggers.logging import logging
 # from anime_recommender.exception.exception import AnimeRecommendorException
 #         collaborative_model_trainer_config = CollaborativeModelConfig(training_pipeline_config)
 #         collaborative_model_trainer = CollaborativeModelTrainer(collaborative_model_trainer_config= collaborative_model_trainer_config,data_transformation_artifact=data_transformation_artifact)
 #         logging.info("Initiating Collaborative Model training.")
+#         collaborative_model_trainer_artifact = collaborative_model_trainer.initiate_model_trainer()
 #         logging.info("Collaborative Model training completed.")
 #         print(collaborative_model_trainer_artifact)