Upload 22 files

.gitattributes

@@ -1,35 +1,4 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm 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
+src/trained_model/similarity_matrix.pkl filter=lfs diff=lfs merge=lfs -text
+*.ipynb linguist-detectable=false
+data/credits.csv filter=lfs diff=lfs merge=lfs -text
+src/trained_model/processed_data.pkl filter=lfs diff=lfs merge=lfs -text

.github/workflows/python-app.yml

@@ -0,0 +1,87 @@
+# This workflow will install Python dependencies, run tests and lint with a single version of Python
+# For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-python
+
+name: Python application
+
+on:
+  push:
+    branches: [ "main" ]
+  pull_request:
+    branches: [ "main" ]
+
+permissions:
+  contents: read
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4
+    
+    - name: Set up Python 3.10
+      uses: actions/setup-python@v3
+      with:
+        python-version: "3.10"
+    
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip setuptools wheel
+        pip install flake8 pytest pytest-flask pandas scikit-learn flask fuzzywuzzy python-Levenshtein
+        if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+
+    - name: Verify data and model directories
+      run: |
+        mkdir -p data/processed_dataset
+        mkdir -p src/trained_model
+        touch data/movies.csv data/credits.csv
+        if [ ! -d "src/trained_model" ]; then
+          echo "Model directory missing!"
+          exit 1
+        fi
+        if [ ! -d "src/templates" ] || [ ! -f "src/templates/index.html" ]; then
+          echo "Template files missing!"
+          exit 1
+        fi
+    
+    - name: Lint with flake8
+      run: |
+        flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
+        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
+    
+    - name: Process data and train model
+      run: |
+        python src/app/main.py
+    
+    - name: Verify model artifacts
+      run: |
+        if [ ! -f "src/trained_model/processed_data.pkl" ] || \
+           [ ! -f "src/trained_model/similarity_matrix.pkl" ] || \
+           [ ! -f "src/trained_model/vectorizer.pkl" ]; then
+          echo "Model artifacts missing!"
+          exit 1
+        fi
+    
+    - name: Test with pytest
+      run: |
+        python -m pytest tests/ -v
+
+    - name: Start and Test Flask App
+      run: |
+        python src/app/app.py &
+        sleep 10
+        curl --retry 5 --retry-delay 5 --retry-connrefused http://127.0.0.1:5000/ || exit 1
+        pkill -f "python src/app/app.py"
+      env:
+        FLASK_ENV: testing
+        FLASK_DEBUG: 0
+
+
+    - name: Check setup.py
+      run: |
+        if [ -f setup.py ]; then
+          python setup.py check
+          python setup.py sdist bdist_wheel
+          pip install -e .
+        else
+          echo "setup.py not found - skipping package build"
+        fi

.gitignore

@@ -0,0 +1,171 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# PyPI configuration file
+.pypirc

README.md

@@ -1,10 +1,93 @@
----
-title: Test2
-emoji: 🏃
-colorFrom: gray
-colorTo: blue
-sdk: docker
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Movie Recommendation System
+
+## 🎥 Watch the Demo👇
+
+![Watch on YouTube|Movie_recommendation_system](https://www.youtube.com/watch?v=FWnURzv_P0Q)
+
+## Overview
+The **Movie Recommendation System** is a Python-based project designed to recommend movies to users based on content similarity. Using natural language processing and machine learning techniques, this system analyzes movie metadata to provide tailored recommendations.
+
+---
+
+## Features
+1. **Data Preprocessing**: Cleans and merges raw movie datasets.
+2. **Model Training**: Creates a similarity matrix using cosine similarity on vectorized features.
+3. **Fuzzy Matching**: Matches user input to the closest movie title using fuzzy string matching.
+4. **Recommendations**: Recommends movies with similarity scores.
+5. **Modular Design**: Separate modules for preprocessing, training, and recommendations.
+
+---
+
+## Project Structure
+```
+├── data
+│   ├── credits.csv               # Raw credits dataset
+│   ├── movies.csv                # Raw movies dataset
+│   └── processed_dataset
+│       └── movies_processed.csv  # Preprocessed movie data
+├── src
+│   ├── scripts
+│   │   ├── preprocessing.py      # Data preprocessing pipeline
+│   │   ├── model.py              # Model training and artifact creation
+│   │   ├── recommender.py        # Recommendation engine
+│   └── trained_model
+│       ├── similarity_matrix.pkl # Precomputed similarity matrix
+│       ├── vectorizer.pkl        # Saved CountVectorizer instance
+│       └── feature_names.pkl     # Feature names from vectorization
+├── main.py                       # Central script for running pipelines
+├── requirements.txt              # Project dependencies
+└── README.md                     # Project documentation
+```
+
+
+
+---
+
+## Technical Details
+### Preprocessing
+- Extracts key features (`genres`, `keywords`, `cast`, `crew`).
+- Combines features into a unified text field (`tags`) for vectorization.
+
+### Model
+- **Vectorization**: Converts text into numerical vectors using `CountVectorizer`.
+- **Similarity Matrix**: Computes cosine similarity between movie vectors.
+
+### Recommendation Logic
+1. Matches user input to the closest movie title using fuzzy string matching.
+2. Fetches the most similar movies based on the similarity matrix.
+3. Outputs a ranked list of recommendations with similarity scores.
+
+---
+
+## Example Output
+```bash
+Recommendations for 'The Dark Knight':
+- The Dark Knight Rises (95.67% match)
+- Batman Begins (89.23% match)
+- Inception (82.45% match)
+```
+
+---
+
+## Challenges and Solutions
+- **Large Dataset**: Optimized vectorization using `CountVectorizer` with a feature limit.
+- **Matching Errors**: Improved title matching accuracy with fuzzy string matching.
+
+---
+
+## Future Enhancements
+1. Implement collaborative filtering for better recommendations.
+2. Introduce a user-friendly web interface.
+3. Integrate additional data sources, such as IMDb ratings and reviews.
+
+---
+
+## Contributing
+Contributions are welcome! Fork the repository, make changes, and submit a pull request.
+
+---
+
+## Contact
+For questions or suggestions, feel free to reach out:
+- Email: [maazuddin173@gmail.com](mailto:maazuddin173@gmail.com)
+- GitHub: [Maazuddin1](https://github.com/Maazuddin1)

data/credits.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2671838f8f178271eecf4e7e62463eb2ad85c40f2213067c614329eb7cb8ca0a
+size 40049097

setup.py

@@ -0,0 +1,17 @@
+from setuptools import setup, find_packages
+
+setup(
+    name="Content based Movie Recommedation system",
+    version="1.0",
+    description="A machine learning project for Movie Recommedation",
+    author="Maaz uddin",
+    packages=find_packages(),
+    install_requires=[
+        "flask",
+        "pandas",
+        "numpy",
+        "scikit-learn",
+        "seaborn",
+        "matplotlib"
+    ]
+)

src/app/app.py

@@ -0,0 +1,29 @@
+from flask import Flask, render_template, request
+import sys
+import os
+from pathlib import Path
+# Add project root to sys.path
+project_root = Path(__file__).resolve().parents[2]
+sys.path.append(str(project_root))
+from src.scripts.recommender import MovieRecommender
+# app.py (Flask backend)
+app = Flask(__name__,template_folder='src/templates')
+
+recommender = MovieRecommender(model_dir='src/trained_model')
+
+@app.route('/', methods=['GET', 'POST'])
+def home():
+    recommendations = []
+    matched_title = ""
+    
+    if request.method == 'POST':
+        movie_title = request.form.get('movie_title')
+        recommender.load_model_artifacts()
+        recommendations, matched_title = recommender.recommend_movies(movie_title)
+        
+    return render_template('index.html', recommendations=recommendations, matched_title=matched_title)
+
+if __name__ == '__main__':
+    debug_mode = os.getenv('FLASK_DEBUG', 'False').lower() in ['true', '1', 'yes']
+    app.run(debug=debug_mode)
+

src/app/main.py

@@ -0,0 +1,80 @@
+import sys
+import logging
+import sys
+from pathlib import Path
+# Add project root to sys.path
+project_root = Path(__file__).resolve().parents[2]
+sys.path.append(str(project_root))
+
+
+# Import from scripts
+from src.scripts.preprocessing import DataPreprocessor
+from src.scripts.recommender import MovieRecommender
+
+# Set up logging
+logging.basicConfig(
+    level=logging.INFO,
+    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
+)
+logger = logging.getLogger(__name__)
+
+def main():
+    try:
+        # Define base project path
+        base_path = Path(__file__).resolve().parents[2]
+
+        # File paths
+        credits_path = base_path/'data'/'credits.csv'
+        movies_path = base_path/'data'/'movies.csv'
+        processed_path = base_path/'data'/'processed_dataset'/'movies_preprocessed.csv'
+        model_dir = base_path/'src'/'trained_model'
+
+        # Ensure necessary directories exist
+        model_dir.mkdir(parents=True, exist_ok=True)
+        processed_path.parent.mkdir(parents=True, exist_ok=True)
+
+
+        # Data Preprocessing
+        logger.info("Starting data preprocessing...")
+        preprocessor = DataPreprocessor(
+                            credits_path=credits_path,
+                            movies_path=movies_path,
+                            output_path=processed_path
+        )
+        preprocessor.load_data()
+        processed_df = preprocessor.preprocess_data()
+        preprocessor.save_preprocessed_data()
+        logger.info("Data preprocessing completed successfully.")
+
+
+
+        # Model Training
+        logger.info("Starting model training...")
+        recommender = MovieRecommender(model_dir=str(model_dir))
+        recommender.create_similarity_matrix(processed_df)
+        logger.info("Model training completed successfully.")
+        # Model Testing with a Sample Recommendation
+        logger.info("Testing model with a sample recommendation...")
+        recommender.load_model_artifacts()
+        movie_title = "Dark Knight"
+        recommendations, matched_title = recommender.recommend_movies(movie_title)
+
+
+
+        # Display Recommendations
+        if recommendations and matched_title:
+            print(f"\nRecommendations for '{matched_title}':")
+            for movie in recommendations:
+                print(f"- {movie['title']} ({movie['similarity']}% match)")
+        else:
+            print(f"No recommendations found for '{movie_title}'.")
+
+    except Exception as e:
+        logger.error(f"Error in main: {str(e)}")
+        raise
+
+if __name__ == "__main__":
+    # Add project root to sys.path for module resolution
+    project_root = Path(__file__).resolve().parents[2]
+    sys.path.append(str(project_root))
+    main()

src/scripts/EDA.py

@@ -0,0 +1,43 @@
+# src/scripts/EDA.py
+import pandas as pd
+import matplotlib.pyplot as plt
+from pathlib import Path
+
+def perform_eda(credits_df, movies_df):
+    """Perform exploratory data analysis on the datasets."""
+    print("Dataset Information:")
+    print("\nMovies Dataset Shape:", movies_df.shape)
+    print("Credits Dataset Shape:", credits_df.shape)
+
+
+    pd.options.display.float_format = '{:.2f}'.format
+    
+
+    # Missing values analysis
+    print("\nMissing Values:")
+    print(movies_df.isnull().sum())
+    
+    # Basic statistics
+    print("\nNumerical Columns Statistics:")
+    print(movies_df.describe())
+    
+    # Generate visualizations
+    plt.figure(figsize=(10, 6))
+    movies_df['vote_average'].hist()
+    plt.title('Distribution of Movie Ratings')
+    plt.xlabel('Rating')
+    plt.ylabel('Count')
+    #plt.savefig('data/visualizations/ratings_dist.png')
+    #plt.close()
+
+
+def main():
+    # Load the preprocessed data
+    credits_df = pd.read_csv('g:/my projects/Content-based-Movie_Recommedation_system/data/credits.csv')
+    movies_df = pd.read_csv('g:/my projects/Content-based-Movie_Recommedation_system/data/movies.csv')
+    
+    # Perform EDA
+    perform_eda(credits_df, movies_df)
+
+if __name__ == "__main__":
+    main()

src/scripts/model.py

@@ -0,0 +1,52 @@
+# src/scripts/train_model.py
+from pathlib import Path
+from preprocessing import DataPreprocessor
+import sys
+import os
+from recommender import MovieRecommender
+import logging
+import pandas as pd
+
+# Set up logging
+logging.basicConfig(
+    level=logging.INFO,
+    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
+)
+logger = logging.getLogger(__name__)
+
+def main():
+    try:
+        # Get absolute paths
+        base_path = Path(__file__).resolve().parents[2]
+        
+        # Setup paths
+        credits_path = base_path/'data'/'credits.csv'
+        movies_path = base_path/'data'/'movies.csv'
+        processed_path = base_path/'data'/'processed_dataset'/'movies_preprocessed.csv'
+        model_dir = base_path/'src'/'trained_model'
+
+        logger.info("Preprocessed data found. Loading it directly...")
+        processed_df = pd.read_csv(processed_path)  # Adjust based on file format (e.g., CSV, pickle)
+        logger.info("Starting model training...")
+        
+        # Initialize and train recommender
+        recommender = MovieRecommender(model_dir=str(model_dir))
+        recommender.create_similarity_matrix(processed_df)
+        logger.info("Model training completed successfully!")
+        
+        # Test the model
+        logger.info("Testing model with a sample recommendation...")
+        recommender.load_model_artifacts()
+        recommendations, matched_title = recommender.recommend_movies("The Dark Knight")
+        
+        if recommendations and matched_title:
+            print(f"\nRecommendations for {matched_title}:")
+            for movie in recommendations:
+                print(f"- {movie['title']} ({movie['similarity']}% match)")
+        
+    except Exception as e:
+        logger.error(f"Error in main: {str(e)}")
+        raise
+
+if __name__ == "__main__":
+    main()

src/scripts/preprocessing.py

@@ -0,0 +1,131 @@
+# src/scripts/preprocessing.py
+import pandas as pd
+import numpy as np
+import ast
+import logging
+from pathlib import Path
+
+logging.basicConfig(
+    level=logging.INFO,
+    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
+)
+logger = logging.getLogger(__name__)
+
+class DataPreprocessor:
+    def __init__(self, credits_path,movies_path,output_path):
+        self.credits_path = Path(credits_path)
+        self.movies_path = Path(movies_path)
+        self.output_path = Path(output_path)
+        self.data = None
+
+    def load_data(self):
+        """Load and merge the movies and credits datasets."""
+        try:
+            logger.info("Loading datasets...")
+            credits_df = pd.read_csv(self.credits_path)
+            movies_df = pd.read_csv(self.movies_path)
+            self.data = movies_df.merge(credits_df)
+            logger.info(f"Successfully loaded {len(self.data)} movies")
+            return self.data
+        except Exception as e:
+            logger.error(f"Error loading data: {str(e)}")
+            raise
+
+    @staticmethod
+    def convert_literals(obj):
+        """Convert string literals to list of names."""
+        return [item['name'] for item in ast.literal_eval(obj)]
+
+    @staticmethod
+    def cast3only(obj):
+        """Extract top 3 cast members."""
+        cast = []
+        counter = 0
+        for i in ast.literal_eval(obj):
+            if counter != 3:
+                cast.append(i['name'])
+                counter += 1
+        return cast
+
+    @staticmethod
+    def find_director(obj):
+        """Extract director name from crew."""
+        for i in ast.literal_eval(obj):
+            if i['job'] == 'Director':
+                return [i['name']]
+        return []
+
+    def preprocess_data(self):
+        """Main preprocessing function."""
+        try:
+            if self.data is None:
+                self.load_data()
+                
+            logger.info("Preprocessing data...")
+            # Select required columns
+            self.data = self.data[['movie_id', 'title', 'overview', 'genres', 'keywords', 'cast', 'crew']]
+            
+            # Drop missing values
+            self.data = self.data.dropna()
+            
+            # Apply transformations
+            self.data['genres'] = self.data['genres'].apply(self.convert_literals)
+            self.data['keywords'] = self.data['keywords'].apply(self.convert_literals)
+            self.data['cast'] = self.data['cast'].apply(self.cast3only)
+            self.data['crew'] = self.data['crew'].apply(self.find_director)
+            
+            # Process text data
+            self.data['overview'] = self.data['overview'].apply(lambda x: x.split())
+            
+            # Remove spaces from all lists
+            for col in ['overview', 'genres', 'keywords', 'cast']:
+                self.data[col] = self.data[col].apply(lambda x: [i.replace(' ', '') for i in x])
+            
+            # Combine features
+            self.data['tags'] = self.data['overview'] + self.data['genres'] + self.data['keywords'] + self.data['cast'] + self.data['crew']
+            
+            self.data = self.data[['movie_id', 'title', 'tags']]
+            self.data['tags'] = self.data['tags'].apply(lambda x: ' '.join(x))
+            self.data['tags'] = self.data['tags'].apply(lambda x: x.lower())
+
+            logger.info("Data preprocessing completed.")
+            return self.data
+
+        except Exception as e:
+            logger.error(f"Error during preprocessing: {str(e)}")
+            raise
+
+    def save_preprocessed_data(self):
+        """Save preprocessed data to a csv file."""
+        try:
+            self.output_path.parent.mkdir(parents=True, exist_ok=True)
+            self.data.to_csv(self.output_path, index=False)
+            logger.info(f"Saved preprocessed data to {self.output_path}")
+        except Exception as e:
+            logger.error(f"Error saving preprocessed data: {str(e)}")
+            raise
+
+def main():
+    # Set file paths
+    credits_path = 'data/credits.csv'
+    movies_path = 'data/movies.csv'
+    output_path = 'data/processed_dataset/movies_preprocessed.csv'
+    
+    # Create an instance of DataPreprocessor
+    preprocessor = DataPreprocessor(credits_path, movies_path, output_path)
+    
+    try:
+        # Load and preprocess data
+        preprocessor.load_data()
+        preprocessor.preprocess_data()
+        # Save preprocessed data
+        preprocessor.save_preprocessed_data()
+        
+        logger.info("Preprocessing pipeline executed successfully.")
+
+    except Exception as e:
+        logger.error(f"An error occurred during the preprocessing pipeline: {str(e)}")
+
+
+if __name__ == '__main__':
+    main()

src/scripts/recommender.py

@@ -0,0 +1,142 @@
+# src/scripts/recommender.py
+
+# THIS A FILE FUNCTIONS IS CALLED BY "model.py" 
+# THIS FILE CONTAINS FUNCTIONS REQUIRED BY model.py
+
+
+
+import pandas as pd
+from sklearn.feature_extraction.text import CountVectorizer
+from sklearn.metrics.pairwise import cosine_similarity
+from fuzzywuzzy import fuzz, process
+import pickle
+import logging
+from pathlib import Path
+
+# Set up logging
+logging.basicConfig(
+    level=logging.INFO,
+    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
+)
+logger = logging.getLogger(__name__)
+
+class MovieRecommender:
+    def __init__(self, model_dir='src/trained_model'):
+        self.model_dir = Path(model_dir)
+        self.processed_data_path = self.model_dir/'processed_data.pkl'
+        self.similarity_matrix_path = self.model_dir/'similarity_matrix.pkl'
+        self.vectorizer_path = self.model_dir/'vectorizer.pkl'
+        self.feature_names_path = self.model_dir/'feature_names.pkl'
+        self.df = None
+        self.similarity_matrix = None
+        self.vectorizer = None
+
+# to create and save trained model pickle files
+    def create_similarity_matrix(self,df):
+        """Create and save similarity matrix from processed data."""
+        try:
+            logger.info("Creating similarity matrix...")
+            
+            # Create vectors
+            cv = CountVectorizer(max_features=5000, stop_words='english')
+            vectors = cv.fit_transform(df['tags']).toarray()
+            similarity_matrix = cosine_similarity(vectors)
+
+            # Create models directory if it doesn't exist
+            self.model_dir.mkdir(parents=True, exist_ok=True)
+
+            # Save all artifacts
+            logger.info("Saving model artifacts...")
+            with open(self.vectorizer_path, 'wb') as f:
+                pickle.dump(cv, f)
+
+            with open(self.similarity_matrix_path, 'wb') as f:
+                pickle.dump(similarity_matrix, f)
+
+            df.to_pickle(self.processed_data_path)
+
+            feature_names = cv.get_feature_names_out()
+            with open(self.feature_names_path, 'wb') as f:
+                pickle.dump(feature_names, f)
+
+            logger.info("Successfully created and saved all model artifacts")
+            self.df = df
+            self.similarity_matrix = similarity_matrix
+            self.vectorizer = cv
+            
+            return similarity_matrix
+
+        except Exception as e:
+            logger.error(f"Error in create_similarity_matrix: {str(e)}")
+            raise
+
+# CALLED BY "model.py" TO READ PICKLE FILES FOR PREDICTION
+    def load_model_artifacts(self):
+        """Load saved model artifacts."""
+        try:
+            logger.info("Loading model artifacts...")
+            self.df = pd.read_pickle(self.processed_data_path)
+            with open(self.similarity_matrix_path, 'rb') as f:
+                self.similarity_matrix = pickle.load(f)
+            with open(self.vectorizer_path, 'rb') as f:
+                self.vectorizer = pickle.load(f)
+            logger.info("Model artifacts loaded successfully.")
+        except Exception as e:
+            logger.error(f"Error loading model artifacts: {str(e)}")
+            raise
+
+
+
+# this will be called in recommend_movies 👇method(below fuction)
+    def find_closest_title(self, input_title, score_cutoff=60):
+        """Find the closest matching movie title using fuzzy string matching."""
+        input_title = input_title.lower()
+        title_list = self.df['title'].tolist()
+        matches = process.extractBests(
+            input_title,
+            title_list,
+            scorer=fuzz.token_sort_ratio,
+            score_cutoff=score_cutoff,
+            limit=5
+        )
+        return matches[0][0] if matches else None
+    def recommend_movies(self, movie_title, n_recommendations=5):
+        """Get movie recommendations based on similarity with fuzzy matching."""
+        try:
+            if self.df is None or self.similarity_matrix is None:
+                raise ValueError("Model artifacts are not loaded. Please load them first.")
+
+            # Find closest matching title
+            matched_title = self.find_closest_title(movie_title)
+
+            if matched_title is None:
+                logger.warning(f"No close matches found for '{movie_title}'")
+                return [], None
+
+            # Get movie index
+            movie_index = self.df[self.df['title'] == matched_title].index[0]
+            distances = self.similarity_matrix[movie_index]
+
+            # Get similar movies
+            movie_list = sorted(list(enumerate(distances)), 
+                              reverse=True, 
+                              key=lambda x: x[1])[1:n_recommendations+1]
+
+            # Get recommendations with similarity scores
+            recommendations = [
+                {
+                    'title': self.df.iloc[i[0]].title,
+                    'similarity': round(i[1] * 100, 2)
+                }
+                for i in movie_list
+            ]
+
+            return recommendations, matched_title
+
+        except Exception as e:
+            logger.error(f"Error generating recommendations: {str(e)}")
+            return [], None
+
+
+if __name__ == "__main__":
+    pass

src/templates/index.html

@@ -0,0 +1,162 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>Movie Recommendation System</title>
+    <style>
+        body {
+            font-family: Arial, sans-serif;
+            margin: 0;
+            padding: 0;
+            background-color: #f7f7f7;
+            color: #333;
+        }
+
+        header {
+            background-color: #3e8e41;
+            padding: 20px;
+            text-align: center;
+            color: white;
+        }
+
+        .container {
+            max-width: 900px;
+            margin: 0 auto;
+            padding: 20px;
+        }
+
+        h1 {
+            font-size: 36px;
+            margin-bottom: 20px;
+        }
+
+        .form-container {
+            background-color: white;
+            padding: 20px;
+            border-radius: 5px;
+            box-shadow: 0 4px 8px rgba(0, 0, 0, 0.1);
+            margin-bottom: 30px;
+        }
+
+        label {
+            font-size: 18px;
+            margin-bottom: 10px;
+            display: inline-block;
+        }
+
+        input[type="text"] {
+            width: 100%;
+            padding: 10px;
+            margin-top: 5px;
+            border: 1px solid #ddd;
+            border-radius: 5px;
+            font-size: 16px;
+        }
+
+        button {
+            padding: 10px 20px;
+            background-color: #3e8e41;
+            color: white;
+            border: none;
+            border-radius: 5px;
+            font-size: 16px;
+            cursor: pointer;
+            margin-top: 20px;
+            width: 100%;
+        }
+
+        button:hover {
+            background-color: #2d6a29;
+        }
+
+        .recommendations {
+            background-color: white;
+            padding: 20px;
+            border-radius: 5px;
+            box-shadow: 0 4px 8px rgba(0, 0, 0, 0.1);
+        }
+
+        .recommendations h2 {
+            font-size: 28px;
+            margin-bottom: 20px;
+        }
+
+        .recommendations ul {
+            list-style: none;
+            padding: 0;
+        }
+
+        .recommendations li {
+            background-color: #f9f9f9;
+            margin-bottom: 10px;
+            padding: 10px;
+            border-radius: 5px;
+            font-size: 18px;
+            display: flex;
+            justify-content: space-between;
+            align-items: center;
+        }
+
+        .recommendations li span {
+            font-size: 14px;
+            color: #666;
+        }
+
+        .error-message {
+            background-color: #ffcccb;
+            padding: 10px;
+            border-radius: 5px;
+            text-align: center;
+            color: #d8000c;
+            margin-bottom: 20px;
+        }
+    </style>
+</head>
+<body>
+
+<header>
+    <h1>Movie Recommendation System</h1>
+</header>
+
+<div class="container">
+    <div class="form-container">
+        <h2>Get Movie Recommendations</h2>
+        <p>Enter a movie title below, and we will suggest similar movies for you!</p>
+
+        <form action="/" method="POST">
+            <label for="movie_title">Movie Title:</label>
+            <input type="text" id="movie_title" name="movie_title" required placeholder="e.g., The Dark Knight">
+            <button type="submit">Get Recommendations</button>
+        </form>
+    </div>
+
+    <!-- Display Error if no recommendations are found -->
+    {% if not recommendations %}
+        <div class="error-message">
+            <strong>No recommendations found. Please try a different movie title.</strong>
+        </div>
+    {% endif %}
+
+    <!-- Display Recommendations -->
+    {% if recommendations %}
+        <div class="recommendations">
+            <h2>Recommendations for "{{ matched_title }}"</h2>
+            <ul>
+                {% for movie in recommendations %}
+                    <li>
+                        <div>
+                            <strong>{{ movie['title'] }}</strong>
+                        </div>
+                        <div>
+                            <span>{{ movie['similarity'] }}% match</span>
+                        </div>
+                    </li>
+                {% endfor %}
+            </ul>
+        </div>
+    {% endif %}
+</div>
+
+</body>
+</html>

src/trained_model/processed_data.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62114f41cbb99ba6360b1d199877b3ddbfd42bd96d012b7b4a1d3e10d537a610
+size 2396007

src/trained_model/similarity_matrix.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9e97fd615845dcc92e67c58ea7c066ed419a3b8fecb769a81e6f7a7b219f0d0
+size 184704363

tests/test_model.py

@@ -0,0 +1,57 @@
+import pytest
+from src.scripts.recommender import MovieRecommender
+import pandas as pd
+import numpy as np
+
+@pytest.fixture
+def sample_movies_df():
+    return pd.DataFrame({
+        'movie_id': [1, 2, 3],
+        'title': ['The Dark Knight', 'Inception', 'Interstellar'],
+        'tags': [
+            'batman dark knight action',
+            'dreams inception thriller',
+            'space interstellar scifi'
+        ]
+    })
+
+def test_movie_recommender_initialization():
+    recommender = MovieRecommender()
+    assert recommender is not None
+    assert recommender.df is None
+    assert recommender.similarity_matrix is None
+
+def test_find_closest_title(sample_movies_df):
+    recommender = MovieRecommender()
+    recommender.df = sample_movies_df
+    
+    # Test exact match
+    assert recommender.find_closest_title('The Dark Knight') == 'The Dark Knight'
+    
+    # Test partial match
+    assert recommender.find_closest_title('Dark Knight') == 'The Dark Knight'
+    
+    # Test no match
+    assert recommender.find_closest_title('Nonexistent Movie') is None
+
+def test_recommend_movies(sample_movies_df):
+    recommender = MovieRecommender()
+    recommender.df = sample_movies_df
+    
+    # Create a simple similarity matrix for testing
+    recommender.similarity_matrix = np.array([
+        [1.0, 0.5, 0.3],
+        [0.5, 1.0, 0.4],
+        [0.3, 0.4, 1.0]
+    ])
+    
+    # Test recommendations
+    recommendations, matched_title = recommender.recommend_movies('The Dark Knight')
+    
+    assert matched_title == 'The Dark Knight'
+    assert len(recommendations) == 2  # Should return 2 recommendations
+    assert recommendations[0]['title'] in ['Inception', 'Interstellar']
+    assert 0 <= recommendations[0]['similarity'] <= 100
+
+if __name__ == '__main__':
+    pytest.main(['-v'])