This README provides an overview of the Content-Based Recommendation System implemented using the Sentence Transformers library in Python. This system generates product recommendations based on the textual data and content features.
The Content-Based Recommendation System is designed to recommend products to users based on the textual features of the products, such as product names, descriptions, and product specifications. The system uses pre-trained models to encode textual data into embeddings and then calculates similarity scores to make recommendations.
- Python 3.x
- Pandas
- Sentence Transformers
- NLTK (Natural Language Toolkit)
You can install the required Python packages using pip:
-
Clone the repository or download the code files to your local machine.
-
Create a virtual environment (optional but recommended):
-
Activate the virtual environment:
-
On Windows:
-
On macOS and Linux:
- Run the recommendation system with your data:
# Create an instance of the recommendation system
recommender = ProductRecommendation()
# Fit the recommender with your data
recommender.fit(df)
# Make recommendations and enter exact product name
product_name = 'Product_Name'
recommendations = recommender.predict(product_name)
for rec in recommendations:
print("->", rec)
This README provides an overview of the content-based recommendation system, its requirements, how to get started, and usage instructions.