NoSQL databases emerged to address the limitations of traditional relational database management systems in handling massive volumes of diverse, rapidly changing, and unstructured data. In Data Science and Big Data environments, scalability, flexibility, and high availability are critical requirements. Column-based, document-based, and graph-based NoSQL databases represent three major categories designed to support different data models and workload patterns. Each type organizes data differently and is optimized for specific analytical and operational use cases. Column-based NoSQL databases, also known as wide-column stores, organize data into columns rather than rows. Unlike relational systems where data is stored row by row, column-based systems group related data into column families. Each row can have a different set of columns, making the schema highly flexible. This structure allows efficient storage and retrieval of large datasets, particularly when queries focus on a subset of columns across many rows. One well-known example is Apache Cassandra. Cassandra distributes data across multiple nodes in a cluster, ensuring high availability and fault tolerance without a single point of failure. In a real-world Big Data scenario, column-based databases are highly suitable for time-series data analytics. For example, in an Internet of Things (IoT) application where millions of sensors generate readings every second, the system must handle continuous writes and allow fast retrieval of specific metrics such as temperature or humidity over time. Cassandra can efficiently store sensor data partitioned by device ID and timestamp. Data scientists can then query specific columns, such as average temperature readings over a time interval, without scanning unnecessary fields. The distributed architecture supports horizontal scaling, which is essential when the data volume grows to terabytes or petabytes. This makes column-based databases ideal for logging systems, recommendation engines, and real-time analytics platforms. Document-based NoSQL databases store data in the form of documents, typically using formats like JSON or BSON. Each document contains key-value pairs and may include nested structures such as arrays and sub-documents. Unlike relational databases,