Why tools come next
Machine learning teams in Ghana and abroad work in Python, and adverts for data science and machine learning roles name the same small set of libraries again and again: NumPy, pandas, scikit learn, and a deep learning library such as PyTorch, TensorFlow or Keras. Learning this toolkit well matters more than chasing every new tool you see online.
The toolkit
Think of the tools as a workshop with a few benches:
- Python is the language that ties everything together. You already know the basics from the Data Analyst track.
- NumPy handles fast maths on arrays of numbers. Vectors and matrices from the maths section live here.
- pandas handles tables with named columns, which is how real data arrives: CSV files, spreadsheet exports and database queries.
- scikit learn provides classic models, tools to split and test data, and ways to prepare features. You will use it throughout the classic machine learning section.
- A deep learning library, such as PyTorch or Keras, builds neural networks. You meet one later in the track.
- matplotlib or a similar library draws charts so you can see your data and your results.