Pandas and Scikit-Learn in ML

• 

  Visualization of music-recommender.dot file in VS Code

Inspiration

Inspired by the 'Try a Technology you've been intimidated by' challenge in INIT 2022, I wanted to understand how Machine Learning works in data science. Sincere credits to "Programming with Mosh" channel with the video (https://www.youtube.com/watch?v=7eh4d6sabA0) for a breakdown of how it works.

What it does

The project uses Scikit-Learn Decision Tree Classifier as a logical Machine Learning (ML) model to predict musical interests of different age groups and genders.

How I built it

Using Jupyter, I imported the pandas module (for 2D dataframes) and scikit-learn module (for ML models) and trained the Decision Tree Classifier model with 10% test size and 90% training size. We determine how accurately it predicts the musical genre interest based on age and gender.

Challenges I ran into

Finding the right modules and function arguments.

Accomplishments that I am proud of

I managed to navigate Jupyter and apply my understanding of class objects and function calls in Python.

What I learned

I understood the whole process of building a ML model. These include acquiring and cleaning the data testing and training a model, and evaluating the performance.

What's next for Pandas and Scikit-Learn in ML

My plan is to apply this basic understanding of ML in data science to more complex program involving more datasets.

Built With

• joblib
• jupyter
• machine-learning
• pandas
• python
• scikit-learn