In this section of the course I'm taking, I'll get a hands-on introduction to selected portions of the Python libraries NumPy, Pandas, and SciKit-Learn. I'll also use these in combination with other libraries to create basic data visualizations. These lectures only cover a handful of functions/methods in each library, and don't go in depth -- they only cover common functionality for beginner's deep learning projects. Here I'll provide a brief set of notes I took in the beginning of this section, but the substance of this post will lay in the Jupyter Notebooks that I've created while following along with the lectures and while implementing the review challenge at the end of the section. I'll also mention any trouble I had.
Crash Course Intro Notes
- Three types of data: training data, test data, and holdout data
- To "fit data" means to divide each data point by the largest data point in the set, which means the all data will be between 0 and 1.
- Will typically fit data to training data, not test data because we don’t want to assume anything about the test data (i.e. that it will be within the bounds of the training data)
Here are links to all of the code I've completed in this section.
The Review Exercise was a "quiz" of sorts, reviewing everything that was covered in this section of the course. It was all pretty straightforward, although it did take me a few minutes to figure out how to make a scatter plot of column 0 vs column 1. I kept trying things like x=mat[:0], y=mat[:1], but Turns out, I just needed to specify x=0, y=1. Once again, a simple solution that evaded me.
I think my favorite part of this section were the data visualization tools. In a world of GUI-free commands and data sets, it's nice to have a colorful overview of information. For example, I learned how to represent relatively large sets of (random) data points as scatter plots and color-coded blocks:
That was a fun section, but now it's time to finally get into some real deep learning, which I'll write about in the next post.


Comments
Post a Comment