Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Change the order of the EDA/Data wrangling section and add a few missing things to other parts #12

Closed
Hellisotherpeople opened this issue Nov 10, 2020 · 1 comment

Comments

@Hellisotherpeople
Copy link

Hellisotherpeople commented Nov 10, 2020

Hi all, this is a very nice chart but I believe that there should be slight modifications.

Data Science Roadmap

"Dimensionality and Numerosity Reduction" is a large topic which would include the study of the "Principal Component Analysis" (PCA) algorithm as the very first thing you'd do. Yet PCA is seen as being the very final thing you look at in this section. I think you should put PCA right before Dimensionality Reduction or you should combine them.

In the "Visualization section" you list some nice plotting libraries, but I think that Bokeh should be included here because it is a superior python plotting library (out of the box GPU/OpenGL support allowing for plotting millions of points, significantly more flexible interaction system) combined to the other options and is quickly becoming one of the important graphing libraries.

Under "Data Sources" you may want to put "Data Mining and Web Scraping" or something along those lines since I think a Data Scientist should be able to get their own data rather than go on Kaggle or github awesome pages.

Machine Learning Roadmap

Subsections under "Association Rule Learning" should be "Apriori algorithm", "ECLAT algorithm" and "Fp-trees"

Subsections under Dimensionality Reduction should include (after PCA): "Random Projection", "NMF", "T-SNE", "UMAP"

Subsections under Clustering should include (after Agglomerative): "OPTICS" and "HDBSCAN"

Subsections under "Classification" should include "Guassian Mixture Models"

Logistic Regression is actually a binary classification algorithm, despite its name, so move it from regression to Classification

Moving Huggingface Transformers out from here and into the Deep Learning section.

Deep Learning Roadmap

Add a new section under "Architectures" called "Attention Mechanisms/Transformers"
Add a new section under Architectures called "NEAT/Evolving Architectures"

Big Data Engineer

Add a new blue section under "Tools" for Dask, Numba, Onnx, and OpenVino

If it's really easy to generate these plots, I'm willing to make these changes and submit a PR. What are your thoughts on implementing some or all of these changes?

@JStumpp
Copy link
Contributor

JStumpp commented Nov 30, 2020

Thanks a lot for your suggestions, this is fixed in #18

@JStumpp JStumpp closed this as completed Nov 30, 2020
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants
@JStumpp @Hellisotherpeople and others