Exploratory Data Analysis (EDA）and t-distributed Stochastic Neighbor Embedding (t-SNE)

1. Definition of EDA

Directly refer to Rapid-Fire EDA process using Python for ML Implementation.

Clearly, PCA is a part of EDA.

Here is another good tutorial for EDA: A Starter Pack to Exploratory Data Analysis with Python, pandas, seaborn, and scikit-learn.

2. Visualization with t-SNE

• Definition: t-SNE on Wikipedia
• t-SNE in scikit-learn: sklearn.manifold.TSNE
• Tutorials:
  • Visualising high-dimensional datasets using PCA and t-SNE in Python
  • Introduction to t-SNE

3. Try Analyzing and Visualizing MNIST

Let's just refer to the FIRST tutorial and try out how to analyze and visualize the famous dataset MNIST.

Please refer to my copy-paste-modification jupyter notebook code at https://github.com/LongerVision/Kaggle.

4. Try Analyzing and Visualizing Fashion-MNIST

Let's then refer to the SECOND tutorial and try out how to analyze and visualize Fashion-MNIST.

Please refer to my copy-paste-modification jupyter notebook code at https://github.com/LongerVision/Kaggle.