My t-SNE plot shows clear clusters. Can I run K-Means on the 2D coordinates, or feed them into a model?

Find answers to your programming questions.
My t-SNE plot shows clear clusters. Can I run K-Means on the 2D coordinates, or feed them into a model?
t-SNE on 100,000 rows with 300 features has been running for hours.
Every run gives a different picture, and changing perplexity changes the clusters completely. Which plot is correct?
I fit t-SNE on my training data and want to project my test data into the same 2D space, but TSNE has no transform method.
My PC1 values are the negative of what I got last week (or what R / another library gives). Which one is correct?
I have millions of rows (or a large TF-IDF matrix) and PCA crashes with a MemoryError or a TypeError about sparse input.
I reduced my data with PCA. Can I get back to the original feature space? How much information did I lose?
I ran fittransform on my training data and then again on my test data. My model's predictions make no sense." / "I got a feature-count mismatch error when I pas