Count Word Frequency (Bag of Words)

Given a string of text, return a dictionary mapping each word to its frequency. Words are case-insensitive and separated by spaces. Strip punctuation.

This is the Bag of Words (BoW) model -- the simplest text representation used in NLP before neural embeddings.

Example: "The cat sat on the mat" -> {"the": 2, "cat": 1, "sat": 1, "on": 1, "mat": 1}

Follow-up: How would you extend this to bigrams (pairs of consecutive words)?