Python snippets – notes

Neal Caren
things I wish I knew 24 hours ago

Caching Up with Claude

Playing around with Prompt Caching

Structured Data from Images

Analyzing protest pictures with ChatGPT

60,000 news articles from April 20, 2024

Working with the Common Crawl News dataset

Stemming And Lemmatizations

A book section written by Claude Opus

Measuring Bias in LLMs, Variant II

Mapping Name Embeddings

Measuring Bias in LLMs, Variant I

Conjoint Experiment Replication

From Articles to Events, Part III

Categorizing texts with an LLM

Topic models

Using tomotopy to extract text themes

From Articles to Events, Part II

Extracting text from media HTML files

From Articles to Events, Part I

Downloading lots of articles.

More with sentence embeddings

Adding and subtracting concepts from a text.

Text similarity with sentence embeddings

Measuring the distance between a concept and a text.

What percent of sociology journal abstracts start with a question?

Using NLTK to pull out the first sentence of an abstract.

Creating Synthetic Data with ChatGPT

Writing 600 fake article abstracts.

Web Scraping in Bulk

Dwnloading websites in parallel with pyppeteer

Using ChatGPT to Make Social Media Posts

More using Pydantic for OpenAI function calling

Getting Structured Data from ChatGPT

Using Pydantic for OpenAI function calling

Audio Transcription with Speaker Identification

Transcribing an audio file with WhisperPlus.

Text to Speech using OpenAI’s API

We are almost there with computer talking.