docs: update quickstart notebook #564
Conversation
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
| "## 2. Download the Data\n", | ||
| "\n", | ||
| "Download the curated dataset." | ||
| "Download production and training image data containing photographs of people performing various actions (sleeping, eating, running, etc.)." |
There was a problem hiding this comment.
Might add a note how you would do this on their own infra (like a inference bucket or collect it from the output of their models, or just have data in a dataframe)
| "\n", | ||
| "## 1. Install Dependencies and Import Libraries" | ||
| "Install Phoenix." |
There was a problem hiding this comment.
I would set the stage a bit, add a bit of an intro as to what they. are about to do. E.g. add a TLDR - give them a description of the lifecyle / troubleshooting journey they are embarking on.
There was a problem hiding this comment.
Explain how comparing production vs training can identify areas where production has drifted off course.
| "- **prediction_id:** a unique identifier for each data point\n", | ||
| "- **prediction_ts:** the Unix timestamps of your predictions\n", | ||
| "- **url:** a link to the image data\n", | ||
| "- **image_vector:** the embedding vectors representing each image\n", |
There was a problem hiding this comment.
maybe a brief note of how they would typically get these
| "metadata": {}, | ||
| "source": [ | ||
| "The columns of the DataFrame are:\n", | ||
| "- **prediction_id:** a unique identifier for each data point\n", |
There was a problem hiding this comment.
explain why this is important - correlating data back to other data stores
| "id": "jFYdi3vktf4L" | ||
| }, | ||
| "source": [ | ||
| "Navigate to the embeddings page. Select a period of high drift. Select a drifted cluster. Color your data by the `merchant_ID` feature. Select a cluster of drifted production data. Notice that much of this data consists of fraudulent transactions from the Scammeds merchant. Export the cluster." |
There was a problem hiding this comment.
Might help to rephrase this a bit into "how" they should be seeing the drift rather than telling them "what" they should be seeing.
* main: v0.0.13 fix: don't compile js/html if exists - unblock conda (#597) docs: credit card fraud tutorial notebook update (#555) docs: update quickstart notebook (#564) don't raise error during dimension type inference (#596) fix: Update pyproject.toml (#595) chore: change https to http for downloading fixtures and example datasets (#589) chore: Use pre commit for prettier and eslint (#588) ci: Create .github/dependabot.yml (#587) chore: create SECURITY.md (#586) chore: legal info (#583) fix: ignore non-vectors for embeddings (#584) chore: bump to typescript 5 (#585) v0.0.12 feat(embeddings): grid view improvements: sizes, multi-modal output (#565)
No description provided.