docs: add llm kmeans notebook as an included example #177
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
ashleyxuu
reviewed
Nov 7, 2023
There was a problem hiding this comment.
Would you mind adding a "Clean up" section like: https://github.com/googleapis/python-bigquery-dataframes/blob/main/notebooks/generative_ai/bq_dataframes_llm_code_generation.ipynb.
nit: We should also be consistent with this structure, adding: Installation, authentication, etc... section
ashleyxuu
reviewed
Nov 7, 2023
ashleyxuu
reviewed
Nov 7, 2023
Some of those sections are not needed anymore or not needed for this notebook right? For example |
added 12 commits
November 8, 2023 01:27
added 2 commits
November 8, 2023 23:03
Ok! I have added all the sections that I think are needed, including all the code needed for the Vertex AI connection. The clean up section luckily it sounds like is not necessary based on discussion with @GarrettWu . I have tested the most recent version of the notebook in Colab. Based on discussion with @shobsi , we have deny listed this type of notebook from being run by the e2e tester, so I deny listed this one as well. Looks like we'll have to rely on manual testing for the time being. Ready for re-review. Thank you! |
jiaxunwu
approved these changes
Nov 9, 2023
ashleyxuu
approved these changes
Nov 9, 2023
gcf-merge-on-green bot
pushed a commit
that referenced
this pull request
Nov 15, 2023
🤖 I have created a release *beep* *boop* --- ## [0.14.0](https://togithub.com/googleapis/python-bigquery-dataframes/compare/v0.13.0...v0.14.0) (2023-11-14) ### Features * Add 'cross' join support ([#176](https://togithub.com/googleapis/python-bigquery-dataframes/issues/176)) ([765446a](https://togithub.com/googleapis/python-bigquery-dataframes/commit/765446a929abe1ac076c3037afa7892f64105356)) * Add 'index', 'pad', 'nearest' interpolate methods ([#162](https://togithub.com/googleapis/python-bigquery-dataframes/issues/162)) ([6a28403](https://togithub.com/googleapis/python-bigquery-dataframes/commit/6a2840349a23035bdfdabacd1e231b41bbb5ed7a)) * Add series.sample (identical to existing dataframe.sample) ([#187](https://togithub.com/googleapis/python-bigquery-dataframes/issues/187)) ([37914a4](https://togithub.com/googleapis/python-bigquery-dataframes/commit/37914a4077c681881491f5c36d1a9c9f4255e18f)) * Add unordered sql compilation ([#156](https://togithub.com/googleapis/python-bigquery-dataframes/issues/156)) ([58f420c](https://togithub.com/googleapis/python-bigquery-dataframes/commit/58f420c91d94ca085e9810f36513ffe772bfddcf)) * Log most recent API calls as `recent-bigframes-api-xx` labels on BigQuery jobs ([#145](https://togithub.com/googleapis/python-bigquery-dataframes/issues/145)) ([4ea33b7](https://togithub.com/googleapis/python-bigquery-dataframes/commit/4ea33b7433532ae3a386a6ffa9eb57360ea39526)) * Read_gbq creates order deterministically without table copy ([#191](https://togithub.com/googleapis/python-bigquery-dataframes/issues/191)) ([8ab81de](https://togithub.com/googleapis/python-bigquery-dataframes/commit/8ab81dee4d0eee499094f2dd576550f0c59d7551)) * Support `date_series.astype("string[pyarrow]")` to cast DATE to STRING ([#186](https://togithub.com/googleapis/python-bigquery-dataframes/issues/186)) ([aee0e8e](https://togithub.com/googleapis/python-bigquery-dataframes/commit/aee0e8e2518c59bd1e0b07940c3309871fde8899)) * Support `series.at[row_label] = scalar` ([#173](https://togithub.com/googleapis/python-bigquery-dataframes/issues/173)) ([0c8bd33](https://togithub.com/googleapis/python-bigquery-dataframes/commit/0c8bd33806bb99206b8b12dbdf7d7485c6ffb759)) * Temporary resources no longer use BigQuery Sessions ([#194](https://togithub.com/googleapis/python-bigquery-dataframes/issues/194)) ([4a02cac](https://togithub.com/googleapis/python-bigquery-dataframes/commit/4a02cac88c7d7b46bed1fa813a862fc2ef9ef084)) ### Bug Fixes * All sort operation are now stable ([#195](https://togithub.com/googleapis/python-bigquery-dataframes/issues/195)) ([3a2761f](https://togithub.com/googleapis/python-bigquery-dataframes/commit/3a2761f3c38d0de8b8eda47fffa15b8412aa84b0)) * Default to 7 days expiration for `read_csv`, `read_json`, `read_parquet` ([#193](https://togithub.com/googleapis/python-bigquery-dataframes/issues/193)) ([03606cd](https://togithub.com/googleapis/python-bigquery-dataframes/commit/03606cda30eb7645bfd4534460112dcca56b0ab0)) * Deprecate the `remote_service_type` in llm model ([#180](https://togithub.com/googleapis/python-bigquery-dataframes/issues/180)) ([a8a409a](https://togithub.com/googleapis/python-bigquery-dataframes/commit/a8a409ab0bd1f99dfb442df0703bf8786e0fe58e)) * For reset_index on unnamed multiindex, always use level_[n] label ([#182](https://togithub.com/googleapis/python-bigquery-dataframes/issues/182)) ([f95000d](https://togithub.com/googleapis/python-bigquery-dataframes/commit/f95000d3f88662be4d88c8b0152f1b838e99ec55)) * Match pandas behavior when assigning listlike to empty dfs ([#172](https://togithub.com/googleapis/python-bigquery-dataframes/issues/172)) ([c1d1f42](https://togithub.com/googleapis/python-bigquery-dataframes/commit/c1d1f42a21cc089877f79ebb46a39ddef6958e04)) * Use anonymous dataset instead of session dataset for temp tables ([#181](https://togithub.com/googleapis/python-bigquery-dataframes/issues/181)) ([800d44e](https://togithub.com/googleapis/python-bigquery-dataframes/commit/800d44eb5eb77da5d87b2e005f5a2ed53842e7b5)) * Use random table for `read_pandas` ([#192](https://togithub.com/googleapis/python-bigquery-dataframes/issues/192)) ([741c75e](https://togithub.com/googleapis/python-bigquery-dataframes/commit/741c75e5797e26a1487ff3da76a07953d9537f3f)) * Use random table when loading data for `read_csv`, `read_json`, `read_parquet` ([#175](https://togithub.com/googleapis/python-bigquery-dataframes/issues/175)) ([9d2e6dc](https://togithub.com/googleapis/python-bigquery-dataframes/commit/9d2e6dc1ae4e11e80da4aabe0daa3a6044137cc6)) ### Documentation * Add code samples for `read_gbq_function` using community UDFs ([#188](https://togithub.com/googleapis/python-bigquery-dataframes/issues/188)) ([7506eab](https://togithub.com/googleapis/python-bigquery-dataframes/commit/7506eabf2e58159507809e36abfe90c417dfe92f)) * Add docstring code samples for `Series.apply` and `DataFrame.map` ([#185](https://togithub.com/googleapis/python-bigquery-dataframes/issues/185)) ([c816d84](https://togithub.com/googleapis/python-bigquery-dataframes/commit/c816d843e6f3c5a944cd4395ed0e1e91cec49812)) * Add llm kmeans notebook as an included example ([#177](https://togithub.com/googleapis/python-bigquery-dataframes/issues/177)) ([d49ae42](https://togithub.com/googleapis/python-bigquery-dataframes/commit/d49ae42a379fafd601cc94227e7f8f14b3d5f8c3)) * Use `head()` to get top `n` results, not to preview results ([#190](https://togithub.com/googleapis/python-bigquery-dataframes/issues/190)) ([87f84c9](https://togithub.com/googleapis/python-bigquery-dataframes/commit/87f84c9e58e7d0ea521ac386c9f02791cdddd19f)) --- This PR was generated with [Release Please](https://togithub.com/googleapis/release-please). See [documentation](https://togithub.com/googleapis/release-please#release-please).
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Original notebook written by Jiaxunwu.
I have tested the notebook by running it on Colab with a test prod project. Any feedback on content or format would be appreciated. I didn't change very much code from Jiaxun's original. Thanks!