docs: add examples of running bigframes in kaggle #2002

tswast · 2025-08-18T19:53:51Z

Thank you for opening a Pull Request! Before submitting your PR, there are a few things you can do to make sure it goes smoothly:

Make sure to open an issue as a bug/issue before writing your code! That way we can discuss the change, evaluate designs, and agree on the general idea
Ensure the tests and linter pass
Code coverage does not decrease (if any source code was changed)
Appropriate docs were updated (if necessary)

Fixes #<issue_number_goes_here> 🦕

review-notebook-app · 2025-08-18T19:53:56Z

Check out this pull request on

See visual diffs & provide feedback on Jupyter Notebooks.

Powered by ReviewNB

GarrettWu · 2025-08-18T21:57:38Z

notebooks/kaggle/bq_dataframes_ai_forecast.ipynb

@@ -0,0 +1 @@
+{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.11.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":110281,"databundleVersionId":13391012,"sourceType":"competition"}],"dockerImageVersionId":31089,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# BigQuery DataFrames (BigFrames) AI Forecast\n\nThis notebook is adapted from https://github.com/googleapis/python-bigquery-dataframes/blob/main/notebooks/generative_ai/bq_dataframes_ai_forecast.ipynb to work in the Kaggle runtime. It introduces forecasting with GenAI Foundation Model with BigFrames AI.\n\nInstall the bigframes package and upgrade other packages that are already included in Kaggle but have versions incompatible with bigframes.","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19"}},{"cell_type":"code","source":"%pip install --upgrade bigframes google-cloud-automl google-cloud-translate google-ai-generativelanguage tensorflow ","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"**Important:** restart the kernel by going to \"Run -> Restart & clear cell outputs\" before continuing.\n\nConfigure bigframes to use your GCP project. First, go to \"Add-ons -> Google Cloud SDK\" and click the \"Attach\" button. Then,","metadata":{}},{"cell_type":"code","source":"from kaggle_secrets import UserSecretsClient\nuser_secrets = UserSecretsClient()\nuser_credential = user_secrets.get_gcloud_credential()\nuser_secrets.set_tensorflow_credential(user_credential)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-08-18T19:16:10.449563Z","iopub.execute_input":"2025-08-18T19:16:10.449828Z","iopub.status.idle":"2025-08-18T19:16:10.618943Z","shell.execute_reply.started":"2025-08-18T19:16:10.449803Z","shell.execute_reply":"2025-08-18T19:16:10.617631Z"}},"outputs":[],"execution_count":1},{"cell_type":"code","source":"PROJECT = \"swast-scratch\" # replace with your project\n\n\nimport bigframes.pandas as bpd\nbpd.options.bigquery.project = PROJECT\nbpd.options.bigquery.ordering_mode = \"partial\" # Optional: partial ordering mode can accelerate executions and save costs\n\nimport bigframes.exceptions\nimport warnings\nwarnings.filterwarnings(\"ignore\", category=bigframes.exceptions.AmbiguousWindowWarning)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-08-18T19:20:00.851472Z","iopub.execute_input":"2025-08-18T19:20:00.851870Z","iopub.status.idle":"2025-08-18T19:20:00.858175Z","shell.execute_reply.started":"2025-08-18T19:20:00.851842Z","shell.execute_reply":"2025-08-18T19:20:00.857098Z"}},"outputs":[],"execution_count":4},{"cell_type":"markdown","source":"## 1. Create a BigFrames DataFrames from BigQuery public data.","metadata":{}},{"cell_type":"code","source":"df = bpd.read_gbq(\"bigquery-public-data.san_francisco_bikeshare.bikeshare_trips\")\ndf","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-08-18T19:20:02.254706Z","iopub.execute_input":"2025-08-18T19:20:02.255184Z","iopub.status.idle":"2025-08-18T19:20:04.754064Z","shell.execute_reply.started":"2025-08-18T19:20:02.255149Z","shell.execute_reply":"2025-08-18T19:20:04.752940Z"}},"outputs":[{"name":"stderr","text":"/usr/local/lib/python3.11/dist-packages/bigframes/core/log_adapter.py:175: TimeTravelCacheWarning: Reading cached table from 2025-08-18 19:19:20.590271+00:00 to avoid\nincompatibilies with previous reads of this table. To read the latest\nversion, set `use_cache=False` or close the current session with\nSession.close() or bigframes.pandas.close_session().\n  return method(*args, **kwargs)\n","output_type":"stream"},{"execution_count":5,"output_type":"execute_result","data":{"text/plain":"           trip_id  duration_sec                start_date  \\\n201802092135083596           788 2018-02-09 21:35:08+00:00   \n201708152357422491           965 2017-08-15 23:57:42+00:00   \n201802281657253632           560 2018-02-28 16:57:25+00:00   \n201711170046091337           497 2017-11-17 00:46:09+00:00   \n201802201913231257           596 2018-02-20 19:13:23+00:00   \n201708242325001279          1341 2017-08-24 23:25:00+00:00   \n201801161800473291           489 2018-01-16 18:00:47+00:00   \n 20180408155601183          1105 2018-04-08 15:56:01+00:00   \n201803141857032204           619 2018-03-14 18:57:03+00:00   \n201708192053311490           743 2017-08-19 20:53:31+00:00   \n201711181823281960           353 2017-11-18 18:23:28+00:00   \n 20170810204454839          1256 2017-08-10 20:44:54+00:00   \n201801171656553504           500 2018-01-17 16:56:55+00:00   \n201801111613101305           858 2018-01-11 16:13:10+00:00   \n201802241826551215          1235 2018-02-24 18:26:55+00:00   \n201803091621483450           857 2018-03-09 16:21:48+00:00   \n201801021932232717           914 2018-01-02 19:32:23+00:00   \n201803161910283751           564 2018-03-16 19:10:28+00:00   \n 20171212152403227           854 2017-12-12 15:24:03+00:00   \n201803131437033724           917 2018-03-13 14:37:03+00:00   \n201712061755593426           519 2017-12-06 17:55:59+00:00   \n 20180404210034451           366 2018-04-04 21:00:34+00:00   \n201801231907161787           626 2018-01-23 19:07:16+00:00   \n201708271057061157           973 2017-08-27 10:57:06+00:00   \n201709071348372074         11434 2017-09-07 13:48:37+00:00   \n\n         start_station_name  start_station_id                  end_date  \\\n      10th Ave at E 15th St               222 2018-02-09 21:48:17+00:00   \n       10th St at Fallon St               201 2017-08-16 00:13:48+00:00   \n       10th St at Fallon St               201 2018-02-28 17:06:46+00:00   \n       10th St at Fallon St               201 2017-11-17 00:54:26+00:00   \n       10th St at Fallon St               201 2018-02-20 19:23:19+00:00   \n       10th St at Fallon St               201 2017-08-24 23:47:22+00:00   \n       10th St at Fallon St               201 2018-01-16 18:08:56+00:00   \n     13th St at Franklin St               338 2018-04-08 16:14:26+00:00   \n     13th St at Franklin St               338 2018-03-14 19:07:23+00:00   \n       2nd Ave at E 18th St               200 2017-08-19 21:05:54+00:00   \n       2nd Ave at E 18th St               200 2017-11-18 18:29:22+00:00   \n       2nd Ave at E 18th St               200 2017-08-10 21:05:50+00:00   \nEl Embarcadero at Grand Ave               197 2018-01-17 17:05:16+00:00   \n        Frank H Ogawa Plaza                 7 2018-01-11 16:27:28+00:00   \n        Frank H Ogawa Plaza                 7 2018-02-24 18:47:31+00:00   \n        Frank H Ogawa Plaza                 7 2018-03-09 16:36:06+00:00   \n        Frank H Ogawa Plaza                 7 2018-01-02 19:47:38+00:00   \n        Frank H Ogawa Plaza                 7 2018-03-16 19:19:52+00:00   \n        Frank H Ogawa Plaza                 7 2017-12-12 15:38:17+00:00   \n    Grand Ave at Webster St               181 2018-03-13 14:52:20+00:00   \n  Lake Merritt BART Station               163 2017-12-06 18:04:39+00:00   \n  Lake Merritt BART Station               163 2018-04-04 21:06:41+00:00   \n  Lake Merritt BART Station               163 2018-01-23 19:17:43+00:00   \n  Lake Merritt BART Station               163 2017-08-27 11:13:19+00:00   \n  Lake Merritt BART Station               163 2017-09-07 16:59:12+00:00   \n\n     end_station_name  end_station_id  bike_number zip_code  ...  \\\n10th Ave at E 15th St             222         3596     <NA>  ...   \n10th Ave at E 15th St             222         2491     <NA>  ...   \n10th Ave at E 15th St             222         3632     <NA>  ...   \n10th Ave at E 15th St             222         1337     <NA>  ...   \n10th Ave at E 15th St             222         1257     <NA>  ...   \n10th Ave at E 15th St             222         1279     <NA>  ...   \n10th Ave at E 15th St             222         3291     <NA>  ...   \n10th Ave at E 15th St             222          183     <NA>  ...   \n10th Ave at E 15th St             222         2204     <NA>  ...   \n10th Ave at E 15th St             222         1490     <NA>  ...   \n10th Ave at E 15th St             222         1960     <NA>  ...   \n10th Ave at E 15th St             222          839     <NA>  ...   \n10th Ave at E 15th St             222         3504     <NA>  ...   \n10th Ave at E 15th St             222         1305     <NA>  ...   \n10th Ave at E 15th St             222         1215     <NA>  ...   \n10th Ave at E 15th St             222         3450     <NA>  ...   \n10th Ave at E 15th St             222         2717     <NA>  ...   \n10th Ave at E 15th St             222         3751     <NA>  ...   \n10th Ave at E 15th St             222          227     <NA>  ...   \n10th Ave at E 15th St             222         3724     <NA>  ...   \n10th Ave at E 15th St             222         3426     <NA>  ...   \n10th Ave at E 15th St             222          451     <NA>  ...   \n10th Ave at E 15th St             222         1787     <NA>  ...   \n10th Ave at E 15th St             222         1157     <NA>  ...   \n10th Ave at E 15th St             222         2074     <NA>  ...   \n\nc_subscription_type start_station_latitude  start_station_longitude  \\\n               <NA>              37.792714               -122.24878   \n               <NA>              37.797673              -122.262997   \n               <NA>              37.797673              -122.262997   \n               <NA>              37.797673              -122.262997   \n               <NA>              37.797673              -122.262997   \n               <NA>              37.797673              -122.262997   \n               <NA>              37.797673              -122.262997   \n               <NA>              37.803189              -122.270579   \n               <NA>              37.803189              -122.270579   \n               <NA>              37.800214               -122.25381   \n               <NA>              37.800214               -122.25381   \n               <NA>              37.800214               -122.25381   \n               <NA>              37.808848               -122.24968   \n               <NA>              37.804562              -122.271738   \n               <NA>              37.804562              -122.271738   \n               <NA>              37.804562              -122.271738   \n               <NA>              37.804562              -122.271738   \n               <NA>              37.804562              -122.271738   \n               <NA>              37.804562              -122.271738   \n               <NA>              37.811377              -122.265192   \n               <NA>               37.79732               -122.26532   \n               <NA>               37.79732               -122.26532   \n               <NA>               37.79732               -122.26532   \n               <NA>               37.79732               -122.26532   \n               <NA>               37.79732               -122.26532   \n\n end_station_latitude  end_station_longitude  member_birth_year  \\\n            37.792714             -122.24878               1984   \n            37.792714             -122.24878               <NA>   \n            37.792714             -122.24878               1984   \n            37.792714             -122.24878               <NA>   \n            37.792714             -122.24878               1984   \n            37.792714             -122.24878               1969   \n            37.792714             -122.24878               1984   \n            37.792714             -122.24878               1987   \n            37.792714             -122.24878               1982   \n            37.792714             -122.24878               <NA>   \n            37.792714             -122.24878               1988   \n            37.792714             -122.24878               <NA>   \n            37.792714             -122.24878               1987   \n            37.792714             -122.24878               1984   \n            37.792714             -122.24878               1969   \n            37.792714             -122.24878               1984   \n            37.792714             -122.24878               1984   \n            37.792714             -122.24878               1987   \n            37.792714             -122.24878               1984   \n            37.792714             -122.24878               1989   \n            37.792714             -122.24878               1986   \n            37.792714             -122.24878               1987   \n            37.792714             -122.24878               1987   \n            37.792714             -122.24878               <NA>   \n            37.792714             -122.24878               <NA>   \n\n member_gender bike_share_for_all_trip          start_station_geom  \\\n          Male                     Yes POINT (-122.24878 37.79271)   \n          <NA>                    <NA> POINT (-122.26300 37.79767)   \n          Male                     Yes POINT (-122.26300 37.79767)   \n          <NA>                    <NA> POINT (-122.26300 37.79767)   \n          Male                     Yes POINT (-122.26300 37.79767)   \n          Male                    <NA> POINT (-122.26300 37.79767)   \n          Male                     Yes POINT (-122.26300 37.79767)   \n        Female                      No POINT (-122.27058 37.80319)   \n         Other                      No POINT (-122.27058 37.80319)   \n          <NA>                    <NA> POINT (-122.25381 37.80021)   \n          Male                    <NA> POINT (-122.25381 37.80021)   \n          <NA>                    <NA> POINT (-122.25381 37.80021)   \n          Male                      No POINT (-122.24968 37.80885)   \n          Male                     Yes POINT (-122.27174 37.80456)   \n          Male                      No POINT (-122.27174 37.80456)   \n          Male                     Yes POINT (-122.27174 37.80456)   \n          Male                     Yes POINT (-122.27174 37.80456)   \n          Male                      No POINT (-122.27174 37.80456)   \n          Male                    <NA> POINT (-122.27174 37.80456)   \n          Male                      No POINT (-122.26519 37.81138)   \n          Male                    <NA> POINT (-122.26532 37.79732)   \n          Male                      No POINT (-122.26532 37.79732)   \n          Male                      No POINT (-122.26532 37.79732)   \n          <NA>                    <NA> POINT (-122.26532 37.79732)   \n          <NA>                    <NA> POINT (-122.26532 37.79732)   \n\n           end_station_geom  \nPOINT (-122.24878 37.79271)  \nPOINT (-122.24878 37.79271)  \nPOINT (-122.24878 37.79271)  \nPOINT (-122.24878 37.79271)  \nPOINT (-122.24878 37.79271)  \nPOINT (-122.24878 37.79271)  \nPOINT (-122.24878 37.79271)  \nPOINT (-122.24878 37.79271)  \nPOINT (-122.24878 37.79271)  \nPOINT (-122.24878 37.79271)  \nPOINT (-122.24878 37.79271)  \nPOINT (-122.24878 37.79271)  \nPOINT (-122.24878 37.79271)  \nPOINT (-122.24878 37.79271)  \nPOINT (-122.24878 37.79271)  \nPOINT (-122.24878 37.79271)  \nPOINT (-122.24878 37.79271)  \nPOINT (-122.24878 37.79271)  \nPOINT (-122.24878 37.79271)  \nPOINT (-122.24878 37.79271)  \nPOINT (-122.24878 37.79271)  \nPOINT (-122.24878 37.79271)  \nPOINT (-122.24878 37.79271)  \nPOINT (-122.24878 37.79271)  \nPOINT (-122.24878 37.79271)  \n...\n\n[1947417 rows x 21 columns]","text/html":"<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>trip_id</th>\n      <th>duration_sec</th>\n      <th>start_date</th>\n      <th>start_station_name</th>\n      <th>start_station_id</th>\n      <th>end_date</th>\n      <th>end_station_name</th>\n      <th>end_station_id</th>\n      <th>bike_number</th>\n      <th>zip_code</th>\n      <th>...</th>\n      <th>c_subscription_type</th>\n      <th>start_station_latitude</th>\n      <th>start_station_longitude</th>\n      <th>end_station_latitude</th>\n      <th>end_station_longitude</th>\n      <th>member_birth_year</th>\n      <th>member_gender</th>\n      <th>bike_share_for_all_trip</th>\n      <th>start_station_geom</th>\n      <th>end_station_geom</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>201802092135083596</td>\n      <td>788</td>\n      <td>2018-02-09 21:35:08+00:00</td>\n      <td>10th Ave at E 15th St</td>\n      <td>222</td>\n      <td>2018-02-09 21:48:17+00:00</td>\n      <td>10th Ave at E 15th St</td>\n      <td>222</td>\n      <td>3596</td>\n      <td>&lt;NA&gt;</td>\n      <td>...</td>\n      <td>&lt;NA&gt;</td>\n      <td>37.792714</td>\n      <td>-122.24878</td>\n      <td>37.792714</td>\n      <td>-122.24878</td>\n      <td>1984</td>\n      <td>Male</td>\n      <td>Yes</td>\n      <td>POINT (-122.24878 37.79271)</td>\n      <td>POINT (-122.24878 37.79271)</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>201708152357422491</td>\n      <td>965</td>\n      <td>2017-08-15 23:57:42+00:00</td>\n      <td>10th St at Fallon St</td>\n      <td>201</td>\n      <td>2017-08-16 00:13:48+00:00</td>\n      <td>10th Ave at E 15th St</td>\n      <td>222</td>\n      <td>2491</td>\n      <td>&lt;NA&gt;</td>\n      <td>...</td>\n      <td>&lt;NA&gt;</td>\n      <td>37.797673</td>\n      <td>-122.262997</td>\n      <td>37.792714</td>\n      <td>-122.24878</td>\n      <td>&lt;NA&gt;</td>\n      <td>&lt;NA&gt;</td>\n      <td>&lt;NA&gt;</td>\n      <td>POINT (-122.26300 37.79767)</td>\n      <td>POINT (-122.24878 37.79271)</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>201802281657253632</td>\n      <td>560</td>\n      <td>2018-02-28 16:57:25+00:00</td>\n      <td>10th St at Fallon St</td>\n      <td>201</td>\n      <td>2018-02-28 17:06:46+00:00</td>\n      <td>10th Ave at E 15th St</td>\n      <td>222</td>\n      <td>3632</td>\n      <td>&lt;NA&gt;</td>\n      <td>...</td>\n      <td>&lt;NA&gt;</td>\n      <td>37.797673</td>\n      <td>-122.262997</td>\n      <td>37.792714</td>\n      <td>-122.24878</td>\n      <td>1984</td>\n      <td>Male</td>\n      <td>Yes</td>\n      <td>POINT (-122.26300 37.79767)</td>\n      <td>POINT (-122.24878 37.79271)</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>201711170046091337</td>\n      <td>497</td>\n      <td>2017-11-17 00:46:09+00:00</td>\n      <td>10th St at Fallon St</td>\n      <td>201</td>\n      <td>2017-11-17 00:54:26+00:00</td>\n      <td>10th Ave at E 15th St</td>\n      <td>222</td>\n      <td>1337</td>\n      <td>&lt;NA&gt;</td>\n      <td>...</td>\n      <td>&lt;NA&gt;</td>\n      <td>37.797673</td>\n      <td>-122.262997</td>\n      <td>37.792714</td>\n      <td>-122.24878</td>\n      <td>&lt;NA&gt;</td>\n      <td>&lt;NA&gt;</td>\n      <td>&lt;NA&gt;</td>\n      <td>POINT (-122.26300 37.79767)</td>\n      <td>POINT (-122.24878 37.79271)</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>201802201913231257</td>\n      <td>596</td>\n      <td>2018-02-20 19:13:23+00:00</td>\n      <td>10th St at Fallon St</td>\n      <td>201</td>\n      <td>2018-02-20 19:23:19+00:00</td>\n      <td>10th Ave at E 15th St</td>\n      <td>222</td>\n      <td>1257</td>\n      <td>&lt;NA&gt;</td>\n      <td>...</td>\n      <td>&lt;NA&gt;</td>\n      <td>37.797673</td>\n      <td>-122.262997</td>\n      <td>37.792714</td>\n      <td>-122.24878</td>\n      <td>1984</td>\n      <td>Male</td>\n      <td>Yes</td>\n      <td>POINT (-122.26300 37.79767)</td>\n      <td>POINT (-122.24878 37.79271)</td>\n    </tr>\n    <tr>\n      <th>5</th>\n      <td>201708242325001279</td>\n      <td>1341</td>\n      <td>2017-08-24 23:25:00+00:00</td>\n      <td>10th St at Fallon St</td>\n      <td>201</td>\n      <td>2017-08-24 23:47:22+00:00</td>\n      <td>10th Ave at E 15th St</td>\n      <td>222</td>\n      <td>1279</td>\n      <td>&lt;NA&gt;</td>\n      <td>...</td>\n      <td>&lt;NA&gt;</td>\n      <td>37.797673</td>\n      <td>-122.262997</td>\n      <td>37.792714</td>\n      <td>-122.24878</td>\n      <td>1969</td>\n      <td>Male</td>\n      <td>&lt;NA&gt;</td>\n      <td>POINT (-122.26300 37.79767)</td>\n      <td>POINT (-122.24878 37.79271)</td>\n    </tr>\n    <tr>\n      <th>6</th>\n      <td>201801161800473291</td>\n      <td>489</td>\n      <td>2018-01-16 18:00:47+00:00</td>\n      <td>10th St at Fallon St</td>\n      <td>201</td>\n      <td>2018-01-16 18:08:56+00:00</td>\n      <td>10th Ave at E 15th St</td>\n      <td>222</td>\n      <td>3291</td>\n      <td>&lt;NA&gt;</td>\n      <td>...</td>\n      <td>&lt;NA&gt;</td>\n      <td>37.797673</td>\n      <td>-122.262997</td>\n      <td>37.792714</td>\n      <td>-122.24878</td>\n      <td>1984</td>\n      <td>Male</td>\n      <td>Yes</td>\n      <td>POINT (-122.26300 37.79767)</td>\n      <td>POINT (-122.24878 37.79271)</td>\n    </tr>\n    <tr>\n      <th>7</th>\n      <td>20180408155601183</td>\n      <td>1105</td>\n      <td>2018-04-08 15:56:01+00:00</td>\n      <td>13th St at Franklin St</td>\n      <td>338</td>\n      <td>2018-04-08 16:14:26+00:00</td>\n      <td>10th Ave at E 15th St</td>\n      <td>222</td>\n      <td>183</td>\n      <td>&lt;NA&gt;</td>\n      <td>...</td>\n      <td>&lt;NA&gt;</td>\n      <td>37.803189</td>\n      <td>-122.270579</td>\n      <td>37.792714</td>\n      <td>-122.24878</td>\n      <td>1987</td>\n      <td>Female</td>\n      <td>No</td>\n      <td>POINT (-122.27058 37.80319)</td>\n      <td>POINT (-122.24878 37.79271)</td>\n    </tr>\n    <tr>\n      <th>8</th>\n      <td>201803141857032204</td>\n      <td>619</td>\n      <td>2018-03-14 18:57:03+00:00</td>\n      <td>13th St at Franklin St</td>\n      <td>338</td>\n      <td>2018-03-14 19:07:23+00:00</td>\n      <td>10th Ave at E 15th St</td>\n      <td>222</td>\n      <td>2204</td>\n      <td>&lt;NA&gt;</td>\n      <td>...</td>\n      <td>&lt;NA&gt;</td>\n      <td>37.803189</td>\n      <td>-122.270579</td>\n      <td>37.792714</td>\n      <td>-122.24878</td>\n      <td>1982</td>\n      <td>Other</td>\n      <td>No</td>\n      <td>POINT (-122.27058 37.80319)</td>\n      <td>POINT (-122.24878 37.79271)</td>\n    </tr>\n    <tr>\n      <th>9</th>\n      <td>201708192053311490</td>\n      <td>743</td>\n      <td>2017-08-19 20:53:31+00:00</td>\n      <td>2nd Ave at E 18th St</td>\n      <td>200</td>\n      <td>2017-08-19 21:05:54+00:00</td>\n      <td>10th Ave at E 15th St</td>\n      <td>222</td>\n      <td>1490</td>\n      <td>&lt;NA&gt;</td>\n      <td>...</td>\n      <td>&lt;NA&gt;</td>\n      <td>37.800214</td>\n      <td>-122.25381</td>\n      <td>37.792714</td>\n      <td>-122.24878</td>\n      <td>&lt;NA&gt;</td>\n      <td>&lt;NA&gt;</td>\n      <td>&lt;NA&gt;</td>\n      <td>POINT (-122.25381 37.80021)</td>\n      <td>POINT (-122.24878 37.79271)</td>\n    </tr>\n    <tr>\n      <th>10</th>\n      <td>201711181823281960</td>\n      <td>353</td>\n      <td>2017-11-18 18:23:28+00:00</td>\n      <td>2nd Ave at E 18th St</td>\n      <td>200</td>\n      <td>2017-11-18 18:29:22+00:00</td>\n      <td>10th Ave at E 15th St</td>\n      <td>222</td>\n      <td>1960</td>\n      <td>&lt;NA&gt;</td>\n      <td>...</td>\n      <td>&lt;NA&gt;</td>\n      <td>37.800214</td>\n      <td>-122.25381</td>\n      <td>37.792714</td>\n      <td>-122.24878</td>\n      <td>1988</td>\n      <td>Male</td>\n      <td>&lt;NA&gt;</td>\n      <td>POINT (-122.25381 37.80021)</td>\n      <td>POINT (-122.24878 37.79271)</td>\n    </tr>\n    <tr>\n      <th>11</th>\n      <td>20170810204454839</td>\n      <td>1256</td>\n      <td>2017-08-10 20:44:54+00:00</td>\n      <td>2nd Ave at E 18th St</td>\n      <td>200</td>\n      <td>2017-08-10 21:05:50+00:00</td>\n      <td>10th Ave at E 15th St</td>\n      <td>222</td>\n      <td>839</td>\n      <td>&lt;NA&gt;</td>\n      <td>...</td>\n      <td>&lt;NA&gt;</td>\n      <td>37.800214</td>\n      <td>-122.25381</td>\n      <td>37.792714</td>\n      <td>-122.24878</td>\n      <td>&lt;NA&gt;</td>\n      <td>&lt;NA&gt;</td>\n      <td>&lt;NA&gt;</td>\n      <td>POINT (-122.25381 37.80021)</td>\n      <td>POINT (-122.24878 37.79271)</td>\n    </tr>\n    <tr>\n      <th>12</th>\n      <td>201801171656553504</td>\n      <td>500</td>\n      <td>2018-01-17 16:56:55+00:00</td>\n      <td>El Embarcadero at Grand Ave</td>\n      <td>197</td>\n      <td>2018-01-17 17:05:16+00:00</td>\n      <td>10th Ave at E 15th St</td>\n      <td>222</td>\n      <td>3504</td>\n      <td>&lt;NA&gt;</td>\n      <td>...</td>\n      <td>&lt;NA&gt;</td>\n      <td>37.808848</td>\n      <td>-122.24968</td>\n      <td>37.792714</td>\n      <td>-122.24878</td>\n      <td>1987</td>\n      <td>Male</td>\n      <td>No</td>\n      <td>POINT (-122.24968 37.80885)</td>\n      <td>POINT (-122.24878 37.79271)</td>\n    </tr>\n    <tr>\n      <th>13</th>\n      <td>201801111613101305</td>\n      <td>858</td>\n      <td>2018-01-11 16:13:10+00:00</td>\n      <td>Frank H Ogawa Plaza</td>\n      <td>7</td>\n      <td>2018-01-11 16:27:28+00:00</td>\n      <td>10th Ave at E 15th St</td>\n      <td>222</td>\n      <td>1305</td>\n      <td>&lt;NA&gt;</td>\n      <td>...</td>\n      <td>&lt;NA&gt;</td>\n      <td>37.804562</td>\n      <td>-122.271738</td>\n      <td>37.792714</td>\n      <td>-122.24878</td>\n      <td>1984</td>\n      <td>Male</td>\n      <td>Yes</td>\n      <td>POINT (-122.27174 37.80456)</td>\n      <td>POINT (-122.24878 37.79271)</td>\n    </tr>\n    <tr>\n      <th>14</th>\n      <td>201802241826551215</td>\n      <td>1235</td>\n      <td>2018-02-24 18:26:55+00:00</td>\n      <td>Frank H Ogawa Plaza</td>\n      <td>7</td>\n      <td>2018-02-24 18:47:31+00:00</td>\n      <td>10th Ave at E 15th St</td>\n      <td>222</td>\n      <td>1215</td>\n      <td>&lt;NA&gt;</td>\n      <td>...</td>\n      <td>&lt;NA&gt;</td>\n      <td>37.804562</td>\n      <td>-122.271738</td>\n      <td>37.792714</td>\n      <td>-122.24878</td>\n      <td>1969</td>\n      <td>Male</td>\n      <td>No</td>\n      <td>POINT (-122.27174 37.80456)</td>\n      <td>POINT (-122.24878 37.79271)</td>\n    </tr>\n    <tr>\n      <th>15</th>\n      <td>201803091621483450</td>\n      <td>857</td>\n      <td>2018-03-09 16:21:48+00:00</td>\n      <td>Frank H Ogawa Plaza</td>\n      <td>7</td>\n      <td>2018-03-09 16:36:06+00:00</td>\n      <td>10th Ave at E 15th St</td>\n      <td>222</td>\n      <td>3450</td>\n      <td>&lt;NA&gt;</td>\n      <td>...</td>\n      <td>&lt;NA&gt;</td>\n      <td>37.804562</td>\n      <td>-122.271738</td>\n      <td>37.792714</td>\n      <td>-122.24878</td>\n      <td>1984</td>\n      <td>Male</td>\n      <td>Yes</td>\n      <td>POINT (-122.27174 37.80456)</td>\n      <td>POINT (-122.24878 37.79271)</td>\n    </tr>\n    <tr>\n      <th>16</th>\n      <td>201801021932232717</td>\n      <td>914</td>\n      <td>2018-01-02 19:32:23+00:00</td>\n      <td>Frank H Ogawa Plaza</td>\n      <td>7</td>\n      <td>2018-01-02 19:47:38+00:00</td>\n      <td>10th Ave at E 15th St</td>\n      <td>222</td>\n      <td>2717</td>\n      <td>&lt;NA&gt;</td>\n      <td>...</td>\n      <td>&lt;NA&gt;</td>\n      <td>37.804562</td>\n      <td>-122.271738</td>\n      <td>37.792714</td>\n      <td>-122.24878</td>\n      <td>1984</td>\n      <td>Male</td>\n      <td>Yes</td>\n      <td>POINT (-122.27174 37.80456)</td>\n      <td>POINT (-122.24878 37.79271)</td>\n    </tr>\n    <tr>\n      <th>17</th>\n      <td>201803161910283751</td>\n      <td>564</td>\n      <td>2018-03-16 19:10:28+00:00</td>\n      <td>Frank H Ogawa Plaza</td>\n      <td>7</td>\n      <td>2018-03-16 19:19:52+00:00</td>\n      <td>10th Ave at E 15th St</td>\n      <td>222</td>\n      <td>3751</td>\n      <td>&lt;NA&gt;</td>\n      <td>...</td>\n      <td>&lt;NA&gt;</td>\n      <td>37.804562</td>\n      <td>-122.271738</td>\n      <td>37.792714</td>\n      <td>-122.24878</td>\n      <td>1987</td>\n      <td>Male</td>\n      <td>No</td>\n      <td>POINT (-122.27174 37.80456)</td>\n      <td>POINT (-122.24878 37.79271)</td>\n    </tr>\n    <tr>\n      <th>18</th>\n      <td>20171212152403227</td>\n      <td>854</td>\n      <td>2017-12-12 15:24:03+00:00</td>\n      <td>Frank H Ogawa Plaza</td>\n      <td>7</td>\n      <td>2017-12-12 15:38:17+00:00</td>\n      <td>10th Ave at E 15th St</td>\n      <td>222</td>\n      <td>227</td>\n      <td>&lt;NA&gt;</td>\n      <td>...</td>\n      <td>&lt;NA&gt;</td>\n      <td>37.804562</td>\n      <td>-122.271738</td>\n      <td>37.792714</td>\n      <td>-122.24878</td>\n      <td>1984</td>\n      <td>Male</td>\n      <td>&lt;NA&gt;</td>\n      <td>POINT (-122.27174 37.80456)</td>\n      <td>POINT (-122.24878 37.79271)</td>\n    </tr>\n    <tr>\n      <th>19</th>\n      <td>201803131437033724</td>\n      <td>917</td>\n      <td>2018-03-13 14:37:03+00:00</td>\n      <td>Grand Ave at Webster St</td>\n      <td>181</td>\n      <td>2018-03-13 14:52:20+00:00</td>\n      <td>10th Ave at E 15th St</td>\n      <td>222</td>\n      <td>3724</td>\n      <td>&lt;NA&gt;</td>\n      <td>...</td>\n      <td>&lt;NA&gt;</td>\n      <td>37.811377</td>\n      <td>-122.265192</td>\n      <td>37.792714</td>\n      <td>-122.24878</td>\n      <td>1989</td>\n      <td>Male</td>\n      <td>No</td>\n      <td>POINT (-122.26519 37.81138)</td>\n      <td>POINT (-122.24878 37.79271)</td>\n    </tr>\n    <tr>\n      <th>20</th>\n      <td>201712061755593426</td>\n      <td>519</td>\n      <td>2017-12-06 17:55:59+00:00</td>\n      <td>Lake Merritt BART Station</td>\n      <td>163</td>\n      <td>2017-12-06 18:04:39+00:00</td>\n      <td>10th Ave at E 15th St</td>\n      <td>222</td>\n      <td>3426</td>\n      <td>&lt;NA&gt;</td>\n      <td>...</td>\n      <td>&lt;NA&gt;</td>\n      <td>37.79732</td>\n      <td>-122.26532</td>\n      <td>37.792714</td>\n      <td>-122.24878</td>\n      <td>1986</td>\n      <td>Male</td>\n      <td>&lt;NA&gt;</td>\n      <td>POINT (-122.26532 37.79732)</td>\n      <td>POINT (-122.24878 37.79271)</td>\n    </tr>\n    <tr>\n      <th>21</th>\n      <td>20180404210034451</td>\n      <td>366</td>\n      <td>2018-04-04 21:00:34+00:00</td>\n      <td>Lake Merritt BART Station</td>\n      <td>163</td>\n      <td>2018-04-04 21:06:41+00:00</td>\n      <td>10th Ave at E 15th St</td>\n      <td>222</td>\n      <td>451</td>\n      <td>&lt;NA&gt;</td>\n      <td>...</td>\n      <td>&lt;NA&gt;</td>\n      <td>37.79732</td>\n      <td>-122.26532</td>\n      <td>37.792714</td>\n      <td>-122.24878</td>\n      <td>1987</td>\n      <td>Male</td>\n      <td>No</td>\n      <td>POINT (-122.26532 37.79732)</td>\n      <td>POINT (-122.24878 37.79271)</td>\n    </tr>\n    <tr>\n      <th>22</th>\n      <td>201801231907161787</td>\n      <td>626</td>\n      <td>2018-01-23 19:07:16+00:00</td>\n      <td>Lake Merritt BART Station</td>\n      <td>163</td>\n      <td>2018-01-23 19:17:43+00:00</td>\n      <td>10th Ave at E 15th St</td>\n      <td>222</td>\n      <td>1787</td>\n      <td>&lt;NA&gt;</td>\n      <td>...</td>\n      <td>&lt;NA&gt;</td>\n      <td>37.79732</td>\n      <td>-122.26532</td>\n      <td>37.792714</td>\n      <td>-122.24878</td>\n      <td>1987</td>\n      <td>Male</td>\n      <td>No</td>\n      <td>POINT (-122.26532 37.79732)</td>\n      <td>POINT (-122.24878 37.79271)</td>\n    </tr>\n    <tr>\n      <th>23</th>\n      <td>201708271057061157</td>\n      <td>973</td>\n      <td>2017-08-27 10:57:06+00:00</td>\n      <td>Lake Merritt BART Station</td>\n      <td>163</td>\n      <td>2017-08-27 11:13:19+00:00</td>\n      <td>10th Ave at E 15th St</td>\n      <td>222</td>\n      <td>1157</td>\n      <td>&lt;NA&gt;</td>\n      <td>...</td>\n      <td>&lt;NA&gt;</td>\n      <td>37.79732</td>\n      <td>-122.26532</td>\n      <td>37.792714</td>\n      <td>-122.24878</td>\n      <td>&lt;NA&gt;</td>\n      <td>&lt;NA&gt;</td>\n      <td>&lt;NA&gt;</td>\n      <td>POINT (-122.26532 37.79732)</td>\n      <td>POINT (-122.24878 37.79271)</td>\n    </tr>\n    <tr>\n      <th>24</th>\n      <td>201709071348372074</td>\n      <td>11434</td>\n      <td>2017-09-07 13:48:37+00:00</td>\n      <td>Lake Merritt BART Station</td>\n      <td>163</td>\n      <td>2017-09-07 16:59:12+00:00</td>\n      <td>10th Ave at E 15th St</td>\n      <td>222</td>\n      <td>2074</td>\n      <td>&lt;NA&gt;</td>\n      <td>...</td>\n      <td>&lt;NA&gt;</td>\n      <td>37.79732</td>\n      <td>-122.26532</td>\n      <td>37.792714</td>\n      <td>-122.24878</td>\n      <td>&lt;NA&gt;</td>\n      <td>&lt;NA&gt;</td>\n      <td>&lt;NA&gt;</td>\n      <td>POINT (-122.26532 37.79732)</td>\n      <td>POINT (-122.24878 37.79271)</td>\n    </tr>\n  </tbody>\n</table>\n<p>25 rows × 21 columns</p>\n</div>[1947417 rows x 21 columns in total]"},"metadata":{}}],"execution_count":5},{"cell_type":"markdown","source":"## 2. Preprocess Data\n\nOnly take the `start_date` after 2018 and the \"Subscriber\" category as input. `start_date` are truncated to each hour.","metadata":{}},{"cell_type":"code","source":"df = df[df[\"start_date\"] >= \"2018-01-01\"]\ndf = df[df[\"subscriber_type\"] == \"Subscriber\"]\ndf[\"trip_hour\"] = df[\"start_date\"].dt.floor(\"h\")\ndf = df[[\"trip_hour\", \"trip_id\"]]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-08-18T19:20:44.397712Z","iopub.execute_input":"2025-08-18T19:20:44.398876Z","iopub.status.idle":"2025-08-18T19:20:44.421504Z","shell.execute_reply.started":"2025-08-18T19:20:44.398742Z","shell.execute_reply":"2025-08-18T19:20:44.420509Z"}},"outputs":[],"execution_count":6},{"cell_type":"markdown","source":"Group and count each hour's num of trips.","metadata":{}},{"cell_type":"code","source":"df_grouped = df.groupby(\"trip_hour\").count()\ndf_grouped = df_grouped.reset_index().rename(columns={\"trip_id\": \"num_trips\"})\ndf_grouped","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-08-18T19:20:57.499571Z","iopub.execute_input":"2025-08-18T19:20:57.500413Z","iopub.status.idle":"2025-08-18T19:21:02.999663Z","shell.execute_reply.started":"2025-08-18T19:20:57.500376Z","shell.execute_reply":"2025-08-18T19:21:02.998792Z"}},"outputs":[{"output_type":"display_data","data":{"text/plain":"<IPython.core.display.HTML object>","text/html":"Query job e3df71d2-9248-491a-8e5f-4bb5bfedb686 is DONE. 58.7 MB processed. <a target=\"_blank\" href=\"https://console.cloud.google.com/bigquery?project=swast-scratch&j=bq:US:e3df71d2-9248-491a-8e5f-4bb5bfedb686&page=queryresults\">Open Job</a>"},"metadata":{}},{"execution_count":7,"output_type":"execute_result","data":{"text/plain":"                trip_hour  num_trips\n2018-01-01 00:00:00+00:00         20\n2018-01-01 01:00:00+00:00         25\n2018-01-01 02:00:00+00:00         13\n2018-01-01 03:00:00+00:00         11\n2018-01-01 05:00:00+00:00          4\n2018-01-01 06:00:00+00:00          8\n2018-01-01 07:00:00+00:00          8\n2018-01-01 08:00:00+00:00         20\n2018-01-01 09:00:00+00:00         30\n2018-01-01 10:00:00+00:00         41\n2018-01-01 11:00:00+00:00         45\n2018-01-01 12:00:00+00:00         54\n2018-01-01 13:00:00+00:00         57\n2018-01-01 14:00:00+00:00         68\n2018-01-01 15:00:00+00:00         86\n2018-01-01 16:00:00+00:00         72\n2018-01-01 17:00:00+00:00         72\n2018-01-01 18:00:00+00:00         47\n2018-01-01 19:00:00+00:00         32\n2018-01-01 20:00:00+00:00         34\n2018-01-01 21:00:00+00:00         27\n2018-01-01 22:00:00+00:00         15\n2018-01-01 23:00:00+00:00          6\n2018-01-02 00:00:00+00:00          2\n2018-01-02 01:00:00+00:00          1\n...\n\n[2842 rows x 2 columns]","text/html":"<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>trip_hour</th>\n      <th>num_trips</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>2018-01-01 00:00:00+00:00</td>\n      <td>20</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>2018-01-01 01:00:00+00:00</td>\n      <td>25</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>2018-01-01 02:00:00+00:00</td>\n      <td>13</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>2018-01-01 03:00:00+00:00</td>\n      <td>11</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>2018-01-01 05:00:00+00:00</td>\n      <td>4</td>\n    </tr>\n    <tr>\n      <th>5</th>\n      <td>2018-01-01 06:00:00+00:00</td>\n      <td>8</td>\n    </tr>\n    <tr>\n      <th>6</th>\n      <td>2018-01-01 07:00:00+00:00</td>\n      <td>8</td>\n    </tr>\n    <tr>\n      <th>7</th>\n      <td>2018-01-01 08:00:00+00:00</td>\n      <td>20</td>\n    </tr>\n    <tr>\n      <th>8</th>\n      <td>2018-01-01 09:00:00+00:00</td>\n      <td>30</td>\n    </tr>\n    <tr>\n      <th>9</th>\n      <td>2018-01-01 10:00:00+00:00</td>\n      <td>41</td>\n    </tr>\n    <tr>\n      <th>10</th>\n      <td>2018-01-01 11:00:00+00:00</td>\n      <td>45</td>\n    </tr>\n    <tr>\n      <th>11</th>\n      <td>2018-01-01 12:00:00+00:00</td>\n      <td>54</td>\n    </tr>\n    <tr>\n      <th>12</th>\n      <td>2018-01-01 13:00:00+00:00</td>\n      <td>57</td>\n    </tr>\n    <tr>\n      <th>13</th>\n      <td>2018-01-01 14:00:00+00:00</td>\n      <td>68</td>\n    </tr>\n    <tr>\n      <th>14</th>\n      <td>2018-01-01 15:00:00+00:00</td>\n      <td>86</td>\n    </tr>\n    <tr>\n      <th>15</th>\n      <td>2018-01-01 16:00:00+00:00</td>\n      <td>72</td>\n    </tr>\n    <tr>\n      <th>16</th>\n      <td>2018-01-01 17:00:00+00:00</td>\n      <td>72</td>\n    </tr>\n    <tr>\n      <th>17</th>\n      <td>2018-01-01 18:00:00+00:00</td>\n      <td>47</td>\n    </tr>\n    <tr>\n      <th>18</th>\n      <td>2018-01-01 19:00:00+00:00</td>\n      <td>32</td>\n    </tr>\n    <tr>\n      <th>19</th>\n      <td>2018-01-01 20:00:00+00:00</td>\n      <td>34</td>\n    </tr>\n    <tr>\n      <th>20</th>\n      <td>2018-01-01 21:00:00+00:00</td>\n      <td>27</td>\n    </tr>\n    <tr>\n      <th>21</th>\n      <td>2018-01-01 22:00:00+00:00</td>\n      <td>15</td>\n    </tr>\n    <tr>\n      <th>22</th>\n      <td>2018-01-01 23:00:00+00:00</td>\n      <td>6</td>\n    </tr>\n    <tr>\n      <th>23</th>\n      <td>2018-01-02 00:00:00+00:00</td>\n      <td>2</td>\n    </tr>\n    <tr>\n      <th>24</th>\n      <td>2018-01-02 01:00:00+00:00</td>\n      <td>1</td>\n    </tr>\n  </tbody>\n</table>\n<p>25 rows × 2 columns</p>\n</div>[2842 rows x 2 columns in total]"},"metadata":{}}],"execution_count":7},{"cell_type":"markdown","source":"## 3. Make forecastings for next 1 week with DataFrames.ai.forecast API","metadata":{}},{"cell_type":"code","source":"# Using all the data except the last week (2842-168) for training. And predict the last week (168).\nresult = df_grouped.head(2842-168).ai.forecast(timestamp_column=\"trip_hour\", data_column=\"num_trips\", horizon=168) \nresult","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-08-18T19:22:58.943589Z","iopub.execute_input":"2025-08-18T19:22:58.944068Z","iopub.status.idle":"2025-08-18T19:23:11.364356Z","shell.execute_reply.started":"2025-08-18T19:22:58.944036Z","shell.execute_reply":"2025-08-18T19:23:11.363152Z"}},"outputs":[{"output_type":"display_data","data":{"text/plain":"<IPython.core.display.HTML object>","text/html":"Query job 3f1225a8-b80b-4dfa-a7cf-94b93e7c18c2 is DONE. 68.2 kB processed. <a target=\"_blank\" href=\"https://console.cloud.google.com/bigquery?project=swast-scratch&j=bq:US:3f1225a8-b80b-4dfa-a7cf-94b93e7c18c2&page=queryresults\">Open Job</a>"},"metadata":{}},{"execution_count":8,"output_type":"execute_result","data":{"text/plain":"       forecast_timestamp  forecast_value  confidence_level  \\\n2018-04-24 12:00:00+00:00      144.577728              0.95   \n2018-04-25 00:00:00+00:00       54.215515              0.95   \n2018-04-26 05:00:00+00:00        8.140533              0.95   \n2018-04-26 14:00:00+00:00      198.744949              0.95   \n2018-04-27 02:00:00+00:00         9.91806              0.95   \n2018-04-29 03:00:00+00:00       32.063339              0.95   \n2018-04-27 04:00:00+00:00       25.757111              0.95   \n2018-04-30 06:00:00+00:00       89.808456              0.95   \n2018-04-30 02:00:00+00:00      -10.584175              0.95   \n2018-04-30 05:00:00+00:00       18.118111              0.95   \n2018-04-24 07:00:00+00:00      359.036957              0.95   \n2018-04-25 10:00:00+00:00      227.272049              0.95   \n2018-04-27 15:00:00+00:00      208.631363              0.95   \n2018-04-25 13:00:00+00:00      159.799911              0.95   \n2018-04-26 12:00:00+00:00      190.226944              0.95   \n2018-04-24 04:00:00+00:00       11.162338              0.95   \n2018-04-24 14:00:00+00:00       136.70816              0.95   \n2018-04-28 21:00:00+00:00       65.308899              0.95   \n2018-04-29 20:00:00+00:00       71.788849              0.95   \n2018-04-30 15:00:00+00:00      142.560944              0.95   \n2018-04-26 18:00:00+00:00      533.783813              0.95   \n2018-04-28 03:00:00+00:00       25.379761              0.95   \n2018-04-30 12:00:00+00:00      158.313385              0.95   \n2018-04-25 07:00:00+00:00      358.756592              0.95   \n2018-04-27 22:00:00+00:00      103.589096              0.95   \n\n prediction_interval_lower_bound  prediction_interval_upper_bound  \\\n                       120.01921                       169.136247   \n                         46.8394                        61.591631   \n                      -14.613272                        30.894339   \n                      174.982268                        222.50763   \n                      -26.749948                        46.586069   \n                      -35.730978                        99.857656   \n                        8.178037                        43.336184   \n                       15.214961                       164.401952   \n                      -60.772024                        39.603674   \n                      -40.902133                        77.138355   \n                      250.880334                       467.193579   \n                      170.918819                       283.625279   \n                      188.977435                       228.285291   \n                      150.066363                        169.53346   \n                      177.898865                       202.555023   \n                      -18.581041                        40.905717   \n                      134.165413                       139.250907   \n                       63.000915                        67.616883   \n                        -2.49023                       146.067928   \n                       41.495553                       243.626334   \n                      412.068752                       655.498875   \n                       22.565752                        28.193769   \n                       79.466457                       237.160313   \n                      276.305603                       441.207581   \n                        94.45235                       112.725842   \n\nai_forecast_status  \n                    \n                    \n                    \n                    \n                    \n                    \n                    \n                    \n                    \n                    \n                    \n                    \n                    \n                    \n                    \n                    \n                    \n                    \n                    \n                    \n                    \n                    \n                    \n                    \n                    \n...\n\n[168 rows x 6 columns]","text/html":"<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>forecast_timestamp</th>\n      <th>forecast_value</th>\n      <th>confidence_level</th>\n      <th>prediction_interval_lower_bound</th>\n      <th>prediction_interval_upper_bound</th>\n      <th>ai_forecast_status</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>2018-04-24 12:00:00+00:00</td>\n      <td>144.577728</td>\n      <td>0.95</td>\n      <td>120.01921</td>\n      <td>169.136247</td>\n      <td></td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>2018-04-25 00:00:00+00:00</td>\n      <td>54.215515</td>\n      <td>0.95</td>\n      <td>46.8394</td>\n      <td>61.591631</td>\n      <td></td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>2018-04-26 05:00:00+00:00</td>\n      <td>8.140533</td>\n      <td>0.95</td>\n      <td>-14.613272</td>\n      <td>30.894339</td>\n      <td></td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>2018-04-26 14:00:00+00:00</td>\n      <td>198.744949</td>\n      <td>0.95</td>\n      <td>174.982268</td>\n      <td>222.50763</td>\n      <td></td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>2018-04-27 02:00:00+00:00</td>\n      <td>9.91806</td>\n      <td>0.95</td>\n      <td>-26.749948</td>\n      <td>46.586069</td>\n      <td></td>\n    </tr>\n    <tr>\n      <th>5</th>\n      <td>2018-04-29 03:00:00+00:00</td>\n      <td>32.063339</td>\n      <td>0.95</td>\n      <td>-35.730978</td>\n      <td>99.857656</td>\n      <td></td>\n    </tr>\n    <tr>\n      <th>6</th>\n      <td>2018-04-27 04:00:00+00:00</td>\n      <td>25.757111</td>\n      <td>0.95</td>\n      <td>8.178037</td>\n      <td>43.336184</td>\n      <td></td>\n    </tr>\n    <tr>\n      <th>7</th>\n      <td>2018-04-30 06:00:00+00:00</td>\n      <td>89.808456</td>\n      <td>0.95</td>\n      <td>15.214961</td>\n      <td>164.401952</td>\n      <td></td>\n    </tr>\n    <tr>\n      <th>8</th>\n      <td>2018-04-30 02:00:00+00:00</td>\n      <td>-10.584175</td>\n      <td>0.95</td>\n      <td>-60.772024</td>\n      <td>39.603674</td>\n      <td></td>\n    </tr>\n    <tr>\n      <th>9</th>\n      <td>2018-04-30 05:00:00+00:00</td>\n      <td>18.118111</td>\n      <td>0.95</td>\n      <td>-40.902133</td>\n      <td>77.138355</td>\n      <td></td>\n    </tr>\n    <tr>\n      <th>10</th>\n      <td>2018-04-24 07:00:00+00:00</td>\n      <td>359.036957</td>\n      <td>0.95</td>\n      <td>250.880334</td>\n      <td>467.193579</td>\n      <td></td>\n    </tr>\n    <tr>\n      <th>11</th>\n      <td>2018-04-25 10:00:00+00:00</td>\n      <td>227.272049</td>\n      <td>0.95</td>\n      <td>170.918819</td>\n      <td>283.625279</td>\n      <td></td>\n    </tr>\n    <tr>\n      <th>12</th>\n      <td>2018-04-27 15:00:00+00:00</td>\n      <td>208.631363</td>\n      <td>0.95</td>\n      <td>188.977435</td>\n      <td>228.285291</td>\n      <td></td>\n    </tr>\n    <tr>\n      <th>13</th>\n      <td>2018-04-25 13:00:00+00:00</td>\n      <td>159.799911</td>\n      <td>0.95</td>\n      <td>150.066363</td>\n      <td>169.53346</td>\n      <td></td>\n    </tr>\n    <tr>\n      <th>14</th>\n      <td>2018-04-26 12:00:00+00:00</td>\n      <td>190.226944</td>\n      <td>0.95</td>\n      <td>177.898865</td>\n      <td>202.555023</td>\n      <td></td>\n    </tr>\n    <tr>\n      <th>15</th>\n      <td>2018-04-24 04:00:00+00:00</td>\n      <td>11.162338</td>\n      <td>0.95</td>\n      <td>-18.581041</td>\n      <td>40.905717</td>\n      <td></td>\n    </tr>\n    <tr>\n      <th>16</th>\n      <td>2018-04-24 14:00:00+00:00</td>\n      <td>136.70816</td>\n      <td>0.95</td>\n      <td>134.165413</td>\n      <td>139.250907</td>\n      <td></td>\n    </tr>\n    <tr>\n      <th>17</th>\n      <td>2018-04-28 21:00:00+00:00</td>\n      <td>65.308899</td>\n      <td>0.95</td>\n      <td>63.000915</td>\n      <td>67.616883</td>\n      <td></td>\n    </tr>\n    <tr>\n      <th>18</th>\n      <td>2018-04-29 20:00:00+00:00</td>\n      <td>71.788849</td>\n      <td>0.95</td>\n      <td>-2.49023</td>\n      <td>146.067928</td>\n      <td></td>\n    </tr>\n    <tr>\n      <th>19</th>\n      <td>2018-04-30 15:00:00+00:00</td>\n      <td>142.560944</td>\n      <td>0.95</td>\n      <td>41.495553</td>\n      <td>243.626334</td>\n      <td></td>\n    </tr>\n    <tr>\n      <th>20</th>\n      <td>2018-04-26 18:00:00+00:00</td>\n      <td>533.783813</td>\n      <td>0.95</td>\n      <td>412.068752</td>\n      <td>655.498875</td>\n      <td></td>\n    </tr>\n    <tr>\n      <th>21</th>\n      <td>2018-04-28 03:00:00+00:00</td>\n      <td>25.379761</td>\n      <td>0.95</td>\n      <td>22.565752</td>\n      <td>28.193769</td>\n      <td></td>\n    </tr>\n    <tr>\n      <th>22</th>\n      <td>2018-04-30 12:00:00+00:00</td>\n      <td>158.313385</td>\n      <td>0.95</td>\n      <td>79.466457</td>\n      <td>237.160313</td>\n      <td></td>\n    </tr>\n    <tr>\n      <th>23</th>\n      <td>2018-04-25 07:00:00+00:00</td>\n      <td>358.756592</td>\n      <td>0.95</td>\n      <td>276.305603</td>\n      <td>441.207581</td>\n      <td></td>\n    </tr>\n    <tr>\n      <th>24</th>\n      <td>2018-04-27 22:00:00+00:00</td>\n      <td>103.589096</td>\n      <td>0.95</td>\n      <td>94.45235</td>\n      <td>112.725842</td>\n      <td></td>\n    </tr>\n  </tbody>\n</table>\n<p>25 rows × 6 columns</p>\n</div>[168 rows x 6 columns in total]"},"metadata":{}}],"execution_count":8},{"cell_type":"markdown","source":"# 4. Process the raw result and draw a line plot along with the training data","metadata":{}},{"cell_type":"code","source":"result = result.sort_values(\"forecast_timestamp\")\nresult = result[[\"forecast_timestamp\", \"forecast_value\"]]\nresult = result.rename(columns={\"forecast_timestamp\": \"trip_hour\", \"forecast_value\": \"num_trips_forecast\"})\ndf_all = bpd.concat([df_grouped, result])\ndf_all = df_all.tail(672) # 4 weeks","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-08-18T19:27:08.305886Z","iopub.execute_input":"2025-08-18T19:27:08.306367Z","iopub.status.idle":"2025-08-18T19:27:08.318514Z","shell.execute_reply.started":"2025-08-18T19:27:08.306336Z","shell.execute_reply":"2025-08-18T19:27:08.317016Z"}},"outputs":[],"execution_count":9},{"cell_type":"markdown","source":"Plot a line chart and compare with the actual result.","metadata":{}},{"cell_type":"code","source":"df_all = df_all.set_index(\"trip_hour\")\ndf_all.plot.line(figsize=(16, 8))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-08-18T19:27:19.461164Z","iopub.execute_input":"2025-08-18T19:27:19.461528Z","iopub.status.idle":"2025-08-18T19:27:20.737558Z","shell.execute_reply.started":"2025-08-18T19:27:19.461497Z","shell.execute_reply":"2025-08-18T19:27:20.736422Z"}},"outputs":[{"execution_count":10,"output_type":"execute_result","data":{"text/plain":"<Axes: xlabel='trip_hour'>"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<Figure size 1600x800 with 1 Axes>","image/png":"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\n"},"metadata":{}}],"execution_count":10},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}


Should "pip install --upgrade" also upgrade other dependencies? Unless --no-deps?

Reply via ReviewNB

I'll give --no-deps a try.

I think upgrading the other dependencies is necessary. Example:

--------------------------------------------------------------------------- ModuleNotFoundError Traceback (most recent call last) /tmp/ipykernel_77/1103434230.py in <cell line: 0>() ----> 1 import bigframes._config 2 import bigframes.pandas as bpd 3 4 bpd.options.bigquery.location = "US" 5 /usr/local/lib/python3.11/dist-packages/bigframes/__init__.py in <module> 17 from bigframes._config import option_context, options 18 from bigframes._config.bigquery_options import BigQueryOptions ---> 19 from bigframes.core.global_session import close_session, get_global_session 20 import bigframes.enums as enums 21 import bigframes.exceptions as exceptions /usr/local/lib/python3.11/dist-packages/bigframes/core/global_session.py in <module> 24 import bigframes._config 25 import bigframes.exceptions as bfe ---> 26 import bigframes.session 27 28 _global_session: Optional[bigframes.session.Session] = None /usr/local/lib/python3.11/dist-packages/bigframes/session/__init__.py in <module> 42 import bigframes_vendored.constants as constants 43 import bigframes_vendored.google_cloud_bigquery.retry as third_party_gcb_retry ---> 44 import bigframes_vendored.ibis.backends.bigquery as ibis_bigquery # noqa 45 import bigframes_vendored.pandas.io.gbq as third_party_pandas_gbq 46 import bigframes_vendored.pandas.io.parquet as third_party_pandas_parquet /usr/local/lib/python3.11/dist-packages/bigframes_vendored/ibis/__init__.py in <module> 12 from bigframes_vendored.ibis import util 13 from bigframes_vendored.ibis.backends import BaseBackend ---> 14 import bigframes_vendored.ibis.backends.bigquery as bigquery 15 from bigframes_vendored.ibis.common.exceptions import IbisError 16 from bigframes_vendored.ibis.config import options /usr/local/lib/python3.11/dist-packages/bigframes_vendored/ibis/backends/bigquery/__init__.py in <module> 36 import google.auth.credentials 37 import google.cloud.bigquery as bq ---> 38 import google.cloud.bigquery_storage_v1 as bqstorage 39 import pydata_google_auth 40 from pydata_google_auth import cache ModuleNotFoundError: No module named 'google.cloud.bigquery_storage_v1'

GarrettWu · 2025-08-18T21:57:38Z

notebooks/kaggle/vector-search-with-bigframes-over-national-jukebox.ipynb

@@ -0,0 +1 @@
+{"metadata":{"kernelspec":{"name":"python3","display_name":"Python 3","language":"python"},"language_info":{"name":"python","version":"3.11.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":110281,"databundleVersionId":13238728,"sourceType":"competition"}],"dockerImageVersionId":31089,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# Creating a searchable index of the National Jukebox\n\n_Extracting text from audio and indexing it with BigQuery DataFrames_\n\n* Tim Swena (formerly, Swast)\n* swast@google.com\n* https://vis.social/@timswast on Mastodon\n\nThis notebook lives in\n\n* https://github.com/tswast/code-snippets\n* at https://github.com/tswast/code-snippets/blob/main/2025/national-jukebox/transcribe_songs.ipynb\n\nTo follow along, you'll need a Google Cloud project\n\n* Go to https://cloud.google.com/free to start a free trial.","metadata":{"@deathbeds/jupyterlab-fonts":{"styles":{"":{"body[data-jp-deck-mode='presenting'] &":{"zoom":"194%"}}}},"editable":true,"slideshow":{"slide_type":"subslide"},"tags":[]}},{"cell_type":"markdown","source":"The National Jukebox is a project of the USA Library of Congress to provide access to thousands of acoustic sound recordings from the very earliest days of the commercial record industry.\n\n* Learn more at https://www.loc.gov/collections/national-jukebox/about-this-collection/\n\n<img src=\"https://www.loc.gov/static/collections/national-jukebox/images/acoustic-session.jpg\" alt=\"recording 100+ years ago\" width=\"400px\" />","metadata":{"@deathbeds/jupyterlab-fonts":{"styles":{"":{"body[data-jp-deck-mode='presenting'] &":{"z-index":"0","zoom":"216%"}}}},"slideshow":{"slide_type":"slide"}}},{"cell_type":"markdown","source":"\nTo search the National Jukebox, we combine powerful features of BigQuery:\n\n<img src=\"data:image/png;base64,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\" alt=\"audio video logos\" style=\"float:left; height:200px;\" />\n\n1. Integrations with multi-modal AI models to extract information from unstructured data, in this case audio files.\n\n   https://cloud.google.com/bigquery/docs/multimodal-data-dataframes-tutorial\n   \n2. Vector search to find similar text using embedding models.\n\n   https://cloud.google.com/bigquery/docs/vector-index-text-search-tutorial\n\n3. BigQuery DataFrames to use Python instead of SQL.\n\n   https://cloud.google.com/bigquery/docs/bigquery-dataframes-introduction","metadata":{"@deathbeds/jupyterlab-fonts":{"styles":{"":{"body[data-jp-deck-mode='presenting'] &":{"z-index":"0","zoom":"181%"}}}},"slideshow":{"slide_type":"slide"}}},{"cell_type":"markdown","source":"## Getting started with BigQuery DataFrames (bigframes)\n\nInstall the bigframes package.","metadata":{"@deathbeds/jupyterlab-fonts":{"styles":{"":{"body[data-jp-deck-mode='presenting'] &":{"zoom":"275%"}}}},"slideshow":{"slide_type":"slide"}}},{"cell_type":"code","source":"%pip install --upgrade bigframes google-cloud-automl google-cloud-translate google-ai-generativelanguage tensorflow ","metadata":{"@deathbeds/jupyterlab-fonts":{"styles":{"":{"body[data-jp-deck-mode='presenting'] &":{"zoom":"214%"}}}},"trusted":true,"execution":{"iopub.status.busy":"2025-08-14T15:53:02.493469Z","iopub.execute_input":"2025-08-14T15:53:02.494188Z","iopub.status.idle":"2025-08-14T15:53:08.492291Z","shell.execute_reply.started":"2025-08-14T15:53:02.494152Z","shell.execute_reply":"2025-08-14T15:53:08.491183Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"**Important:** restart the kernel by going to \"Run -> Restart & clear cell outputs\" before continuing.\n\nConfigure bigframes to use your GCP project. First, go to \"Add-ons -> Google Cloud SDK\" and click the \"Attach\" button. Then,","metadata":{"@deathbeds/jupyterlab-fonts":{"styles":{"":{"body[data-jp-deck-mode='presenting'] &":{"z-index":"4","zoom":"236%"}}}}}},{"cell_type":"code","source":"from kaggle_secrets import UserSecretsClient\nuser_secrets = UserSecretsClient()\nuser_credential = user_secrets.get_gcloud_credential()\nuser_secrets.set_tensorflow_credential(user_credential)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-08-14T15:53:08.494313Z","iopub.execute_input":"2025-08-14T15:53:08.494636Z","iopub.status.idle":"2025-08-14T15:53:08.609706Z","shell.execute_reply.started":"2025-08-14T15:53:08.494604Z","shell.execute_reply":"2025-08-14T15:53:08.608705Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import bigframes._config\nimport bigframes.pandas as bpd\n\nbpd.options.bigquery.location = \"US\"\n\n# Set to your GCP project ID.\nbpd.options.bigquery.project = \"swast-scratch\"","metadata":{"@deathbeds/jupyterlab-fonts":{"styles":{"":{"body[data-jp-deck-mode='presenting'] &":{"zoom":"193%"}}}},"trusted":true,"execution":{"iopub.status.busy":"2025-08-14T15:53:08.610686Z","iopub.execute_input":"2025-08-14T15:53:08.610982Z","iopub.status.idle":"2025-08-14T15:53:17.658993Z","shell.execute_reply.started":"2025-08-14T15:53:08.610961Z","shell.execute_reply":"2025-08-14T15:53:17.657745Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## Reading data\n\nBigQuery DataFrames can read data from BigQuery, GCS, or even local sources. With `engine=\"bigquery\"`, BigQuery's distributed processing reads the file without it ever having to reach your local Python environment.","metadata":{"@deathbeds/jupyterlab-fonts":{"styles":{"":{"body[data-jp-deck-mode='presenting'] &":{"zoom":"207%"}}}},"slideshow":{"slide_type":"slide"}}},{"cell_type":"code","source":"df = bpd.read_json(\n    \"gs://cloud-samples-data/third-party/usa-loc-national-jukebox/jukebox.jsonl\",\n    engine=\"bigquery\",\n    orient=\"records\",\n    lines=True,\n)","metadata":{"@deathbeds/jupyterlab-fonts":{"styles":{"":{"body[data-jp-deck-mode='presenting'] &":{"zoom":"225%"}}}},"trusted":true,"execution":{"iopub.status.busy":"2025-08-14T15:53:17.661901Z","iopub.execute_input":"2025-08-14T15:53:17.662234Z","iopub.status.idle":"2025-08-14T15:53:34.486799Z","shell.execute_reply.started":"2025-08-14T15:53:17.662207Z","shell.execute_reply":"2025-08-14T15:53:34.485777Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Use `peek()` instead of `head()` to see arbitrary rows rather than the \"first\" rows.\ndf.peek()","metadata":{"@deathbeds/jupyterlab-fonts":{"styles":{"":{"body[data-jp-deck-mode='presenting'] &":{"zoom":"122%"}}}},"slideshow":{"slide_type":"slide"},"trusted":true,"execution":{"iopub.status.busy":"2025-08-14T15:53:34.488332Z","iopub.execute_input":"2025-08-14T15:53:34.488610Z","iopub.status.idle":"2025-08-14T15:53:40.347014Z","shell.execute_reply.started":"2025-08-14T15:53:34.488589Z","shell.execute_reply":"2025-08-14T15:53:40.345773Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.shape","metadata":{"@deathbeds/jupyterlab-fonts":{"styles":{"":{"body[data-jp-deck-mode='presenting'] &":{"zoom":"134%"}}}},"trusted":true,"execution":{"iopub.status.busy":"2025-08-14T15:53:40.348021Z","iopub.execute_input":"2025-08-14T15:53:40.348376Z","iopub.status.idle":"2025-08-14T15:53:40.364129Z","shell.execute_reply.started":"2025-08-14T15:53:40.348351Z","shell.execute_reply":"2025-08-14T15:53:40.363204Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# For the purposes of a demo, select only a subset of rows.\ndf = df.sample(n=250)\ndf.cache()\ndf.shape","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-08-14T15:55:55.448310Z","iopub.execute_input":"2025-08-14T15:55:55.448664Z","iopub.status.idle":"2025-08-14T15:55:59.440964Z","shell.execute_reply.started":"2025-08-14T15:55:55.448637Z","shell.execute_reply":"2025-08-14T15:55:59.439988Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# As a side effect of how I extracted the song information from the HTML DOM,\n# we ended up with lists in places where we only expect one item.\n#\n# We can \"explode\" to flatten these lists.\nflattened = df.explode([\n    \"Recording Repository\",\n    \"Recording Label\",\n    \"Recording Take Number\",\n    \"Recording Date\",\n    \"Recording Matrix Number\",\n    \"Recording Catalog Number\",\n    \"Media Size\",\n    \"Recording Location\",\n    \"Summary\",\n    \"Rights Advisory\",\n    \"Title\",\n])\nflattened.peek()","metadata":{"@deathbeds/jupyterlab-fonts":{"styles":{"":{"body[data-jp-deck-mode='presenting'] &":{"zoom":"161%"}}}},"slideshow":{"slide_type":"slide"},"trusted":true,"execution":{"iopub.status.busy":"2025-08-14T15:56:02.040450Z","iopub.execute_input":"2025-08-14T15:56:02.040804Z","iopub.status.idle":"2025-08-14T15:56:06.544384Z","shell.execute_reply.started":"2025-08-14T15:56:02.040777Z","shell.execute_reply":"2025-08-14T15:56:06.543240Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"flattened.shape","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-08-14T15:56:06.546140Z","iopub.execute_input":"2025-08-14T15:56:06.546531Z","iopub.status.idle":"2025-08-14T15:56:06.566005Z","shell.execute_reply.started":"2025-08-14T15:56:06.546494Z","shell.execute_reply":"2025-08-14T15:56:06.564355Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"To access unstructured data from BigQuery, create a URI pointing to a file in Google Cloud Storage (GCS). Then, construct a \"blob\" (also known as an \"Object Ref\" in BigQuery terms) so that BigQuery can read from GCS.","metadata":{"@deathbeds/jupyterlab-fonts":{"styles":{"":{"body[data-jp-deck-mode='presenting'] &":{"zoom":"216%"}}}},"editable":true,"slideshow":{"slide_type":"slide"},"tags":[]}},{"cell_type":"code","source":"flattened = flattened.assign(**{\n    \"GCS Prefix\": \"gs://cloud-samples-data/third-party/usa-loc-national-jukebox/\",\n    \"GCS Stub\": flattened['URL'].str.extract(r'/(jukebox-[0-9]+)/'),\n})\nflattened.cache()\nflattened[\"GCS URI\"] = flattened[\"GCS Prefix\"] + flattened[\"GCS Stub\"] + \".mp3\"\nflattened[\"GCS Blob\"] = flattened[\"GCS URI\"].str.to_blob()","metadata":{"@deathbeds/jupyterlab-fonts":{"styles":{"":{"body[data-jp-deck-mode='presenting'] &":{"zoom":"211%"}}}},"editable":true,"slideshow":{"slide_type":""},"tags":[],"trusted":true,"execution":{"iopub.status.busy":"2025-08-14T15:56:07.394509Z","iopub.execute_input":"2025-08-14T15:56:07.394879Z","iopub.status.idle":"2025-08-14T15:56:12.217017Z","shell.execute_reply.started":"2025-08-14T15:56:07.394853Z","shell.execute_reply":"2025-08-14T15:56:12.215852Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"BigQuery (and BigQuery DataFrames) provide access to powerful models and multimodal capabilities. Here, we transcribe audio to text.","metadata":{"@deathbeds/jupyterlab-fonts":{"styles":{"":{"body[data-jp-deck-mode='presenting'] &":{"zoom":"317%"}}}},"editable":true,"slideshow":{"slide_type":"slide"},"tags":[]}},{"cell_type":"code","source":"flattened[\"Transcription\"] = flattened[\"GCS Blob\"].blob.audio_transcribe(\n    model_name=\"gemini-2.0-flash-001\",\n    verbose=True,\n)\nflattened[\"Transcription\"]","metadata":{"editable":true,"slideshow":{"slide_type":""},"tags":[],"trusted":true,"execution":{"iopub.status.busy":"2025-08-14T15:56:20.907791Z","iopub.execute_input":"2025-08-14T15:56:20.908198Z","iopub.status.idle":"2025-08-14T15:58:45.909086Z","shell.execute_reply.started":"2025-08-14T15:56:20.908170Z","shell.execute_reply":"2025-08-14T15:58:45.908060Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Sometimes the model has transient errors. Check the status column to see if there are errors.","metadata":{"@deathbeds/jupyterlab-fonts":{"styles":{"":{"body[data-jp-deck-mode='presenting'] &":{"zoom":"229%"}}}},"slideshow":{"slide_type":"slide"}}},{"cell_type":"code","source":"print(f\"Successful rows: {(flattened['Transcription'].struct.field('status') == '').sum()}\")\nprint(f\"Failed rows: {(flattened['Transcription'].struct.field('status') != '').sum()}\")\nflattened.shape","metadata":{"@deathbeds/jupyterlab-fonts":{"styles":{"":{"body[data-jp-deck-mode='presenting'] &":{"zoom":"177%"}}}},"editable":true,"slideshow":{"slide_type":""},"tags":[],"trusted":true,"execution":{"iopub.status.busy":"2025-08-14T15:59:43.607976Z","iopub.execute_input":"2025-08-14T15:59:43.609239Z","iopub.status.idle":"2025-08-14T15:59:44.515118Z","shell.execute_reply.started":"2025-08-14T15:59:43.609201Z","shell.execute_reply":"2025-08-14T15:59:44.514275Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Show transcribed lyrics.\nflattened[\"Transcription\"].struct.field(\"content\")","metadata":{"@deathbeds/jupyterlab-fonts":{"styles":{"":{"body[data-jp-deck-mode='presenting'] &":{"zoom":"141%"}}}},"trusted":true,"execution":{"iopub.status.busy":"2025-08-14T15:59:44.819926Z","iopub.execute_input":"2025-08-14T15:59:44.820256Z","iopub.status.idle":"2025-08-14T15:59:53.147159Z","shell.execute_reply.started":"2025-08-14T15:59:44.820232Z","shell.execute_reply":"2025-08-14T15:59:53.146281Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Find all instrumentatal songs\ninstrumental = flattened[flattened[\"Transcription\"].struct.field(\"content\") == \"\"]\nprint(instrumental.shape)\nsong = instrumental.peek(1)\nsong","metadata":{"@deathbeds/jupyterlab-fonts":{"styles":{"":{"body[data-jp-deck-mode='presenting'] &":{"zoom":"152%"}}}},"slideshow":{"slide_type":"slide"},"trusted":true,"execution":{"iopub.status.busy":"2025-08-14T15:59:53.148783Z","iopub.execute_input":"2025-08-14T15:59:53.149222Z","iopub.status.idle":"2025-08-14T15:59:58.868959Z","shell.execute_reply.started":"2025-08-14T15:59:53.149198Z","shell.execute_reply":"2025-08-14T15:59:58.867804Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import gcsfs\nimport IPython.display\n\nfs = gcsfs.GCSFileSystem(project='bigframes-dev')\nwith fs.open(song[\"GCS URI\"].iloc[0]) as song_file:\n    song_bytes = song_file.read()\n\nIPython.display.Audio(song_bytes)","metadata":{"@deathbeds/jupyterlab-fonts":{"styles":{"":{"body[data-jp-deck-mode='presenting'] &":{"zoom":"152%"}}}},"editable":true,"slideshow":{"slide_type":""},"tags":[],"trusted":true,"execution":{"iopub.status.busy":"2025-08-14T15:59:58.869868Z","iopub.execute_input":"2025-08-14T15:59:58.870143Z","iopub.status.idle":"2025-08-14T16:00:15.502470Z","shell.execute_reply.started":"2025-08-14T15:59:58.870123Z","shell.execute_reply":"2025-08-14T16:00:15.500813Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## Creating a searchable index\n\nTo be able to search by semantics rather than just text, generate embeddings and then create an index to efficiently search these.\n\nSee also, this example: https://github.com/googleapis/python-bigquery-dataframes/blob/main/notebooks/generative_ai/bq_dataframes_llm_vector_search.ipynb","metadata":{"@deathbeds/jupyterlab-fonts":{"styles":{"":{"body[data-jp-deck-mode='presenting'] &":{"zoom":"181%"}}}},"slideshow":{"slide_type":"slide"}}},{"cell_type":"code","source":"from bigframes.ml.llm import TextEmbeddingGenerator\n\ntext_model = TextEmbeddingGenerator(model_name=\"text-multilingual-embedding-002\")","metadata":{"@deathbeds/jupyterlab-fonts":{"styles":{"":{"body[data-jp-deck-mode='presenting'] &":{"zoom":"163%"}}}},"trusted":true,"execution":{"iopub.status.busy":"2025-08-14T16:00:15.505775Z","iopub.execute_input":"2025-08-14T16:00:15.506380Z","iopub.status.idle":"2025-08-14T16:00:25.134987Z","shell.execute_reply.started":"2025-08-14T16:00:15.506337Z","shell.execute_reply":"2025-08-14T16:00:25.134124Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df_to_index = (\n    flattened\n    .assign(content=flattened[\"Transcription\"].struct.field(\"content\"))\n    [flattened[\"Transcription\"].struct.field(\"content\") != \"\"]\n)\nembedding = text_model.predict(df_to_index)\nembedding.peek(1)","metadata":{"@deathbeds/jupyterlab-fonts":{"styles":{"":{"body[data-jp-deck-mode='presenting'] &":{"zoom":"125%"}}}},"trusted":true,"execution":{"iopub.status.busy":"2025-08-14T16:00:25.135744Z","iopub.execute_input":"2025-08-14T16:00:25.136017Z","iopub.status.idle":"2025-08-14T16:00:34.860878Z","shell.execute_reply.started":"2025-08-14T16:00:25.135997Z","shell.execute_reply":"2025-08-14T16:00:34.859925Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Check the status column to look for errors.\nprint(f\"Successful rows: {(embedding['ml_generate_embedding_status'] == '').sum()}\")\nprint(f\"Failed rows: {(embedding['ml_generate_embedding_status'] != '').sum()}\")\nembedding.shape","metadata":{"@deathbeds/jupyterlab-fonts":{"styles":{"":{"body[data-jp-deck-mode='presenting'] &":{"zoom":"178%"}}}},"editable":true,"slideshow":{"slide_type":"slide"},"tags":[],"trusted":true,"execution":{"iopub.status.busy":"2025-08-14T16:01:20.816523Z","iopub.execute_input":"2025-08-14T16:01:20.816923Z","iopub.status.idle":"2025-08-14T16:01:22.480554Z","shell.execute_reply.started":"2025-08-14T16:01:20.816894Z","shell.execute_reply":"2025-08-14T16:01:22.479604Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"We're now ready to save this to a table.","metadata":{"@deathbeds/jupyterlab-fonts":{"styles":{"":{"body[data-jp-deck-mode='presenting'] &":{"zoom":"224%"}}}}}},{"cell_type":"code","source":"embedding_table_id = f\"{bpd.options.bigquery.project}.kaggle.national_jukebox\"\nembedding.to_gbq(embedding_table_id, if_exists=\"replace\")","metadata":{"@deathbeds/jupyterlab-fonts":{"styles":{"":{"body[data-jp-deck-mode='presenting'] &":{"zoom":"172%"}}}},"trusted":true,"execution":{"iopub.status.busy":"2025-08-14T16:03:43.611265Z","iopub.execute_input":"2025-08-14T16:03:43.611592Z","iopub.status.idle":"2025-08-14T16:03:47.459025Z","shell.execute_reply.started":"2025-08-14T16:03:43.611568Z","shell.execute_reply":"2025-08-14T16:03:47.458079Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## Searching the database\n\nTo search by semantics, we:\n\n1. Turn our search string into an embedding using the same model as our index.\n2. Find the closest matches to the search string.","metadata":{"@deathbeds/jupyterlab-fonts":{"styles":{"":{"body[data-jp-deck-mode='presenting'] &":{"zoom":"183%"}}}},"slideshow":{"slide_type":"slide"}}},{"cell_type":"code","source":"import bigframes.pandas as bpd\n\ndf_written = bpd.read_gbq(embedding_table_id)\ndf_written.peek(1)","metadata":{"@deathbeds/jupyterlab-fonts":{"styles":{"":{"body[data-jp-deck-mode='presenting'] &":{"zoom":"92%"}}}},"slideshow":{"slide_type":"skip"},"trusted":true,"execution":{"iopub.status.busy":"2025-08-14T16:03:52.673629Z","iopub.execute_input":"2025-08-14T16:03:52.674429Z","iopub.status.idle":"2025-08-14T16:03:59.962635Z","shell.execute_reply.started":"2025-08-14T16:03:52.674399Z","shell.execute_reply":"2025-08-14T16:03:59.961482Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from bigframes.ml.llm import TextEmbeddingGenerator\n\nsearch_string = \"walking home\"\n\ntext_model = TextEmbeddingGenerator(model_name=\"text-multilingual-embedding-002\")\nsearch_df = bpd.DataFrame([search_string], columns=['search_string'])\nsearch_embedding = text_model.predict(search_df)\nsearch_embedding","metadata":{"@deathbeds/jupyterlab-fonts":{"styles":{"":{"body[data-jp-deck-mode='presenting'] &":{"zoom":"127%"}}}},"trusted":true,"execution":{"iopub.status.busy":"2025-08-14T16:03:59.964268Z","iopub.execute_input":"2025-08-14T16:03:59.964634Z","iopub.status.idle":"2025-08-14T16:04:55.051531Z","shell.execute_reply.started":"2025-08-14T16:03:59.964598Z","shell.execute_reply":"2025-08-14T16:04:55.050393Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import bigframes.bigquery as bbq\n\nvector_search_results = bbq.vector_search(\n    base_table=f\"swast-scratch.scipy2025.national_jukebox\",\n    column_to_search=\"ml_generate_embedding_result\",\n    query=search_embedding,\n    distance_type=\"COSINE\",\n    query_column_to_search=\"ml_generate_embedding_result\",\n    top_k=5,\n)","metadata":{"@deathbeds/jupyterlab-fonts":{"styles":{"":{"body[data-jp-deck-mode='presenting'] &":{"zoom":"175%"}}}},"editable":true,"slideshow":{"slide_type":"slide"},"tags":[],"trusted":true,"execution":{"iopub.status.busy":"2025-08-14T16:05:46.473056Z","iopub.execute_input":"2025-08-14T16:05:46.473357Z","iopub.status.idle":"2025-08-14T16:05:50.564470Z","shell.execute_reply.started":"2025-08-14T16:05:46.473336Z","shell.execute_reply":"2025-08-14T16:05:50.563277Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"vector_search_results.dtypes","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-08-14T16:05:50.566422Z","iopub.execute_input":"2025-08-14T16:05:50.566930Z","iopub.status.idle":"2025-08-14T16:05:50.576293Z","shell.execute_reply.started":"2025-08-14T16:05:50.566893Z","shell.execute_reply":"2025-08-14T16:05:50.575186Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"results = vector_search_results[[\"Title\", \"Summary\", \"Names\", \"GCS URI\", \"Transcription\", \"distance\"]].sort_values(\"distance\").to_pandas()\nresults","metadata":{"@deathbeds/jupyterlab-fonts":{"styles":{"":{"body[data-jp-deck-mode='presenting'] &":{"zoom":"158%"}}}},"slideshow":{"slide_type":"slide"},"trusted":true,"execution":{"iopub.status.busy":"2025-08-14T16:05:54.786649Z","iopub.execute_input":"2025-08-14T16:05:54.787080Z","iopub.status.idle":"2025-08-14T16:05:55.581285Z","shell.execute_reply.started":"2025-08-14T16:05:54.787054Z","shell.execute_reply":"2025-08-14T16:05:55.580012Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(results[\"Transcription\"].struct.field(\"content\").iloc[0])","metadata":{"@deathbeds/jupyterlab-fonts":{"styles":{"":{"body[data-jp-deck-mode='presenting'] &":{"zoom":"138%"}}}},"trusted":true,"execution":{"iopub.status.busy":"2025-08-14T16:05:56.142038Z","iopub.execute_input":"2025-08-14T16:05:56.142373Z","iopub.status.idle":"2025-08-14T16:05:56.149020Z","shell.execute_reply.started":"2025-08-14T16:05:56.142350Z","shell.execute_reply":"2025-08-14T16:05:56.147966Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import gcsfs\nimport IPython.display\n\nfs = gcsfs.GCSFileSystem(project='bigframes-dev')\nwith fs.open(results[\"GCS URI\"].iloc[0]) as song_file:\n    song_bytes = song_file.read()\n\nIPython.display.Audio(song_bytes)","metadata":{"editable":true,"scrolled":true,"slideshow":{"slide_type":""},"tags":[],"trusted":true,"execution":{"iopub.status.busy":"2025-08-14T16:06:04.542537Z","iopub.execute_input":"2025-08-14T16:06:04.542878Z","iopub.status.idle":"2025-08-14T16:06:04.843052Z","shell.execute_reply.started":"2025-08-14T16:06:04.542854Z","shell.execute_reply":"2025-08-14T16:06:04.841220Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}


may be unclear to the user why df.cache() is needed here.

Reply via ReviewNB

Good catch! That's a leftover from a bug where we didn't implement __radd__. I think I can remove it now.

Removed. PTAL.

docs: add examples of running bigframes in kaggle

e5e6eae

product-auto-label bot added the size: xl Pull request size is extra large. label Aug 18, 2025

product-auto-label bot added the api: bigquery Issues related to the googleapis/python-bigquery-dataframes API. label Aug 18, 2025

add vector search and multimodal examples

d248b0f

tswast marked this pull request as ready for review August 18, 2025 21:26

Merge branch 'main' into kaggle

fdd2ad5

tswast requested review from a team as code owners August 18, 2025 21:26

tswast requested a review from TrevorBergeron August 18, 2025 21:26

blunderbuss-gcf bot assigned ivansmf Aug 18, 2025

GarrettWu reviewed Aug 18, 2025

View reviewed changes

tswast added 2 commits August 19, 2025 18:31

remove unnecessary cache()

b4d7d23

Merge remote-tracking branch 'origin/kaggle' into kaggle

28cabac

tswast requested a review from GarrettWu August 19, 2025 18:32

GarrettWu approved these changes Aug 19, 2025

View reviewed changes

tswast merged commit 7d89d76 into main Aug 19, 2025
23 of 25 checks passed

tswast deleted the kaggle branch August 19, 2025 23:51

release-please bot mentioned this pull request Aug 19, 2025

chore(main): release 2.16.0 #1983

Merged

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

docs: add examples of running bigframes in kaggle #2002

docs: add examples of running bigframes in kaggle #2002

tswast commented Aug 18, 2025

Uh oh!

review-notebook-app bot commented Aug 18, 2025

Uh oh!

GarrettWu Aug 18, 2025 •

edited

Loading

Uh oh!

tswast Aug 19, 2025

Uh oh!

tswast Aug 19, 2025

Uh oh!

GarrettWu Aug 18, 2025 •

edited

Loading

Uh oh!

tswast Aug 19, 2025

Uh oh!

tswast Aug 19, 2025

Uh oh!

Uh oh!

Uh oh!

docs: add examples of running bigframes in kaggle #2002

docs: add examples of running bigframes in kaggle #2002

Conversation

tswast commented Aug 18, 2025

Uh oh!

review-notebook-app bot commented Aug 18, 2025

Uh oh!

GarrettWu Aug 18, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

tswast Aug 19, 2025

Choose a reason for hiding this comment

Uh oh!

tswast Aug 19, 2025

Choose a reason for hiding this comment

Uh oh!

GarrettWu Aug 18, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

tswast Aug 19, 2025

Choose a reason for hiding this comment

Uh oh!

tswast Aug 19, 2025

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

GarrettWu Aug 18, 2025 •

edited

Loading

GarrettWu Aug 18, 2025 •

edited

Loading