Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

DM-44956: Update for newer stack and OR4 #24

Merged
merged 5 commits into from
Jun 22, 2024
Merged

DM-44956: Update for newer stack and OR4 #24

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
341e4b4
Rename day_obs so to avoid name conflict with dimension
hsinfang Jun 4, 2024
70c9188
Use day_obs natively in the where clause
hsinfang Jun 4, 2024
19405ea
Use group instead of group_name
hsinfang Jun 4, 2024
4c53a4e
Switch to the Embargo Rack bucket for ComCamSim data
hsinfang Jun 21, 2024
2a07777
Update log record search phrase for newer version of prompt-service
hsinfang Jun 21, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
29 changes: 18 additions & 11 deletions prompt-processing/groups.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -154,7 +154,10 @@
"source": [
"from lsst.daf.butler import Butler\n",
"\n",
"butler = Butler(\"/repo/embargo\", writeable=False)"
"if instrument == \"LATISS\":\n",
" butler = Butler(\"/repo/embargo\", writeable=False)\n",
"else:\n",
" butler = Butler(\"embargo_or4\", writeable=False)"
]
},
{
Expand All @@ -167,7 +170,7 @@
"results = butler.registry.queryDimensionRecords(\n",
" \"exposure\",\n",
" where=\"exposure.science_program IN (survey) \"\n",
" \"and instrument=instrument_name and exposure.day_obs=dayobs \",\n",
" \"and instrument=instrument_name and day_obs=dayobs \",\n",
" bind={\"dayobs\": dayobs, \"instrument_name\": instrument, \"survey\": survey},\n",
")\n",
"logger.info(f\"Found {results.count()} raw exposure records in {butler} for {dayobs}\")\n",
Expand All @@ -179,7 +182,7 @@
"if embargo_records:\n",
" df_butler = pandas.DataFrame.from_records(\n",
" [embargo_records[num].toDict() for num in embargo_records]\n",
" ).set_index(\"group_name\")\n",
" ).set_index(\"group\")\n",
"else:\n",
" df_butler = None\n",
" logger.warning(\"No raw records found in /repo/embargo. Notebook will fail.\")"
Expand Down Expand Up @@ -232,7 +235,7 @@
" df_butler.reset_index(),\n",
" how=\"outer\",\n",
" left_on=\"groupId\",\n",
" right_on=\"group_name\",\n",
" right_on=\"group\",\n",
" suffixes=(\"_efd\", \"_butler\"),\n",
" validate=\"one_to_one\",\n",
").set_index(\"groupId\")\n",
Expand Down Expand Up @@ -386,12 +389,12 @@
" results = butler.registry.queryDimensionRecords(\n",
" \"exposure\",\n",
" where=\"instrument=instrument_name and exposure.observation_type='science' and\"\n",
" \" exposure.day_obs=dayobs\",\n",
" \" day_obs=dayobs\",\n",
" bind={\"dayobs\": dayobs, \"instrument_name\": instrument},\n",
" )\n",
"\n",
" df = pandas.DataFrame(\n",
" [(_.group_name, _.id) for _ in results], columns=[\"groupId\", \"expId\"]\n",
" [(_.group, _.id) for _ in results], columns=[\"groupId\", \"expId\"]\n",
" ).set_index(\"groupId\")\n",
"\n",
" return df"
Expand All @@ -412,7 +415,11 @@
" -------\n",
" df : `pandas.DataFrame`\n",
" \"\"\"\n",
" s3_endpoint = \"https://s3dfrgw.slac.stanford.edu\"\n",
" if instrument == \"LATISS\":\n",
" s3_endpoint = \"https://s3dfrgw.slac.stanford.edu\"\n",
" else:\n",
" # embargo_or4\n",
" s3_endpoint = \"https://sdfembs3.sdf.slac.stanford.edu\"\n",
" s3client = boto3.client(\"s3\", endpoint_url=s3_endpoint)\n",
" refs = butler.registry.queryDatasets(\n",
" datasetType=datasetType,\n",
Expand All @@ -432,7 +439,7 @@
" dimension = \"exposure\"\n",
" fits_uri = butler.getURI(ref)\n",
" time_written = s3client.head_object(\n",
" Bucket=fits_uri.netloc,\n",
" Bucket=fits_uri.netloc.split(\"@\")[-1],\n",
" Key=fits_uri.relativeToPathRoot,\n",
" )[\"LastModified\"]\n",
" timestamps.append((ref.dataId[dimension], ref.dataId[\"detector\"], time_written))\n",
Expand Down Expand Up @@ -471,7 +478,7 @@
" butler,\n",
" \"raw\",\n",
" collections=[f\"{instrument}/raw/all\"],\n",
" where=f\"exposure.science_program IN ('{survey}') and instrument='{instrument}' and exposure.day_obs={dayobs}\",\n",
" where=f\"exposure.science_program IN ('{survey}') and instrument='{instrument}' and day_obs={dayobs}\",\n",
")"
]
},
Expand Down Expand Up @@ -671,7 +678,7 @@
" \"prepBtlr\": \"Preparing Butler for visit\",\n",
" \"waitSnap\": \"Waiting for snaps\",\n",
" \"runPipe1\": \"Running pipeline\",\n",
" \"pipeSucc\": \"Pipeline successfully run\",\n",
" \"pipeSucc\": \"Main pipeline successfully run\",\n",
" # There can be more than 1 of this log line per exposure when retry...\n",
" \"outputSa\": \"Pipeline products saved to collection\",\n",
" \"timeout1\": \"Timed out waiting for image after receiving exposures \",\n",
Expand Down Expand Up @@ -907,7 +914,7 @@
")\n",
"\n",
"# typically a small fraction of seconds before sndStamp\n",
"df_md2[\"ts_group_utc\"] = df_md2[\"group_name\"].apply(\n",
"df_md2[\"ts_group_utc\"] = df_md2[\"group\"].apply(\n",
" lambda _: pandas.Timestamp(Time(_, scale=\"tai\").utc.datetime, tz=\"UTC\")\n",
")\n",
"\n",
Expand Down
8 changes: 4 additions & 4 deletions prompt-processing/history.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -77,8 +77,8 @@
" datasets=\"raw\",\n",
" collections=f\"{instrument}/raw/all\",\n",
" where=\"exposure.science_program=survey and \"\n",
" \"instrument=instrument_name and exposure.day_obs=day_obs \",\n",
" bind={\"day_obs\": dayobs, \"instrument_name\": instrument, \"survey\": survey},\n",
" \"instrument=instrument_name and day_obs=dayobs \",\n",
" bind={\"dayobs\": dayobs, \"instrument_name\": instrument, \"survey\": survey},\n",
" )\n",
"\n",
" output_chain = f\"{instrument}/prompt/output-{date}\"\n",
Expand All @@ -88,8 +88,8 @@
" refs = butler.registry.queryDatasets(\n",
" datasetType=\"isr_log\",\n",
" collections=output_chain,\n",
" where=\"instrument=instrument_name and exposure.day_obs=day_obs\",\n",
" bind={\"day_obs\": dayobs, \"instrument_name\": instrument},\n",
" where=\"instrument=instrument_name and day_obs=dayobs\",\n",
" bind={\"dayobs\": dayobs, \"instrument_name\": instrument},\n",
" )\n",
" except MissingCollectionError:\n",
" refs = None\n",
Expand Down
4 changes: 2 additions & 2 deletions prompt-processing/timing.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -267,7 +267,7 @@
"# butler repo sanity check\n",
"count = butler.registry.queryDimensionRecords(\n",
" \"exposure\",\n",
" where=f\"exposure.science_program IN ('{survey}') and instrument='{instrument}' and exposure.day_obs={dayobs}\",\n",
" where=f\"exposure.science_program IN ('{survey}') and instrument='{instrument}' and day_obs={dayobs}\",\n",
").count()\n",
"Markdown(\"%i exposure in butler registry records\" % (count,))"
]
Expand All @@ -285,7 +285,7 @@
" butler,\n",
" \"raw\",\n",
" collections=[f\"{instrument}/raw/all\"],\n",
" where=f\"exposure.science_program IN ('{survey}') and instrument='{instrument}' and exposure.day_obs={dayobs}\",\n",
" where=f\"exposure.science_program IN ('{survey}') and instrument='{instrument}' and day_obs={dayobs}\",\n",
")"
]
},
Expand Down
Loading