Skip to content

Commit

Permalink
remove last cell
Browse files Browse the repository at this point in the history
  • Loading branch information
mrocklin committed Apr 23, 2024
1 parent 2fc20ee commit c649857
Showing 1 changed file with 0 additions and 35 deletions.
35 changes: 0 additions & 35 deletions spark.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -100,41 +100,6 @@
"source": [
"df.count()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "829de2bc-ed09-4e10-b06f-268aa79ead59",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"import dask\n",
"import dask.dataframe as dd\n",
"dask.config.set({\"dataframe.convert-string\": True}) # use PyArrow strings by default\n",
"\n",
"while True:\n",
" client.restart()\n",
"\n",
" df = dd.read_parquet(\n",
" \"s3://coiled-datasets/uber-lyft-tlc/\",\n",
" storage_options={\"anon\": True},\n",
" ).persist()\n",
"\n",
" for _ in range(10):\n",
" df[\"tipped\"] = df.tips != 0\n",
"\n",
" df.groupby(\"hvfhs_license_num\").tipped.mean().compute()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f4b6b9f9-7ef3-4ca0-b769-0dd7e4ce6b0b",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
Expand Down

0 comments on commit c649857

Please sign in to comment.