Skip to content

demo notebook fixes for EMR #1093

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

Closed
oavdeev wants to merge 1 commit into from
Closed

demo notebook fixes for EMR #1093

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
75 changes: 21 additions & 54 deletions examples/minimal/Feast 101.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -59,47 +59,6 @@
"### Configuration"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import os"
]
},
{
"cell_type": "code",
"execution_count": 54,
"metadata": {},
"outputs": [],
"source": [
"# os.environ['FEAST_SPARK_LAUNCHER'] = 'standalone'\n",
"# os.environ['FEAST_SPARK_STANDALONE_MASTER'] = 'local[*]'\n",
"# os.environ['FEAST_SPARK_HOME'] = os.path.dirname(pyspark.__file__)\n",
"# os.environ['FEAST_SPARK_EXTRA_OPTIONS'] = '--jars https://storage.googleapis.com/hadoop-lib/gcs/gcs-connector-hadoop2-latest.jar'\\\n",
"# ' --conf spark.hadoop.fs.gs.impl=com.google.cloud.hadoop.fs.gcs.GoogleHadoopFileSystem'"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"os.environ['FEAST_SPARK_STAGING_LOCATION'] = \"gs://feast-templocation-kf-feast/demo/staging/\"\n",
"os.environ['FEAST_HISTORICAL_FEATURE_OUTPUT_LOCATION'] = \"gs://feast-templocation-kf-feast/demo/output\""
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"# os.environ['GOOGLE_APPLICATION_CREDENTIALS'] = \"/path/to/key\""
]
},
{
"cell_type": "markdown",
"metadata": {},
Expand All @@ -126,13 +85,13 @@
"metadata": {},
"outputs": [],
"source": [
"CORE_HOST = os.getenv(\"DEMO_FEAST_CORE_SERVICE_HOST\", \"localhost\")\n",
"SERVING_HOST = os.getenv(\"DEMO_FEAST_ONLINE_SERVING_SERVICE_HOST\", \"localhost\")\n",
"REDIS_HOST = os.getenv('DEMO_REDIS_MASTER_SERVICE_HOST', 'localhost')\n",
"REDIS_HOST = os.getenv('DEMO_REDIS_MASTER_SERVICE_HOST', os.getenv('FEAST_REDIS_HOST'))\n",
"DEMO_DATA_LOCATION = os.getenv(\"DEMO_DATA_LOCATION\")\n",

@woop woop Oct 23, 2020

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Should we rename this from demo to something more generic? demo seems specific to our demos whereas this notebook is version controlled for use as a tutorial.

@khorshuheng khorshuheng Oct 23, 2020

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I have already moved the demo variable in #1086.

So perhaps we can #1086 merged first?

"# os.environ['GOOGLE_APPLICATION_CREDENTIALS'] = \"/path/to/key\"\n",
"\n",
"client = Client(\n",
" core_url=f\"{CORE_HOST}:6565\",\n",
" serving_url=f\"{SERVING_HOST}:6566\", \n",
" core_url=os.getenv('FEAST_CORE_URL', \"localhost:6565\"),\n",
" serving_url=os.getenv('FEAST_ONLINE_SERVING_URL', \"localhost:6566\"),\n",
" redis_host=REDIS_HOST\n",
")"
]
Expand Down Expand Up @@ -251,7 +210,7 @@
" event_timestamp_column=\"datetime\",\n",
" created_timestamp_column=\"created\",\n",
" file_format=ParquetFormat(),\n",
" file_url=\"gs://feast-demo-data-lake/driver_statistics\",\n",
" file_url=os.path.join(DEMO_DATA_LOCATION, \"driver_statistics\"),\n",
" date_partition_column=\"date\"\n",
" )\n",
")"
Expand All @@ -273,7 +232,7 @@
" event_timestamp_column=\"datetime\",\n",
" created_timestamp_column=\"created\",\n",
" file_format=ParquetFormat(),\n",
" file_url=\"gs://feast-demo-data-lake/driver_trips\",\n",
" file_url=os.path.join(DEMO_DATA_LOCATION, \"driver_trips\"),\n",
" date_partition_column=\"date\"\n",
" )\n",
")"
Expand Down Expand Up @@ -563,7 +522,7 @@
"metadata": {},
"outputs": [],
"source": [
"import gcsfs\n",
"\n",
"from pyarrow.parquet import ParquetDataset"
]
},
Expand All @@ -574,8 +533,16 @@
"outputs": [],
"source": [
"def read_remote_parquet(path):\n",
" fs = gcsfs.GCSFileSystem()\n",
" files = [\"gs://\" + path for path in gcsfs.GCSFileSystem().glob(path)]\n",
" prefix = path[:5]\n",
" if prefix == 'gs://':\n",
" import gcsfs\n",
" fs = gcsfs.GCSFileSystem()\n",
" elif prefix == 's3://':\n",
" import s3fs\n",
" fs = s3fs.S3FileSystem()\n",
" else:\n",
" raise Exception(f'Unsupported fs {prefix}')\n",
" files = [prefix + path for path in fs.glob(path)]\n",
" ds = ParquetDataset(files, filesystem=fs)\n",
" return ds.read().to_pandas()"
]
Expand Down Expand Up @@ -1138,7 +1105,7 @@
"metadata": {},
"outputs": [],
"source": [
"KAFKA_BROKER = \"kafka:9092\""
"KAFKA_BROKER = os.getenv(\"DEMO_KAFKA_BROKERS\", \"kafka:9092\")"

@woop woop Oct 23, 2020

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Would it make sense to hoist these variables to the top so that we know which env vars to set outside the notebook?

]
},
{
Expand Down Expand Up @@ -1235,7 +1202,7 @@
"metadata": {},
"outputs": [],
"source": [
"entities_sample = np.random.choice(entities, 10)\n",
"entities_sample = np.random.choice(entities, 10, replace=False)\n",
"entities_sample = [{\"driver_id\": e} for e in entities_sample]\n",
"entities_sample"
]
Expand Down Expand Up @@ -1298,4 +1265,4 @@
},
"nbformat": 4,
"nbformat_minor": 4
}
}