-
Notifications
You must be signed in to change notification settings - Fork 173
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Signed-off-by: Constantin M Adam <[email protected]>
- Loading branch information
Showing
1 changed file
with
152 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,152 @@ | ||
{ | ||
"cells": [ | ||
{ | ||
"cell_type": "markdown", | ||
"id": "afd55886-5f5b-4794-838e-ef8179fb0394", | ||
"metadata": {}, | ||
"source": [ | ||
"##### **** These pip installs need to be adapted to use the appropriate release level. Alternatively, The venv running the jupyter lab could be pre-configured with a requirement file that includes the right release. Example for transform developers working from git clone:\n", | ||
"```\n", | ||
"make venv\n", | ||
"source venv/bin/activate && pip install jupyterlab\n", | ||
"```" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"id": "4c45c3c6-e4d7-4e61-8de6-32d61f2ce695", | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"%%capture\n", | ||
"## This is here as a reference only\n", | ||
"# Users and application developers must use the right tag for the latest from pypi\n", | ||
"#!pip install data-prep-toolkit\n", | ||
"#!pip install data-prep-toolkit-transforms\n", | ||
"#!pip install data-prep-connector" | ||
] | ||
}, | ||
{ | ||
"cell_type": "markdown", | ||
"id": "ebf1f782-0e61-485c-8670-81066beb734c", | ||
"metadata": {}, | ||
"source": [ | ||
"##### ***** Import required Classes and modules" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"id": "c2a12abc-9460-4e45-8961-873b48a9ab19", | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"import ast\n", | ||
"import os\n", | ||
"import sys\n", | ||
"\n", | ||
"from data_processing.utils import ParamsUtils\n", | ||
"from fdedup_transform_python import parse_args\n", | ||
"from fdedup_transform_ray import RayServiceOrchestrator" | ||
] | ||
}, | ||
{ | ||
"cell_type": "markdown", | ||
"id": "7234563c-2924-4150-8a31-4aec98c1bf33", | ||
"metadata": {}, | ||
"source": [ | ||
"##### ***** Setup runtime parameters for this transform" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"id": "e90a853e-412f-45d7-af3d-959e755aeebb", | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"# create parameters\n", | ||
"input_folder = os.path.join(\"ray\", \"test-data\", \"input\")\n", | ||
"output_folder = os.path.join( \"ray\", \"output\")\n", | ||
"params = {\n", | ||
" # transform configuration parameters\n", | ||
" \"input_folder\": input_folder,\n", | ||
" \"output_folder\": output_folder,\n", | ||
" \"contents_column\": \"contents\",\n", | ||
" \"document_id_column\": \"int_id_column\",\n", | ||
" \"num_permutations\": 112,\n", | ||
" \"num_bands\": 14,\n", | ||
" \"num_minhashes_per_band\": 8,\n", | ||
" \"num_segments\": 1,\n", | ||
" \"operation_mode\": \"annotate\",\n", | ||
" # ray configuration parameters\n", | ||
" \"run_locally\": True,\n", | ||
"}\n" | ||
] | ||
}, | ||
{ | ||
"cell_type": "markdown", | ||
"id": "7949f66a-d207-45ef-9ad7-ad9406f8d42a", | ||
"metadata": {}, | ||
"source": [ | ||
"##### ***** Use ray runtime to invoke the transform" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"id": "0775e400-7469-49a6-8998-bd4772931459", | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"%%capture\n", | ||
"args = parse_args()\n", | ||
"# Initialize the orchestrator\n", | ||
"orchestrator = RayServiceOrchestrator(global_params=args)\n", | ||
"# Launch ray fuzzy dedup execution\n", | ||
"orchestrator.orchestrate()\n" | ||
] | ||
}, | ||
{ | ||
"cell_type": "markdown", | ||
"id": "c3df5adf-4717-4a03-864d-9151cd3f134b", | ||
"metadata": {}, | ||
"source": [ | ||
"##### **** The specified folder will include the transformed parquet files." | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"id": "7276fe84-6512-4605-ab65-747351e13a7c", | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"import glob\n", | ||
"glob.glob(\"python/output/*\")" | ||
] | ||
} | ||
], | ||
"metadata": { | ||
"kernelspec": { | ||
"display_name": "Python 3 (ipykernel)", | ||
"language": "python", | ||
"name": "python3" | ||
}, | ||
"language_info": { | ||
"codemirror_mode": { | ||
"name": "ipython", | ||
"version": 3 | ||
}, | ||
"file_extension": ".py", | ||
"mimetype": "text/x-python", | ||
"name": "python", | ||
"nbconvert_exporter": "python", | ||
"pygments_lexer": "ipython3", | ||
"version": "3.9.19" | ||
} | ||
}, | ||
"nbformat": 4, | ||
"nbformat_minor": 5 | ||
} |