first version of a notebook

Signed-off-by: SHAHROKH DAIJAVAD <shahrokh@us.ibm.com>

transforms/language/doc_quality/doc_quality.ipynb

@@ -0,0 +1,169 @@
+{
+ "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 \n",
+    "pip install jupyterlab\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "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": "407fd4e4-265d-4ec7-bbc9-b43158f5f1f3",
+   "metadata": {
+    "jp-MarkdownHeadingCollapsed": true
+   },
+   "source": [
+    "##### **** Configure the transform parameters. The set of dictionary keys holding DocQualityTransform configuration for values are as follows: \n",
+    "* text_lang - specifies language used in the text content. By default, \"en\" is used.\n",
+    "* doc_content_column - specifies column name that contains document text. By default, \"contents\" is used.\n",
+    "* bad_word_filepath - specifies a path to bad word file: local folder (file or directory) that points to bad word file. You don't have to set this parameter if you don't need to set bad words.\n",
+    "#####"
+   ]
+  },
+  {
+   "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.runtime.pure_python import PythonTransformLauncher\n",
+    "from data_processing.utils import ParamsUtils\n",
+    "from doc_quality_transform import (bad_word_filepath_cli_param, doc_content_column_cli_param, text_lang_cli_param,)\n",
+    "from doc_quality_transform_python import DocQualityPythonTransformConfiguration"
+   ]
+  },
+  {
+   "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": [
+    "\n",
+    "# create parameters\n",
+    "input_folder = os.path.join(\"python\", \"test-data\", \"input\")\n",
+    "output_folder = os.path.join( \"python\", \"output\")\n",
+    "local_conf = {\n",
+    "    \"input_folder\": input_folder,\n",
+    "    \"output_folder\": output_folder,\n",
+    "}\n",
+    "params = {\n",
+    "    # Data access. Only required parameters are specified\n",
+    "    \"data_local_config\": ParamsUtils.convert_to_ast(local_conf),\n",
+    "    # execution info\n",
+    "    \"runtime_pipeline_id\": \"pipeline_id\",\n",
+    "    \"runtime_job_id\": \"job_id\",\n",
+    "    \"runtime_code_location\": ParamsUtils.convert_to_ast(code_location),\n",
+    "    # doc_quality params\n",
+    "    text_lang_cli_param: \"en\",\n",
+    "    doc_content_column_cli_param: \"contents\",\n",
+    "    bad_word_filepath_cli_param: os.path.join(\"python\", \"ldnoobw\", \"en\"),\n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7949f66a-d207-45ef-9ad7-ad9406f8d42a",
+   "metadata": {},
+   "source": [
+    "##### ***** Use python runtime to invoke the transform"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0775e400-7469-49a6-8998-bd4772931459",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%%capture\n",
+    "sys.argv = ParamsUtils.dict_to_req(d=params)\n",
+    "launcher = PythonTransformLauncher(runtime_config=DocQualityPythonTransformConfiguration())\n",
+    "launcher.launch()"
+   ]
+  },
+  {
+   "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": "3.10.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}