From ac9b95471a8f0ca1f02e8e062e33b544cc17d39c Mon Sep 17 00:00:00 2001
From: Maroun Touma <touma@us.ibm.com>
Date: Wed, 11 Dec 2024 07:16:23 +0100
Subject: [PATCH] added hap extra to pip install

Signed-off-by: Maroun Touma <touma@us.ibm.com>
---
 transforms/universal/hap/hap_python.ipynb | 52 ++++++++---------------
 1 file changed, 18 insertions(+), 34 deletions(-)

diff --git a/transforms/universal/hap/hap_python.ipynb b/transforms/universal/hap/hap_python.ipynb
index 4fb1ad4c3d..1b7b954175 100644
--- a/transforms/universal/hap/hap_python.ipynb
+++ b/transforms/universal/hap/hap_python.ipynb
@@ -15,7 +15,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "id": "4a84e965-feeb-424d-9263-9f127e53a1aa",
    "metadata": {},
    "outputs": [],
@@ -24,7 +24,7 @@
     "## 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==0.2.2.dev3"
+    "%pip install data-prep-toolkit-transforms[hap]"
    ]
   },
   {
@@ -48,22 +48,6 @@
     "***** Import required classes and modules"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "38aebf49-9460-4951-bb04-7045dec28690",
-   "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 dpk_hap.transform_python import HAPPythonTransformConfiguration"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": 1,
@@ -93,7 +77,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 2,
    "id": "6a8ec5e4-1f52-4c61-9c9e-4618f9034b80",
    "metadata": {},
    "outputs": [
@@ -101,14 +85,14 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "12:08:21 INFO - hap params are {'model_name_or_path': 'ibm-granite/granite-guardian-hap-38m', 'annotation_column': 'hap_score', 'doc_text_column': 'contents', 'inference_engine': 'CPU', 'max_length': 512, 'batch_size': 128} \n",
-      "12:08:21 INFO - pipeline id pipeline_id\n",
-      "12:08:21 INFO - code location None\n",
-      "12:08:21 INFO - data factory data_ is using local data access: input_folder - test-data/input output_folder - output\n",
-      "12:08:21 INFO - data factory data_ max_files -1, n_sample -1\n",
-      "12:08:21 INFO - data factory data_ Not using data sets, checkpointing False, max files -1, random samples -1, files to use ['.parquet'], files to checkpoint ['.parquet']\n",
-      "12:08:21 INFO - orchestrator hap started at 2024-12-10 12:08:21\n",
-      "12:08:21 INFO - Number of files is 1, source profile {'max_file_size': 0.10423946380615234, 'min_file_size': 0.10423946380615234, 'total_file_size': 0.10423946380615234}\n"
+      "07:12:05 INFO - hap params are {'model_name_or_path': 'ibm-granite/granite-guardian-hap-38m', 'annotation_column': 'hap_score', 'doc_text_column': 'contents', 'inference_engine': 'CPU', 'max_length': 512, 'batch_size': 128} \n",
+      "07:12:05 INFO - pipeline id pipeline_id\n",
+      "07:12:05 INFO - code location None\n",
+      "07:12:05 INFO - data factory data_ is using local data access: input_folder - test-data/input output_folder - output\n",
+      "07:12:05 INFO - data factory data_ max_files -1, n_sample -1\n",
+      "07:12:05 INFO - data factory data_ Not using data sets, checkpointing False, max files -1, random samples -1, files to use ['.parquet'], files to checkpoint ['.parquet']\n",
+      "07:12:05 INFO - orchestrator hap started at 2024-12-11 07:12:05\n",
+      "07:12:05 INFO - Number of files is 1, source profile {'max_file_size': 0.10423946380615234, 'min_file_size': 0.10423946380615234, 'total_file_size': 0.10423946380615234}\n"
      ]
     },
     {
@@ -133,10 +117,10 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "12:08:55 INFO - Completed 1 files (100.0%) in 0.467 min\n",
-      "12:08:55 INFO - Done processing 1 files, waiting for flush() completion.\n",
-      "12:08:55 INFO - done flushing in 0.0 sec\n",
-      "12:08:55 INFO - Completed execution in 0.568 min, execution result 0\n"
+      "07:12:38 INFO - Completed 1 files (100.0%) in 0.458 min\n",
+      "07:12:38 INFO - Done processing 1 files, waiting for flush() completion.\n",
+      "07:12:38 INFO - done flushing in 0.0 sec\n",
+      "07:12:38 INFO - Completed execution in 0.543 min, execution result 0\n"
      ]
     },
     {
@@ -202,7 +186,7 @@
        "0"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 2,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -230,7 +214,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 3,
    "id": "f21d5d9b-562d-4530-8cea-2de5b63eb1dc",
    "metadata": {},
    "outputs": [
@@ -240,7 +224,7 @@
        "['output/metadata.json', 'output/test1.parquet']"
       ]
      },
-     "execution_count": 6,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }