Merge pull request #16 from massi-ang/fix_data_notebooks

Fix to data notebooks
aws-samples · Nov 8, 2024 · bfe1daf · bfe1daf
2 parents 1d495af + cd112d1
commit bfe1daf
Show file tree

Hide file tree

Showing 5 changed files with 555 additions and 580 deletions.
diff --git a/data_pipelines/01-validate-sagemaker-jobs-connection-to-postgreSQL.ipynb b/data_pipelines/01-validate-sagemaker-jobs-connection-to-postgreSQL.ipynb
@@ -84,7 +84,8 @@
     "db_secret_arn = db_secret_arn[\"Parameter\"][\"Value\"]\n",
     "\n",
     "subnet_ids = ssm.get_parameter(Name=subnet_ids_parameter)\n",
-    "private_subnets_with_egress_ids = json.loads(subnet_ids[\"Parameter\"][\"Value\"])"
+    "private_subnets_with_egress_ids = json.loads(subnet_ids[\"Parameter\"][\"Value\"])\n",
+    "script_processor_container_uri = ssm.get_parameter(Name=script_processor_container_parameter)[\"Parameter\"][\"Value\"]"
    ]
   },
   {
@@ -175,7 +176,7 @@
    "id": "dcb8bed1-bef3-4fd7-84b7-29dd4b418362",
    "metadata": {},
    "source": [
-    "## Attempt the same in a SageMaker processing job with VPC network config"
+    "## Attempt the same in a SageMaker processing job with VPC network config"
    ]
   },
   {

diff --git a/data_pipelines/02-download-raw-pdf-documents.ipynb b/data_pipelines/02-download-raw-pdf-documents.ipynb
@@ -163,15 +163,15 @@
    },
    "outputs": [],
    "source": [
-    "ls {raw_base_directory}/Amazon"
+    "!ls {raw_base_directory}/Amazon"
    ]
   },
   {
    "cell_type": "markdown",
    "id": "87a9f7bd-81e0-46b2-aa37-abddd1b0f1ec",
    "metadata": {},
    "source": [
-    "## Keep relevant pages\n",
+    "## Keep relevant pages\n",
     "\n",
     "Although you can run the full PDF documents through the solution, to optimize the extraction costs, we suggest that you select the relevant pages from each pdf documents."
    ]
@@ -354,7 +354,7 @@
    },
    "outputs": [],
    "source": [
-    "ls {prepared_base_directory}"
+    "!ls {prepared_base_directory}"
    ]
   },
   {
@@ -366,7 +366,7 @@
    },
    "outputs": [],
    "source": [
-    "cat {prepared_base_directory}/metadata.json | python -m json.tool"
+    "!cat {prepared_base_directory}/metadata.json | python -m json.tool"
    ]
   }
  ],