Fixed python packages install issue with pip, switched to conda install

aws-samples · Nov 27, 2021 · 39d809a · 39d809a
1 parent bf65b96
commit 39d809a
Showing 1 changed file with 74 additions and 5 deletions.
diff --git a/ml-models/pacs008/xgboost/pacs008_xgboost_local.ipynb b/ml-models/pacs008/xgboost/pacs008_xgboost_local.ipynb
@@ -37,8 +37,75 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "!pip install nltk\n",
-    "!pip install xgboost"
+    "#!pip install nltk\n",
+    "!conda install nltk -y\n",
+    "#!pip install xgboost\n",
+    "!conda install xgboost -y"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Download Labeled Dataset"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import boto3\n",
+    "import sagemaker\n",
+    "from sagemaker import get_execution_role\n",
+    "\n",
+    "sm_client = boto3.Session().client('sagemaker')\n",
+    "sm_session = sagemaker.Session()\n",
+    "region = boto3.session.Session().region_name\n",
+    "\n",
+    "role = get_execution_role()\n",
+    "print (\"Notebook is running with assumed role {}\".format (role))\n",
+    "print(\"Working with AWS services in the {} region\".format(region))\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Working directory for the notebook\n",
+    "WORKDIR = os.getcwd()\n",
+    "BASENAME = os.path.dirname(WORKDIR)\n",
+    "print(f\"WORKDIR: {WORKDIR}\")\n",
+    "print(f\"BASENAME: {BASENAME}\")\n",
+    "\n",
+    "# Create a directory storing local data\n",
+    "iso20022_data_path = 'iso20022-data'\n",
+    "if not os.path.exists(iso20022_data_path):\n",
+    "    # Create a new directory because it does not exist \n",
+    "    os.makedirs(iso20022_data_path)\n",
+    "\n",
+    "# Store all prototype assets in this bucket\n",
+    "s3_bucket_name = 'iso20022-prototype-t3'\n",
+    "s3_bucket_uri = 's3://' + s3_bucket_name\n",
+    "\n",
+    "# Prefix for all files in this prototype\n",
+    "prefix = 'iso20022'\n",
+    "\n",
+    "pacs008_prefix = prefix + '/pacs008'\n",
+    "raw_data_prefix = pacs008_prefix + '/raw-data'\n",
+    "labeled_data_prefix = pacs008_prefix + '/labeled-data'\n",
+    "\n",
+    "\n",
+    "labeled_data_location = s3_bucket_uri + '/' + labeled_data_prefix\n",
+    "print(f\"Raw labeled data location = {labeled_data_location}\")\n",
+    "\n",
+    "# Download labeled raw dataset from S3\n",
+    "s3_client = boto3.client('s3')\n",
+    "s3_client.download_file(s3_bucket_name, labeled_data_prefix + '/labeled_data.csv', 'iso20022-data/labeled_data.csv')"
    ]
   },
   {
@@ -62,6 +129,7 @@
     "import matplotlib.pyplot as plt\n",
     "import seaborn as sns\n",
     "import nltk\n",
+    "nltk.download('stopwords')\n",
     "from nltk.corpus import stopwords\n",
     "import string\n",
     "import xgboost as xgb\n",
@@ -1358,10 +1426,11 @@
   }
  ],
  "metadata": {
+  "instance_type": "ml.t3.medium",
   "kernelspec": {
-   "display_name": "conda_python3",
+   "display_name": "Python 3 (Data Science)",
    "language": "python",
-   "name": "conda_python3"
+   "name": "python3__SAGEMAKER_INTERNAL__arn:aws:sagemaker:us-east-1:081325390199:image/datascience-1.0"
   },
   "language_info": {
    "codemirror_mode": {
@@ -1373,7 +1442,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.13"
+   "version": "3.7.10"
   }
  },
  "nbformat": 4,