Upload 2 files
Browse files- S3Access.ipynb +136 -0
- S3AccessWriteBack.ipynb +161 -0
S3Access.ipynb
ADDED
|
@@ -0,0 +1,136 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cells": [
|
| 3 |
+
{
|
| 4 |
+
"cell_type": "code",
|
| 5 |
+
"execution_count": 1,
|
| 6 |
+
"id": "6205f0fb-db74-44d2-bfb1-98760790125c",
|
| 7 |
+
"metadata": {},
|
| 8 |
+
"outputs": [
|
| 9 |
+
{
|
| 10 |
+
"ename": "SyntaxError",
|
| 11 |
+
"evalue": "invalid syntax (3925509796.py, line 1)",
|
| 12 |
+
"output_type": "error",
|
| 13 |
+
"traceback": [
|
| 14 |
+
"\u001b[0;36m Cell \u001b[0;32mIn[1], line 1\u001b[0;36m\u001b[0m\n\u001b[0;31m pip install boto3\u001b[0m\n\u001b[0m ^\u001b[0m\n\u001b[0;31mSyntaxError\u001b[0m\u001b[0;31m:\u001b[0m invalid syntax\n"
|
| 15 |
+
]
|
| 16 |
+
}
|
| 17 |
+
],
|
| 18 |
+
"source": [
|
| 19 |
+
"pip install boto3\n",
|
| 20 |
+
"pip install pandas"
|
| 21 |
+
]
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"cell_type": "code",
|
| 25 |
+
"execution_count": null,
|
| 26 |
+
"id": "4afe577f-283e-431a-8109-56228af5f203",
|
| 27 |
+
"metadata": {},
|
| 28 |
+
"outputs": [],
|
| 29 |
+
"source": [
|
| 30 |
+
"import boto3\n",
|
| 31 |
+
"import json\n",
|
| 32 |
+
"import pandas as pd\n",
|
| 33 |
+
"import matplotlib.pyplot as plt"
|
| 34 |
+
]
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"cell_type": "code",
|
| 38 |
+
"execution_count": null,
|
| 39 |
+
"id": "80ea967b-3787-4c5a-b90b-692782bb9460",
|
| 40 |
+
"metadata": {},
|
| 41 |
+
"outputs": [],
|
| 42 |
+
"source": [
|
| 43 |
+
"# Initialize a session using your credentials\n",
|
| 44 |
+
"session = boto3.Session(\n",
|
| 45 |
+
" aws_access_key_id='AKIAZ3CL7RBT67UNF7CU',\n",
|
| 46 |
+
" aws_secret_access_key='1C1gUZflYJ0Q8voiI4Iv+DBBXeLv0w9PQjOZm8Kr',\n",
|
| 47 |
+
" region_name='us-west-2' # e.g., us-east-1\n",
|
| 48 |
+
")\n",
|
| 49 |
+
"\n",
|
| 50 |
+
"# Create an S3 client using the session\n",
|
| 51 |
+
"s3 = session.client('s3')"
|
| 52 |
+
]
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"cell_type": "code",
|
| 56 |
+
"execution_count": null,
|
| 57 |
+
"id": "b05018cb-03d4-4d47-9c60-149a8f73cf1c",
|
| 58 |
+
"metadata": {},
|
| 59 |
+
"outputs": [],
|
| 60 |
+
"source": [
|
| 61 |
+
"bucket_name = 'caetestbucket'\n",
|
| 62 |
+
"\n",
|
| 63 |
+
"try:\n",
|
| 64 |
+
" contents = s3.list_objects(Bucket=bucket_name)['Contents']\n",
|
| 65 |
+
" for item in contents:\n",
|
| 66 |
+
" print(item['Key'])\n",
|
| 67 |
+
"except NoCredentialsError:\n",
|
| 68 |
+
" print(\"Credentials not available\")\n",
|
| 69 |
+
"except KeyError:\n",
|
| 70 |
+
" print(\"Bucket is empty or does not exist\")"
|
| 71 |
+
]
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"cell_type": "code",
|
| 75 |
+
"execution_count": null,
|
| 76 |
+
"id": "028e3460-0485-4bfc-aa41-044276439838",
|
| 77 |
+
"metadata": {},
|
| 78 |
+
"outputs": [],
|
| 79 |
+
"source": [
|
| 80 |
+
"import boto3\n",
|
| 81 |
+
"import json\n",
|
| 82 |
+
"\n",
|
| 83 |
+
"file_key = 'MOCK_VEHICLE.json'\n",
|
| 84 |
+
"\n",
|
| 85 |
+
"response = s3.get_object(Bucket=bucket_name, Key=file_key)\n",
|
| 86 |
+
"# Assuming each line in the file is a separate JSON object\n",
|
| 87 |
+
"vehicle_data_lines = response['Body'].read().decode('utf-8').splitlines()\n",
|
| 88 |
+
"\n",
|
| 89 |
+
"vehicle_data = []\n",
|
| 90 |
+
"for line in vehicle_data_lines:\n",
|
| 91 |
+
" try:\n",
|
| 92 |
+
" vehicle = json.loads(line)\n",
|
| 93 |
+
" vehicle_data.append(vehicle)\n",
|
| 94 |
+
" except json.JSONDecodeError as e:\n",
|
| 95 |
+
" print(f\"Error decoding JSON: {e}\")"
|
| 96 |
+
]
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"cell_type": "code",
|
| 100 |
+
"execution_count": null,
|
| 101 |
+
"id": "4e4c78c3-bd9d-417e-9b96-9046cce33df2",
|
| 102 |
+
"metadata": {},
|
| 103 |
+
"outputs": [],
|
| 104 |
+
"source": []
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"cell_type": "code",
|
| 108 |
+
"execution_count": null,
|
| 109 |
+
"id": "ebc83569-2645-4f5d-a8c4-1192dd7aa72d",
|
| 110 |
+
"metadata": {},
|
| 111 |
+
"outputs": [],
|
| 112 |
+
"source": []
|
| 113 |
+
}
|
| 114 |
+
],
|
| 115 |
+
"metadata": {
|
| 116 |
+
"kernelspec": {
|
| 117 |
+
"display_name": "venv",
|
| 118 |
+
"language": "python",
|
| 119 |
+
"name": "venv"
|
| 120 |
+
},
|
| 121 |
+
"language_info": {
|
| 122 |
+
"codemirror_mode": {
|
| 123 |
+
"name": "ipython",
|
| 124 |
+
"version": 3
|
| 125 |
+
},
|
| 126 |
+
"file_extension": ".py",
|
| 127 |
+
"mimetype": "text/x-python",
|
| 128 |
+
"name": "python",
|
| 129 |
+
"nbconvert_exporter": "python",
|
| 130 |
+
"pygments_lexer": "ipython3",
|
| 131 |
+
"version": "3.12.3"
|
| 132 |
+
}
|
| 133 |
+
},
|
| 134 |
+
"nbformat": 4,
|
| 135 |
+
"nbformat_minor": 5
|
| 136 |
+
}
|
S3AccessWriteBack.ipynb
ADDED
|
@@ -0,0 +1,161 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cells": [
|
| 3 |
+
{
|
| 4 |
+
"cell_type": "code",
|
| 5 |
+
"execution_count": 3,
|
| 6 |
+
"id": "6205f0fb-db74-44d2-bfb1-98760790125c",
|
| 7 |
+
"metadata": {},
|
| 8 |
+
"outputs": [
|
| 9 |
+
{
|
| 10 |
+
"name": "stdout",
|
| 11 |
+
"output_type": "stream",
|
| 12 |
+
"text": [
|
| 13 |
+
"Defaulting to user installation because normal site-packages is not writeable\n",
|
| 14 |
+
"Collecting boto3\n",
|
| 15 |
+
" Downloading boto3-1.34.83-py3-none-any.whl.metadata (6.6 kB)\n",
|
| 16 |
+
"Collecting botocore<1.35.0,>=1.34.83 (from boto3)\n",
|
| 17 |
+
" Downloading botocore-1.34.83-py3-none-any.whl.metadata (5.7 kB)\n",
|
| 18 |
+
"Collecting jmespath<2.0.0,>=0.7.1 (from boto3)\n",
|
| 19 |
+
" Downloading jmespath-1.0.1-py3-none-any.whl.metadata (7.6 kB)\n",
|
| 20 |
+
"Collecting s3transfer<0.11.0,>=0.10.0 (from boto3)\n",
|
| 21 |
+
" Downloading s3transfer-0.10.1-py3-none-any.whl.metadata (1.7 kB)\n",
|
| 22 |
+
"Requirement already satisfied: python-dateutil<3.0.0,>=2.1 in /opt/anaconda/envs/myenv/lib/python3.8/site-packages (from botocore<1.35.0,>=1.34.83->boto3) (2.9.0)\n",
|
| 23 |
+
"Collecting urllib3<1.27,>=1.25.4 (from botocore<1.35.0,>=1.34.83->boto3)\n",
|
| 24 |
+
" Downloading urllib3-1.26.18-py2.py3-none-any.whl.metadata (48 kB)\n",
|
| 25 |
+
"\u001b[2K \u001b[90mβββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m48.9/48.9 kB\u001b[0m \u001b[31m758.9 kB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m \u001b[36m0:00:01\u001b[0m\n",
|
| 26 |
+
"\u001b[?25hRequirement already satisfied: six>=1.5 in /opt/anaconda/envs/myenv/lib/python3.8/site-packages (from python-dateutil<3.0.0,>=2.1->botocore<1.35.0,>=1.34.83->boto3) (1.16.0)\n",
|
| 27 |
+
"Downloading boto3-1.34.83-py3-none-any.whl (139 kB)\n",
|
| 28 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m139.3/139.3 kB\u001b[0m \u001b[31m2.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0ma \u001b[36m0:00:01\u001b[0m\n",
|
| 29 |
+
"\u001b[?25hDownloading botocore-1.34.83-py3-none-any.whl (12.1 MB)\n",
|
| 30 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m12.1/12.1 MB\u001b[0m \u001b[31m24.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
|
| 31 |
+
"\u001b[?25hDownloading jmespath-1.0.1-py3-none-any.whl (20 kB)\n",
|
| 32 |
+
"Downloading s3transfer-0.10.1-py3-none-any.whl (82 kB)\n",
|
| 33 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m82.2/82.2 kB\u001b[0m \u001b[31m2.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
| 34 |
+
"\u001b[?25hDownloading urllib3-1.26.18-py2.py3-none-any.whl (143 kB)\n",
|
| 35 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m143.8/143.8 kB\u001b[0m \u001b[31m5.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
| 36 |
+
"\u001b[?25hInstalling collected packages: urllib3, jmespath, botocore, s3transfer, boto3\n",
|
| 37 |
+
"Successfully installed boto3-1.34.83 botocore-1.34.83 jmespath-1.0.1 s3transfer-0.10.1 urllib3-1.26.18\n",
|
| 38 |
+
"Note: you may need to restart the kernel to use updated packages.\n"
|
| 39 |
+
]
|
| 40 |
+
}
|
| 41 |
+
],
|
| 42 |
+
"source": [
|
| 43 |
+
"pip install boto3"
|
| 44 |
+
]
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"cell_type": "code",
|
| 48 |
+
"execution_count": 23,
|
| 49 |
+
"id": "4afe577f-283e-431a-8109-56228af5f203",
|
| 50 |
+
"metadata": {},
|
| 51 |
+
"outputs": [],
|
| 52 |
+
"source": [
|
| 53 |
+
"import boto3\n",
|
| 54 |
+
"import json\n",
|
| 55 |
+
"import pandas as pd\n",
|
| 56 |
+
"import matplotlib.pyplot as plt"
|
| 57 |
+
]
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"cell_type": "code",
|
| 61 |
+
"execution_count": 15,
|
| 62 |
+
"id": "80ea967b-3787-4c5a-b90b-692782bb9460",
|
| 63 |
+
"metadata": {},
|
| 64 |
+
"outputs": [],
|
| 65 |
+
"source": [
|
| 66 |
+
"# Initialize a session using your credentials\n",
|
| 67 |
+
"session = boto3.Session(\n",
|
| 68 |
+
" aws_access_key_id='AKIAZ3CL7RBT67UNF7CU',\n",
|
| 69 |
+
" aws_secret_access_key='1C1gUZflYJ0Q8voiI4Iv+DBBXeLv0w9PQjOZm8Kr',\n",
|
| 70 |
+
" region_name='us-west-2' # e.g., us-east-1\n",
|
| 71 |
+
")\n",
|
| 72 |
+
"\n",
|
| 73 |
+
"# Create an S3 client using the session\n",
|
| 74 |
+
"s3 = session.client('s3')"
|
| 75 |
+
]
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"cell_type": "code",
|
| 79 |
+
"execution_count": 21,
|
| 80 |
+
"id": "b05018cb-03d4-4d47-9c60-149a8f73cf1c",
|
| 81 |
+
"metadata": {},
|
| 82 |
+
"outputs": [
|
| 83 |
+
{
|
| 84 |
+
"name": "stdout",
|
| 85 |
+
"output_type": "stream",
|
| 86 |
+
"text": [
|
| 87 |
+
"MOCK_PEOPLE.json\n",
|
| 88 |
+
"MOCK_TRAVEL.json\n",
|
| 89 |
+
"MOCK_VEHICLE.json\n"
|
| 90 |
+
]
|
| 91 |
+
}
|
| 92 |
+
],
|
| 93 |
+
"source": [
|
| 94 |
+
"bucket_name = 'caetestbucket'\n",
|
| 95 |
+
"\n",
|
| 96 |
+
"try:\n",
|
| 97 |
+
" contents = s3.list_objects(Bucket=bucket_name)['Contents']\n",
|
| 98 |
+
" for item in contents:\n",
|
| 99 |
+
" print(item['Key'])\n",
|
| 100 |
+
"except NoCredentialsError:\n",
|
| 101 |
+
" print(\"Credentials not available\")\n",
|
| 102 |
+
"except KeyError:\n",
|
| 103 |
+
" print(\"Bucket is empty or does not exist\")"
|
| 104 |
+
]
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"cell_type": "code",
|
| 108 |
+
"execution_count": 25,
|
| 109 |
+
"id": "028e3460-0485-4bfc-aa41-044276439838",
|
| 110 |
+
"metadata": {},
|
| 111 |
+
"outputs": [],
|
| 112 |
+
"source": [
|
| 113 |
+
"import boto3\n",
|
| 114 |
+
"import json\n",
|
| 115 |
+
"\n",
|
| 116 |
+
"file_key = 'MOCK_VEHICLE.json'\n",
|
| 117 |
+
"\n",
|
| 118 |
+
"response = s3.get_object(Bucket=bucket_name, Key=file_key)\n",
|
| 119 |
+
"# Assuming each line in the file is a separate JSON object\n",
|
| 120 |
+
"vehicle_data_lines = response['Body'].read().decode('utf-8').splitlines()\n",
|
| 121 |
+
"\n",
|
| 122 |
+
"vehicle_data = []\n",
|
| 123 |
+
"for line in vehicle_data_lines:\n",
|
| 124 |
+
" try:\n",
|
| 125 |
+
" vehicle = json.loads(line)\n",
|
| 126 |
+
" vehicle_data.append(vehicle)\n",
|
| 127 |
+
" except json.JSONDecodeError as e:\n",
|
| 128 |
+
" print(f\"Error decoding JSON: {e}\")"
|
| 129 |
+
]
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"cell_type": "code",
|
| 133 |
+
"execution_count": null,
|
| 134 |
+
"id": "4e4c78c3-bd9d-417e-9b96-9046cce33df2",
|
| 135 |
+
"metadata": {},
|
| 136 |
+
"outputs": [],
|
| 137 |
+
"source": []
|
| 138 |
+
}
|
| 139 |
+
],
|
| 140 |
+
"metadata": {
|
| 141 |
+
"kernelspec": {
|
| 142 |
+
"display_name": "Python 3 (ipykernel)",
|
| 143 |
+
"language": "python",
|
| 144 |
+
"name": "python3"
|
| 145 |
+
},
|
| 146 |
+
"language_info": {
|
| 147 |
+
"codemirror_mode": {
|
| 148 |
+
"name": "ipython",
|
| 149 |
+
"version": 3
|
| 150 |
+
},
|
| 151 |
+
"file_extension": ".py",
|
| 152 |
+
"mimetype": "text/x-python",
|
| 153 |
+
"name": "python",
|
| 154 |
+
"nbconvert_exporter": "python",
|
| 155 |
+
"pygments_lexer": "ipython3",
|
| 156 |
+
"version": "3.8.19"
|
| 157 |
+
}
|
| 158 |
+
},
|
| 159 |
+
"nbformat": 4,
|
| 160 |
+
"nbformat_minor": 5
|
| 161 |
+
}
|