Skip to content

Commit cb2e4a3

Browse files
mandawatDeepika Mandawatjaidisido
authored
feat: Timestream Add multi measure write record example (#2317)
* Timestream: Add multi measure write record example * minor - Timestream tutorial adjustments --------- Co-authored-by: Deepika Mandawat <[email protected]> Co-authored-by: Abdel Jaidi <[email protected]>
1 parent b3eb4a5 commit cb2e4a3

File tree

1 file changed

+139
-79
lines changed

1 file changed

+139
-79
lines changed

‎tutorials/026 - Amazon Timestream.ipynb‎

Lines changed: 139 additions & 79 deletions
Original file line numberDiff line numberDiff line change
@@ -1,70 +1,59 @@
11
{
22
"cells": [
33
{
4+
"attachments": {},
5+
"cell_type": "markdown",
6+
"metadata": {},
47
"source": [
58
"[![AWS SDK for pandas](_static/logo.png \"AWS SDK for pandas\")](https://github.com/aws/aws-sdk-pandas)\n",
69
"\n",
710
"# 26 - Amazon Timestream"
8-
],
9-
"cell_type": "markdown",
10-
"metadata": {
11-
"pycharm": {
12-
"name": "#%% md\n"
13-
}
14-
}
11+
]
1512
},
1613
{
14+
"attachments": {},
15+
"cell_type": "markdown",
16+
"metadata": {},
1717
"source": [
1818
"## Creating resources"
19-
],
20-
"cell_type": "markdown",
21-
"metadata": {
22-
"pycharm": {
23-
"name": "#%% md\n"
24-
}
25-
}
19+
]
2620
},
2721
{
2822
"cell_type": "code",
2923
"execution_count": 10,
30-
"metadata": {
31-
"pycharm": {
32-
"name": "#%%\n"
33-
}
34-
},
24+
"metadata": {},
3525
"outputs": [],
3626
"source": [
3727
"import awswrangler as wr\n",
3828
"import pandas as pd\n",
3929
"from datetime import datetime\n",
4030
"\n",
41-
"wr.timestream.create_database(\"sampleDB\")\n",
42-
"wr.timestream.create_table(\"sampleDB\", \"sampleTable\", memory_retention_hours=1, magnetic_retention_days=1)"
31+
"database = \"sampleDB\"\n",
32+
"table_1 = \"sampleTable1\"\n",
33+
"table_2 = \"sampleTable2\"\n",
34+
"wr.timestream.create_database(database)\n",
35+
"wr.timestream.create_table(database, table_1, memory_retention_hours=1, magnetic_retention_days=1)\n",
36+
"wr.timestream.create_table(database, table_2, memory_retention_hours=1, magnetic_retention_days=1)"
4337
]
4438
},
4539
{
40+
"attachments": {},
4641
"cell_type": "markdown",
47-
"metadata": {
48-
"pycharm": {
49-
"name": "#%% md\n"
50-
}
51-
},
42+
"metadata": {},
5243
"source": [
53-
"## Write"
44+
"## Write\n",
45+
"\n",
46+
"### Single measure WriteRecord"
5447
]
5548
},
5649
{
5750
"cell_type": "code",
5851
"execution_count": 11,
59-
"metadata": {
60-
"pycharm": {
61-
"name": "#%%\n"
62-
}
63-
},
52+
"metadata": {},
6453
"outputs": [
6554
{
66-
"output_type": "stream",
6755
"name": "stdout",
56+
"output_type": "stream",
6857
"text": [
6958
"Number of rejected records: 0\n"
7059
]
@@ -73,7 +62,7 @@
7362
"source": [
7463
"df = pd.DataFrame(\n",
7564
" {\n",
76-
" \"time\": [datetime.now(), datetime.now(), datetime.now()],\n",
65+
" \"time\": [datetime.now()] * 3,\n",
7766
" \"dim0\": [\"foo\", \"boo\", \"bar\"],\n",
7867
" \"dim1\": [1, 2, 3],\n",
7968
" \"measure\": [1.0, 1.1, 1.2],\n",
@@ -82,8 +71,8 @@
8271
"\n",
8372
"rejected_records = wr.timestream.write(\n",
8473
" df=df,\n",
85-
" database=\"sampleDB\",\n",
86-
" table=\"sampleTable\",\n",
74+
" database=database,\n",
75+
" table=table_1,\n",
8776
" time_col=\"time\",\n",
8877
" measure_col=\"measure\",\n",
8978
" dimensions_cols=[\"dim0\", \"dim1\"],\n",
@@ -93,99 +82,170 @@
9382
]
9483
},
9584
{
85+
"attachments": {},
9686
"cell_type": "markdown",
9787
"metadata": {
98-
"pycharm": {
99-
"name": "#%% md\n"
100-
}
88+
"collapsed": false
10189
},
10290
"source": [
103-
"## Query"
91+
"### Multi measure WriteRecord"
10492
]
10593
},
10694
{
10795
"cell_type": "code",
108-
"execution_count": 12,
96+
"execution_count": null,
10997
"metadata": {
110-
"pycharm": {
111-
"name": "#%%\n"
112-
}
98+
"collapsed": false
11399
},
100+
"outputs": [],
101+
"source": [
102+
"df = pd.DataFrame(\n",
103+
" {\n",
104+
" \"time\": [datetime.now()] * 3,\n",
105+
" \"measure_1\": [\"10\", \"20\", \"30\"],\n",
106+
" \"measure_2\": [\"100\", \"200\", \"300\"],\n",
107+
" \"measure_3\": [\"1000\", \"2000\", \"3000\"],\n",
108+
" \"tag\": [\"tag123\", \"tag456\", \"tag789\"],\n",
109+
" }\n",
110+
")\n",
111+
"rejected_records = wr.timestream.write(\n",
112+
" df=df,\n",
113+
" database=database,\n",
114+
" table=table_2,\n",
115+
" time_col=\"time\",\n",
116+
" measure_col=[\"measure_1\", \"measure_2\", \"measure_3\"],\n",
117+
" dimensions_cols=[\"tag\"]\n",
118+
")\n",
119+
"\n",
120+
"print(f\"Number of rejected records: {len(rejected_records)}\")"
121+
]
122+
},
123+
{
124+
"attachments": {},
125+
"cell_type": "markdown",
126+
"metadata": {},
127+
"source": [
128+
"## Query"
129+
]
130+
},
131+
{
132+
"cell_type": "code",
133+
"execution_count": 12,
134+
"metadata": {},
114135
"outputs": [
115136
{
116-
"output_type": "execute_result",
117137
"data": {
138+
"text/html": [
139+
"<div>\n",
140+
"<style scoped>\n",
141+
" .dataframe tbody tr th:only-of-type {\n",
142+
" vertical-align: middle;\n",
143+
" }\n",
144+
"\n",
145+
" .dataframe tbody tr th {\n",
146+
" vertical-align: top;\n",
147+
" }\n",
148+
"\n",
149+
" .dataframe thead th {\n",
150+
" text-align: right;\n",
151+
" }\n",
152+
"</style>\n",
153+
"<table border=\"1\" class=\"dataframe\">\n",
154+
" <thead>\n",
155+
" <tr style=\"text-align: right;\">\n",
156+
" <th></th>\n",
157+
" <th>time</th>\n",
158+
" <th>measure_value::double</th>\n",
159+
" <th>dim0</th>\n",
160+
" <th>dim1</th>\n",
161+
" </tr>\n",
162+
" </thead>\n",
163+
" <tbody>\n",
164+
" <tr>\n",
165+
" <th>0</th>\n",
166+
" <td>2020-12-08 19:15:32.468</td>\n",
167+
" <td>1.0</td>\n",
168+
" <td>foo</td>\n",
169+
" <td>1</td>\n",
170+
" </tr>\n",
171+
" <tr>\n",
172+
" <th>1</th>\n",
173+
" <td>2020-12-08 19:15:32.468</td>\n",
174+
" <td>1.2</td>\n",
175+
" <td>bar</td>\n",
176+
" <td>3</td>\n",
177+
" </tr>\n",
178+
" <tr>\n",
179+
" <th>2</th>\n",
180+
" <td>2020-12-08 19:15:32.468</td>\n",
181+
" <td>1.1</td>\n",
182+
" <td>boo</td>\n",
183+
" <td>2</td>\n",
184+
" </tr>\n",
185+
" </tbody>\n",
186+
"</table>\n",
187+
"</div>"
188+
],
118189
"text/plain": [
119190
" time measure_value::double dim0 dim1\n",
120191
"0 2020-12-08 19:15:32.468 1.0 foo 1\n",
121192
"1 2020-12-08 19:15:32.468 1.2 bar 3\n",
122193
"2 2020-12-08 19:15:32.468 1.1 boo 2"
123-
],
124-
"text/html": "<div>\n<style scoped>\n .dataframe tbody tr th:only-of-type {\n vertical-align: middle;\n }\n\n .dataframe tbody tr th {\n vertical-align: top;\n }\n\n .dataframe thead th {\n text-align: right;\n }\n</style>\n<table border=\"1\" class=\"dataframe\">\n <thead>\n <tr style=\"text-align: right;\">\n <th></th>\n <th>time</th>\n <th>measure_value::double</th>\n <th>dim0</th>\n <th>dim1</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th>0</th>\n <td>2020-12-08 19:15:32.468</td>\n <td>1.0</td>\n <td>foo</td>\n <td>1</td>\n </tr>\n <tr>\n <th>1</th>\n <td>2020-12-08 19:15:32.468</td>\n <td>1.2</td>\n <td>bar</td>\n <td>3</td>\n </tr>\n <tr>\n <th>2</th>\n <td>2020-12-08 19:15:32.468</td>\n <td>1.1</td>\n <td>boo</td>\n <td>2</td>\n </tr>\n </tbody>\n</table>\n</div>"
194+
]
125195
},
196+
"execution_count": 12,
126197
"metadata": {},
127-
"execution_count": 12
198+
"output_type": "execute_result"
128199
}
129200
],
130201
"source": [
131202
"wr.timestream.query(\n",
132-
" 'SELECT time, measure_value::double, dim0, dim1 FROM \"sampleDB\".\"sampleTable\" ORDER BY time DESC LIMIT 3'\n",
203+
" f'SELECT time, measure_value::double, dim0, dim1 FROM \"{database}\".\"{table_1}\" ORDER BY time DESC LIMIT 3'\n",
133204
")"
134205
]
135206
},
136207
{
208+
"attachments": {},
137209
"cell_type": "markdown",
210+
"metadata": {
211+
"collapsed": false
212+
},
138213
"source": [
139214
"## Unload"
140-
],
141-
"metadata": {
142-
"collapsed": false,
143-
"pycharm": {
144-
"name": "#%% md\n"
145-
}
146-
}
215+
]
147216
},
148217
{
149218
"cell_type": "code",
150219
"execution_count": null,
220+
"metadata": {
221+
"collapsed": false
222+
},
151223
"outputs": [],
152224
"source": [
153225
"df = wr.timestream.unload(\n",
154-
" sql='SELECT time, measure_value, dim0, dim1 FROM \"sampleDB\".\"sampleTable\"',\n",
226+
" sql=f'SELECT time, measure_value, dim0, dim1 FROM \"{database}\".\"{table_1}\"',\n",
155227
" path=\"s3://bucket/extracted_parquet_files/\",\n",
156228
" partition_cols=[\"dim1\"],\n",
157229
")"
158-
],
159-
"metadata": {
160-
"collapsed": false,
161-
"pycharm": {
162-
"name": "#%%\n"
163-
}
164-
}
230+
]
165231
},
166232
{
233+
"attachments": {},
234+
"cell_type": "markdown",
235+
"metadata": {},
167236
"source": [
168237
"## Deleting resources"
169-
],
170-
"cell_type": "markdown",
171-
"metadata": {
172-
"pycharm": {
173-
"name": "#%% md\n"
174-
}
175-
}
238+
]
176239
},
177240
{
178241
"cell_type": "code",
179242
"execution_count": 13,
180-
"metadata": {
181-
"pycharm": {
182-
"name": "#%%\n"
183-
}
184-
},
243+
"metadata": {},
185244
"outputs": [],
186245
"source": [
187-
"wr.timestream.delete_table(\"sampleDB\", \"sampleTable\")\n",
188-
"wr.timestream.delete_database(\"sampleDB\")"
246+
"wr.timestream.delete_table(database, table_1)\n",
247+
"wr.timestream.delete_table(database, table_2)\n",
248+
"wr.timestream.delete_database(database)"
189249
]
190250
}
191251
],
@@ -219,4 +279,4 @@
219279
},
220280
"nbformat": 4,
221281
"nbformat_minor": 4
222-
}
282+
}

0 commit comments

Comments
 (0)