Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Satish Kumar Matti
committed
May 31, 2019
1 parent
224b1e1
commit 2593180
Showing
1 changed file
with
125 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,125 @@ | ||
{ | ||
"cells": [ | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"from streamz.dataframe import DataFrame\n", | ||
"import cudf" | ||
] | ||
}, | ||
{ | ||
"cell_type": "markdown", | ||
"metadata": {}, | ||
"source": [ | ||
"# Basic example" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"\n", | ||
"cu_df = cudf.DataFrame({'x': np.arange(10, dtype=float)+10, 'y': [1.0, 2.0] * 5})\n", | ||
"\n", | ||
"sdf = DataFrame(example=cu_df)\n", | ||
"\n", | ||
"L = sdf.window(n=15).x.sum().stream.sink_to_list()" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"sdf.emit(cu_df.iloc[:8])\n", | ||
"sdf.emit(cu_df)\n", | ||
"sdf.emit(cu_df)" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"print(L[0])\n", | ||
"print(L[1])\n", | ||
"print(L[2])" | ||
] | ||
}, | ||
{ | ||
"cell_type": "markdown", | ||
"metadata": {}, | ||
"source": [ | ||
"# Advanced example\n", | ||
"The following pipeline reads json encoded strings from Kafka in batches and process them on GPUs and write the result back to a different Kafka topic. This pipeline can be easily extended to run on Dask Stream as well.\n", | ||
"Note: Uses cudf 0.8" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"# read messages from kafka and create a stream\n", | ||
"\n", | ||
"consume_topic = \"my-topic\"\n", | ||
"produce_topic = \"my-out-topic\"\n", | ||
"bootstrap_servers = 'localhost:9092'\n", | ||
"consumer_conf = {'bootstrap.servers': bootstrap_servers,\n", | ||
" 'group.id': 'group-123', 'session.timeout.ms': 600}\n", | ||
"producer_conf = {'bootstrap.servers': bootstrap_servers}\n", | ||
"\n", | ||
"stream = Stream.from_kafka_batched(consume_topic, consumer_conf, poll_interval='10s',\n", | ||
" npartitions=10, asynchronous=True)" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"# convert batch of encoded json strings to gpu dataframes\n", | ||
"cudf_stream = stream\\\n", | ||
" .map(lambda msgs: \"\\n\".join([msg.decode('utf-8') for msg in msgs]))\\\n", | ||
" .map(cudf.read_json, lines=True)\n", | ||
"\n", | ||
"# create a streamz dataframe from the above stream and sample dataframe\n", | ||
"cudf_example = cudf.DataFrame({'x': np.arange(10, dtype=float)+10, 'y': [1.0, 2.0] * 5})\n", | ||
"stdf = DataFrame(cudf_stream, example=cudf_example)\n", | ||
"\n", | ||
"# perform aggregation and write to kafka\n", | ||
"stdf.window(n=15).x.mean().stream.to_kafka(produce_topic, producer_conf)\n" | ||
] | ||
} | ||
], | ||
"metadata": { | ||
"kernelspec": { | ||
"display_name": "Python 3", | ||
"language": "python", | ||
"name": "python3" | ||
}, | ||
"language_info": { | ||
"codemirror_mode": { | ||
"name": "ipython", | ||
"version": 3 | ||
}, | ||
"file_extension": ".py", | ||
"mimetype": "text/x-python", | ||
"name": "python", | ||
"nbconvert_exporter": "python", | ||
"pygments_lexer": "ipython3", | ||
"version": "3.6.3" | ||
} | ||
}, | ||
"nbformat": 4, | ||
"nbformat_minor": 2 | ||
} |