Created
August 21, 2019 16:04
-
-
Save quasiben/9b86e189f3e4fe714c7ef8a566707236 to your computer and use it in GitHub Desktop.
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
{ | |
"cells": [ | |
{ | |
"cell_type": "code", | |
"execution_count": 1, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"import numpy as np\n", | |
"import pandas as pd\n", | |
"import cudf" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 2, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"df = pd.DataFrame({'a': range(100000)})\n", | |
"arr = np.arange(40, 50000)\n", | |
"cdf = cudf.from_pandas(df)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 3, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"24.1 ms ± 1.57 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n" | |
] | |
} | |
], | |
"source": [ | |
"%timeit cdf.iloc[arr] # vanilla numpy array" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 4, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"1.77 ms ± 17.9 µs per loop (mean ± std. dev. of 7 runs, 1000 loops each)\n" | |
] | |
} | |
], | |
"source": [ | |
"%timeit cdf.iloc[slice(40, 50000)] # slicing" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 6, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"519 µs ± 4.14 µs per loop (mean ± std. dev. of 7 runs, 1000 loops each)\n" | |
] | |
} | |
], | |
"source": [ | |
"%timeit sr = cudf.Series(arr)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 7, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"513 µs ± 8.24 µs per loop (mean ± std. dev. of 7 runs, 1000 loops each)\n" | |
] | |
} | |
], | |
"source": [ | |
"%timeit cudf.Series(arr) # timing for device->host transfer" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 9, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"sr = cudf.Series(arr)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 10, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"20.1 ms ± 2.44 ms per loop (mean ± std. dev. of 7 runs, 100 loops each)\n" | |
] | |
} | |
], | |
"source": [ | |
"%timeit cdf.iloc[sr] # gpu backed array" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"**Indexing into cudf DataFrame wiith GPU and NumPy index run at nearly the same speed.**" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"## Test With Shuffled Indicies" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 11, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"np.random.shuffle(arr)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 12, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"array([ 3130, 25506, 820, ..., 17052, 9296, 16724])" | |
] | |
}, | |
"execution_count": 12, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"arr" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 15, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"12.5 ms ± 760 µs per loop (mean ± std. dev. of 7 runs, 1 loop each)\n" | |
] | |
} | |
], | |
"source": [ | |
"%timeit cdf.iloc[arr] # shuffled numpy array" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 14, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"0 3130\n", | |
"1 25506\n", | |
"2 820\n", | |
"3 31545\n", | |
"4 7816\n", | |
"dtype: int64" | |
] | |
}, | |
"execution_count": 14, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"sr = cudf.Series(arr)\n", | |
"sr.head()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 16, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"14.6 ms ± 641 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n" | |
] | |
} | |
], | |
"source": [ | |
"%timeit cdf.iloc[sr] # gpu backed array" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"## Try with CuPy" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 17, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"import cupy\n", | |
"c_arr = cupy.asarray(arr)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 21, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"13.1 ms ± 2.01 ms per loop (mean ± std. dev. of 7 runs, 100 loops each)\n" | |
] | |
} | |
], | |
"source": [ | |
"%timeit cdf.iloc[c_arr]" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 23, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"%load_ext snakeviz" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"## Try with Integer Column name" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 25, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"df = pd.DataFrame({0: range(100000)})\n", | |
"arr = np.arange(40, 50000)\n", | |
"cdf = cudf.from_pandas(df)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 26, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"13.9 ms ± 302 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n" | |
] | |
} | |
], | |
"source": [ | |
"%timeit cdf.iloc[arr]" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 27, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
" \n", | |
"*** Profile stats marshalled to file '/tmp/tmp5s87ym3m'. \n", | |
"Embedding SnakeViz in this document...\n" | |
] | |
}, | |
{ | |
"data": { | |
"text/html": [ | |
"\n", | |
"<iframe id='snakeviz-9b960bd2-c42c-11e9-a06b-d8c49764f624' frameborder=0 seamless width='100%' height='1000'></iframe>\n", | |
"<script>document.getElementById(\"snakeviz-9b960bd2-c42c-11e9-a06b-d8c49764f624\").setAttribute(\"src\", \"http://\" + document.location.hostname + \":8080/snakeviz/%2Ftmp%2Ftmp5s87ym3m\")</script>\n" | |
], | |
"text/plain": [ | |
"<IPython.core.display.HTML object>" | |
] | |
}, | |
"metadata": {}, | |
"output_type": "display_data" | |
} | |
], | |
"source": [ | |
"%%snakeviz\n", | |
"cdf.iloc[arr]" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [] | |
} | |
], | |
"metadata": { | |
"kernelspec": { | |
"display_name": "Python [conda env:rapids-0.9]", | |
"language": "python", | |
"name": "conda-env-rapids-0.9-py" | |
}, | |
"language_info": { | |
"codemirror_mode": { | |
"name": "ipython", | |
"version": 3 | |
}, | |
"file_extension": ".py", | |
"mimetype": "text/x-python", | |
"name": "python", | |
"nbconvert_exporter": "python", | |
"pygments_lexer": "ipython3", | |
"version": "3.7.3" | |
} | |
}, | |
"nbformat": 4, | |
"nbformat_minor": 4 | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment