{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Predicting DWPC Query runtime ahead of time"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"import json\n",
"\n",
"import matplotlib.pyplot\n",
"import pandas\n",
"import numpy\n",
"import seaborn\n",
"import mpld3\n",
"\n",
"%matplotlib inline"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"path = 'data/all-features/metapaths.json'\n",
"with open(path) as fp:\n",
" metapaths = json.load(fp)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"
\n",
"
\n",
" \n",
" \n",
" | \n",
" metapath | \n",
" nonzero | \n",
" seconds_per_query | \n",
" auroc | \n",
" auroc_permuted | \n",
" delta_auroc | \n",
" pval_auroc | \n",
" length | \n",
"
\n",
" \n",
" \n",
" \n",
" 0 | \n",
" CbGaD | \n",
" 0.312 | \n",
" 0.0145 | \n",
" 0.715 | \n",
" 0.580 | \n",
" 0.13500 | \n",
" 0.000003 | \n",
" 2 | \n",
"
\n",
" \n",
" 1 | \n",
" CbGdD | \n",
" 0.149 | \n",
" 0.0136 | \n",
" 0.512 | \n",
" 0.515 | \n",
" -0.00332 | \n",
" 0.921000 | \n",
" 2 | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" metapath nonzero seconds_per_query auroc auroc_permuted delta_auroc \\\n",
"0 CbGaD 0.312 0.0145 0.715 0.580 0.13500 \n",
"1 CbGdD 0.149 0.0136 0.512 0.515 -0.00332 \n",
"\n",
" pval_auroc length \n",
"0 0.000003 2 \n",
"1 0.921000 2 "
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"auroc_df = pandas.read_table('data/all-features/auroc.tsv')\n",
"auroc_df.head(2)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"cols = ['sequential_complexity', 'optimal_join_complexity', 'midpoint_join_complexity']\n",
"\n",
"rows = [[item['abbreviation']] + [item[col] for col in cols] for item in metapaths]\n",
"complexity_df = pandas.DataFrame(rows, columns=['metapath'] + cols)\n",
"complexity_df = auroc_df.merge(complexity_df)\n",
"complexity_df['log10_seconds_per_query'] = numpy.log10(complexity_df['seconds_per_query'])"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"\n",
"
\n",
" \n",
" \n",
" | \n",
" metapath | \n",
" nonzero | \n",
" seconds_per_query | \n",
" auroc | \n",
" auroc_permuted | \n",
" delta_auroc | \n",
" pval_auroc | \n",
" length | \n",
" sequential_complexity | \n",
" optimal_join_complexity | \n",
" midpoint_join_complexity | \n",
" log10_seconds_per_query | \n",
"
\n",
" \n",
" \n",
" \n",
" 0 | \n",
" CbGaD | \n",
" 0.312 | \n",
" 0.0145 | \n",
" 0.715 | \n",
" 0.580 | \n",
" 0.13500 | \n",
" 0.000003 | \n",
" 2 | \n",
" 0.620478 | \n",
" 0.713766 | \n",
" 0.876638 | \n",
" -1.838632 | \n",
"
\n",
" \n",
" 1 | \n",
" CbGdD | \n",
" 0.149 | \n",
" 0.0136 | \n",
" 0.512 | \n",
" 0.515 | \n",
" -0.00332 | \n",
" 0.921000 | \n",
" 2 | \n",
" 1.206737 | \n",
" 0.966103 | \n",
" 0.966103 | \n",
" -1.866461 | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" metapath nonzero seconds_per_query auroc auroc_permuted delta_auroc \\\n",
"0 CbGaD 0.312 0.0145 0.715 0.580 0.13500 \n",
"1 CbGdD 0.149 0.0136 0.512 0.515 -0.00332 \n",
"\n",
" pval_auroc length sequential_complexity optimal_join_complexity \\\n",
"0 0.000003 2 0.620478 0.713766 \n",
"1 0.921000 2 1.206737 0.966103 \n",
"\n",
" midpoint_join_complexity log10_seconds_per_query \n",
"0 0.876638 -1.838632 \n",
"1 0.966103 -1.866461 "
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"complexity_df.head(2)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## sequential_complexity"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"\n",
"\n",
"\n",
""
],
"text/plain": [
""
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"matplotlib.pyplot.figure(figsize=(10, 7))\n",
"ax = seaborn.regplot('sequential_complexity', 'log10_seconds_per_query', data=complexity_df,\n",
" lowess=True, scatter_kws={'alpha': 0.5}, line_kws={'color': 'black'}, ci=False)\n",
"points = ax.collections[0]\n",
"labels = complexity_df.metapath.tolist()\n",
"tooltip = mpld3.plugins.PointLabelTooltip(points, labels)\n",
"mpld3.plugins.connect(ax.figure, tooltip)\n",
"mpld3.display()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## optimal_join_complexity"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"\n",
"\n",
"\n",
""
],
"text/plain": [
""
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"matplotlib.pyplot.figure(figsize=(10, 7))\n",
"ax = seaborn.regplot('optimal_join_complexity', 'log10_seconds_per_query', data=complexity_df,\n",
" lowess=True, scatter_kws={'alpha': 0.5}, line_kws={'color': 'black'}, ci=False)\n",
"points = ax.collections[0]\n",
"labels = complexity_df.metapath.tolist()\n",
"tooltip = mpld3.plugins.PointLabelTooltip(points, labels)\n",
"mpld3.plugins.connect(ax.figure, tooltip)\n",
"mpld3.display()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## midpoint_join_complexity"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"\n",
"\n",
"\n",
""
],
"text/plain": [
""
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"matplotlib.pyplot.figure(figsize=(10, 7))\n",
"ax = seaborn.regplot('midpoint_join_complexity', 'log10_seconds_per_query', data=complexity_df,\n",
" lowess=True, scatter_kws={'alpha': 0.5}, line_kws={'color': 'black'}, ci=False)\n",
"points = ax.collections[0]\n",
"labels = complexity_df.metapath.tolist()\n",
"tooltip = mpld3.plugins.PointLabelTooltip(points, labels)\n",
"mpld3.plugins.connect(ax.figure, tooltip)\n",
"mpld3.display()"
]
}
],
"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": "3.5.1"
}
},
"nbformat": 4,
"nbformat_minor": 0
}