Skip to content

Instantly share code, notes, and snippets.

@puyokw

puyokw/otto_submission.ipynb

Created March 9, 2016 11:18
Show Gist options
  • Save puyokw/9092ce535f3f5f53b7e4 to your computer and use it in GitHub Desktop.
Save puyokw/9092ce535f3f5f53b7e4 to your computer and use it in GitHub Desktop.
Download ZIP
td_intern otto
Display the source blob
Display the rendered blob
Raw
otto_submission.ipynb
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"collapsed": false,
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"<div style=\"border-style: dashed; border-width: 1px;\">\n",
"<div style=\"color: #888;\"># issued at 2016-03-09T11:07:00Z</div>URL: <a href=\"https://console.treasuredata.com/jobs/54798777\" target=\"_blank\">https://console.treasuredata.com/jobs/54798777</a><br>\n",
"<div style=\"color: #888;\"># started at 2016-03-09T11:07:01Z</div><pre style=\"color: #c44;\">\n",
"** WARNING: time index filtering is not set on \n",
"** This query could be very slow as a result.\n",
"** Please see https://docs.treasuredata.com/articles/presto-performance-tuning#leveraging-time-based-partitioning</pre>\n",
"<pre>2016-03-09 11:07:06: rows pending running done / total\n",
" Stage-0: 144K 0 0 1 / 1\n",
" Stage-1: 144K 0 0 1 / 1</pre>Result size: 2,239,637 bytes<br>\n",
"Download: 2,239,637 / 2,239,637 bytes (100.00%)<br>\n",
"<div style=\"color: #888;\"># downloaded at 2016-03-09T11:07:15Z</div></div>\n"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"%matplotlib inline\n",
"\n",
"import os\n",
"import pandas as pd\n",
"import pandas_td as td\n",
"import matplotlib.pyplot as plt\n",
"\n",
"con = td.connect(apikey=os.environ['TD_API_KEY'],endpoint='https://api.treasuredata.com/')\n",
"engine = con.query_engine(database='kaggle_otto', type='presto')\n",
"submission=td.read_td_table('submission', engine, limit=144368)\n",
"del submission['time']"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Id</th>\n",
" <th>Class_1</th>\n",
" <th>Class_2</th>\n",
" <th>Class_3</th>\n",
" <th>Class_4</th>\n",
" <th>Class_5</th>\n",
" <th>Class_6</th>\n",
" <th>Class_7</th>\n",
" <th>Class_8</th>\n",
" <th>Class_9</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>0.026</td>\n",
" <td>0.204</td>\n",
" <td>0.200</td>\n",
" <td>0.532</td>\n",
" <td>0.000</td>\n",
" <td>0.016</td>\n",
" <td>0.010</td>\n",
" <td>0.008</td>\n",
" <td>0.004</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>0.018</td>\n",
" <td>0.044</td>\n",
" <td>0.036</td>\n",
" <td>0.016</td>\n",
" <td>0.004</td>\n",
" <td>0.590</td>\n",
" <td>0.008</td>\n",
" <td>0.268</td>\n",
" <td>0.016</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>0.002</td>\n",
" <td>0.000</td>\n",
" <td>0.000</td>\n",
" <td>0.000</td>\n",
" <td>0.000</td>\n",
" <td>0.996</td>\n",
" <td>0.000</td>\n",
" <td>0.002</td>\n",
" <td>0.000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
" <td>0.000</td>\n",
" <td>0.576</td>\n",
" <td>0.292</td>\n",
" <td>0.054</td>\n",
" <td>0.000</td>\n",
" <td>0.000</td>\n",
" <td>0.006</td>\n",
" <td>0.008</td>\n",
" <td>0.064</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5</td>\n",
" <td>0.104</td>\n",
" <td>0.002</td>\n",
" <td>0.006</td>\n",
" <td>0.000</td>\n",
" <td>0.000</td>\n",
" <td>0.034</td>\n",
" <td>0.020</td>\n",
" <td>0.276</td>\n",
" <td>0.558</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Id Class_1 Class_2 Class_3 Class_4 Class_5 Class_6 Class_7 Class_8 \\\n",
"0 1 0.026 0.204 0.200 0.532 0.000 0.016 0.010 0.008 \n",
"1 2 0.018 0.044 0.036 0.016 0.004 0.590 0.008 0.268 \n",
"2 3 0.002 0.000 0.000 0.000 0.000 0.996 0.000 0.002 \n",
"3 4 0.000 0.576 0.292 0.054 0.000 0.000 0.006 0.008 \n",
"4 5 0.104 0.002 0.006 0.000 0.000 0.034 0.020 0.276 \n",
"\n",
" Class_9 \n",
"0 0.004 \n",
"1 0.016 \n",
"2 0.000 \n",
"3 0.064 \n",
"4 0.558 "
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"submission.columns=['Id','Class_1','Class_2','Class_3','Class_4','Class_5','Class_6','Class_7','Class_8','Class_9']\n",
"submission.head()"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"submission.to_csv('./Downloads/otto_submission.csv', index=False)"
]
}
],
"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
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment