Skip to content

Instantly share code, notes, and snippets.

@michaelaye
Created March 6, 2013 06:21
Show Gist options
  • Save michaelaye/5097158 to your computer and use it in GitHub Desktop.
Save michaelaye/5097158 to your computer and use it in GitHub Desktop.
Display the source blob
Display the rendered blob
Raw
{
"metadata": {
"name": "none selection"
},
"nbformat": 3,
"nbformat_minor": 0,
"worksheets": [
{
"cells": [
{
"cell_type": "code",
"collapsed": false,
"input": [
"import pandas as pd"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 1
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"pd.__version__"
],
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "pyout",
"prompt_number": 2,
"text": [
"'0.11.0.dev-3790f16'"
]
}
],
"prompt_number": 2
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"store = pd.HDFStore('/Users/maye/data/marszoo/planet_four_classifications_2013-02-23.h5')"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 3
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"store"
],
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "pyout",
"prompt_number": 4,
"text": [
"<class 'pandas.io.pytables.HDFStore'>\n",
"File path: /Users/maye/data/marszoo/planet_four_classifications_2013-02-23.h5\n",
"/df frame_table (typ->appendable,nrows->9275468,ncols->17,indexers->[index],dc->[image_id,image_name,user_name,marking])"
]
}
],
"prompt_number": 4
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"store.select('df','marking!=none').head()"
],
"language": "python",
"metadata": {},
"outputs": [
{
"html": [
"<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>classification_id</th>\n",
" <th>created_at</th>\n",
" <th>image_id</th>\n",
" <th>image_name</th>\n",
" <th>user_name</th>\n",
" <th>marking</th>\n",
" <th>x_tile</th>\n",
" <th>y_tile</th>\n",
" <th>x</th>\n",
" <th>y</th>\n",
" <th>image_x</th>\n",
" <th>image_y</th>\n",
" <th>radius_1</th>\n",
" <th>radius_2</th>\n",
" <th>distance</th>\n",
" <th>angle</th>\n",
" <th>spread</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>23</th>\n",
" <td> 50eace09e39956220600081f</td>\n",
" <td> 2013-01-07 13:30:49</td>\n",
" <td> APF00008jy</td>\n",
" <td> ESP_012265_0950</td>\n",
" <td> lukesmith</td>\n",
" <td> none</td>\n",
" <td> 5</td>\n",
" <td> 2</td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" </tr>\n",
" <tr>\n",
" <th>41</th>\n",
" <td> 50eaf01ae3995621fc00093e</td>\n",
" <td> 2013-01-07 15:56:10</td>\n",
" <td> APF00007su</td>\n",
" <td> ESP_012604_0965</td>\n",
" <td> not-logged-in</td>\n",
" <td> none</td>\n",
" <td> 1</td>\n",
" <td> 2</td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" </tr>\n",
" <tr>\n",
" <th>42</th>\n",
" <td> 50eaf01ee3995621d300010a</td>\n",
" <td> 2013-01-07 15:56:14</td>\n",
" <td> APF00003bv</td>\n",
" <td> ESP_011460_0980</td>\n",
" <td> not-logged-in</td>\n",
" <td> none</td>\n",
" <td> 2</td>\n",
" <td> 1</td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" </tr>\n",
" <tr>\n",
" <th>44</th>\n",
" <td> 50eaf03a45d7e142f50000cb</td>\n",
" <td> 2013-01-07 15:56:42</td>\n",
" <td> APF000030j</td>\n",
" <td> ESP_011900_0985</td>\n",
" <td> not-logged-in</td>\n",
" <td> none</td>\n",
" <td> 5</td>\n",
" <td> 1</td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" </tr>\n",
" <tr>\n",
" <th>45</th>\n",
" <td> 50eaf03ce3995621d3000117</td>\n",
" <td> 2013-01-07 15:56:44</td>\n",
" <td> APF0000p3r</td>\n",
" <td> ESP_020150_0950</td>\n",
" <td> not-logged-in</td>\n",
" <td> none</td>\n",
" <td> 7</td>\n",
" <td> 1</td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"output_type": "pyout",
"prompt_number": 6,
"text": [
" classification_id created_at image_id image_name \\\n",
"23 50eace09e39956220600081f 2013-01-07 13:30:49 APF00008jy ESP_012265_0950 \n",
"41 50eaf01ae3995621fc00093e 2013-01-07 15:56:10 APF00007su ESP_012604_0965 \n",
"42 50eaf01ee3995621d300010a 2013-01-07 15:56:14 APF00003bv ESP_011460_0980 \n",
"44 50eaf03a45d7e142f50000cb 2013-01-07 15:56:42 APF000030j ESP_011900_0985 \n",
"45 50eaf03ce3995621d3000117 2013-01-07 15:56:44 APF0000p3r ESP_020150_0950 \n",
"\n",
" user_name marking x_tile y_tile x y image_x image_y radius_1 radius_2 distance \\\n",
"23 lukesmith none 5 2 \n",
"41 not-logged-in none 1 2 \n",
"42 not-logged-in none 2 1 \n",
"44 not-logged-in none 5 1 \n",
"45 not-logged-in none 7 1 \n",
"\n",
" angle spread \n",
"23 \n",
"41 \n",
"42 \n",
"44 \n",
"45 "
]
}
],
"prompt_number": 6
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"store.select('df',pd.Term('marking','!=','none')).head()"
],
"language": "python",
"metadata": {},
"outputs": [
{
"html": [
"<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>classification_id</th>\n",
" <th>created_at</th>\n",
" <th>image_id</th>\n",
" <th>image_name</th>\n",
" <th>user_name</th>\n",
" <th>marking</th>\n",
" <th>x_tile</th>\n",
" <th>y_tile</th>\n",
" <th>x</th>\n",
" <th>y</th>\n",
" <th>image_x</th>\n",
" <th>image_y</th>\n",
" <th>radius_1</th>\n",
" <th>radius_2</th>\n",
" <th>distance</th>\n",
" <th>angle</th>\n",
" <th>spread</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>23</th>\n",
" <td> 50eace09e39956220600081f</td>\n",
" <td> 2013-01-07 13:30:49</td>\n",
" <td> APF00008jy</td>\n",
" <td> ESP_012265_0950</td>\n",
" <td> lukesmith</td>\n",
" <td> none</td>\n",
" <td> 5</td>\n",
" <td> 2</td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" </tr>\n",
" <tr>\n",
" <th>41</th>\n",
" <td> 50eaf01ae3995621fc00093e</td>\n",
" <td> 2013-01-07 15:56:10</td>\n",
" <td> APF00007su</td>\n",
" <td> ESP_012604_0965</td>\n",
" <td> not-logged-in</td>\n",
" <td> none</td>\n",
" <td> 1</td>\n",
" <td> 2</td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" </tr>\n",
" <tr>\n",
" <th>42</th>\n",
" <td> 50eaf01ee3995621d300010a</td>\n",
" <td> 2013-01-07 15:56:14</td>\n",
" <td> APF00003bv</td>\n",
" <td> ESP_011460_0980</td>\n",
" <td> not-logged-in</td>\n",
" <td> none</td>\n",
" <td> 2</td>\n",
" <td> 1</td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" </tr>\n",
" <tr>\n",
" <th>44</th>\n",
" <td> 50eaf03a45d7e142f50000cb</td>\n",
" <td> 2013-01-07 15:56:42</td>\n",
" <td> APF000030j</td>\n",
" <td> ESP_011900_0985</td>\n",
" <td> not-logged-in</td>\n",
" <td> none</td>\n",
" <td> 5</td>\n",
" <td> 1</td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" </tr>\n",
" <tr>\n",
" <th>45</th>\n",
" <td> 50eaf03ce3995621d3000117</td>\n",
" <td> 2013-01-07 15:56:44</td>\n",
" <td> APF0000p3r</td>\n",
" <td> ESP_020150_0950</td>\n",
" <td> not-logged-in</td>\n",
" <td> none</td>\n",
" <td> 7</td>\n",
" <td> 1</td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"output_type": "pyout",
"prompt_number": 7,
"text": [
" classification_id created_at image_id image_name \\\n",
"23 50eace09e39956220600081f 2013-01-07 13:30:49 APF00008jy ESP_012265_0950 \n",
"41 50eaf01ae3995621fc00093e 2013-01-07 15:56:10 APF00007su ESP_012604_0965 \n",
"42 50eaf01ee3995621d300010a 2013-01-07 15:56:14 APF00003bv ESP_011460_0980 \n",
"44 50eaf03a45d7e142f50000cb 2013-01-07 15:56:42 APF000030j ESP_011900_0985 \n",
"45 50eaf03ce3995621d3000117 2013-01-07 15:56:44 APF0000p3r ESP_020150_0950 \n",
"\n",
" user_name marking x_tile y_tile x y image_x image_y radius_1 radius_2 distance \\\n",
"23 lukesmith none 5 2 \n",
"41 not-logged-in none 1 2 \n",
"42 not-logged-in none 2 1 \n",
"44 not-logged-in none 5 1 \n",
"45 not-logged-in none 7 1 \n",
"\n",
" angle spread \n",
"23 \n",
"41 \n",
"42 \n",
"44 \n",
"45 "
]
}
],
"prompt_number": 7
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"store.select('df',['marking','!=','none']).head()"
],
"language": "python",
"metadata": {},
"outputs": [
{
"html": [
"<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>classification_id</th>\n",
" <th>created_at</th>\n",
" <th>image_id</th>\n",
" <th>image_name</th>\n",
" <th>user_name</th>\n",
" <th>marking</th>\n",
" <th>x_tile</th>\n",
" <th>y_tile</th>\n",
" <th>x</th>\n",
" <th>y</th>\n",
" <th>image_x</th>\n",
" <th>image_y</th>\n",
" <th>radius_1</th>\n",
" <th>radius_2</th>\n",
" <th>distance</th>\n",
" <th>angle</th>\n",
" <th>spread</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>23</th>\n",
" <td> 50eace09e39956220600081f</td>\n",
" <td> 2013-01-07 13:30:49</td>\n",
" <td> APF00008jy</td>\n",
" <td> ESP_012265_0950</td>\n",
" <td> lukesmith</td>\n",
" <td> none</td>\n",
" <td> 5</td>\n",
" <td> 2</td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" </tr>\n",
" <tr>\n",
" <th>41</th>\n",
" <td> 50eaf01ae3995621fc00093e</td>\n",
" <td> 2013-01-07 15:56:10</td>\n",
" <td> APF00007su</td>\n",
" <td> ESP_012604_0965</td>\n",
" <td> not-logged-in</td>\n",
" <td> none</td>\n",
" <td> 1</td>\n",
" <td> 2</td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" </tr>\n",
" <tr>\n",
" <th>42</th>\n",
" <td> 50eaf01ee3995621d300010a</td>\n",
" <td> 2013-01-07 15:56:14</td>\n",
" <td> APF00003bv</td>\n",
" <td> ESP_011460_0980</td>\n",
" <td> not-logged-in</td>\n",
" <td> none</td>\n",
" <td> 2</td>\n",
" <td> 1</td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" </tr>\n",
" <tr>\n",
" <th>44</th>\n",
" <td> 50eaf03a45d7e142f50000cb</td>\n",
" <td> 2013-01-07 15:56:42</td>\n",
" <td> APF000030j</td>\n",
" <td> ESP_011900_0985</td>\n",
" <td> not-logged-in</td>\n",
" <td> none</td>\n",
" <td> 5</td>\n",
" <td> 1</td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" </tr>\n",
" <tr>\n",
" <th>45</th>\n",
" <td> 50eaf03ce3995621d3000117</td>\n",
" <td> 2013-01-07 15:56:44</td>\n",
" <td> APF0000p3r</td>\n",
" <td> ESP_020150_0950</td>\n",
" <td> not-logged-in</td>\n",
" <td> none</td>\n",
" <td> 7</td>\n",
" <td> 1</td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" <td> </td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"output_type": "pyout",
"prompt_number": 8,
"text": [
" classification_id created_at image_id image_name \\\n",
"23 50eace09e39956220600081f 2013-01-07 13:30:49 APF00008jy ESP_012265_0950 \n",
"41 50eaf01ae3995621fc00093e 2013-01-07 15:56:10 APF00007su ESP_012604_0965 \n",
"42 50eaf01ee3995621d300010a 2013-01-07 15:56:14 APF00003bv ESP_011460_0980 \n",
"44 50eaf03a45d7e142f50000cb 2013-01-07 15:56:42 APF000030j ESP_011900_0985 \n",
"45 50eaf03ce3995621d3000117 2013-01-07 15:56:44 APF0000p3r ESP_020150_0950 \n",
"\n",
" user_name marking x_tile y_tile x y image_x image_y radius_1 radius_2 distance \\\n",
"23 lukesmith none 5 2 \n",
"41 not-logged-in none 1 2 \n",
"42 not-logged-in none 2 1 \n",
"44 not-logged-in none 5 1 \n",
"45 not-logged-in none 7 1 \n",
"\n",
" angle spread \n",
"23 \n",
"41 \n",
"42 \n",
"44 \n",
"45 "
]
}
],
"prompt_number": 8
},
{
"cell_type": "code",
"collapsed": false,
"input": [],
"language": "python",
"metadata": {},
"outputs": []
}
],
"metadata": {}
}
]
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment