Skip to content

Instantly share code, notes, and snippets.

@zonca

zonca/Five_minutes_of_pandas.ipynb

Created June 27, 2014 02:31
Show Gist options
  • Save zonca/2ba58f53fa545aa0784c to your computer and use it in GitHub Desktop.
Save zonca/2ba58f53fa545aa0784c to your computer and use it in GitHub Desktop.
Download ZIP
Display the source blob
Display the rendered blob
Raw
Five_minutes_of_pandas.ipynb
{
"metadata": {
"name": "",
"signature": "sha256:78e1e460c52cafe0a216572bddcf17b2231de3003bc16b2161cab37620866749"
},
"nbformat": 3,
"nbformat_minor": 0,
"worksheets": [
{
"cells": [
{
"cell_type": "code",
"collapsed": false,
"input": [
"!wget https://raw.github.com/amplab/datascience-sp14/master/lab2/data/wc_day6_1_sample.tar.bz2"
],
"language": "python",
"metadata": {},
"outputs": []
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"!tar xjvf wc_day6_1_sample.tar.bz2"
],
"language": "python",
"metadata": {},
"outputs": []
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"!head wc_day6_1_sample.csv"
],
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "stream",
"stream": "stdout",
"text": [
"1044,30/Apr/1998,22:46:12,/images/11104.gif,200,508\r\n",
"10871,01/May/1998,12:10:53,/images/ligne.gif,200,169\r\n",
"11012,01/May/1998,12:17:30,/english/individuals/player111503.htm,200,7027\r\n",
"11435,01/May/1998,13:15:13,/french/frntpage.htm,304,0\r\n",
"12128,01/May/1998,13:30:21,/english/images/nav_sitemap_off.gif,304,-\r\n",
"13649,01/May/1998,14:55:01,/images/hm_anime_e.gif,200,15609\r\n",
"15006,01/May/1998,16:14:32,/english/images/comp_bu_group_off.gif,200,1557\r\n",
"16366,01/May/1998,17:14:13,/images/arw_lk.gif,200,669\r\n",
"16877,01/May/1998,17:46:37,/images/32p49807.jpg,200,13856\r\n",
"17165,01/May/1998,17:58:46,/images/home_fr_button.gif,200,2140\r\n"
]
}
],
"prompt_number": 1
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"import pandas as pd\n",
"import numpy as np"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 2
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"data = pd.read_csv(\"wc_day6_1_sample.csv\", \n",
" names=['ClientID', 'Date', 'Time', 'URL', 'ResponseCode', 'Size'],\n",
" na_values=['-'])"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 3
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"type(data)"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "pyout",
"prompt_number": 4,
"text": [
"pandas.core.frame.DataFrame"
]
}
],
"prompt_number": 4
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"data.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>ClientID</th>\n",
" <th>Date</th>\n",
" <th>Time</th>\n",
" <th>URL</th>\n",
" <th>ResponseCode</th>\n",
" <th>Size</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td> 1044</td>\n",
" <td> 30/Apr/1998</td>\n",
" <td> 22:46:12</td>\n",
" <td> /images/11104.gif</td>\n",
" <td> 200</td>\n",
" <td> 508</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td> 10871</td>\n",
" <td> 01/May/1998</td>\n",
" <td> 12:10:53</td>\n",
" <td> /images/ligne.gif</td>\n",
" <td> 200</td>\n",
" <td> 169</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td> 11012</td>\n",
" <td> 01/May/1998</td>\n",
" <td> 12:17:30</td>\n",
" <td> /english/individuals/player111503.htm</td>\n",
" <td> 200</td>\n",
" <td> 7027</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td> 11435</td>\n",
" <td> 01/May/1998</td>\n",
" <td> 13:15:13</td>\n",
" <td> /french/frntpage.htm</td>\n",
" <td> 304</td>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td> 12128</td>\n",
" <td> 01/May/1998</td>\n",
" <td> 13:30:21</td>\n",
" <td> /english/images/nav_sitemap_off.gif</td>\n",
" <td> 304</td>\n",
" <td> NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows \u00d7 6 columns</p>\n",
"</div>"
],
"metadata": {},
"output_type": "pyout",
"prompt_number": 5,
"text": [
" ClientID Date Time URL \\\n",
"0 1044 30/Apr/1998 22:46:12 /images/11104.gif \n",
"1 10871 01/May/1998 12:10:53 /images/ligne.gif \n",
"2 11012 01/May/1998 12:17:30 /english/individuals/player111503.htm \n",
"3 11435 01/May/1998 13:15:13 /french/frntpage.htm \n",
"4 12128 01/May/1998 13:30:21 /english/images/nav_sitemap_off.gif \n",
"\n",
" ResponseCode Size \n",
"0 200 508 \n",
"1 200 169 \n",
"2 200 7027 \n",
"3 304 0 \n",
"4 304 NaN \n",
"\n",
"[5 rows x 6 columns]"
]
}
],
"prompt_number": 5
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"pd.DataFrame(dict(mylabel = [1, 2, 3, 4]), index=[\"a\", \"b\", \"c\", \"d\"])"
],
"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>mylabel</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>a</th>\n",
" <td> 1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>b</th>\n",
" <td> 2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>c</th>\n",
" <td> 3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>d</th>\n",
" <td> 4</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>4 rows \u00d7 1 columns</p>\n",
"</div>"
],
"metadata": {},
"output_type": "pyout",
"prompt_number": 6,
"text": [
" mylabel\n",
"a 1\n",
"b 2\n",
"c 3\n",
"d 4\n",
"\n",
"[4 rows x 1 columns]"
]
}
],
"prompt_number": 6
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"data.Size"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "pyout",
"prompt_number": 7,
"text": [
"0 508\n",
"1 169\n",
"2 7027\n",
"3 0\n",
"4 NaN\n",
"5 15609\n",
"6 1557\n",
"7 669\n",
"8 13856\n",
"9 2140\n",
"10 297\n",
"11 318\n",
"12 3541\n",
"13 4573\n",
"14 43\n",
"...\n",
"199985 0\n",
"199986 15529\n",
"199987 982\n",
"199988 279\n",
"199989 44502\n",
"199990 2861\n",
"199991 828\n",
"199992 33665\n",
"199993 211\n",
"199994 2843\n",
"199995 1740\n",
"199996 1573\n",
"199997 42591\n",
"199998 776\n",
"199999 944\n",
"Name: Size, Length: 200000, dtype: float64"
]
}
],
"prompt_number": 7
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"data.ix[:10]"
],
"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>ClientID</th>\n",
" <th>Date</th>\n",
" <th>Time</th>\n",
" <th>URL</th>\n",
" <th>ResponseCode</th>\n",
" <th>Size</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0 </th>\n",
" <td> 1044</td>\n",
" <td> 30/Apr/1998</td>\n",
" <td> 22:46:12</td>\n",
" <td> /images/11104.gif</td>\n",
" <td> 200</td>\n",
" <td> 508</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1 </th>\n",
" <td> 10871</td>\n",
" <td> 01/May/1998</td>\n",
" <td> 12:10:53</td>\n",
" <td> /images/ligne.gif</td>\n",
" <td> 200</td>\n",
" <td> 169</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2 </th>\n",
" <td> 11012</td>\n",
" <td> 01/May/1998</td>\n",
" <td> 12:17:30</td>\n",
" <td> /english/individuals/player111503.htm</td>\n",
" <td> 200</td>\n",
" <td> 7027</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3 </th>\n",
" <td> 11435</td>\n",
" <td> 01/May/1998</td>\n",
" <td> 13:15:13</td>\n",
" <td> /french/frntpage.htm</td>\n",
" <td> 304</td>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4 </th>\n",
" <td> 12128</td>\n",
" <td> 01/May/1998</td>\n",
" <td> 13:30:21</td>\n",
" <td> /english/images/nav_sitemap_off.gif</td>\n",
" <td> 304</td>\n",
" <td> NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5 </th>\n",
" <td> 13649</td>\n",
" <td> 01/May/1998</td>\n",
" <td> 14:55:01</td>\n",
" <td> /images/hm_anime_e.gif</td>\n",
" <td> 200</td>\n",
" <td> 15609</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6 </th>\n",
" <td> 15006</td>\n",
" <td> 01/May/1998</td>\n",
" <td> 16:14:32</td>\n",
" <td> /english/images/comp_bu_group_off.gif</td>\n",
" <td> 200</td>\n",
" <td> 1557</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7 </th>\n",
" <td> 16366</td>\n",
" <td> 01/May/1998</td>\n",
" <td> 17:14:13</td>\n",
" <td> /images/arw_lk.gif</td>\n",
" <td> 200</td>\n",
" <td> 669</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8 </th>\n",
" <td> 16877</td>\n",
" <td> 01/May/1998</td>\n",
" <td> 17:46:37</td>\n",
" <td> /images/32p49807.jpg</td>\n",
" <td> 200</td>\n",
" <td> 13856</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9 </th>\n",
" <td> 17165</td>\n",
" <td> 01/May/1998</td>\n",
" <td> 17:58:46</td>\n",
" <td> /images/home_fr_button.gif</td>\n",
" <td> 200</td>\n",
" <td> 2140</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td> 17251</td>\n",
" <td> 01/May/1998</td>\n",
" <td> 18:06:07</td>\n",
" <td> /images/s102438.gif</td>\n",
" <td> 200</td>\n",
" <td> 297</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>11 rows \u00d7 6 columns</p>\n",
"</div>"
],
"metadata": {},
"output_type": "pyout",
"prompt_number": 8,
"text": [
" ClientID Date Time URL \\\n",
"0 1044 30/Apr/1998 22:46:12 /images/11104.gif \n",
"1 10871 01/May/1998 12:10:53 /images/ligne.gif \n",
"2 11012 01/May/1998 12:17:30 /english/individuals/player111503.htm \n",
"3 11435 01/May/1998 13:15:13 /french/frntpage.htm \n",
"4 12128 01/May/1998 13:30:21 /english/images/nav_sitemap_off.gif \n",
"5 13649 01/May/1998 14:55:01 /images/hm_anime_e.gif \n",
"6 15006 01/May/1998 16:14:32 /english/images/comp_bu_group_off.gif \n",
"7 16366 01/May/1998 17:14:13 /images/arw_lk.gif \n",
"8 16877 01/May/1998 17:46:37 /images/32p49807.jpg \n",
"9 17165 01/May/1998 17:58:46 /images/home_fr_button.gif \n",
"10 17251 01/May/1998 18:06:07 /images/s102438.gif \n",
"\n",
" ResponseCode Size \n",
"0 200 508 \n",
"1 200 169 \n",
"2 200 7027 \n",
"3 304 0 \n",
"4 304 NaN \n",
"5 200 15609 \n",
"6 200 1557 \n",
"7 200 669 \n",
"8 200 13856 \n",
"9 200 2140 \n",
"10 200 297 \n",
"\n",
"[11 rows x 6 columns]"
]
}
],
"prompt_number": 8
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"len(data[data.Date == \"01/May/1998\"])"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "pyout",
"prompt_number": 9,
"text": [
"183303"
]
}
],
"prompt_number": 9
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"data[\"CompressedSize\"] = data.Size * 0.7"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 10
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"data.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>ClientID</th>\n",
" <th>Date</th>\n",
" <th>Time</th>\n",
" <th>URL</th>\n",
" <th>ResponseCode</th>\n",
" <th>Size</th>\n",
" <th>CompressedSize</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td> 1044</td>\n",
" <td> 30/Apr/1998</td>\n",
" <td> 22:46:12</td>\n",
" <td> /images/11104.gif</td>\n",
" <td> 200</td>\n",
" <td> 508</td>\n",
" <td> 355.6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td> 10871</td>\n",
" <td> 01/May/1998</td>\n",
" <td> 12:10:53</td>\n",
" <td> /images/ligne.gif</td>\n",
" <td> 200</td>\n",
" <td> 169</td>\n",
" <td> 118.3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td> 11012</td>\n",
" <td> 01/May/1998</td>\n",
" <td> 12:17:30</td>\n",
" <td> /english/individuals/player111503.htm</td>\n",
" <td> 200</td>\n",
" <td> 7027</td>\n",
" <td> 4918.9</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td> 11435</td>\n",
" <td> 01/May/1998</td>\n",
" <td> 13:15:13</td>\n",
" <td> /french/frntpage.htm</td>\n",
" <td> 304</td>\n",
" <td> 0</td>\n",
" <td> 0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td> 12128</td>\n",
" <td> 01/May/1998</td>\n",
" <td> 13:30:21</td>\n",
" <td> /english/images/nav_sitemap_off.gif</td>\n",
" <td> 304</td>\n",
" <td> NaN</td>\n",
" <td> NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows \u00d7 7 columns</p>\n",
"</div>"
],
"metadata": {},
"output_type": "pyout",
"prompt_number": 11,
"text": [
" ClientID Date Time URL \\\n",
"0 1044 30/Apr/1998 22:46:12 /images/11104.gif \n",
"1 10871 01/May/1998 12:10:53 /images/ligne.gif \n",
"2 11012 01/May/1998 12:17:30 /english/individuals/player111503.htm \n",
"3 11435 01/May/1998 13:15:13 /french/frntpage.htm \n",
"4 12128 01/May/1998 13:30:21 /english/images/nav_sitemap_off.gif \n",
"\n",
" ResponseCode Size CompressedSize \n",
"0 200 508 355.6 \n",
"1 200 169 118.3 \n",
"2 200 7027 4918.9 \n",
"3 304 0 0.0 \n",
"4 304 NaN NaN \n",
"\n",
"[5 rows x 7 columns]"
]
}
],
"prompt_number": 11
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"data.dropna().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>ClientID</th>\n",
" <th>Date</th>\n",
" <th>Time</th>\n",
" <th>URL</th>\n",
" <th>ResponseCode</th>\n",
" <th>Size</th>\n",
" <th>CompressedSize</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td> 1044</td>\n",
" <td> 30/Apr/1998</td>\n",
" <td> 22:46:12</td>\n",
" <td> /images/11104.gif</td>\n",
" <td> 200</td>\n",
" <td> 508</td>\n",
" <td> 355.6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td> 10871</td>\n",
" <td> 01/May/1998</td>\n",
" <td> 12:10:53</td>\n",
" <td> /images/ligne.gif</td>\n",
" <td> 200</td>\n",
" <td> 169</td>\n",
" <td> 118.3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td> 11012</td>\n",
" <td> 01/May/1998</td>\n",
" <td> 12:17:30</td>\n",
" <td> /english/individuals/player111503.htm</td>\n",
" <td> 200</td>\n",
" <td> 7027</td>\n",
" <td> 4918.9</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td> 11435</td>\n",
" <td> 01/May/1998</td>\n",
" <td> 13:15:13</td>\n",
" <td> /french/frntpage.htm</td>\n",
" <td> 304</td>\n",
" <td> 0</td>\n",
" <td> 0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td> 13649</td>\n",
" <td> 01/May/1998</td>\n",
" <td> 14:55:01</td>\n",
" <td> /images/hm_anime_e.gif</td>\n",
" <td> 200</td>\n",
" <td> 15609</td>\n",
" <td> 10926.3</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows \u00d7 7 columns</p>\n",
"</div>"
],
"metadata": {},
"output_type": "pyout",
"prompt_number": 12,
"text": [
" ClientID Date Time URL \\\n",
"0 1044 30/Apr/1998 22:46:12 /images/11104.gif \n",
"1 10871 01/May/1998 12:10:53 /images/ligne.gif \n",
"2 11012 01/May/1998 12:17:30 /english/individuals/player111503.htm \n",
"3 11435 01/May/1998 13:15:13 /french/frntpage.htm \n",
"5 13649 01/May/1998 14:55:01 /images/hm_anime_e.gif \n",
"\n",
" ResponseCode Size CompressedSize \n",
"0 200 508 355.6 \n",
"1 200 169 118.3 \n",
"2 200 7027 4918.9 \n",
"3 304 0 0.0 \n",
"5 200 15609 10926.3 \n",
"\n",
"[5 rows x 7 columns]"
]
}
],
"prompt_number": 12
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"data['DateTime'] = pd.to_datetime(data.apply(lambda row: row['Date'] + ' ' + row['Time'], axis=1))"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 13
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"data.DateTime.head()"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "pyout",
"prompt_number": 14,
"text": [
"0 1998-04-30 22:46:12\n",
"1 1998-05-01 12:10:53\n",
"2 1998-05-01 12:17:30\n",
"3 1998-05-01 13:15:13\n",
"4 1998-05-01 13:30:21\n",
"Name: DateTime, dtype: datetime64[ns]"
]
}
],
"prompt_number": 14
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"hour = data.DateTime.map(lambda x: x.hour)"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 15
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"hour"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "pyout",
"prompt_number": 16,
"text": [
"0 22\n",
"1 12\n",
"2 12\n",
"3 13\n",
"4 13\n",
"5 14\n",
"6 16\n",
"7 17\n",
"8 17\n",
"9 17\n",
"10 18\n",
"11 12\n",
"12 18\n",
"13 19\n",
"14 19\n",
"...\n",
"199985 22\n",
"199986 9\n",
"199987 16\n",
"199988 16\n",
"199989 11\n",
"199990 16\n",
"199991 13\n",
"199992 14\n",
"199993 23\n",
"199994 23\n",
"199995 15\n",
"199996 15\n",
"199997 8\n",
"199998 18\n",
"199999 19\n",
"Name: DateTime, Length: 200000, dtype: int64"
]
}
],
"prompt_number": 16
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"hour_grouped = data.groupby(hour)\n",
"hour_grouped.ngroups"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "pyout",
"prompt_number": 17,
"text": [
"24"
]
}
],
"prompt_number": 17
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"%matplotlib inline"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 18
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"hour_grouped.Size.count().plot();"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "display_data",
"png": "iVBORw0KGgoAAAANSUhEUgAAAYQAAAEPCAYAAABCyrPIAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nYII=\n",
"text": [
"<matplotlib.figure.Figure at 0x6127910>"
]
}
],
"prompt_number": 19
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"hour_grouped.Size.sum().plot();"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "display_data",
"png": "iVBORw0KGgoAAAANSUhEUgAAAXUAAAEVCAYAAAAfCXWSAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
"text": [
"<matplotlib.figure.Figure at 0x4dd8110>"
]
}
],
"prompt_number": 20
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"hour_grouped.Size.agg(np.sum).plot();"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "display_data",
"png": "iVBORw0KGgoAAAANSUhEUgAAAXUAAAEVCAYAAAAfCXWSAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
"text": [
"<matplotlib.figure.Figure at 0x505eb50>"
]
}
],
"prompt_number": 21
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"data.Size.hist(bins=100, log=True);"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "display_data",
"png": "iVBORw0KGgoAAAANSUhEUgAAAYkAAAEDCAYAAADA9vgDAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nA6vnJqyzGahAAAAAAElFTkSuQmCC\n",
"text": [
"<matplotlib.figure.Figure at 0x4dccf50>"
]
}
],
"prompt_number": 22
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"data.Size[data.URL.map(lambda x:x.endswith(\"jpg\"))].hist(bins=100, log=True);"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "display_data",
"png": "iVBORw0KGgoAAAANSUhEUgAAAYMAAAEDCAYAAADX1GjKAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
"text": [
"<matplotlib.figure.Figure at 0x3f8c8d0>"
]
}
],
"prompt_number": 23
},
{
"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