From 073aa6f75b8366c2517f288fc9df99651401e58f Mon Sep 17 00:00:00 2001 From: Xiaochuang Han Date: Mon, 23 Oct 2017 17:14:49 -0400 Subject: [PATCH] tut4 --- .../mongodb_tut4-checkpoint.ipynb | 2177 +++++++++++++++++ tut3.py => mongodb_tut3.py | 0 mongodb_tut4.ipynb | 2177 +++++++++++++++++ 3 files changed, 4354 insertions(+) create mode 100644 .ipynb_checkpoints/mongodb_tut4-checkpoint.ipynb rename tut3.py => mongodb_tut3.py (100%) create mode 100644 mongodb_tut4.ipynb diff --git a/.ipynb_checkpoints/mongodb_tut4-checkpoint.ipynb b/.ipynb_checkpoints/mongodb_tut4-checkpoint.ipynb new file mode 100644 index 0000000..80735d6 --- /dev/null +++ b/.ipynb_checkpoints/mongodb_tut4-checkpoint.ipynb @@ -0,0 +1,2177 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": { + "deletable": true, + "editable": true + }, + "source": [ + "## Setup" + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": { + "collapsed": true, + "deletable": true, + "editable": true + }, + "outputs": [], + "source": [ + "from pymongo import MongoClient\n", + "\n", + "db = MongoClient('mongodb://143.215.138.132:27017')['big_data']" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "deletable": true, + "editable": true + }, + "source": [ + "## Find Prolific Tweet Writers\n", + "\n", + "Last time: Fetch all tweets, build a counter (dictionary) locally, and sort locally.\n", + "\n", + "This time: Make counting and sorting queries to the server, and then fetch data." + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": { + "collapsed": true, + "deletable": true, + "editable": true + }, + "outputs": [], + "source": [ + "group = {'$group': {'_id': '$author_name', 'count': {'$sum': 1}}}\n", + "\n", + "sort = {'$sort': {'count': -1}}\n", + "\n", + "limit = {'$limit': 1000}\n", + "\n", + "pipeline = [group, sort, limit]" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": { + "collapsed": false, + "deletable": true, + "editable": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{u'count': 1289, u'_id': u'.'}\n", + "{u'count': 1135, u'_id': u'511 New York'}\n", + "{u'count': 686, u'_id': u'\\u3164'}\n", + "{u'count': 538, u'_id': u'SF311 Reports'}\n", + "{u'count': 532, u'_id': u'SONIC Jobs'}\n", + "{u'count': 530, u'_id': u'511NY - New Jersey'}\n", + "{u'count': 522, u'_id': u'B'}\n", + "{u'count': 504, u'_id': u'511 NYC Area'}\n", + "{u'count': 417, u'_id': u'\\u2728'}\n", + "{u'count': 375, u'_id': u'lex'}\n", + "{u'count': 372, u'_id': u'Chris'}\n", + "{u'count': 364, u'_id': u'J'}\n", + "{u'count': 340, u'_id': u'Alex'}\n", + "{u'count': 336, u'_id': u'\\U0001f451'}\n", + "{u'count': 327, u'_id': u'em'}\n", + "{u'count': 323, u'_id': u'Michael'}\n", + "{u'count': 318, u'_id': u'Mike'}\n", + "{u'count': 315, u'_id': u'ash'}\n", + "{u'count': 314, u'_id': u'Jobs at VA'}\n", + "{u'count': 309, u'_id': u'Panera Careers'}\n", + "{u'count': 309, u'_id': u'Trendinalia USA'}\n", + "{u'count': 291, u'_id': u'Kindred Jobs'}\n", + "{u'count': 291, u'_id': u'Sarah'}\n", + "{u'count': 290, u'_id': u'Ryan'}\n", + "{u'count': 287, u'_id': u'Speedway Jobs'}\n", + "{u'count': 285, u'_id': u'Matt'}\n", + "{u'count': 285, u'_id': u'Lauren'}\n", + "{u'count': 273, u'_id': u'Emily'}\n", + "{u'count': 269, u'_id': u'SHC Careers'}\n", + "{u'count': 268, u'_id': u'Jay'}\n", + "{u'count': 267, u'_id': u'TMJ-LAX HRTA Jobs'}\n", + "{u'count': 266, u'_id': u'Lex'}\n", + "{u'count': 262, u'_id': u'CVS Health Jobs'}\n", + "{u'count': 260, u'_id': u'Hannah'}\n", + "{u'count': 260, u'_id': u'David'}\n", + "{u'count': 257, u'_id': u'CUBE Live'}\n", + "{u'count': 256, u'_id': u'Jordan'}\n", + "{u'count': 256, u'_id': u'Em'}\n", + "{u'count': 256, u'_id': u'Jess'}\n", + "{u'count': 253, u'_id': u'D'}\n", + "{u'count': 253, u'_id': u'Ashley'}\n", + "{u'count': 252, u'_id': u'alex'}\n", + "{u'count': 251, u'_id': u'Sam'}\n", + "{u'count': 249, u'_id': u'Taylor'}\n", + "{u'count': 249, u'_id': u'b'}\n", + "{u'count': 246, u'_id': u'Tay'}\n", + "{u'count': 241, u'_id': u'Justin'}\n", + "{u'count': 240, u'_id': u'Daniel'}\n", + "{u'count': 240, u'_id': u'sarah'}\n", + "{u'count': 238, u'_id': u'Chicago Hospitality'}\n", + "{u'count': 235, u'_id': u'Katie'}\n", + "{u'count': 234, u'_id': u'Nick'}\n", + "{u'count': 234, u'_id': u'T'}\n", + "{u'count': 232, u'_id': u'\\U0001f339'}\n", + "{u'count': 230, u'_id': u'K'}\n", + "{u'count': 228, u'_id': u'Anthony'}\n", + "{u'count': 228, u'_id': u'John'}\n", + "{u'count': 225, u'_id': u'Weather'}\n", + "{u'count': 225, u'_id': u'RH Finance Jobs'}\n", + "{u'count': 223, u'_id': u'emily'}\n", + "{u'count': 220, u'_id': u'TPS Calls'}\n", + "{u'count': 220, u'_id': u'OfficeTeam Jobs'}\n", + "{u'count': 219, u'_id': u'sam'}\n", + "{u'count': 218, u'_id': u'Clayton, NC Weather'}\n", + "{u'count': 217, u'_id': u'IASIS Careers'}\n", + "{u'count': 215, u'_id': u'Brandon'}\n", + "{u'count': 214, u'_id': u'Jason'}\n", + "{u'count': 214, u'_id': u'Josh'}\n", + "{u'count': 213, u'_id': u'Megan'}\n", + "{u'count': 212, u'_id': u'TMJ-USA Cosmo Jobs'}\n", + "{u'count': 210, u'_id': u'Nicole'}\n", + "{u'count': 210, u'_id': u'Jake'}\n", + "{u'count': 208, u'_id': u'Ulta Beauty Jobs'}\n", + "{u'count': 208, u'_id': u'jess'}\n", + "{u'count': 207, u'_id': u'Tyler'}\n", + "{u'count': 207, u'_id': u'Ash'}\n", + "{u'count': 204, u'_id': u'BOS:311 Reports'}\n", + "{u'count': 203, u'_id': u'Join BAYADA'}\n", + "{u'count': 200, u'_id': u'TMJ- HOU Health Jobs'}\n", + "{u'count': 200, u'_id': u'Andrew'}\n", + "{u'count': 196, u'_id': u'Accountemps Jobs'}\n", + "{u'count': 196, u'_id': u'DollarGeneralCareers'}\n", + "{u'count': 195, u'_id': u'Sunrise Careers'}\n", + "{u'count': 194, u'_id': u'tay'}\n", + "{u'count': 193, u'_id': u'Samantha'}\n", + "{u'count': 192, u'_id': u'hannah'}\n", + "{u'count': 191, u'_id': u'GDKN'}\n", + "{u'count': 190, u'_id': u'taylor'}\n", + "{u'count': 188, u'_id': u'j'}\n", + "{u'count': 188, u'_id': u'Destination Jobs'}\n", + "{u'count': 187, u'_id': u'TMJ- DFW Health Jobs'}\n", + "{u'count': 185, u'_id': u'G'}\n", + "{u'count': 184, u'_id': u'\\u2661'}\n", + "{u'count': 184, u'_id': u'Brian'}\n", + "{u'count': 182, u'_id': u'James'}\n", + "{u'count': 180, u'_id': u'A'}\n", + "{u'count': 180, u'_id': u'Amanda'}\n", + "{u'count': 180, u'_id': u'Stephanie'}\n", + "{u'count': 176, u'_id': u'TMJ-HOU Nursing Jobs'}\n", + "{u'count': 176, u'_id': u'lauren'}\n", + "{u'count': 175, u'_id': u'Nevada City Weather'}\n", + "{u'count': 173, u'_id': u'Eric'}\n", + "{u'count': 172, u'_id': u'syd'}\n", + "{u'count': 172, u'_id': u'Rachel'}\n", + "{u'count': 172, u'_id': u'Kevin'}\n", + "{u'count': 172, u'_id': u'Alexis'}\n", + "{u'count': 172, u'_id': u'mads'}\n", + "{u'count': 172, u'_id': u'Austin'}\n", + "{u'count': 168, u'_id': u'liv'}\n", + "{u'count': 167, u'_id': u\"Love's Jobs\"}\n", + "{u'count': 165, u'_id': u'Joe'}\n", + "{u'count': 164, u'_id': u'511NY - Catskills'}\n", + "{u'count': 162, u'_id': u'Alyssa'}\n", + "{u'count': 162, u'_id': u'kayla'}\n", + "{u'count': 161, u'_id': u'ashley'}\n", + "{u'count': 161, u'_id': u'Zach'}\n", + "{u'count': 160, u'_id': u'Laura'}\n", + "{u'count': 160, u'_id': u'alyssa'}\n", + "{u'count': 160, u'_id': u'Morgan'}\n", + "{u'count': 159, u'_id': u'Mary'}\n", + "{u'count': 159, u'_id': u'E'}\n", + "{u'count': 159, u'_id': u'M'}\n", + "{u'count': 158, u'_id': u'Kate'}\n", + "{u'count': 158, u'_id': u'Michelle'}\n", + "{u'count': 158, u'_id': u'Bri'}\n", + "{u'count': 158, u'_id': u'Mercy Jobs'}\n", + "{u'count': 157, u'_id': u'Virtual Jukebox'}\n", + "{u'count': 157, u'_id': u'Jessica'}\n", + "{u'count': 156, u'_id': u'James Neva'}\n", + "{u'count': 156, u'_id': u'bri'}\n", + "{u'count': 155, u'_id': u'AvalonBay Jobs'}\n", + "{u'count': 153, u'_id': u'CompassUSAJobBoard'}\n", + "{u'count': 152, u'_id': u'Total Traffic NYC'}\n", + "{u'count': 152, u'_id': u'Regions Bank'}\n", + "{u'count': 151, u'_id': u'\\U0001f940'}\n", + "{u'count': 150, u'_id': u'Cintas Careers'}\n", + "{u'count': 149, u'_id': u'Meg'}\n", + "{u'count': 148, u'_id': u'Noodles Careers'}\n", + "{u'count': 147, u'_id': u'HMSHost Jobs'}\n", + "{u'count': 147, u'_id': u'Dan'}\n", + "{u'count': 147, u'_id': u'Kayla'}\n", + "{u'count': 146, u'_id': u\"BJ's Restaurants\"}\n", + "{u'count': 146, u'_id': u'LA Healthcare Jobs'}\n", + "{u'count': 146, u'_id': u'B.'}\n", + "{u'count': 145, u'_id': u'Scott'}\n", + "{u'count': 143, u'_id': u'Steve'}\n", + "{u'count': 143, u'_id': u'Nordstrom Jobs'}\n", + "{u'count': 143, u'_id': u'Baltimore City 311'}\n", + "{u'count': 142, u'_id': u'Denver Hospitality'}\n", + "{u'count': 142, u'_id': u'Mark'}\n", + "{u'count': 142, u'_id': u'...'}\n", + "{u'count': 142, u'_id': u'kay'}\n", + "{u'count': 142, u'_id': u'\\U0001f48b'}\n", + "{u'count': 141, u'_id': u'Kyle'}\n", + "{u'count': 141, u'_id': u'jordan'}\n", + "{u'count': 141, u'_id': u'Aaron'}\n", + "{u'count': 140, u'_id': u'@haircutteryjob'}\n", + "{u'count': 138, u'_id': u'Lisa'}\n", + "{u'count': 137, u'_id': u'US Hospitality Jobs'}\n", + "{u'count': 137, u'_id': u'meg'}\n", + "{u'count': 137, u'_id': u'\\u2122'}\n", + "{u'count': 136, u'_id': u'Jen'}\n", + "{u'count': 135, u'_id': u'kenz'}\n", + "{u'count': 135, u'_id': u'Robert'}\n", + "{u'count': 135, u'_id': u'\\U0001f5a4'}\n", + "{u'count': 135, u'_id': u'Kay'}\n", + "{u'count': 135, u'_id': u'Emma'}\n", + "{u'count': 134, u'_id': u'Paul'}\n", + "{u'count': 134, u'_id': u'jay'}\n", + "{u'count': 134, u'_id': u'ATL Hospitality Jobs'}\n", + "{u'count': 134, u'_id': u'Melissa'}\n", + "{u'count': 133, u'_id': u'Ty'}\n", + "{u'count': 131, u'_id': u'\\u3164\\u3164\\u3164'}\n", + "{u'count': 131, u'_id': u'Madison'}\n", + "{u'count': 131, u'_id': u'Vanessa'}\n", + "{u'count': 131, u'_id': u'katie'}\n", + "{u'count': 130, u'_id': u'Elizabeth'}\n", + "{u'count': 130, u'_id': u'Liz'}\n", + "{u'count': 129, u'_id': u'Brittany'}\n", + "{u'count': 129, u'_id': u'Portland Police log'}\n", + "{u'count': 129, u'_id': u'Rich'}\n", + "{u'count': 129, u'_id': u'Carl King'}\n", + "{u'count': 129, u'_id': u'Proviscalling'}\n", + "{u'count': 128, u'_id': u'amanda'}\n", + "{u'count': 128, u'_id': u'kat'}\n", + "{u'count': 128, u'_id': u'TMJ-CA HRTA Jobs'}\n", + "{u'count': 128, u'_id': u'nicole'}\n", + "{u'count': 128, u'_id': u'Drew'}\n", + "{u'count': 128, u'_id': u'megan'}\n", + "{u'count': 127, u'_id': u'TMJ-BOS HRTA Jobs'}\n", + "{u'count': 127, u'_id': u'han'}\n", + "{u'count': 126, u'_id': u'Brooke'}\n", + "{u'count': 125, u'_id': u'\\ufe0f'}\n", + "{u'count': 125, u'_id': u'TMJ-MSP HRTA Jobs'}\n", + "{u'count': 125, u'_id': u'Kat'}\n", + "{u'count': 125, u'_id': u'Erin'}\n", + "{u'count': 125, u'_id': u'Liv'}\n", + "{u'count': 124, u'_id': u'Mel'}\n", + "{u'count': 124, u'_id': u'haley'}\n", + "{u'count': 124, u'_id': u'Amy'}\n", + "{u'count': 123, u'_id': u'maurices careers'}\n", + "{u'count': 123, u'_id': u'$'}\n", + "{u'count': 122, u'_id': u'MENTOR Network Jobs'}\n", + "{u'count': 122, u'_id': u'Jeff'}\n", + "{u'count': 121, u'_id': u'vanessa'}\n", + "{u'count': 121, u'_id': u'Victoria'}\n", + "{u'count': 121, u'_id': u'Brad'}\n", + "{u'count': 121, u'_id': u'JP'}\n", + "{u'count': 121, u'_id': u'Han'}\n", + "{u'count': 121, u'_id': u'Dallas Hospitality'}\n", + "{u'count': 120, u'_id': u'TMJ-TX HRTA Jobs'}\n", + "{u'count': 120, u'_id': u'MJ'}\n", + "{u'count': 119, u'_id': u'Janie'}\n", + "{u'count': 119, u'_id': u'grace'}\n", + "{u'count': 118, u'_id': u'Courtney'}\n", + "{u'count': 118, u'_id': u'maddie'}\n", + "{u'count': 118, u'_id': u'k'}\n", + "{u'count': 118, u'_id': u'Danielle'}\n", + "{u'count': 118, u'_id': u'Lexi'}\n", + "{u'count': 118, u'_id': u'Sara'}\n", + "{u'count': 117, u'_id': u'morgan'}\n", + "{u'count': 117, u'_id': u'alexis'}\n", + "{u'count': 117, u'_id': u'Natalie'}\n", + "{u'count': 117, u'_id': u'Dom'}\n", + "{u'count': 116, u'_id': u'CTS Jobs'}\n", + "{u'count': 116, u'_id': u'V'}\n", + "{u'count': 115, u'_id': u'C'}\n", + "{u'count': 115, u'_id': u'Dave'}\n", + "{u'count': 115, u'_id': u'Jasmine'}\n", + "{u'count': 115, u'_id': u'Ken'}\n", + "{u'count': 115, u'_id': u'Ben'}\n", + "{u'count': 115, u'_id': u'nat'}\n", + "{u'count': 115, u'_id': u'Diana'}\n", + "{u'count': 114, u'_id': u'Jenna'}\n", + "{u'count': 114, u'_id': u'Jennifer'}\n", + "{u'count': 113, u'_id': u'Hunter'}\n", + "{u'count': 113, u'_id': u'Will'}\n", + "{u'count': 113, u'_id': u'Matthew'}\n", + "{u'count': 113, u'_id': u'tori'}\n", + "{u'count': 112, u'_id': u'liz'}\n", + "{u'count': 112, u'_id': u'\\U0001f33b'}\n", + "{u'count': 112, u'_id': u'A.'}\n", + "{u'count': 111, u'_id': u'Sydney'}\n", + "{u'count': 111, u'_id': u'-'}\n", + "{u'count': 111, u'_id': u'Amber'}\n", + "{u'count': 111, u'_id': u'Rob'}\n", + "{u'count': 111, u'_id': u'Danny'}\n", + "{u'count': 111, u'_id': u'Q'}\n", + "{u'count': 110, u'_id': u'madison'}\n", + "{u'count': 110, u'_id': u'Mads'}\n", + "{u'count': 110, u'_id': u'\\U0001f984'}\n", + "{u'count': 110, u'_id': u'al'}\n", + "{u'count': 110, u'_id': u'Cam'}\n", + "{u'count': 110, u'_id': u'Anna'}\n", + "{u'count': 109, u'_id': u'AJ'}\n", + "{u'count': 109, u'_id': u'TMJ-STL HRTA Jobs'}\n", + "{u'count': 108, u'_id': u'NYC Hospitality Jobs'}\n", + "{u'count': 108, u'_id': u'WHBM Careers'}\n", + "{u'count': 108, u'_id': u'Sean'}\n", + "{u'count': 108, u'_id': u'Joey'}\n", + "{u'count': 108, u'_id': u'Jacob'}\n", + "{u'count': 108, u'_id': u'S'}\n", + "{u'count': 107, u'_id': u'kt'}\n", + "{u'count': 107, u'_id': u'Ryder Jobs'}\n", + "{u'count': 107, u'_id': u'Adam'}\n", + "{u'count': 106, u'_id': u'kels'}\n", + "{u'count': 106, u'_id': u'Brianna'}\n", + "{u'count': 105, u'_id': u'Christian'}\n", + "{u'count': 105, u'_id': u'TMJ-ORL HRTA Jobs'}\n", + "{u'count': 105, u'_id': u'brooke'}\n", + "{u'count': 105, u'_id': u'Ally'}\n", + "{u'count': 105, u'_id': u'Abby'}\n", + "{u'count': 105, u'_id': u'abby'}\n", + "{u'count': 105, u'_id': u'sav'}\n", + "{u'count': 105, u'_id': u'michael'}\n", + "{u'count': 105, u'_id': u'Syd'}\n", + "{u'count': 104, u'_id': u'court'}\n", + "{u'count': 104, u'_id': u'Andrea'}\n", + "{u'count': 104, u'_id': u'Chicago Retail Jobs'}\n", + "{u'count': 104, u'_id': u'\\xaf\\\\_(\\u30c4)_/\\xaf'}\n", + "{u'count': 104, u'_id': u'Logan'}\n", + "{u'count': 104, u'_id': u'rach'}\n", + "{u'count': 104, u'_id': u'rachel'}\n", + "{u'count': 103, u'_id': u'steph'}\n", + "{u'count': 103, u'_id': u'Los Angeles Jobs'}\n", + "{u'count': 103, u'_id': u'Julie'}\n", + "{u'count': 103, u'_id': u'J.'}\n", + "{u'count': 103, u'_id': u'Jack'}\n", + "{u'count': 103, u'_id': u'cam'}\n", + "{u'count': 103, u'_id': u'emma'}\n", + "{u'count': 103, u'_id': u'Dani'}\n", + "{u'count': 103, u'_id': u'kate'}\n", + "{u'count': 103, u'_id': u'Haley'}\n", + "{u'count': 103, u'_id': u'\\U0001f410'}\n", + "{u'count': 102, u'_id': u'Erica'}\n", + "{u'count': 102, u'_id': u'TMJ-PHL HRTA Jobs'}\n", + "{u'count': 102, u'_id': u'samantha'}\n", + "{u'count': 102, u'_id': u'Heather'}\n", + "{u'count': 101, u'_id': u'One God Only'}\n", + "{u'count': 101, u'_id': u'Jon'}\n", + "{u'count': 101, u'_id': u\"Chico's Careers\"}\n", + "{u'count': 101, u'_id': u'Paige'}\n", + "{u'count': 100, u'_id': u'Newark Hosp/Rest/Tou'}\n", + "{u'count': 100, u'_id': u'K.'}\n", + "{u'count': 100, u'_id': u'TMJ-AR HRTA Jobs'}\n", + "{u'count': 100, u'_id': u'Monica'}\n", + "{u'count': 100, u'_id': u'Steph'}\n", + "{u'count': 100, u'_id': u'Lo'}\n", + "{u'count': 100, u'_id': u'RestaurantCareers'}\n", + "{u'count': 99, u'_id': u'olivia'}\n", + "{u'count': 99, u'_id': u'm'}\n", + "{u'count': 99, u'_id': u'G RACE'}\n", + "{u'count': 99, u'_id': u'Al'}\n", + "{u'count': 98, u'_id': u'jasmine'}\n", + "{u'count': 98, u'_id': u'Angel'}\n", + "{u'count': 98, u'_id': u'sydney'}\n", + "{u'count': 98, u'_id': u't'}\n", + "{u'count': 98, u'_id': u'Tony'}\n", + "{u'count': 98, u'_id': u'Joshua'}\n", + "{u'count': 97, u'_id': u'Jesse'}\n", + "{u'count': 97, u'_id': u'victoria'}\n", + "{u'count': 97, u'_id': u'Andy'}\n", + "{u'count': 96, u'_id': u'Total Traffic DFW'}\n", + "{u'count': 96, u'_id': u'Nate'}\n", + "{u'count': 96, u'_id': u'TMJ-WAS HRTA Jobs'}\n", + "{u'count': 96, u'_id': u'ken'}\n", + "{u'count': 96, u'_id': u'Maddie'}\n", + "{u'count': 96, u'_id': u'Jenn'}\n", + "{u'count': 96, u'_id': u'Bruno'}\n", + "{u'count': 95, u'_id': u'Nikki'}\n", + "{u'count': 95, u'_id': u'Ray'}\n", + "{u'count': 95, u'_id': u'Cameron Craig Group'}\n", + "{u'count': 94, u'_id': u'Kelly'}\n", + "{u'count': 94, u'_id': u'paige'}\n", + "{u'count': 94, u'_id': u'lyss'}\n", + "{u'count': 94, u'_id': u'UAMS Nursing Jobs'}\n", + "{u'count': 94, u'_id': u'chris'}\n", + "{u'count': 94, u'_id': u'TMJ-USA Cleric. Jobs'}\n", + "{u'count': 93, u'_id': u'KT'}\n", + "{u'count': 93, u'_id': u'Patrick'}\n", + "{u'count': 93, u'_id': u'Jules'}\n", + "{u'count': 93, u'_id': u'TMJ-BAL HRTA Jobs'}\n", + "{u'count': 93, u'_id': u'James Wolter'}\n", + "{u'count': 92, u'_id': u'britt'}\n", + "{u'count': 92, u'_id': u'Tweet3po'}\n", + "{u'count': 92, u'_id': u'Seattle Hospitality'}\n", + "{u'count': 92, u'_id': u'PFG Careers'}\n", + "{u'count': 92, u'_id': u'Mouton Cove Weather'}\n", + "{u'count': 91, u'_id': u'Dee'}\n", + "{u'count': 91, u'_id': u'maria'}\n", + "{u'count': 91, u'_id': u'JJ'}\n", + "{u'count': 91, u'_id': u'allison'}\n", + "{u'count': 91, u'_id': u'\\u2022'}\n", + "{u'count': 90, u'_id': u'danielle'}\n", + "{u'count': 90, u'_id': u'jen'}\n", + "{u'count': 90, u'_id': u'\\u2764\\ufe0f'}\n", + "{u'count': 90, u'_id': u'dani'}\n", + "{u'count': 90, u'_id': u'Jonathan'}\n", + "{u'count': 89, u'_id': u'Cass'}\n", + "{u'count': 89, u'_id': u'mel'}\n", + "{u'count': 89, u'_id': u'Boston, MA Jobs'}\n", + "{u'count': 89, u'_id': u'TMJ-CAP HRTA Jobs'}\n", + "{u'count': 88, u'_id': u'TMJ-BNA HRTA Jobs'}\n", + "{u'count': 88, u'_id': u'Mandarin Las Vegas'}\n", + "{u'count': 88, u'_id': u'attCAREERS'}\n", + "{u'count': 88, u'_id': u'Earth Rover Bot'}\n", + "{u'count': 88, u'_id': u'TCG Jobs'}\n", + "{u'count': 88, u'_id': u'Ishmael'}\n", + "{u'count': 87, u'_id': u'Des'}\n", + "{u'count': 87, u'_id': u'\\u2605\\u2605\\u2605Stephen Nix\\u2605\\u2605\\u2605'}\n", + "{u'count': 87, u'_id': u'Angela'}\n", + "{u'count': 87, u'_id': u'Mo'}\n", + "{u'count': 87, u'_id': u'TMJ-PIT HRTA Jobs'}\n", + "{u'count': 87, u'_id': u'Maria'}\n", + "{u'count': 87, u'_id': u'Einstein Bros. Jobs'}\n", + "{u'count': 87, u'_id': u'TMJ-LAX Legal Jobs'}\n", + "{u'count': 87, u'_id': u'TMJ-CLT HRTA Jobs'}\n", + "{u'count': 86, u'_id': u'erin'}\n", + "{u'count': 86, u'_id': u'TMJ-DFW Retail Jobs'}\n", + "{u'count': 86, u'_id': u'Providence Careers'}\n", + "{u'count': 86, u'_id': u'Chicago, IL Jobs'}\n", + "{u'count': 86, u'_id': u'Kim'}\n", + "{u'count': 85, u'_id': u'Z'}\n", + "{u'count': 85, u'_id': u'Evan'}\n", + "{u'count': 85, u'_id': u'nick'}\n", + "{u'count': 85, u'_id': u'NYC Jobs'}\n", + "{u'count': 85, u'_id': u'TMJ-AUS HRTA Jobs'}\n", + "{u'count': 85, u'_id': u'TMJ- BOS Health Jobs'}\n", + "{u'count': 85, u'_id': u'HCA'}\n", + "{u'count': 85, u'_id': u'Christina'}\n", + "{u'count': 85, u'_id': u'Sav'}\n", + "{u'count': 85, u'_id': u'Jo'}\n", + "{u'count': 85, u'_id': u'Court'}\n", + "{u'count': 84, u'_id': u'Aurora Careers'}\n", + "{u'count': 84, u'_id': u'\\U0001f338'}\n", + "{u'count': 84, u'_id': u'TMJ-STL Nursing Jobs'}\n", + "{u'count': 84, u'_id': u'Caris Health Jobs'}\n", + "{u'count': 84, u'_id': u'Ry'}\n", + "{u'count': 84, u'_id': u'L'}\n", + "{u'count': 84, u'_id': u'\\U0001f54a'}\n", + "{u'count': 84, u'_id': u'cass'}\n", + "{u'count': 84, u'_id': u'Chelsea'}\n", + "{u'count': 83, u'_id': u'TMJ-AZS HRTA Jobs'}\n", + "{u'count': 83, u'_id': u'Grace'}\n", + "{u'count': 83, u'_id': u'Baltimore Health Job'}\n", + "{u'count': 83, u'_id': u'SF Healthcare Jobs'}\n", + "{u'count': 83, u'_id': u'Linda'}\n", + "{u'count': 83, u'_id': u'P'}\n", + "{u'count': 83, u'_id': u'lexi'}\n", + "{u'count': 83, u'_id': u'Jackie'}\n", + "{u'count': 83, u'_id': u'jessica'}\n", + "{u'count': 83, u'_id': u'Rach'}\n", + "{u'count': 83, u'_id': u'Janet'}\n", + "{u'count': 83, u'_id': u'Dev'}\n", + "{u'count': 82, u'_id': u'princess'}\n", + "{u'count': 82, u'_id': u'madi'}\n", + "{u'count': 82, u'_id': u'Derek'}\n", + "{u'count': 82, u'_id': u'Jobs at Dressbarn'}\n", + "{u'count': 82, u'_id': u'Jamie'}\n", + "{u'count': 82, u'_id': u'Sandra'}\n", + "{u'count': 82, u'_id': u'CGI'}\n", + "{u'count': 82, u'_id': u'TMJ-AR Nursing Jobs'}\n", + "{u'count': 81, u'_id': u'bella'}\n", + "{u'count': 81, u'_id': u'Phoenix Hospitality'}\n", + "{u'count': 81, u'_id': u'TMJ-BOS Retail Jobs'}\n", + "{u'count': 81, u'_id': u'JB'}\n", + "{u'count': 81, u'_id': u'Karen'}\n", + "{u'count': 81, u'_id': u'S.'}\n", + "{u'count': 81, u'_id': u\"Brian Keith O'Hara\"}\n", + "{u'count': 81, u'_id': u'Daddy'}\n", + "{u'count': 81, u'_id': u'TMJ-USA Manuf Jobs'}\n", + "{u'count': 81, u'_id': u'Jenny'}\n", + "{u'count': 81, u'_id': u'Aroon Dani'}\n", + "{u'count': 80, u'_id': u'Mult Co Fire/EMS log'}\n", + "{u'count': 80, u'_id': u'Toronto Fire'}\n", + "{u'count': 80, u'_id': u'Allison'}\n", + "{u'count': 80, u'_id': u'Shannon'}\n", + "{u'count': 80, u'_id': u'd'}\n", + "{u'count': 80, u'_id': u'Meijer Jobs'}\n", + "{u'count': 80, u'_id': u'TMJ- PHL Health Jobs'}\n", + "{u'count': 80, u'_id': u'OC, CA Health Jobs'}\n", + "{u'count': 80, u'_id': u'Tim'}\n", + "{u'count': 80, u'_id': u'Marissa'}\n", + "{u'count': 79, u'_id': u'TMJ-SAT HRTA Jobs'}\n", + "{u'count': 79, u'_id': u'TMJ-GTA Jobs'}\n", + "{u'count': 79, u'_id': u'Mariah'}\n", + "{u'count': 79, u'_id': u'TMJ-PHL Jobs'}\n", + "{u'count': 79, u'_id': u'Bree'}\n", + "{u'count': 79, u'_id': u'julie'}\n", + "{u'count': 79, u'_id': u'Matthew Boicourt'}\n", + "{u'count': 79, u'_id': u'AMC Careers'}\n", + "{u'count': 79, u'_id': u'Christopher'}\n", + "{u'count': 79, u'_id': u'Judy'}\n", + "{u'count': 78, u'_id': u'TMJ-VAV HRTA Jobs'}\n", + "{u'count': 78, u'_id': u'TMJ-BOS Nursing Jobs'}\n", + "{u'count': 78, u'_id': u'Philly Nursing Jobs'}\n", + "{u'count': 78, u'_id': u'JOHN STRONG'}\n", + "{u'count': 78, u'_id': u'TMJ-FLS HRTA Jobs'}\n", + "{u'count': 78, u'_id': u'ryan'}\n", + "{u'count': 78, u'_id': u'Patricia'}\n", + "{u'count': 78, u'_id': u'Pat'}\n", + "{u'count': 78, u'_id': u'gabby'}\n", + "{u'count': 77, u'_id': u'TMJ-MKE HRTA Jobs'}\n", + "{u'count': 77, u'_id': u'..'}\n", + "{u'count': 77, u'_id': u'john beechy'}\n", + "{u'count': 77, u'_id': u'JT'}\n", + "{u'count': 77, u'_id': u'Olivia'}\n", + "{u'count': 77, u'_id': u'Susan'}\n", + "{u'count': 77, u'_id': u'\\U0001f352'}\n", + "{u'count': 77, u'_id': u'Ghirardelli Careers'}\n", + "{u'count': 77, u'_id': u'TMJ-IND HRTA Jobs'}\n", + "{u'count': 77, u'_id': u'Ed'}\n", + "{u'count': 77, u'_id': u'Nathan'}\n", + "{u'count': 76, u'_id': u'Bryan'}\n", + "{u'count': 76, u'_id': u'Tiffany'}\n", + "{u'count': 76, u'_id': u'Marcus'}\n", + "{u'count': 76, u'_id': u'TMJ - CHI Sales Jobs'}\n", + "{u'count': 76, u'_id': u'des'}\n", + "{u'count': 76, u'_id': u'Bailey'}\n", + "{u'count': 76, u'_id': u'ky'}\n", + "{u'count': 76, u'_id': u'Vincent E Ankner'}\n", + "{u'count': 75, u'_id': u'OhioHealth Jobs'}\n", + "{u'count': 75, u'_id': u'TMJ-LAX Nursing Jobs'}\n", + "{u'count': 75, u'_id': u'Sutter Health Jobs'}\n", + "{u'count': 75, u'_id': u'pat.'}\n", + "{u'count': 75, u'_id': u'Rick'}\n", + "{u'count': 75, u'_id': u'Kels'}\n", + "{u'count': 75, u'_id': u'Chicago Health Jobs'}\n", + "{u'count': 75, u'_id': u'Kristen'}\n", + "{u'count': 75, u'_id': u'Rebecca'}\n", + "{u'count': 75, u'_id': u'julia'}\n", + "{u'count': 75, u'_id': u'jon ewall'}\n", + "{u'count': 75, u'_id': u'Tom'}\n", + "{u'count': 75, u'_id': u'Julie Hale'}\n", + "{u'count': 74, u'_id': u'Dylan'}\n", + "{u'count': 74, u'_id': u'Florida Nursing Jobs'}\n", + "{u'count': 74, u'_id': u'Ali'}\n", + "{u'count': 74, u'_id': u'natalie'}\n", + "{u'count': 74, u'_id': u'TMJ-WAT Nursing Jobs'}\n", + "{u'count': 74, u'_id': u'MTC Jobs'}\n", + "{u'count': 74, u'_id': u'Ebb Tide Bot'}\n", + "{u'count': 74, u'_id': u'KC'}\n", + "{u'count': 74, u'_id': u'TM-STL Health Jobs'}\n", + "{u'count': 74, u'_id': u'TJ'}\n", + "{u'count': 74, u'_id': u'TMJ-CA-US Nursing'}\n", + "{u'count': 74, u'_id': u'Julia'}\n", + "{u'count': 73, u'_id': u'Golden Corral Jobs'}\n", + "{u'count': 73, u'_id': u'Carlos'}\n", + "{u'count': 73, u'_id': u'Atlanta, GA Jobs'}\n", + "{u'count': 73, u'_id': u'Cameron'}\n", + "{u'count': 73, u'_id': u'Luke'}\n", + "{u'count': 73, u'_id': u'\\U0001f608'}\n", + "{u'count': 73, u'_id': u'Nat'}\n", + "{u'count': 73, u'_id': u'TMJ-HOU Mgmt. Jobs'}\n", + "{u'count': 73, u'_id': u'United Rentals Jobs'}\n", + "{u'count': 73, u'_id': u'Britt'}\n", + "{u'count': 72, u'_id': u'Leah'}\n", + "{u'count': 72, u'_id': u'Citi Trends Jobs'}\n", + "{u'count': 72, u'_id': u'Steven'}\n", + "{u'count': 72, u'_id': u'claire'}\n", + "{u'count': 72, u'_id': u'UNC Lenoir Careers'}\n", + "{u'count': 72, u'_id': u'Nassau Hospitality'}\n", + "{u'count': 72, u'_id': u'Jerry'}\n", + "{u'count': 72, u'_id': u'Tori'}\n", + "{u'count': 72, u'_id': u'TMJ-PDX HRTA Jobs'}\n", + "{u'count': 72, u'_id': u'Mychel Russell Ward'}\n", + "{u'count': 72, u'_id': u'Connor'}\n", + "{u'count': 71, u'_id': u'jules'}\n", + "{u'count': 71, u'_id': u'CarpoolWorld'}\n", + "{u'count': 71, u'_id': u'g'}\n", + "{u'count': 71, u'_id': u'TMJ-OKC HRTA Jobs'}\n", + "{u'count': 71, u'_id': u'TMJ-CAO Jobs'}\n", + "{u'count': 71, u'_id': u'Max'}\n", + "{u'count': 71, u'_id': u'Jeremy'}\n", + "{u'count': 71, u'_id': u'jas'}\n", + "{u'count': 71, u'_id': u'CHOMP'}\n", + "{u'count': 71, u'_id': u'Miranda'}\n", + "{u'count': 71, u'_id': u'Milwaukee News'}\n", + "{u'count': 71, u'_id': u'Annie'}\n", + "{u'count': 71, u'_id': u'ally'}\n", + "{u'count': 71, u'_id': u'Israel Carbuckle'}\n", + "{u'count': 70, u'_id': u'TMJ-LAX Retail Jobs'}\n", + "{u'count': 70, u'_id': u'CJ'}\n", + "{u'count': 70, u'_id': u'Jimmy'}\n", + "{u'count': 70, u'_id': u'chlo'}\n", + "{u'count': 70, u'_id': u'Dallas, TX Jobs'}\n", + "{u'count': 70, u'_id': u'c'}\n", + "{u'count': 70, u'_id': u'KJ'}\n", + "{u'count': 70, u'_id': u'Caroline'}\n", + "{u'count': 70, u'_id': u'Ky'}\n", + "{u'count': 70, u'_id': u'\\U0001f319'}\n", + "{u'count': 70, u'_id': u'amber'}\n", + "{u'count': 70, u'_id': u'mariah'}\n", + "{u'count': 69, u'_id': u'Bill'}\n", + "{u'count': 69, u'_id': u'a'}\n", + "{u'count': 69, u'_id': u'TMJ-HOU Retail Jobs'}\n", + "{u'count': 69, u'_id': u'stephanie'}\n", + "{u'count': 69, u'_id': u'Cognizant Careers US'}\n", + "{u'count': 69, u'_id': u'Leslie'}\n", + "{u'count': 69, u'_id': u'KB'}\n", + "{u'count': 69, u'_id': u'T.'}\n", + "{u'count': 69, u'_id': u'Jared'}\n", + "{u'count': 69, u'_id': u'\\U0001f334 Ashley Perkins \\U0001f334'}\n", + "{u'count': 69, u'_id': u'TMJ-HOU Educ. Jobs'}\n", + "{u'count': 69, u'_id': u'Sunstate Jobs'}\n", + "{u'count': 69, u'_id': u'anna'}\n", + "{u'count': 69, u'_id': u'Lindsey'}\n", + "{u'count': 68, u'_id': u'Jake Hamby'}\n", + "{u'count': 68, u'_id': u'Stephanie Collins'}\n", + "{u'count': 68, u'_id': u'Richard'}\n", + "{u'count': 68, u'_id': u'josh'}\n", + "{u'count': 68, u'_id': u'TMJ-MIT HRTA Jobs'}\n", + "{u'count': 68, u'_id': u'Brenda'}\n", + "{u'count': 68, u'_id': u'Kelsey'}\n", + "{u'count': 68, u'_id': u'Johnny'}\n", + "{u'count': 68, u'_id': u'TMJ-RDU HRTA Jobs'}\n", + "{u'count': 68, u'_id': u'\\u26a1\\ufe0f'}\n", + "{u'count': 68, u'_id': u'511NY - Long Island'}\n", + "{u'count': 68, u'_id': u'SRHS Careers'}\n", + "{u'count': 68, u'_id': u'Cody'}\n", + "{u'count': 68, u'_id': u'Chase'}\n", + "{u'count': 68, u'_id': u'Kimberly'}\n", + "{u'count': 68, u'_id': u'TMJ-SFO Jobs'}\n", + "{u'count': 68, u'_id': u'Sabrina'}\n", + "{u'count': 67, u'_id': u'_'}\n", + "{u'count': 67, u'_id': u'Nick Moreno'}\n", + "{u'count': 67, u'_id': u'Statewide CTDOT'}\n", + "{u'count': 67, u'_id': u'\\u265b'}\n", + "{u'count': 67, u'_id': u'andrea'}\n", + "{u'count': 67, u'_id': u'NYC Retail Jobs'}\n", + "{u'count': 67, u'_id': u'GRACE HOLMES'}\n", + "{u'count': 67, u'_id': u'TMJ-CHI Transp. Jobs'}\n", + "{u'count': 67, u'_id': u'soph'}\n", + "{u'count': 67, u'_id': u'jenna'}\n", + "{u'count': 67, u'_id': u'Joel'}\n", + "{u'count': 67, u'_id': u'OC, CA Nursing Jobs'}\n", + "{u'count': 67, u'_id': u'marissa'}\n", + "{u'count': 67, u'_id': u'Christine'}\n", + "{u'count': 66, u'_id': u'Emerson'}\n", + "{u'count': 66, u'_id': u'RH Legal Jobs'}\n", + "{u'count': 66, u'_id': u'sara'}\n", + "{u'count': 66, u'_id': u'caroline'}\n", + "{u'count': 66, u'_id': u'TMJ-DEN Nursing Jobs'}\n", + "{u'count': 66, u'_id': u'courtney'}\n", + "{u'count': 66, u'_id': u'TravelNursesPHP'}\n", + "{u'count': 66, u'_id': u'Fresenius Careers'}\n", + "{u'count': 66, u'_id': u'Charlie'}\n", + "{u'count': 66, u'_id': u'Jas'}\n", + "{u'count': 66, u'_id': u'KP'}\n", + "{u'count': 66, u'_id': u'TMJ-LAS HRTA Jobs'}\n", + "{u'count': 66, u'_id': u'TampaBay Health Job'}\n", + "{u'count': 66, u'_id': u'MSC Jobs'}\n", + "{u'count': 66, u'_id': u'Tommy'}\n", + "{u'count': 66, u'_id': u'Adrian'}\n", + "{u'count': 65, u'_id': u'jo'}\n", + "{u'count': 65, u'_id': u'Deb'}\n", + "{u'count': 65, u'_id': u'TMJ-MS HRTA Jobs'}\n", + "{u'count': 65, u'_id': u'Troy'}\n", + "{u'count': 65, u'_id': u'TMJ-MO HRTA Jobs'}\n", + "{u'count': 65, u'_id': u'linds'}\n", + "{u'count': 65, u'_id': u'CCA'}\n", + "{u'count': 65, u'_id': u'Denise'}\n", + "{u'count': 65, u'_id': u'Charles'}\n", + "{u'count': 65, u'_id': u'Trump Hotels Jobs'}\n", + "{u'count': 65, u'_id': u'Carolyn'}\n", + "{u'count': 64, u'_id': u'CO Hospitality Jobs'}\n", + "{u'count': 64, u'_id': u'Michael Obrien'}\n", + "{u'count': 64, u'_id': u'\\U0001f31e'}\n", + "{u'count': 64, u'_id': u'Soma Careers'}\n", + "{u'count': 64, u'_id': u'Memorial Hermann TA'}\n", + "{u'count': 64, u'_id': u'Patricia Snyder'}\n", + "{u'count': 64, u'_id': u'ari'}\n", + "{u'count': 64, u'_id': u'William'}\n", + "{u'count': 64, u'_id': u'TMJ-KAN HRTA Jobs'}\n", + "{u'count': 63, u'_id': u'maddy'}\n", + "{u'count': 63, u'_id': u'Jobs at Hobsons'}\n", + "{u'count': 63, u'_id': u'TMJ-LAS Jobs'}\n", + "{u'count': 63, u'_id': u'Crystal'}\n", + "{u'count': 63, u'_id': u'tyler'}\n", + "{u'count': 63, u'_id': u'D.'}\n", + "{u'count': 63, u'_id': u'TMJ-FLF HRTA Jobs'}\n", + "{u'count': 63, u'_id': u'TMJ-CIN HRTA Jobs'}\n", + "{u'count': 63, u'_id': u'Frank'}\n", + "{u'count': 63, u'_id': u'Dallas Sales Jobs'}\n", + "{u'count': 63, u'_id': u'Riley'}\n", + "{u'count': 63, u'_id': u'Molly'}\n", + "{u'count': 63, u'_id': u'lil mama'}\n", + "{u'count': 62, u'_id': u'Meredith'}\n", + "{u'count': 62, u'_id': u'Alicia'}\n", + "{u'count': 62, u'_id': u's'}\n", + "{u'count': 62, u'_id': u'Kenz'}\n", + "{u'count': 62, u'_id': u'Shawn'}\n", + "{u'count': 62, u'_id': u'Teresa Morris'}\n", + "{u'count': 62, u'_id': u'Gabby'}\n", + "{u'count': 62, u'_id': u'Erika'}\n", + "{u'count': 62, u'_id': u'TMJ-PHL Retail Jobs'}\n", + "{u'count': 62, u'_id': u'Vic'}\n", + "{u'count': 62, u'_id': u'Stephen'}\n", + "{u'count': 62, u'_id': u'Rose'}\n", + "{u'count': 62, u'_id': u'Central Garden & Pet'}\n", + "{u'count': 62, u'_id': u'Alexandra'}\n", + "{u'count': 62, u'_id': u'brianna'}\n", + "{u'count': 62, u'_id': u'Noah'}\n", + "{u'count': 62, u'_id': u'Kenny'}\n", + "{u'count': 62, u'_id': u'Joseph'}\n", + "{u'count': 61, u'_id': u'chels'}\n", + "{u'count': 61, u'_id': u'Rae'}\n", + "{u'count': 61, u'_id': u'#FREEGATES'}\n", + "{u'count': 61, u'_id': u'594 Graffiti'}\n", + "{u'count': 61, u'_id': u'Sierra'}\n", + "{u'count': 61, u'_id': u'kenzie'}\n", + "{u'count': 61, u'_id': u'TMJ-HOU Jobs'}\n", + "{u'count': 61, u'_id': u'Aly'}\n", + "{u'count': 61, u'_id': u'Atlanta Nursing Jobs'}\n", + "{u'count': 61, u'_id': u'Madi'}\n", + "{u'count': 61, u'_id': u'Nassau Retail'}\n", + "{u'count': 61, u'_id': u'Ian'}\n", + "{u'count': 61, u'_id': u'matt'}\n", + "{u'count': 61, u'_id': u'BH Media Jobs'}\n", + "{u'count': 61, u'_id': u'Lyss'}\n", + "{u'count': 61, u'_id': u'JONATHON'}\n", + "{u'count': 61, u'_id': u'Zlicepromoteam'}\n", + "{u'count': 61, u'_id': u'TMJ-OK HRTA Jobs'}\n", + "{u'count': 61, u'_id': u'TMJ-TUL HRTA Jobs'}\n", + "{u'count': 61, u'_id': u'Kev'}\n", + "{u'count': 61, u'_id': u'Shay'}\n", + "{u'count': 60, u'_id': u'allie'}\n", + "{u'count': 60, u'_id': u'M.'}\n", + "{u'count': 60, u'_id': u'zach'}\n", + "{u'count': 60, u'_id': u'Tara'}\n", + "{u'count': 60, u'_id': u'michelle'}\n", + "{u'count': 60, u'_id': u'shelbs'}\n", + "{u'count': 60, u'_id': u'Matthew Lopez'}\n", + "{u'count': 60, u'_id': u'Kaplan Test Prep'}\n", + "{u'count': 60, u'_id': u'KING BRYON SHARPE'}\n", + "{u'count': 60, u'_id': u'Allie'}\n", + "{u'count': 60, u'_id': u'X'}\n", + "{u'count': 60, u'_id': u'Ethan'}\n", + "{u'count': 60, u'_id': u'MK'}\n", + "{u'count': 60, u'_id': u'molly'}\n", + "{u'count': 60, u'_id': u'Cait'}\n", + "{u'count': 60, u'_id': u'Val'}\n", + "{u'count': 60, u'_id': u'TMJ-PA Health Jobs'}\n", + "{u'count': 60, u'_id': u'destiny'}\n", + "{u'count': 60, u'_id': u'Kam'}\n", + "{u'count': 60, u'_id': u'Alan'}\n", + "{u'count': 60, u'_id': u'jake'}\n", + "{u'count': 60, u'_id': u'Jade'}\n", + "{u'count': 60, u'_id': u'k.'}\n", + "{u'count': 60, u'_id': u'Bash Org'}\n", + "{u'count': 60, u'_id': u'Ron'}\n", + "{u'count': 59, u'_id': u'Sheri Lynn Pritchett'}\n", + "{u'count': 59, u'_id': u'TMJ-GTA HRTA Jobs'}\n", + "{u'count': 59, u'_id': u'babygirl'}\n", + "{u'count': 59, u'_id': u'OG'}\n", + "{u'count': 59, u'_id': u'cait'}\n", + "{u'count': 59, u'_id': u'Maggie'}\n", + "{u'count': 59, u'_id': u'Robert Haviland'}\n", + "{u'count': 59, u'_id': u'Corey'}\n", + "{u'count': 59, u'_id': u'jade'}\n", + "{u'count': 59, u'_id': u'bailey'}\n", + "{u'count': 59, u'_id': u'hailey'}\n", + "{u'count': 59, u'_id': u'TMJ-SJC Jobs'}\n", + "{u'count': 59, u'_id': u'JD'}\n", + "{u'count': 59, u'_id': u'Ramapo Hospitality'}\n", + "{u'count': 59, u'_id': u'Melanie'}\n", + "{u'count': 59, u'_id': u'Casey'}\n", + "{u'count': 59, u'_id': u'christian'}\n", + "{u'count': 59, u'_id': u'TMJ-CLT Jobs'}\n", + "{u'count': 58, u'_id': u'xavier'}\n", + "{u'count': 58, u'_id': u'Milwaukee Health'}\n", + "{u'count': 58, u'_id': u'Charlotte Now'}\n", + "{u'count': 58, u'_id': u'Garrett'}\n", + "{u'count': 58, u'_id': u'Tiffeny Luvs MJ & 3T'}\n", + "{u'count': 58, u'_id': u'TMJ-LAJ HRTA Jobs'}\n", + "{u'count': 58, u'_id': u'Sacramento Health'}\n", + "{u'count': 58, u'_id': u'Michaela'}\n", + "{u'count': 58, u'_id': u'Zack'}\n", + "{u'count': 58, u'_id': u'Swedish Careers'}\n", + "{u'count': 58, u'_id': u'Veronica'}\n", + "{u'count': 58, u'_id': u'Savannah'}\n", + "{u'count': 58, u'_id': u'TCC Careers'}\n", + "{u'count': 58, u'_id': u'Mac'}\n", + "{u'count': 58, u'_id': u'TMJ-MKE Nursing Jobs'}\n", + "{u'count': 58, u'_id': u'TMJ- PHX Health Jobs'}\n", + "{u'count': 57, u'_id': u'Premise Health'}\n", + "{u'count': 57, u'_id': u'Total Traffic SEA'}\n", + "{u'count': 57, u'_id': u'TMJ-SAN HRTA Jobs'}\n", + "{u'count': 57, u'_id': u'Kris'}\n", + "{u'count': 57, u'_id': u'kaitlyn'}\n", + "{u'count': 57, u'_id': u'TMJ-HOU Cleric. Jobs'}\n", + "{u'count': 57, u'_id': u'miranda'}\n", + "{u'count': 57, u'_id': u'laur'}\n", + "{u'count': 57, u'_id': u'kait'}\n", + "{u'count': 57, u'_id': u'Gabe'}\n", + "{u'count': 57, u'_id': u'MHCD Careers'}\n", + "{u'count': 57, u'_id': u'sky'}\n", + "{u'count': 57, u'_id': u'Marie'}\n", + "{u'count': 57, u'_id': u'Jobs at Continuum'}\n", + "{u'count': 57, u'_id': u'Jody'}\n", + "{u'count': 57, u'_id': u'jackie'}\n", + "{u'count': 56, u'_id': u'Chuck'}\n", + "{u'count': 56, u'_id': u'Devin'}\n", + "{u'count': 56, u'_id': u'TMJ-SFO HRTA Jobs'}\n", + "{u'count': 56, u'_id': u'Baltimore Now'}\n", + "{u'count': 56, u'_id': u'JC'}\n", + "{u'count': 56, u'_id': u'FREE HUGS \\U0001f1e7\\U0001f1e6'}\n", + "{u'count': 56, u'_id': u'mo'}\n", + "{u'count': 56, u'_id': u'e'}\n", + "{u'count': 56, u'_id': u'Dave Morrison'}\n", + "{u'count': 56, u'_id': u'Seattle CP'}\n", + "{u'count': 56, u'_id': u'Boston Sales Jobs'}\n", + "{u'count': 56, u'_id': u'TMJ-TX Retail Jobs'}\n", + "{u'count': 56, u'_id': u'Beth'}\n", + "{u'count': 56, u'_id': u'Lee'}\n", + "{u'count': 56, u'_id': u'TMJ-CAO Retail Jobs'}\n", + "{u'count': 56, u'_id': u'Kent Palmer'}\n", + "{u'count': 56, u'_id': u'TM-KAN Health Jobs'}\n", + "{u'count': 55, u'_id': u'KG'}\n", + "{u'count': 55, u'_id': u'Mari'}\n", + "{u'count': 55, u'_id': u'Columbus Health Jobs'}\n", + "{u'count': 55, u'_id': u'Debbie'}\n", + "{u'count': 55, u'_id': u'King'}\n", + "{u'count': 55, u'_id': u'shan'}\n", + "{u'count': 55, u'_id': u'Denver Now'}\n", + "{u'count': 55, u'_id': u'Jose'}\n", + "{u'count': 55, u'_id': u'Washington Press'}\n", + "{u'count': 55, u'_id': u'Tookie Trilliams'}\n", + "{u'count': 55, u'_id': u'cat'}\n", + "{u'count': 55, u'_id': u'Thomas'}\n", + "{u'count': 55, u'_id': u'You'}\n", + "{u'count': 55, u'_id': u'TMJ-SDF HRTA Jobs'}\n", + "{u'count': 55, u'_id': u'TMJ-CLE HRTA Jobs'}\n", + "{u'count': 55, u'_id': u'Seattle Health Jobs'}\n", + "{u'count': 55, u'_id': u'Nancy'}\n", + "{u'count': 55, u'_id': u'anthony'}\n", + "{u'count': 55, u'_id': u'TMJ-RIP Jobs'}\n", + "{u'count': 55, u'_id': u'Ant'}\n", + "{u'count': 55, u'_id': u'Tina'}\n", + "{u'count': 55, u'_id': u'Las Vegas Press'}\n", + "{u'count': 55, u'_id': u'kelsey'}\n", + "{u'count': 55, u'_id': u'IG & SC: Zztro'}\n", + "{u'count': 55, u'_id': u'Lori'}\n", + "{u'count': 55, u'_id': u'TMJ-TN HRTA Jobs'}\n", + "{u'count': 55, u'_id': u'vic'}\n", + "{u'count': 54, u'_id': u'brittany'}\n", + "{u'count': 54, u'_id': u'Mitch'}\n", + "{u'count': 54, u'_id': u'Mar'}\n", + "{u'count': 54, u'_id': u'jacob'}\n", + "{u'count': 54, u'_id': u'Newark Other'}\n", + "{u'count': 54, u'_id': u'TTN Houston'}\n", + "{u'count': 54, u'_id': u'Cory'}\n", + "{u'count': 54, u'_id': u'#NotMyPresident'}\n", + "{u'count': 54, u'_id': u'TMJ-CHH HRTA Jobs'}\n", + "{u'count': 54, u'_id': u'kc'}\n", + "{u'count': 54, u'_id': u'Caitlin'}\n", + "{u'count': 54, u'_id': u'kass'}\n", + "{u'count': 54, u'_id': u'Lithia Careers'}\n", + "{u'count': 54, u'_id': u'Dennis S Brotman'}\n", + "{u'count': 54, u'_id': u'NYC Sales Jobs'}\n", + "{u'count': 54, u'_id': u'Karina'}\n", + "{u'count': 54, u'_id': u'Kathy'}\n", + "{u'count': 54, u'_id': u'KRH Careers'}\n", + "{u'count': 54, u'_id': u'Angie'}\n", + "{u'count': 54, u'_id': u'abigail'}\n", + "{u'count': 54, u'_id': u'nina'}\n", + "{u'count': 54, u'_id': u'mom'}\n", + "{u'count': 54, u'_id': u'Mario'}\n", + "{u'count': 54, u'_id': u'Shane'}\n", + "{u'count': 54, u'_id': u'Iveygirl08'}\n", + "{u'count': 54, u'_id': u'\\u3164\\u3164'}\n", + "{u'count': 53, u'_id': u'PUTA'}\n", + "{u'count': 53, u'_id': u'TMJ-DFW Transp. Jobs'}\n", + "{u'count': 53, u'_id': u'SF Sales Jobs'}\n", + "{u'count': 53, u'_id': u'Blake'}\n", + "{u'count': 53, u'_id': u'Shelby'}\n", + "{u'count': 53, u'_id': u'KD'}\n", + "{u'count': 53, u'_id': u'TMJ-CHI CstSrv Jobs'}\n", + "{u'count': 53, u'_id': u'TMJ-CHI Nursing Jobs'}\n", + "{u'count': 53, u'_id': u'George'}\n", + "{u'count': 53, u'_id': u'NetCat Summaries'}\n", + "{u'count': 53, u'_id': u'faith'}\n", + "{u'count': 53, u'_id': u'Destiny'}\n", + "{u'count': 53, u'_id': u'KM'}\n", + "{u'count': 53, u'_id': u'\\U0001f48e'}\n", + "{u'count': 53, u'_id': u'DJ'}\n", + "{u'count': 52, u'_id': u'DTBY/jajaw \\U0001f49bFM2RJ\\u264a\\ufe0f'}\n", + "{u'count': 52, u'_id': u'Linds'}\n", + "{u'count': 52, u'_id': u'mal'}\n", + "{u'count': 52, u'_id': u'Madeline'}\n", + "{u'count': 52, u'_id': u'SIMON Careers'}\n", + "{u'count': 52, u'_id': u'Los Angeles Now'}\n", + "{u'count': 52, u'_id': u'Travis'}\n", + "{u'count': 52, u'_id': u'Newark Retail'}\n", + "{u'count': 52, u'_id': u'TMJ-ATL Retail Jobs'}\n", + "{u'count': 52, u'_id': u'Dre'}\n", + "{u'count': 52, u'_id': u'melissa'}\n", + "{u'count': 52, u'_id': u'ty'}\n", + "{u'count': 52, u'_id': u'Greg'}\n", + "{u'count': 52, u'_id': u'Jobs at Roush'}\n", + "{u'count': 52, u'_id': u'Denver Health Jobs'}\n", + "{u'count': 52, u'_id': u'TMJ-TX Nursing Jobs'}\n", + "{u'count': 52, u'_id': u'Bobby'}\n", + "{u'count': 52, u'_id': u'RHMR Jobs'}\n", + "{u'count': 52, u'_id': u'\\U0001f5e3Politics Are Trash'}\n", + "{u'count': 52, u'_id': u'nikki'}\n", + "{u'count': 52, u'_id': u'AB'}\n", + "{u'count': 52, u'_id': u'erica'}\n", + "{u'count': 52, u'_id': u'Sophia'}\n", + "{u'count': 52, u'_id': u'erlindaandrada'}\n", + "{u'count': 52, u'_id': u'alexandra'}\n", + "{u'count': 52, u'_id': u'Eddie'}\n", + "{u'count': 52, u'_id': u'TMJ-IA Retail Jobs'}\n", + "{u'count': 52, u'_id': u'morg'}\n", + "{u'count': 52, u'_id': u\"Saint Luke's Careers\"}\n", + "{u'count': 52, u'_id': u'TMJ-SEA Nursing Jobs'}\n", + "{u'count': 52, u'_id': u'Kenzie'}\n", + "{u'count': 52, u'_id': u'Sharon Dennis'}\n", + "{u'count': 52, u'_id': u'Maddy'}\n", + "{u'count': 52, u'_id': u'TMJ-BAL Nursing Jobs'}\n", + "{u'count': 52, u'_id': u'Elise Young'}\n", + "{u'count': 51, u'_id': u'shannon'}\n", + "{u'count': 51, u'_id': u'v'}\n", + "{u'count': 51, u'_id': u'maggie'}\n", + "{u'count': 51, u'_id': u'val'}\n", + "{u'count': 51, u'_id': u'Kait'}\n", + "{u'count': 51, u'_id': u'Doug'}\n", + "{u'count': 51, u'_id': u'MedExpress Jobs'}\n", + "{u'count': 51, u'_id': u'Melton Truck Lines'}\n", + "{u'count': 51, u'_id': u'Eli'}\n", + "{u'count': 51, u'_id': u'jack'}\n", + "{u'count': 51, u'_id': u'Spencer'}\n", + "{u'count': 51, u'_id': u'TMJ-JAX HRTA Jobs'}\n", + "{u'count': 51, u'_id': u'AMD'}\n", + "{u'count': 51, u'_id': u'Vincent Steele'}\n", + "{u'count': 51, u'_id': u'TMJ-MSP Jobs'}\n", + "{u'count': 51, u'_id': u'CORT Careers'}\n", + "{u'count': 51, u'_id': u'shelby'}\n", + "{u'count': 51, u'_id': u'Fiserv Careers'}\n", + "{u'count': 51, u'_id': u'\\U0001f3f3\\ufe0f\\u200d\\U0001f308'}\n", + "{u'count': 51, u'_id': u'TMJ-USA PM Jobs'}\n", + "{u'count': 51, u'_id': u'TMJ-SFO Retail Jobs'}\n", + "{u'count': 51, u'_id': u'TMJ-CHI Cosmo Jobs'}\n", + "{u'count': 51, u'_id': u'Felix P. Nater'}\n", + "{u'count': 51, u'_id': u'bre'}\n", + "{u'count': 51, u'_id': u'elizabeth'}\n", + "{u'count': 50, u'_id': u'Alexandria'}\n", + "{u'count': 50, u'_id': u'FL Non-Metro Jobs'}\n", + "{u'count': 50, u'_id': u'Every Earthquake'}\n", + "{u'count': 50, u'_id': u'\\U0001f478\\U0001f3fd'}\n", + "{u'count': 50, u'_id': u'Michigan Automotive'}\n", + "{u'count': 50, u'_id': u'Abigail'}\n", + "{u'count': 50, u'_id': u'Brett'}\n", + "{u'count': 50, u'_id': u'dad'}\n", + "{u'count': 50, u'_id': u'james'}\n", + "{u'count': 50, u'_id': u'Justice'}\n", + "{u'count': 50, u'_id': u'Deplorable Me'}\n", + "{u'count': 50, u'_id': u'Florida Automotive'}\n", + "{u'count': 50, u'_id': u'TMJ - HOU Sales Jobs'}\n", + "{u'count': 50, u'_id': u'alexa'}\n", + "{u'count': 50, u'_id': u'\\U0001f4b0'}\n", + "{u'count': 50, u'_id': u'megs'}\n", + "{u'count': 50, u'_id': u'sierra'}\n", + "{u'count': 50, u'_id': u'San Diego Press'}\n", + "{u'count': 50, u'_id': u'Dallas Now'}\n", + "{u'count': 50, u'_id': u'Gary'}\n", + "{u'count': 50, u'_id': u'TMJ-WAT HRTA Jobs'}\n", + "{u'count': 50, u'_id': u'Bella'}\n", + "{u'count': 49, u'_id': u'William Owen'}\n", + "{u'count': 49, u'_id': u'me'}\n", + "{u'count': 49, u'_id': u'TMJ-ATL Cosmo Jobs'}\n", + "{u'count': 49, u'_id': u'andrew'}\n", + "{u'count': 49, u'_id': u'Keith'}\n", + "{u'count': 49, u'_id': u'mia'}\n", + "{u'count': 49, u'_id': u'Teresa'}\n", + "{u'count': 49, u'_id': u'TMJ-LA HRTA Jobs'}\n", + "{u'count': 49, u'_id': u'angel'}\n", + "{u'count': 49, u'_id': u'TMJ-COB HRTA Jobs'}\n", + "{u'count': 49, u'_id': u':)'}\n", + "{u'count': 49, u'_id': u'gab'}\n", + "{u'count': 49, u'_id': u'\\U0001f5e3'}\n", + "{u'count': 49, u'_id': u'Katelyn'}\n", + "{u'count': 49, u'_id': u'City of Hope Jobs'}\n", + "{u'count': 49, u'_id': u'TTN Oklahoma City'}\n", + "{u'count': 49, u'_id': u'Princess'}\n", + "{u'count': 49, u'_id': u'Queen'}\n", + "{u'count': 49, u'_id': u'Cole'}\n", + "{u'count': 49, u'_id': u'Austin Now'}\n", + "{u'count': 49, u'_id': u'TMJ-FL Retail Jobs'}\n", + "{u'count': 49, u'_id': u'Nassau Other'}\n", + "{u'count': 49, u'_id': u'jenn'}\n", + "{u'count': 49, u'_id': u'CheckOutStore'}\n", + "{u'count': 49, u'_id': u'every lot nyc'}\n", + "{u'count': 49, u'_id': u'TMJ- SJC Health Jobs'}\n", + "{u'count': 49, u'_id': u'My Info'}\n", + "{u'count': 48, u'_id': u'dan'}\n", + "{u'count': 48, u'_id': u'Ana'}\n", + "{u'count': 48, u'_id': u'Royal Tire Jobs'}\n", + "{u'count': 48, u'_id': u'austin'}\n", + "{u'count': 48, u'_id': u'\\U0001f49b'}\n", + "{u'count': 48, u'_id': u'adam'}\n", + "{u'count': 48, u'_id': u'Philadelphia Now'}\n", + "{u'count': 48, u'_id': u'Kara'}\n", + "{u'count': 48, u'_id': u'nick price'}\n", + "{u'count': 48, u'_id': u'Carly'}\n", + "{u'count': 48, u'_id': u'Splendid Savage'}\n", + "{u'count': 48, u'_id': u'Caleb'}\n", + "{u'count': 48, u'_id': u\"Bob's Jobs\"}\n", + "{u'count': 48, u'_id': u'TMJ-PA Retail Jobs'}\n", + "{u'count': 48, u'_id': u'Wash. DC Mgmt. Jobs'}\n", + "{u'count': 48, u'_id': u'TMJ-USA SocSci Jobs'}\n", + "{u'count': 48, u'_id': u'JoinTeamHealth'}\n", + "{u'count': 48, u'_id': u'None.'}\n", + "{u'count': 48, u'_id': u'Jim'}\n", + "{u'count': 48, u'_id': u'dev'}\n", + "{u'count': 48, u'_id': u'hails'}\n", + "{u'count': 48, u'_id': u'Becca'}\n", + "{u'count': 48, u'_id': u'Bob'}\n", + "{u'count': 48, u'_id': u'Bryce'}\n", + "{u'count': 48, u'_id': u'Jane'}\n", + "{u'count': 48, u'_id': u'TMJ-WAT Health Jobs'}\n", + "{u'count': 48, u'_id': u'TMJ-ATL Transp. Jobs'}\n", + "{u'count': 47, u'_id': u'$$$'}\n", + "{u'count': 47, u'_id': u'Ari'}\n", + "{u'count': 47, u'_id': u'jan'}\n", + "{u'count': 47, u'_id': u'JR'}\n", + "{u'count': 47, u'_id': u'\\U0001f478\\U0001f3fe'}\n", + "{u'count': 47, u'_id': u'cp'}\n", + "{u'count': 47, u'_id': u'Plastipak Jobs'}\n", + "{u'count': 47, u'_id': u'TTWN Detroit'}\n", + "{u'count': 47, u'_id': u'Chad'}\n", + "{u'count': 47, u'_id': u'Janet Heinsler'}\n", + "{u'count': 47, u'_id': u'TMJ-SFO Cleric. Jobs'}\n", + "{u'count': 47, u'_id': u'Noble Hospital Jobs'}\n", + "{u'count': 47, u'_id': u'christina'}\n", + "{u'count': 47, u'_id': u'Tum Tum'}\n", + "{u'count': 47, u'_id': u'p'}\n", + "{u'count': 47, u'_id': u'Ricky'}\n", + "{u'count': 47, u'_id': u'Cynthia'}\n", + "{u'count': 47, u'_id': u'ben'}\n" + ] + } + ], + "source": [ + "for element in db.tweet_subset.aggregate(pipeline):\n", + " print element" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "deletable": true, + "editable": true + }, + "source": [ + "## Basic Features of Linguistic Style\n", + "\n", + "1. Bag of Words Model (Word Count)\n", + "\n", + "2. Text Length\n", + "\n", + "3. Stance Markers\n", + "\n", + "..." + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "metadata": { + "collapsed": true, + "deletable": true, + "editable": true + }, + "outputs": [], + "source": [ + "match = {'$match': {}} # match a group of your interest\n", + "\n", + "unwind = {'$unwind': '$words'}\n", + "\n", + "group = {'$group': {'_id': '$words', 'count': {'$sum': 1}}}\n", + "\n", + "sort = {'$sort': {'count': -1}}\n", + "\n", + "limit = {'$limit': 1000}\n", + "\n", + "pipeline = [unwind, group, sort, limit]" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": { + "collapsed": false, + "deletable": true, + "editable": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{u'count': 291655, u'_id': u'the'}\n", + "{u'count': 275782, u'_id': u'i'}\n", + "{u'count': 264514, u'_id': u'to'}\n", + "{u'count': 212552, u'_id': u'a'}\n", + "{u'count': 177003, u'_id': u'you'}\n", + "{u'count': 160562, u'_id': u'in'}\n", + "{u'count': 155971, u'_id': u'and'}\n", + "{u'count': 134292, u'_id': u'for'}\n", + "{u'count': 132118, u'_id': u'my'}\n", + "{u'count': 125645, u'_id': u'is'}\n", + "{u'count': 121012, u'_id': u'this'}\n", + "{u'count': 115160, u'_id': u'of'}\n", + "{u'count': 87154, u'_id': u'on'}\n", + "{u'count': 87022, u'_id': u'me'}\n", + "{u'count': 84363, u'_id': u'co'}\n", + "{u'count': 83995, u'_id': u't'}\n", + "{u'count': 83727, u'_id': u'it'}\n", + "{u'count': 82075, u'_id': u'https'}\n", + "{u'count': 76042, u'_id': u'that'}\n", + "{u'count': 74252, u'_id': u'be'}\n", + "{u'count': 68655, u'_id': u'so'}\n", + "{u'count': 68095, u'_id': u'at'}\n", + "{u'count': 65238, u'_id': u\"i'm\"}\n", + "{u'count': 58313, u'_id': u'with'}\n", + "{u'count': 56741, u'_id': u'just'}\n", + "{u'count': 54924, u'_id': u'-'}\n", + "{u'count': 50208, u'_id': u'have'}\n", + "{u'count': 48564, u'_id': u'like'}\n", + "{u'count': 47479, u'_id': u'but'}\n", + "{u'count': 45610, u'_id': u'not'}\n", + "{u'count': 43863, u'_id': u'are'}\n", + "{u'count': 43185, u'_id': u'was'}\n", + "{u'count': 42825, u'_id': u'all'}\n", + "{u'count': 42229, u'_id': u'your'}\n", + "{u'count': 41452, u'_id': u'up'}\n", + "{u'count': 40793, u'_id': u'out'}\n", + "{u'count': 40534, u'_id': u'if'}\n", + "{u'count': 39349, u'_id': u'get'}\n", + "{u'count': 39284, u'_id': u'amp'}\n", + "{u'count': 38624, u'_id': u'we'}\n", + "{u'count': 37065, u'_id': u'our'}\n", + "{u'count': 37012, u'_id': u'can'}\n", + "{u'count': 36658, u'_id': u\"don't\"}\n", + "{u'count': 34742, u'_id': u\"it's\"}\n", + "{u'count': 34481, u'_id': u'about'}\n", + "{u'count': 34297, u'_id': u'what'}\n", + "{u'count': 34236, u'_id': u'when'}\n", + "{u'count': 34152, u'_id': u'love'}\n", + "{u'count': 33937, u'_id': u'@'}\n", + "{u'count': 33632, u'_id': u'do'}\n", + "{u'count': 29838, u'_id': u'they'}\n", + "{u'count': 29566, u'_id': u'want'}\n", + "{u'count': 29356, u'_id': u'see'}\n", + "{u'count': 28175, u'_id': u'one'}\n", + "{u'count': 27973, u'_id': u'work'}\n", + "{u'count': 27710, u'_id': u'go'}\n", + "{u'count': 27523, u'_id': u'no'}\n", + "{u'count': 27460, u'_id': u'from'}\n", + "{u'count': 27346, u'_id': u'he'}\n", + "{u'count': 26759, u'_id': u'good'}\n", + "{u'count': 26495, u'_id': u'now'}\n", + "{u'count': 26476, u'_id': u'day'}\n", + "{u'count': 25962, u'_id': u'how'}\n", + "{u'count': 25500, u'_id': u'time'}\n", + "{u'count': 25254, u'_id': u'great'}\n", + "{u'count': 24799, u'_id': u'know'}\n", + "{u'count': 23686, u'_id': u'will'}\n", + "{u'count': 23438, u'_id': u'as'}\n", + "{u'count': 23250, u'_id': u'here'}\n", + "{u'count': 22824, u'_id': u'people'}\n", + "{u'count': 22447, u'_id': u'got'}\n", + "{u'count': 21823, u'_id': u'or'}\n", + "{u'count': 21692, u'_id': u'today'}\n", + "{u'count': 21542, u'_id': u'happy'}\n", + "{u'count': 21120, u'_id': u'lol'}\n", + "{u'count': 20828, u'_id': u'latest'}\n", + "{u'count': 20653, u'_id': u'by'}\n", + "{u'count': 20499, u'_id': u'who'}\n", + "{u'count': 19748, u'_id': u'need'}\n", + "{u'count': 19445, u'_id': u'why'}\n", + "{u'count': 19428, u'_id': u\"can't\"}\n", + "{u'count': 19032, u'_id': u'an'}\n", + "{u'count': 18923, u'_id': u'more'}\n", + "{u'count': 18824, u'_id': u\"we're\"}\n", + "{u'count': 18798, u'_id': u'u'}\n", + "{u'count': 18333, u'_id': u'back'}\n", + "{u'count': 18257, u'_id': u'really'}\n", + "{u'count': 18257, u'_id': u'some'}\n", + "{u'count': 17892, u'_id': u\"you're\"}\n", + "{u'count': 16991, u'_id': u'new'}\n", + "{u'count': 16972, u'_id': u'been'}\n", + "{u'count': 16876, u'_id': u'going'}\n", + "{u'count': 16787, u'_id': u'too'}\n", + "{u'count': 16652, u'_id': u'think'}\n", + "{u'count': 16453, u'_id': u'click'}\n", + "{u'count': 16219, u'_id': u'her'}\n", + "{u'count': 16215, u'_id': u'has'}\n", + "{u'count': 16180, u'_id': u'she'}\n", + "{u'count': 15898, u'_id': u'opening'}\n", + "{u'count': 15798, u'_id': u'shit'}\n", + "{u'count': 15623, u'_id': u'right'}\n", + "{u'count': 15585, u'_id': u'much'}\n", + "{u'count': 15294, u'_id': u'his'}\n", + "{u'count': 15281, u'_id': u'still'}\n", + "{u'count': 15063, u'_id': u'anyone'}\n", + "{u'count': 14851, u'_id': u'never'}\n", + "{u'count': 14770, u'_id': u'life'}\n", + "{u'count': 14550, u'_id': u'would'}\n", + "{u'count': 14522, u'_id': u'2'}\n", + "{u'count': 14465, u'_id': u'had'}\n", + "{u'count': 14336, u'_id': u'them'}\n", + "{u'count': 14179, u'_id': u'there'}\n", + "{u'count': 14163, u'_id': u'make'}\n", + "{u'count': 13987, u'_id': u'could'}\n", + "{u'count': 13821, u'_id': u'only'}\n", + "{u'count': 13544, u'_id': u\"that's\"}\n", + "{u'count': 13457, u'_id': u'trump'}\n", + "{u'count': 13060, u'_id': u'even'}\n", + "{u'count': 12915, u'_id': u'am'}\n", + "{u'count': 12895, u'_id': u'us'}\n", + "{u'count': 12731, u'_id': u'off'}\n", + "{u'count': 12574, u'_id': u'night'}\n", + "{u'count': 12560, u'_id': u'best'}\n", + "{u'count': 12441, u'_id': u'birthday'}\n", + "{u'count': 12284, u'_id': u'thank'}\n", + "{u'count': 12252, u'_id': u'over'}\n", + "{u'count': 12012, u'_id': u'come'}\n", + "{u'count': 11978, u'_id': u'him'}\n", + "{u'count': 11868, u'_id': u'man'}\n", + "{u'count': 11841, u'_id': u'did'}\n", + "{u'count': 11738, u'_id': u'tonight'}\n", + "{u'count': 11678, u'_id': u'last'}\n", + "{u'count': 11677, u'_id': u'always'}\n", + "{u'count': 11637, u'_id': u'way'}\n", + "{u'count': 11478, u'_id': u'these'}\n", + "{u'count': 11144, u'_id': u'fit'}\n", + "{u'count': 11115, u'_id': u'take'}\n", + "{u'count': 11064, u'_id': u'down'}\n", + "{u'count': 11057, u'_id': u'team'}\n", + "{u'count': 10905, u'_id': u'say'}\n", + "{u'count': 10899, u'_id': u'game'}\n", + "{u'count': 10805, u'_id': u'than'}\n", + "{u'count': 10796, u'_id': u'then'}\n", + "{u'count': 10743, u'_id': u'thanks'}\n", + "{u'count': 10734, u'_id': u'someone'}\n", + "{u'count': 10665, u'_id': u'because'}\n", + "{u'count': 10628, u'_id': u'being'}\n", + "{u'count': 10621, u'_id': u'apply'}\n", + "{u'count': 10527, u'_id': u'fuck'}\n", + "{u'count': 10474, u'_id': u'ever'}\n", + "{u'count': 10428, u'_id': u'recommend'}\n", + "{u'count': 10390, u'_id': u'their'}\n", + "{u'count': 10305, u'_id': u'looking'}\n", + "{u'count': 10299, u'_id': u'feel'}\n", + "{u'count': 10135, u'_id': u'oh'}\n", + "{u'count': 10074, u'_id': u'should'}\n", + "{u'count': 9976, u'_id': u'better'}\n", + "{u'count': 9976, u'_id': u'first'}\n", + "{u'count': 9887, u'_id': u\"i've\"}\n", + "{u'count': 9805, u'_id': u'3'}\n", + "{u'count': 9760, u'_id': u'look'}\n", + "{u'count': 9739, u'_id': u'gt'}\n", + "{u'count': 9649, u'_id': u'w'}\n", + "{u'count': 9519, u'_id': u'im'}\n", + "{u'count': 9414, u'_id': u'check'}\n", + "{u'count': 9364, u'_id': u'home'}\n", + "{u'count': 9330, u'_id': u'gonna'}\n", + "{u'count': 9096, u'_id': u'hate'}\n", + "{u'count': 9059, u'_id': u'after'}\n", + "{u'count': 9026, u'_id': u'ass'}\n", + "{u'count': 9002, u'_id': u'might'}\n", + "{u'count': 8913, u'_id': u'wanna'}\n", + "{u'count': 8829, u'_id': u\"y'all\"}\n", + "{u'count': 8785, u'_id': u'girl'}\n", + "{u'count': 8782, u'_id': u'getting'}\n", + "{u'count': 8779, u'_id': u'year'}\n", + "{u'count': 8721, u'_id': u'well'}\n", + "{u'count': 8680, u'_id': u'every'}\n", + "{u'count': 8673, u'_id': u'1'}\n", + "{u'count': 8570, u'_id': u'hope'}\n", + "{u'count': 8538, u'_id': u'miss'}\n", + "{u'count': 8528, u'_id': u'next'}\n", + "{u'count': 8430, u'_id': u'god'}\n", + "{u'count': 8355, u'_id': u'read'}\n", + "{u'count': 8295, u'_id': u\"i'll\"}\n", + "{u'count': 8270, u'_id': u'thing'}\n", + "{u'count': 8265, u'_id': u'where'}\n", + "{u'count': 8253, u'_id': u'stop'}\n", + "{u'count': 8217, u'_id': u'bad'}\n", + "{u'count': 8172, u'_id': u'said'}\n", + "{u'count': 8060, u'_id': u'4'}\n", + "{u'count': 8010, u'_id': u'again'}\n", + "{u'count': 7957, u'_id': u'let'}\n", + "{u'count': 7952, u'_id': u\"didn't\"}\n", + "{u'count': 7927, u'_id': u'wait'}\n", + "{u'count': 7880, u'_id': u'real'}\n", + "{u'count': 7729, u'_id': u'week'}\n", + "{u'count': 7673, u'_id': u'were'}\n", + "{u'count': 7660, u'_id': u'please'}\n", + "{u'count': 7655, u'_id': u'ca'}\n", + "{u'count': 7547, u'_id': u'friends'}\n", + "{u'count': 7459, u'_id': u'into'}\n", + "{u'count': 7406, u'_id': u'lmao'}\n", + "{u'count': 7398, u'_id': u'fucking'}\n", + "{u'count': 7262, u'_id': u'keep'}\n", + "{u'count': 7234, u'_id': u'something'}\n", + "{u'count': 7223, u'_id': u'made'}\n", + "{u'count': 7178, u'_id': u'before'}\n", + "{u'count': 7057, u'_id': u'same'}\n", + "{u'count': 7014, u'_id': u'tomorrow'}\n", + "{u'count': 6992, u'_id': u'everyone'}\n", + "{u'count': 6967, u'_id': u'little'}\n", + "{u'count': 6955, u'_id': u'tell'}\n", + "{u'count': 6930, u'_id': u'show'}\n", + "{u'count': 6861, u'_id': u'watch'}\n", + "{u'count': 6850, u'_id': u'school'}\n", + "{u'count': 6802, u'_id': u'morning'}\n", + "{u'count': 6745, u'_id': u'join'}\n", + "{u'count': 6719, u'_id': u'big'}\n", + "{u'count': 6564, u'_id': u'give'}\n", + "{u'count': 6561, u'_id': u'things'}\n", + "{u'count': 6548, u'_id': u'its'}\n", + "{u'count': 6513, u'_id': u'vote'}\n", + "{u'count': 6511, u'_id': u\"ain't\"}\n", + "{u'count': 6478, u'_id': u'yes'}\n", + "{u'count': 6439, u'_id': u'other'}\n", + "{u'count': 6418, u'_id': u'any'}\n", + "{u'count': 6377, u'_id': u'play'}\n", + "{u'count': 6335, u'_id': u'5'}\n", + "{u'count': 6321, u'_id': u'many'}\n", + "{u'count': 6320, u'_id': u'days'}\n", + "{u'count': 6252, u'_id': u\"he's\"}\n", + "{u'count': 6242, u'_id': u'does'}\n", + "{u'count': 6234, u'_id': u'done'}\n", + "{u'count': 6211, u'_id': u'doing'}\n", + "{u'count': 6206, u'_id': u'world'}\n", + "{u'count': 6171, u'_id': u'damn'}\n", + "{u'count': 6150, u'_id': u'view'}\n", + "{u'count': 6107, u'_id': u'most'}\n", + "{u'count': 6106, u'_id': u'already'}\n", + "{u'count': 6025, u'_id': u'baby'}\n", + "{u'count': 5949, u'_id': u'very'}\n", + "{u'count': 5846, u'_id': u'years'}\n", + "{u'count': 5797, u'_id': u'long'}\n", + "{u'count': 5795, u'_id': u'two'}\n", + "{u'count': 5784, u'_id': u'interested'}\n", + "{u'count': 5774, u'_id': u'put'}\n", + "{u'count': 5764, u'_id': u'live'}\n", + "{u'count': 5764, u'_id': u'another'}\n", + "{u'count': 5761, u'_id': u'gotta'}\n", + "{u'count': 5753, u'_id': u'bitch'}\n", + "{u'count': 5710, u'_id': u'sleep'}\n", + "{u'count': 5710, u'_id': u'nothing'}\n", + "{u'count': 5687, u'_id': u'sure'}\n", + "{u'count': 5629, u'_id': u'win'}\n", + "{u'count': 5626, u'_id': u'ready'}\n", + "{u'count': 5595, u'_id': u'everything'}\n", + "{u'count': 5587, u'_id': u'wish'}\n", + "{u'count': 5586, u'_id': u'hard'}\n", + "{u'count': 5544, u'_id': u'trying'}\n", + "{u'count': 5518, u'_id': u'details'}\n", + "{u'count': 5497, u'_id': u'start'}\n", + "{u'count': 5471, u'_id': u'ya'}\n", + "{u'count': 5465, u'_id': u'myself'}\n", + "{u'count': 5453, u'_id': u'house'}\n", + "{u'count': 5445, u'_id': u'old'}\n", + "{u'count': 5441, u'_id': u'those'}\n", + "{u'count': 5340, u'_id': u'talk'}\n", + "{u'count': 5311, u'_id': u'help'}\n", + "{u'count': 5309, u'_id': u'guys'}\n", + "{u'count': 5283, u'_id': u'care'}\n", + "{u'count': 5272, u'_id': u\"doesn't\"}\n", + "{u'count': 5266, u'_id': u'also'}\n", + "{u'count': 5257, u'_id': u'tx'}\n", + "{u'count': 5226, u'_id': u'thought'}\n", + "{u'count': 5142, u'_id': u'makes'}\n", + "{u'count': 5138, u'_id': u'rn'}\n", + "{u'count': 5123, u'_id': u'find'}\n", + "{u'count': 5112, u'_id': u'actually'}\n", + "{u'count': 5105, u'_id': u'mom'}\n", + "{u'count': 5102, u'_id': u'yeah'}\n", + "{u'count': 5087, u'_id': u'call'}\n", + "{u'count': 5063, u'_id': u'beautiful'}\n", + "{u'count': 5036, u'_id': u'coming'}\n", + "{u'count': 5024, u'_id': u'weekend'}\n", + "{u'count': 5015, u'_id': u\"let's\"}\n", + "{u'count': 5015, u'_id': u'watching'}\n", + "{u'count': 4983, u'_id': u'class'}\n", + "{u'count': 4982, u'_id': u'nice'}\n", + "{u'count': 4956, u'_id': u'10'}\n", + "{u'count': 4925, u'_id': u'literally'}\n", + "{u'count': 4923, u'_id': u'friend'}\n", + "{u'count': 4916, u'_id': u'fun'}\n", + "{u'count': 4907, u'_id': u'pretty'}\n", + "{u'count': 4903, u'_id': u'having'}\n", + "{u'count': 4886, u'_id': u'nigga'}\n", + "{u'count': 4836, u'_id': u'guy'}\n", + "{u'count': 4835, u'_id': u'cause'}\n", + "{u'count': 4822, u'_id': u'around'}\n", + "{u'count': 4815, u'_id': u'ok'}\n", + "{u'count': 4809, u'_id': u'while'}\n", + "{u'count': 4798, u'_id': u'person'}\n", + "{u'count': 4765, u'_id': u'money'}\n", + "{u'count': 4726, u'_id': u'family'}\n", + "{u'count': 4659, u'_id': u'high'}\n", + "{u'count': 4644, u'_id': u'through'}\n", + "{u'count': 4641, u'_id': u'left'}\n", + "{u'count': 4639, u'_id': u'since'}\n", + "{u'count': 4634, u'_id': u'white'}\n", + "{u'count': 4632, u'_id': u'bro'}\n", + "{u'count': 4541, u'_id': u'anything'}\n", + "{u'count': 4523, u'_id': u'away'}\n", + "{u'count': 4499, u'_id': u'amazing'}\n", + "{u'count': 4498, u'_id': u'twitter'}\n", + "{u'count': 4473, u'_id': u'lot'}\n", + "{u'count': 4436, u'_id': u'stay'}\n", + "{u'count': 4415, u'_id': u'until'}\n", + "{u'count': 4414, u'_id': u'such'}\n", + "{u'count': 4396, u'_id': u'7'}\n", + "{u'count': 4354, u'_id': u'ur'}\n", + "{u'count': 4350, u'_id': u'free'}\n", + "{u'count': 4347, u'_id': u'favorite'}\n", + "{u'count': 4308, u'_id': u'bc'}\n", + "{u'count': 4290, u'_id': u'black'}\n", + "{u'count': 4287, u'_id': u'heart'}\n", + "{u'count': 4286, u'_id': u'omg'}\n", + "{u'count': 4265, u'_id': u'believe'}\n", + "{u'count': 4251, u'_id': u'music'}\n", + "{u'count': 4243, u'_id': u'both'}\n", + "{u'count': 4236, u'_id': u'mean'}\n", + "{u'count': 4211, u'_id': u'making'}\n", + "{u'count': 4210, u'_id': u'job'}\n", + "{u'count': 4196, u'_id': u'6'}\n", + "{u'count': 4194, u'_id': u'season'}\n", + "{u'count': 4188, u'_id': u'hey'}\n", + "{u'count': 4142, u'_id': u'wow'}\n", + "{u'count': 4142, u'_id': u'president'}\n", + "{u'count': 4138, u'_id': u'try'}\n", + "{u'count': 4118, u'_id': u'whole'}\n", + "{u'count': 4118, u'_id': u'talking'}\n", + "{u'count': 4111, u'_id': u'hair'}\n", + "{u'count': 4099, u'_id': u'crazy'}\n", + "{u'count': 4092, u'_id': u'end'}\n", + "{u'count': 4061, u'_id': u'0'}\n", + "{u'count': 4058, u'_id': u'state'}\n", + "{u'count': 4044, u'_id': u'own'}\n", + "{u'count': 4042, u'_id': u'wrong'}\n", + "{u'count': 4038, u'_id': u\"there's\"}\n", + "{u'count': 4026, u'_id': u\"isn't\"}\n", + "{u'count': 4014, u'_id': u'looks'}\n", + "{u'count': 4009, u'_id': u'30'}\n", + "{u'count': 4007, u'_id': u'hell'}\n", + "{u'count': 4004, u'_id': u'boy'}\n", + "{u'count': 4003, u'_id': u\"what's\"}\n", + "{u'count': 3925, u'_id': u'phone'}\n", + "{u'count': 3911, u'_id': u'girls'}\n", + "{u'count': 3910, u'_id': u'tho'}\n", + "{u'count': 3903, u'_id': u'went'}\n", + "{u'count': 3881, u'_id': u'told'}\n", + "{u'count': 3862, u'_id': u'sad'}\n", + "{u'count': 3844, u'_id': u'wind'}\n", + "{u'count': 3844, u'_id': u\"won't\"}\n", + "{u'count': 3842, u'_id': u'party'}\n", + "{u'count': 3827, u'_id': u'food'}\n", + "{u'count': 3808, u'_id': u'ny'}\n", + "{u'count': 3802, u'_id': u'cute'}\n", + "{u'count': 3788, u'_id': u'true'}\n", + "{u'count': 3739, u'_id': u'hit'}\n", + "{u'count': 3732, u'_id': u'yet'}\n", + "{u'count': 3731, u'_id': u'though'}\n", + "{u'count': 3722, u'_id': u'via'}\n", + "{u'count': 3713, u'_id': u'st'}\n", + "{u'count': 3693, u'_id': u'name'}\n", + "{u'count': 3663, u'_id': u'video'}\n", + "{u'count': 3659, u'_id': u'remember'}\n", + "{u'count': 3656, u'_id': u'place'}\n", + "{u'count': 3652, u'_id': u'car'}\n", + "{u'count': 3645, u'_id': u'face'}\n", + "{u'count': 3645, u'_id': u'part'}\n", + "{u'count': 3644, u'_id': u'excited'}\n", + "{u'count': 3634, u'_id': u'gone'}\n", + "{u'count': 3630, u'_id': u'head'}\n", + "{u'count': 3594, u'_id': u'america'}\n", + "{u'count': 3591, u'_id': u'use'}\n", + "{u'count': 3590, u'_id': u'seen'}\n", + "{u'count': 3586, u'_id': u'soon'}\n", + "{u'count': 3582, u'_id': u'finally'}\n", + "{u'count': 3577, u'_id': u'eat'}\n", + "{u'count': 3576, u'_id': u'maybe'}\n", + "{u'count': 3574, u'_id': u'8'}\n", + "{u'count': 3562, u'_id': u'sorry'}\n", + "{u'count': 3549, u'_id': u'tweet'}\n", + "{u'count': 3549, u'_id': u'hours'}\n", + "{u'count': 3543, u'_id': u'bed'}\n", + "{u'count': 3538, u'_id': u'times'}\n", + "{u'count': 3528, u'_id': u'playing'}\n", + "{u'count': 3528, u'_id': u'run'}\n", + "{u'count': 3522, u'_id': u'country'}\n", + "{u'count': 3519, u'_id': u'change'}\n", + "{u'count': 3514, u'_id': u'friday'}\n", + "{u'count': 3512, u'_id': u'dude'}\n", + "{u'count': 3505, u'_id': u'yo'}\n", + "{u'count': 3498, u'_id': u'enough'}\n", + "{u'count': 3489, u'_id': u'cool'}\n", + "{u'count': 3466, u'_id': u'point'}\n", + "{u'count': 3464, u'_id': u'college'}\n", + "{u'count': 3463, u'_id': u\"she's\"}\n", + "{u'count': 3444, u'_id': u'funny'}\n", + "{u'count': 3442, u'_id': u'without'}\n", + "{u'count': 3435, u'_id': u'fl'}\n", + "{u'count': 3428, u'_id': u'guess'}\n", + "{u'count': 3428, u'_id': u'city'}\n", + "{u'count': 3418, u'_id': u'niggas'}\n", + "{u'count': 3409, u'_id': u'break'}\n", + "{u'count': 3387, u'_id': u\"i'd\"}\n", + "{u'count': 3386, u'_id': u'full'}\n", + "{u'count': 3384, u'_id': u'dont'}\n", + "{u'count': 3383, u'_id': u'may'}\n", + "{u'count': 3372, u'_id': u'okay'}\n", + "{u'count': 3370, u'_id': u'needs'}\n", + "{u'count': 3368, u'_id': u'must'}\n", + "{u'count': 3365, u'_id': u'song'}\n", + "{u'count': 3360, u'_id': u'lost'}\n", + "{u'count': 3343, u'_id': u'hillary'}\n", + "{u'count': 3341, u'_id': u'manager'}\n", + "{u'count': 3334, u'_id': u'leave'}\n", + "{u'count': 3331, u'_id': u'kids'}\n", + "{u'count': 3326, u'_id': u'election'}\n", + "{u'count': 3326, u'_id': u'support'}\n", + "{u'count': 3303, u'_id': u'b'}\n", + "{u'count': 3295, u'_id': u'n'}\n", + "{u'count': 3248, u'_id': u'follow'}\n", + "{u'count': 3241, u'_id': u'says'}\n", + "{u'count': 3241, u'_id': u'saying'}\n", + "{u'count': 3213, u'_id': u'gets'}\n", + "{u'count': 3208, u'_id': u'probably'}\n", + "{u'count': 3206, u'_id': u'feeling'}\n", + "{u'count': 3177, u'_id': u'photo'}\n", + "{u'count': 3168, u'_id': u's'}\n", + "{u'count': 3164, u'_id': u'mad'}\n", + "{u'count': 3154, u'_id': u'working'}\n", + "{u'count': 3146, u'_id': u'awesome'}\n", + "{u'count': 3139, u'_id': u'hear'}\n", + "{u'count': 3135, u'_id': u'news'}\n", + "{u'count': 3120, u'_id': u'ask'}\n", + "{u'count': 3106, u'_id': u'else'}\n", + "{u'count': 3101, u'_id': u'mind'}\n", + "{u'count': 3092, u'_id': u'took'}\n", + "{u'count': 3087, u'_id': u\"they're\"}\n", + "{u'count': 3080, u'_id': u'early'}\n", + "{u'count': 3046, u'_id': u'honestly'}\n", + "{u'count': 3038, u'_id': u'almost'}\n", + "{u'count': 3030, u'_id': u'together'}\n", + "{u'count': 3026, u'_id': u'dead'}\n", + "{u'count': 3015, u'_id': u'which'}\n", + "{u'count': 3015, u'_id': u\"haven't\"}\n", + "{u'count': 3007, u'_id': u'idk'}\n", + "{u'count': 3004, u'_id': u'drinking'}\n", + "{u'count': 3001, u'_id': u'taking'}\n", + "{u'count': 2992, u'_id': u'saw'}\n", + "{u'count': 2978, u'_id': u'proud'}\n", + "{u'count': 2973, u'_id': u'sick'}\n", + "{u'count': 2943, u'_id': u'few'}\n", + "{u'count': 2940, u'_id': u'halloween'}\n", + "{u'count': 2930, u'_id': u'tired'}\n", + "{u'count': 2911, u'_id': u'women'}\n", + "{u'count': 2910, u'_id': u'half'}\n", + "{u'count': 2891, u'_id': u'open'}\n", + "{u'count': 2884, u'_id': u'room'}\n", + "{u'count': 2865, u'_id': u'dog'}\n", + "{u'count': 2864, u'_id': u'11'}\n", + "{u'count': 2857, u'_id': u'r'}\n", + "{u'count': 2845, u'_id': u'came'}\n", + "{u'count': 2838, u'_id': u'humidity'}\n", + "{u'count': 2832, u'_id': u'lil'}\n", + "{u'count': 2826, u'_id': u'dad'}\n", + "{u'count': 2820, u'_id': u'bring'}\n", + "{u'count': 2807, u'_id': u'af'}\n", + "{u'count': 2804, u'_id': u'move'}\n", + "{u'count': 2784, u'_id': u'buy'}\n", + "{u'count': 2783, u'_id': u'thinking'}\n", + "{u'count': 2772, u'_id': u'weather'}\n", + "{u'count': 2767, u'_id': u'top'}\n", + "{u'count': 2758, u'_id': u'used'}\n", + "{u'count': 2754, u'_id': u'wants'}\n", + "{u'count': 2748, u'_id': u'media'}\n", + "{u'count': 2730, u'_id': u'smh'}\n", + "{u'count': 2729, u'_id': u'thanksgiving'}\n", + "{u'count': 2725, u'_id': u'once'}\n", + "{u'count': 2705, u'_id': u'9'}\n", + "{u'count': 2697, u'_id': u'yourself'}\n", + "{u'count': 2685, u'_id': u'ago'}\n", + "{u'count': 2684, u'_id': u'listen'}\n", + "{u'count': 2677, u'_id': u'glad'}\n", + "{u'count': 2675, u'_id': u'understand'}\n", + "{u'count': 2667, u'_id': u'late'}\n", + "{u'count': 2657, u'_id': u'hot'}\n", + "{u'count': 2649, u'_id': u'movie'}\n", + "{u'count': 2643, u'_id': u'called'}\n", + "{u'count': 2639, u'_id': u'line'}\n", + "{u'count': 2631, u'_id': u'story'}\n", + "{u'count': 2621, u'_id': u'far'}\n", + "{u'count': 2618, u'_id': u'least'}\n", + "{u'count': 2613, u'_id': u'rain'}\n", + "{u'count': 2608, u'_id': u'sometimes'}\n", + "{u'count': 2601, u'_id': u'bout'}\n", + "{u'count': 2596, u'_id': u'posted'}\n", + "{u'count': 2586, u'_id': u\"wasn't\"}\n", + "{u'count': 2577, u'_id': u'against'}\n", + "{u'count': 2576, u'_id': u'waiting'}\n", + "{u'count': 2573, u'_id': u'obama'}\n", + "{u'count': 2566, u'_id': u'park'}\n", + "{u'count': 2561, u'_id': u'ppl'}\n", + "{u'count': 2558, u'_id': u'fall'}\n", + "{u'count': 2550, u'_id': u'health'}\n", + "{u'count': 2550, u'_id': u'boys'}\n", + "{u'count': 2542, u'_id': u'found'}\n", + "{u'count': 2538, u'_id': u'wtf'}\n", + "{u'count': 2519, u'_id': u'wanted'}\n", + "{u'count': 2519, u'_id': u'goes'}\n", + "{u'count': 2515, u'_id': u'seeing'}\n", + "{u'count': 2508, u'_id': u'swear'}\n", + "{u'count': 2504, u'_id': u'anymore'}\n", + "{u'count': 2500, u'_id': u'reason'}\n", + "{u'count': 2492, u'_id': u'lit'}\n", + "{u'count': 2487, u'_id': u'2017'}\n", + "{u'count': 2482, u'_id': u'hour'}\n", + "{u'count': 2481, u'_id': u'o'}\n", + "{u'count': 2472, u'_id': u'il'}\n", + "{u'count': 2455, u'_id': u'post'}\n", + "{u'count': 2454, u'_id': u'minutes'}\n", + "{u'count': 2448, u'_id': u'street'}\n", + "{u'count': 2428, u'_id': u'different'}\n", + "{u'count': 2425, u'_id': u'pay'}\n", + "{u'count': 2423, u'_id': u'stupid'}\n", + "{u'count': 2416, u'_id': u'christmas'}\n", + "{u'count': 2413, u'_id': u'perfect'}\n", + "{u'count': 2395, u'_id': u'saturday'}\n", + "{u'count': 2393, u'_id': u'side'}\n", + "{u'count': 2392, u'_id': u'worst'}\n", + "{u'count': 2389, u'_id': u'la'}\n", + "{u'count': 2381, u'_id': u'beat'}\n", + "{u'count': 2379, u'_id': u'fake'}\n", + "{u'count': 2370, u'_id': u'stuff'}\n", + "{u'count': 2335, u'_id': u'store'}\n", + "{u'count': 2329, u'_id': u'2016'}\n", + "{u'count': 2328, u'_id': u'won'}\n", + "{u'count': 2315, u'_id': u'york'}\n", + "{u'count': 2312, u'_id': u'turn'}\n", + "{u'count': 2302, u'_id': u'started'}\n", + "{u'count': 2301, u'_id': u'pa'}\n", + "{u'count': 2294, u'_id': u'super'}\n", + "{u'count': 2281, u'_id': u'ma'}\n", + "{u'count': 2269, u'_id': u'nc'}\n", + "{u'count': 2266, u'_id': u'text'}\n", + "{u'count': 2262, u'_id': u'drive'}\n", + "{u'count': 2259, u'_id': u'center'}\n", + "{u'count': 2255, u'_id': u'sales'}\n", + "{u'count': 2247, u'_id': u'lt'}\n", + "{u'count': 2237, u'_id': u'future'}\n", + "{u'count': 2231, u'_id': u'service'}\n", + "{u'count': 2229, u'_id': u'heard'}\n", + "{u'count': 2229, u'_id': u'forget'}\n", + "{u'count': 2227, u'_id': u'set'}\n", + "{u'count': 2225, u'_id': u\"couldn't\"}\n", + "{u'count': 2217, u'_id': u'games'}\n", + "{u'count': 2217, u'_id': u'nobody'}\n", + "{u'count': 2216, u'_id': u'comes'}\n", + "{u'count': 2215, u'_id': u'matter'}\n", + "{u'count': 2215, u'_id': u'12'}\n", + "{u'count': 2214, u'_id': u'vs'}\n", + "{u'count': 2208, u'_id': u'yesterday'}\n", + "{u'count': 2203, u'_id': u'congrats'}\n", + "{u'count': 2200, u'_id': u'cold'}\n", + "{u'count': 2187, u'_id': u'sweet'}\n", + "{u'count': 2184, u'_id': u'definitely'}\n", + "{u'count': 2179, u'_id': u'forever'}\n", + "{u'count': 2178, u'_id': u'young'}\n", + "{u'count': 2168, u'_id': u'feels'}\n", + "{u'count': 2166, u'_id': u'brother'}\n", + "{u'count': 2158, u'_id': u\"wouldn't\"}\n", + "{u'count': 2158, u'_id': u'kind'}\n", + "{u'count': 2156, u'_id': u'chance'}\n", + "{u'count': 2155, u'_id': u'somebody'}\n", + "{u'count': 2149, u'_id': u'enjoy'}\n", + "{u'count': 2148, u'_id': u'fight'}\n", + "{u'count': 2148, u'_id': u'second'}\n", + "{u'count': 2147, u'_id': u'business'}\n", + "{u'count': 2145, u'_id': u'lose'}\n", + "{u'count': 2143, u'_id': u'either'}\n", + "{u'count': 2136, u'_id': u'seriously'}\n", + "{u'count': 2134, u'_id': u'happen'}\n", + "{u'count': 2131, u'_id': u'tryna'}\n", + "{u'count': 2128, u'_id': u'fan'}\n", + "{u'count': 2115, u'_id': u'send'}\n", + "{u'count': 2114, u'_id': u'20'}\n", + "{u'count': 2113, u'_id': u'past'}\n", + "{u'count': 2106, u'_id': u'close'}\n", + "{u'count': 2096, u'_id': u'va'}\n", + "{u'count': 2095, u'_id': u'die'}\n", + "{u'count': 2083, u'_id': u'hurt'}\n", + "{u'count': 2079, u'_id': u'fire'}\n", + "{u'count': 2078, u'_id': u'sunday'}\n", + "{u'count': 2067, u'_id': u'each'}\n", + "{u'count': 2067, u'_id': u'knew'}\n", + "{u'count': 2062, u'_id': u'1st'}\n", + "{u'count': 2060, u'_id': u'between'}\n", + "{u'count': 2055, u'_id': u'fact'}\n", + "{u'count': 2055, u'_id': u'crying'}\n", + "{u'count': 2054, u'_id': u'mi'}\n", + "{u'count': 2045, u'_id': u'c'}\n", + "{u'count': 2044, u'_id': u'woman'}\n", + "{u'count': 2025, u'_id': u'single'}\n", + "{u'count': 2019, u'_id': u'hi'}\n", + "{u'count': 2012, u'_id': u'meet'}\n", + "{u'count': 2010, u'_id': u'thankful'}\n", + "{u'count': 2009, u'_id': u'month'}\n", + "{u'count': 2007, u'_id': u'spring'}\n", + "{u'count': 2007, u'_id': u'american'}\n", + "{u'count': 2006, u'_id': u'|'}\n", + "{u'count': 2006, u'_id': u'wake'}\n", + "{u'count': 2005, u'_id': u'case'}\n", + "{u'count': 2003, u'_id': u'temperature'}\n", + "{u'count': 2002, u'_id': u'picture'}\n", + "{u'count': 2002, u'_id': u'during'}\n", + "{u'count': 2002, u'_id': u'clinton'}\n", + "{u'count': 2001, u'_id': u'cry'}\n", + "{u'count': 2001, u'_id': u'voted'}\n", + "{u'count': 1995, u'_id': u\"'s\"}\n", + "{u'count': 1994, u'_id': u'under'}\n", + "{u'count': 1994, u'_id': u'till'}\n", + "{u'count': 1990, u'_id': u'cant'}\n", + "{u'count': 1986, u'_id': u'haha'}\n", + "{u'count': 1984, u'_id': u'nj'}\n", + "{u'count': 1970, u'_id': u'red'}\n", + "{u'count': 1970, u'_id': u'words'}\n", + "{u'count': 1968, u'_id': u'weeks'}\n", + "{u'count': 1955, u'_id': u'worth'}\n", + "{u'count': 1952, u'_id': u'dumb'}\n", + "{u'count': 1944, u'_id': u'book'}\n", + "{u'count': 1937, u'_id': u'rest'}\n", + "{u'count': 1937, u'_id': u'ball'}\n", + "{u'count': 1937, u'_id': u'ga'}\n", + "{u'count': 1930, u'_id': u'fine'}\n", + "{u'count': 1929, u'_id': u'walk'}\n", + "{u'count': 1924, u'_id': u'coffee'}\n", + "{u'count': 1923, u'_id': u'kid'}\n", + "{u'count': 1919, u'_id': u'welcome'}\n", + "{u'count': 1917, u'_id': u'word'}\n", + "{u'count': 1908, u'_id': u'alone'}\n", + "{u'count': 1908, u'_id': u'straight'}\n", + "{u'count': 1907, u'_id': u'less'}\n", + "{u'count': 1906, u'_id': u'everybody'}\n", + "{u'count': 1905, u'_id': u'tf'}\n", + "{u'count': 1905, u'_id': u'body'}\n", + "{u'count': 1903, u'_id': u'football'}\n", + "{u'count': 1900, u'_id': u'gave'}\n", + "{u'count': 1899, u'_id': u'months'}\n", + "{u'count': 1895, u'_id': u'idea'}\n", + "{u'count': 1890, u'_id': u'texas'}\n", + "{u'count': 1889, u'_id': u'mine'}\n", + "{u'count': 1881, u'_id': u'pick'}\n", + "{u'count': 1880, u'_id': u'wonder'}\n", + "{u'count': 1880, u'_id': u'shot'}\n", + "{u'count': 1878, u'_id': u'mo'}\n", + "{u'count': 1875, u'_id': u'learn'}\n", + "{u'count': 1875, u'_id': u'd'}\n", + "{u'count': 1874, u'_id': u'kinda'}\n", + "{u'count': 1874, u'_id': u\"who's\"}\n", + "{u'count': 1872, u'_id': u'living'}\n", + "{u'count': 1868, u'_id': u'instead'}\n", + "{u'count': 1867, u'_id': u'office'}\n", + "{u'count': 1866, u'_id': u'light'}\n", + "{u'count': 1864, u'_id': u'mood'}\n", + "{u'count': 1863, u'_id': u'happened'}\n", + "{u'count': 1858, u'_id': u'running'}\n", + "{u'count': 1855, u'_id': u'bitches'}\n", + "{u'count': 1854, u'_id': u'drink'}\n", + "{u'count': 1854, u'_id': u'forward'}\n", + "{u'count': 1845, u'_id': u'donald'}\n", + "{u'count': 1845, u'_id': u'trust'}\n", + "{u'count': 1844, u'_id': u'outside'}\n", + "{u'count': 1843, u'_id': u'fans'}\n", + "{u'count': 1839, u'_id': u'update'}\n", + "{u'count': 1831, u'_id': u'knows'}\n", + "{u'count': 1830, u'_id': u'stand'}\n", + "{u'count': 1829, u'_id': u'eyes'}\n", + "{u'count': 1811, u'_id': u'yall'}\n", + "{u'count': 1810, u'_id': u'cut'}\n", + "{u'count': 1809, u'_id': u'monday'}\n", + "{u'count': 1808, u'_id': u'giving'}\n", + "{u'count': 1807, u'_id': u'rt'}\n", + "{u'count': 1801, u'_id': u'problem'}\n", + "{u'count': 1793, u'_id': u'beach'}\n", + "{u'count': 1793, u'_id': u'act'}\n", + "{u'count': 1788, u'_id': u'kill'}\n", + "{u'count': 1787, u'_id': u'nurse'}\n", + "{u'count': 1780, u'_id': u'ima'}\n", + "{u'count': 1778, u'_id': u'woke'}\n", + "{u'count': 1778, u'_id': u\"aren't\"}\n", + "{u'count': 1777, u'_id': u'sister'}\n", + "{u'count': 1776, u'_id': u'lead'}\n", + "{u'count': 1776, u'_id': u'north'}\n", + "{u'count': 1773, u'_id': u'needed'}\n", + "{u'count': 1771, u'_id': u'fucked'}\n", + "{u'count': 1766, u'_id': u'everyday'}\n", + "{u'count': 1762, u'_id': u'sounds'}\n", + "{u'count': 1754, u'_id': u'road'}\n", + "{u'count': 1745, u'_id': u'west'}\n", + "{u'count': 1744, u'_id': u'weird'}\n", + "{u'count': 1743, u'_id': u'asked'}\n", + "{u'count': 1741, u'_id': u'starting'}\n", + "{u'count': 1740, u'_id': u'men'}\n", + "{u'count': 1737, u'_id': u'listening'}\n", + "{u'count': 1737, u'_id': u'agree'}\n", + "{u'count': 1729, u'_id': u'san'}\n", + "{u'count': 1725, u'_id': u'bar'}\n", + "{u'count': 1719, u'_id': u'special'}\n", + "{u'count': 1719, u'_id': u'luck'}\n", + "{u'count': 1717, u'_id': u'low'}\n", + "{u'count': 1717, u'_id': u'em'}\n", + "{u'count': 1715, u'_id': u'social'}\n", + "{u'count': 1714, u'_id': u'power'}\n", + "{u'count': 1710, u'_id': u'catch'}\n", + "{u'count': 1705, u'_id': u'able'}\n", + "{u'count': 1704, u'_id': u'water'}\n", + "{u'count': 1703, u'_id': u'player'}\n", + "{u'count': 1701, u'_id': u'tbh'}\n", + "{u'count': 1695, u'_id': u'date'}\n", + "{u'count': 1694, u'_id': u'group'}\n", + "{u'count': 1688, u'_id': u'course'}\n", + "{u'count': 1685, u'_id': u'eating'}\n", + "{u'count': 1681, u'_id': u'dinner'}\n", + "{u'count': 1680, u'_id': u'chicago'}\n", + "{u'count': 1676, u'_id': u'00'}\n", + "{u'count': 1672, u'_id': u'incident'}\n", + "{u'count': 1668, u'_id': u'tried'}\n", + "{u'count': 1662, u'_id': u'later'}\n", + "{u'count': 1662, u'_id': u'tv'}\n", + "{u'count': 1661, u'_id': u'forgot'}\n", + "{u'count': 1657, u'_id': u'nah'}\n", + "{u'count': 1657, u'_id': u'clear'}\n", + "{u'count': 1657, u'_id': u'means'}\n", + "{u'count': 1656, u'_id': u'bruh'}\n", + "{u'count': 1652, u'_id': u'wear'}\n", + "{u'count': 1649, u'_id': u'lie'}\n", + "{u'count': 1648, u'_id': u'south'}\n", + "{u'count': 1644, u'_id': u'three'}\n", + "{u'count': 1640, u'_id': u'missed'}\n", + "{u'count': 1637, u'_id': u'15'}\n", + "{u'count': 1632, u'_id': u'question'}\n", + "{u'count': 1629, u'_id': u'save'}\n", + "{u'count': 1628, u'_id': u'truth'}\n", + "{u'count': 1626, u'_id': u'hold'}\n", + "{u'count': 1622, u'_id': u'lady'}\n", + "{u'count': 1619, u'_id': u'broke'}\n", + "{u'count': 1619, u'_id': u'trip'}\n", + "{u'count': 1617, u'_id': u'front'}\n", + "{u'count': 1615, u'_id': u'az'}\n", + "{u'count': 1615, u'_id': u\"you'll\"}\n", + "{u'count': 1606, u'_id': u'cubs'}\n", + "{u'count': 1602, u'_id': u'shift'}\n", + "{u'count': 1601, u'_id': u'assistant'}\n", + "{u'count': 1599, u'_id': u'exactly'}\n", + "{u'count': 1592, u'_id': u'fast'}\n", + "{u'count': 1591, u'_id': u'parents'}\n", + "{u'count': 1587, u'_id': u'loved'}\n", + "{u'count': 1586, u'_id': u'ones'}\n", + "{u'count': 1586, u'_id': u'deal'}\n", + "{u'count': 1579, u'_id': u'voting'}\n", + "{u'count': 1577, u'_id': u'lmfao'}\n", + "{u'count': 1576, u'_id': u'f'}\n", + "{u'count': 1575, u'_id': u'sign'}\n", + "{u'count': 1564, u'_id': u'california'}\n", + "{u'count': 1562, u'_id': u'winning'}\n", + "{u'count': 1555, u'_id': u'behind'}\n", + "{u'count': 1555, u'_id': u'moment'}\n", + "{u'count': 1551, u'_id': u'drunk'}\n", + "{u'count': 1546, u'_id': u'son'}\n", + "{u'count': 1544, u'_id': u'series'}\n", + "{u'count': 1540, u'_id': u'blessed'}\n", + "{u'count': 1538, u'_id': u'takes'}\n", + "{u'count': 1537, u'_id': u'share'}\n", + "{u'count': 1536, u'_id': u'safe'}\n", + "{u'count': 1534, u'_id': u'blue'}\n", + "{u'count': 1532, u'_id': u'cuz'}\n", + "{u'count': 1528, u'_id': u'realize'}\n", + "{u'count': 1528, u'_id': u'cast'}\n", + "{u'count': 1528, u'_id': u'lord'}\n", + "{u'count': 1526, u'_id': u'dream'}\n", + "{u'count': 1525, u'_id': u'e'}\n", + "{u'count': 1523, u'_id': u'album'}\n", + "{u'count': 1523, u'_id': u'l'}\n", + "{u'count': 1520, u'_id': u'pic'}\n", + "{u'count': 1520, u'_id': u'nap'}\n", + "{u'count': 1519, u'_id': u'played'}\n", + "{u'count': 1516, u'_id': u'joke'}\n", + "{u'count': 1515, u'_id': u'thats'}\n", + "{u'count': 1515, u'_id': u'tweets'}\n", + "{u'count': 1514, u'_id': u'pass'}\n", + "{u'count': 1511, u'_id': u'hand'}\n", + "{u'count': 1509, u'_id': u'couple'}\n", + "{u'count': 1505, u'_id': u'throw'}\n", + "{u'count': 1505, u'_id': u'appreciate'}\n", + "{u'count': 1504, u'_id': u'jesus'}\n", + "{u'count': 1502, u'_id': u'respect'}\n", + "{u'count': 1499, u'_id': u'exit'}\n", + "{u'count': 1496, u'_id': u'easy'}\n", + "{u'count': 1490, u'_id': u'm'}\n", + "{u'count': 1489, u'_id': u'rock'}\n", + "{u'count': 1486, u'_id': u'history'}\n", + "{u'count': 1486, u'_id': u'closed'}\n", + "{u'count': 1485, u'_id': u'ugly'}\n", + "{u'count': 1484, u'_id': u'bit'}\n", + "{u'count': 1481, u'_id': u'absolutely'}\n", + "{u'count': 1480, u'_id': u'wa'}\n", + "{u'count': 1476, u'_id': u'important'}\n", + "{u'count': 1475, u'_id': u'club'}\n", + "{u'count': 1472, u'_id': u'pizza'}\n", + "{u'count': 1472, u'_id': u'driver'}\n", + "{u'count': 1472, u'_id': u\"you've\"}\n", + "{u'count': 1470, u'_id': u'walking'}\n", + "{u'count': 1465, u'_id': u'drop'}\n", + "{u'count': 1461, u'_id': u'current'}\n", + "{u'count': 1460, u'_id': u'mr'}\n", + "{u'count': 1460, u'_id': u'plan'}\n", + "{u'count': 1457, u'_id': u'2nd'}\n", + "{u'count': 1453, u'_id': u'pressure'}\n", + "{u'count': 1453, u'_id': u'town'}\n", + "{u'count': 1450, u'_id': u'field'}\n", + "{u'count': 1449, u'_id': u'seems'}\n", + "{u'count': 1447, u'_id': u'summer'}\n", + "{u'count': 1447, u'_id': u'accident'}\n", + "{u'count': 1445, u'_id': u'bless'}\n", + "{u'count': 1445, u'_id': u'bet'}\n", + "{u'count': 1440, u'_id': u'national'}\n", + "{u'count': 1439, u'_id': u'bday'}\n", + "{u'count': 1435, u'_id': u'missing'}\n", + "{u'count': 1429, u'_id': u'cannot'}\n", + "{u'count': 1425, u'_id': u'self'}\n", + "{u'count': 1425, u'_id': u'pm'}\n", + "{u'count': 1424, u'_id': u'lunch'}\n", + "{u'count': 1423, u'_id': u'order'}\n", + "{u'count': 1415, u'_id': u'tn'}\n", + "{u'count': 1414, u'_id': u'art'}\n", + "{u'count': 1410, u'_id': u'senior'}\n", + "{u'count': 1409, u'_id': u'shut'}\n", + "{u'count': 1404, u'_id': u'become'}\n", + "{u'count': 1394, u'_id': u'students'}\n", + "{u'count': 1393, u'_id': u'type'}\n", + "{u'count': 1391, u'_id': u'md'}\n", + "{u'count': 1390, u'_id': u'worse'}\n", + "{u'count': 1390, u'_id': u'florida'}\n", + "{u'count': 1387, u'_id': u'rather'}\n", + "{u'count': 1384, u'_id': u'ave'}\n", + "{u'count': 1381, u'_id': u'trash'}\n", + "{u'count': 1378, u'_id': u'ride'}\n", + "{u'count': 1378, u'_id': u'strong'}\n", + "{u'count': 1377, u'_id': u'gym'}\n", + "{u'count': 1377, u'_id': u'mn'}\n", + "{u'count': 1375, u'_id': u'hands'}\n", + "{u'count': 1363, u'_id': u'extra'}\n", + "{u'count': 1361, u'_id': u'small'}\n", + "{u'count': 1361, u'_id': u'using'}\n", + "{u'count': 1361, u'_id': u'rd'}\n", + "{u'count': 1360, u'_id': u'hoe'}\n", + "{u'count': 1358, u'_id': u'wearing'}\n", + "{u'count': 1357, u'_id': u'account'}\n", + "{u'count': 1356, u'_id': u'middle'}\n", + "{u'count': 1356, u'_id': u'number'}\n", + "{u'count': 1354, u'_id': u'16'}\n", + "{u'count': 1354, u'_id': u'ice'}\n", + "{u'count': 1353, u'_id': u'sound'}\n", + "{u'count': 1352, u'_id': u'fam'}\n", + "{u'count': 1352, u'_id': u'deserve'}\n", + "{u'count': 1351, u'_id': u'lets'}\n", + "{u'count': 1351, u'_id': u'bill'}\n", + "{u'count': 1350, u'_id': u'basketball'}\n", + "{u'count': 1349, u'_id': u'beer'}\n", + "{u'count': 1347, u'_id': u'dick'}\n", + "{u'count': 1346, u'_id': u'spend'}\n", + "{u'count': 1345, u'_id': u'bought'}\n", + "{u'count': 1344, u'_id': u'chill'}\n", + "{u'count': 1343, u'_id': u'tickets'}\n", + "{u'count': 1343, u'_id': u'24'}\n", + "{u'count': 1340, u'_id': u'sitting'}\n", + "{u'count': 1340, u'_id': u'sucks'}\n", + "{u'count': 1338, u'_id': u'telling'}\n", + "{u'count': 1336, u'_id': u'ugh'}\n", + "{u'count': 1334, u'_id': u'calling'}\n", + "{u'count': 1334, u'_id': u'watched'}\n", + "{u'count': 1327, u'_id': u'east'}\n", + "{u'count': 1326, u'_id': u'snow'}\n", + "{u'count': 1326, u'_id': u'sit'}\n", + "{u'count': 1321, u'_id': u'+'}\n", + "{u'count': 1321, u'_id': u'entire'}\n", + "{u'count': 1319, u'_id': u'dr'}\n", + "{u'count': 1317, u'_id': u'event'}\n", + "{u'count': 1315, u'_id': u'list'}\n", + "{u'count': 1314, u'_id': u'holy'}\n", + "{u'count': 1312, u'_id': u'episode'}\n", + "{u'count': 1312, u'_id': u'march'}\n", + "{u'count': 1311, u'_id': u'pictures'}\n", + "{u'count': 1310, u'_id': u'boyfriend'}\n", + "{u'count': 1309, u'_id': u'met'}\n", + "{u'count': 1309, u'_id': u'shows'}\n", + "{u'count': 1308, u'_id': u'traffic'}\n", + "{u'count': 1307, u'_id': u'happens'}\n", + "{u'count': 1302, u'_id': u'snapchat'}\n", + "{u'count': 1300, u'_id': u'coach'}\n", + "{u'count': 1298, u'_id': u'wit'}\n", + "{u'count': 1297, u'_id': u'level'}\n", + "{u'count': 1297, u'_id': u'wild'}\n", + "{u'count': 1296, u'_id': u'g'}\n", + "{u'count': 1295, u'_id': u'green'}\n", + "{u'count': 1295, u'_id': u'beauty'}\n", + "{u'count': 1294, u'_id': u'others'}\n", + "{u'count': 1293, u'_id': u'university'}\n", + "{u'count': 1291, u'_id': u'tuesday'}\n", + "{u'count': 1285, u'_id': u'3rd'}\n", + "{u'count': 1284, u'_id': u'truly'}\n", + "{u'count': 1280, u'_id': u'huge'}\n", + "{u'count': 1273, u'_id': u'relationship'}\n", + "{u'count': 1272, u'_id': u'test'}\n", + "{u'count': 1271, u'_id': u'p'}\n", + "{u'count': 1270, u'_id': u'quick'}\n", + "{u'count': 1270, u'_id': u'whatever'}\n", + "{u'count': 1270, u'_id': u'station'}\n", + "{u'count': 1264, u'_id': u'wins'}\n", + "{u'count': 1264, u'_id': u'registered'}\n", + "{u'count': 1259, u'_id': u'death'}\n", + "{u'count': 1259, u'_id': u'sc'}\n", + "{u'count': 1259, u'_id': u'visit'}\n", + "{u'count': 1258, u'_id': u'fr'}\n", + "{u'count': 1258, u'_id': u'17'}\n", + "{u'count': 1256, u'_id': u'sense'}\n", + "{u'count': 1252, u'_id': u'air'}\n", + "{u'count': 1247, u'_id': u'serious'}\n", + "{u'count': 1246, u'_id': u'wonderful'}\n", + "{u'count': 1245, u'_id': u'snap'}\n", + "{u'count': 1240, u'_id': u'cleared'}\n", + "{u'count': 1237, u'_id': u'scared'}\n", + "{u'count': 1237, u'_id': u'speak'}\n", + "{u'count': 1236, u'_id': u'wi'}\n", + "{u'count': 1232, u'_id': u'experience'}\n", + "{u'count': 1231, u'_id': u'chicken'}\n", + "{u'count': 1227, u'_id': u'fuckin'}\n", + "{u'count': 1226, u'_id': u'public'}\n", + "{u'count': 1225, u'_id': u'due'}\n", + "{u'count': 1224, u'_id': u'21'}\n", + "{u'count': 1223, u'_id': u'boo'}\n", + "{u'count': 1219, u'_id': u'racist'}\n", + "{u'count': 1217, u'_id': u'suck'}\n", + "{u'count': 1216, u'_id': u'laugh'}\n", + "{u'count': 1216, u'_id': u'associate'}\n", + "{u'count': 1214, u'_id': u'thursday'}\n", + "{u'count': 1213, u'_id': u'13'}\n", + "{u'count': 1213, u'_id': u'november'}\n", + "{u'count': 1210, u'_id': u'pull'}\n", + "{u'count': 1210, u'_id': u'sky'}\n", + "{u'count': 1207, u'_id': u'50'}\n", + "{u'count': 1206, u'_id': u'soul'}\n", + "{u'count': 1205, u'_id': u'imma'}\n", + "{u'count': 1202, u'_id': u'final'}\n", + "{u'count': 1201, u'_id': u'paid'}\n", + "{u'count': 1199, u'_id': u'yea'}\n", + "{u'count': 1197, u'_id': u'church'}\n", + "{u'count': 1197, u'_id': u'voice'}\n", + "{u'count': 1194, u'_id': u'inside'}\n", + "{u'count': 1193, u'_id': u'moving'}\n", + "{u'count': 1191, u'_id': u'hoes'}\n", + "{u'count': 1189, u'_id': u\"here's\"}\n", + "{u'count': 1186, u'_id': u'totally'}\n", + "{u'count': 1185, u'_id': u'attention'}\n", + "{u'count': 1182, u'_id': u'x'}\n", + "{u'count': 1179, u'_id': u'child'}\n", + "{u'count': 1174, u'_id': u'movies'}\n", + "{u'count': 1174, u'_id': u'goal'}\n", + "{u'count': 1174, u'_id': u'smoke'}\n", + "{u'count': 1169, u'_id': u'wife'}\n", + "{u'count': 1169, u'_id': u'mph'}\n", + "{u'count': 1168, u'_id': u'states'}\n", + "{u'count': 1166, u'_id': u'annoying'}\n", + "{u'count': 1166, u'_id': u'link'}\n", + "{u'count': 1164, u'_id': u'asking'}\n", + "{u'count': 1163, u'_id': u'human'}\n", + "{u'count': 1163, u'_id': u'pics'}\n", + "{u'count': 1161, u'_id': u'felt'}\n", + "{u'count': 1157, u'_id': u'deserves'}\n", + "{u'count': 1155, u'_id': u'cat'}\n", + "{u'count': 1153, u'_id': u'pls'}\n", + "{u'count': 1153, u'_id': u'control'}\n", + "{u'count': 1153, u'_id': u'john'}\n", + "{u'count': 1151, u'_id': u'biggest'}\n", + "{u'count': 1151, u'_id': u'feelings'}\n", + "{u'count': 1150, u'_id': u'piece'}\n", + "{u'count': 1143, u'_id': u'add'}\n", + "{u'count': 1143, u'_id': u'happening'}\n", + "{u'count': 1142, u'_id': u'supposed'}\n", + "{u'count': 1142, u'_id': u'driving'}\n" + ] + } + ], + "source": [ + "for element in db.tweet_subset.aggregate(pipeline):\n", + " print element" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": true, + "deletable": true, + "editable": true + }, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 2", + "language": "python", + "name": "python2" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 2 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython2", + "version": "2.7.14" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} diff --git a/tut3.py b/mongodb_tut3.py similarity index 100% rename from tut3.py rename to mongodb_tut3.py diff --git a/mongodb_tut4.ipynb b/mongodb_tut4.ipynb new file mode 100644 index 0000000..efcb4d7 --- /dev/null +++ b/mongodb_tut4.ipynb @@ -0,0 +1,2177 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": { + "deletable": true, + "editable": true + }, + "source": [ + "## Setup" + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": { + "collapsed": true, + "deletable": true, + "editable": true + }, + "outputs": [], + "source": [ + "from pymongo import MongoClient\n", + "\n", + "db = MongoClient('mongodb://143.215.138.132:27017')['big_data']" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "deletable": true, + "editable": true + }, + "source": [ + "## Find Prolific Tweet Writers\n", + "\n", + "Last time: Fetch all tweets, build a counter (dictionary) locally, and sort locally.\n", + "\n", + "This time: Make counting and sorting queries to the server, and then fetch data." + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": { + "collapsed": true, + "deletable": true, + "editable": true + }, + "outputs": [], + "source": [ + "group = {'$group': {'_id': '$author_name', 'count': {'$sum': 1}}}\n", + "\n", + "sort = {'$sort': {'count': -1}}\n", + "\n", + "limit = {'$limit': 1000}\n", + "\n", + "pipeline = [group, sort, limit]" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": { + "collapsed": false, + "deletable": true, + "editable": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{u'count': 1289, u'_id': u'.'}\n", + "{u'count': 1135, u'_id': u'511 New York'}\n", + "{u'count': 686, u'_id': u'\\u3164'}\n", + "{u'count': 538, u'_id': u'SF311 Reports'}\n", + "{u'count': 532, u'_id': u'SONIC Jobs'}\n", + "{u'count': 530, u'_id': u'511NY - New Jersey'}\n", + "{u'count': 522, u'_id': u'B'}\n", + "{u'count': 504, u'_id': u'511 NYC Area'}\n", + "{u'count': 417, u'_id': u'\\u2728'}\n", + "{u'count': 375, u'_id': u'lex'}\n", + "{u'count': 372, u'_id': u'Chris'}\n", + "{u'count': 364, u'_id': u'J'}\n", + "{u'count': 340, u'_id': u'Alex'}\n", + "{u'count': 336, u'_id': u'\\U0001f451'}\n", + "{u'count': 327, u'_id': u'em'}\n", + "{u'count': 323, u'_id': u'Michael'}\n", + "{u'count': 318, u'_id': u'Mike'}\n", + "{u'count': 315, u'_id': u'ash'}\n", + "{u'count': 314, u'_id': u'Jobs at VA'}\n", + "{u'count': 309, u'_id': u'Panera Careers'}\n", + "{u'count': 309, u'_id': u'Trendinalia USA'}\n", + "{u'count': 291, u'_id': u'Kindred Jobs'}\n", + "{u'count': 291, u'_id': u'Sarah'}\n", + "{u'count': 290, u'_id': u'Ryan'}\n", + "{u'count': 287, u'_id': u'Speedway Jobs'}\n", + "{u'count': 285, u'_id': u'Matt'}\n", + "{u'count': 285, u'_id': u'Lauren'}\n", + "{u'count': 273, u'_id': u'Emily'}\n", + "{u'count': 269, u'_id': u'SHC Careers'}\n", + "{u'count': 268, u'_id': u'Jay'}\n", + "{u'count': 267, u'_id': u'TMJ-LAX HRTA Jobs'}\n", + "{u'count': 266, u'_id': u'Lex'}\n", + "{u'count': 262, u'_id': u'CVS Health Jobs'}\n", + "{u'count': 260, u'_id': u'Hannah'}\n", + "{u'count': 260, u'_id': u'David'}\n", + "{u'count': 257, u'_id': u'CUBE Live'}\n", + "{u'count': 256, u'_id': u'Jordan'}\n", + "{u'count': 256, u'_id': u'Em'}\n", + "{u'count': 256, u'_id': u'Jess'}\n", + "{u'count': 253, u'_id': u'D'}\n", + "{u'count': 253, u'_id': u'Ashley'}\n", + "{u'count': 252, u'_id': u'alex'}\n", + "{u'count': 251, u'_id': u'Sam'}\n", + "{u'count': 249, u'_id': u'Taylor'}\n", + "{u'count': 249, u'_id': u'b'}\n", + "{u'count': 246, u'_id': u'Tay'}\n", + "{u'count': 241, u'_id': u'Justin'}\n", + "{u'count': 240, u'_id': u'Daniel'}\n", + "{u'count': 240, u'_id': u'sarah'}\n", + "{u'count': 238, u'_id': u'Chicago Hospitality'}\n", + "{u'count': 235, u'_id': u'Katie'}\n", + "{u'count': 234, u'_id': u'Nick'}\n", + "{u'count': 234, u'_id': u'T'}\n", + "{u'count': 232, u'_id': u'\\U0001f339'}\n", + "{u'count': 230, u'_id': u'K'}\n", + "{u'count': 228, u'_id': u'Anthony'}\n", + "{u'count': 228, u'_id': u'John'}\n", + "{u'count': 225, u'_id': u'Weather'}\n", + "{u'count': 225, u'_id': u'RH Finance Jobs'}\n", + "{u'count': 223, u'_id': u'emily'}\n", + "{u'count': 220, u'_id': u'TPS Calls'}\n", + "{u'count': 220, u'_id': u'OfficeTeam Jobs'}\n", + "{u'count': 219, u'_id': u'sam'}\n", + "{u'count': 218, u'_id': u'Clayton, NC Weather'}\n", + "{u'count': 217, u'_id': u'IASIS Careers'}\n", + "{u'count': 215, u'_id': u'Brandon'}\n", + "{u'count': 214, u'_id': u'Jason'}\n", + "{u'count': 214, u'_id': u'Josh'}\n", + "{u'count': 213, u'_id': u'Megan'}\n", + "{u'count': 212, u'_id': u'TMJ-USA Cosmo Jobs'}\n", + "{u'count': 210, u'_id': u'Nicole'}\n", + "{u'count': 210, u'_id': u'Jake'}\n", + "{u'count': 208, u'_id': u'Ulta Beauty Jobs'}\n", + "{u'count': 208, u'_id': u'jess'}\n", + "{u'count': 207, u'_id': u'Tyler'}\n", + "{u'count': 207, u'_id': u'Ash'}\n", + "{u'count': 204, u'_id': u'BOS:311 Reports'}\n", + "{u'count': 203, u'_id': u'Join BAYADA'}\n", + "{u'count': 200, u'_id': u'TMJ- HOU Health Jobs'}\n", + "{u'count': 200, u'_id': u'Andrew'}\n", + "{u'count': 196, u'_id': u'Accountemps Jobs'}\n", + "{u'count': 196, u'_id': u'DollarGeneralCareers'}\n", + "{u'count': 195, u'_id': u'Sunrise Careers'}\n", + "{u'count': 194, u'_id': u'tay'}\n", + "{u'count': 193, u'_id': u'Samantha'}\n", + "{u'count': 192, u'_id': u'hannah'}\n", + "{u'count': 191, u'_id': u'GDKN'}\n", + "{u'count': 190, u'_id': u'taylor'}\n", + "{u'count': 188, u'_id': u'j'}\n", + "{u'count': 188, u'_id': u'Destination Jobs'}\n", + "{u'count': 187, u'_id': u'TMJ- DFW Health Jobs'}\n", + "{u'count': 185, u'_id': u'G'}\n", + "{u'count': 184, u'_id': u'\\u2661'}\n", + "{u'count': 184, u'_id': u'Brian'}\n", + "{u'count': 182, u'_id': u'James'}\n", + "{u'count': 180, u'_id': u'A'}\n", + "{u'count': 180, u'_id': u'Amanda'}\n", + "{u'count': 180, u'_id': u'Stephanie'}\n", + "{u'count': 176, u'_id': u'TMJ-HOU Nursing Jobs'}\n", + "{u'count': 176, u'_id': u'lauren'}\n", + "{u'count': 175, u'_id': u'Nevada City Weather'}\n", + "{u'count': 173, u'_id': u'Eric'}\n", + "{u'count': 172, u'_id': u'syd'}\n", + "{u'count': 172, u'_id': u'Rachel'}\n", + "{u'count': 172, u'_id': u'Kevin'}\n", + "{u'count': 172, u'_id': u'Alexis'}\n", + "{u'count': 172, u'_id': u'mads'}\n", + "{u'count': 172, u'_id': u'Austin'}\n", + "{u'count': 168, u'_id': u'liv'}\n", + "{u'count': 167, u'_id': u\"Love's Jobs\"}\n", + "{u'count': 165, u'_id': u'Joe'}\n", + "{u'count': 164, u'_id': u'511NY - Catskills'}\n", + "{u'count': 162, u'_id': u'Alyssa'}\n", + "{u'count': 162, u'_id': u'kayla'}\n", + "{u'count': 161, u'_id': u'ashley'}\n", + "{u'count': 161, u'_id': u'Zach'}\n", + "{u'count': 160, u'_id': u'Laura'}\n", + "{u'count': 160, u'_id': u'alyssa'}\n", + "{u'count': 160, u'_id': u'Morgan'}\n", + "{u'count': 159, u'_id': u'Mary'}\n", + "{u'count': 159, u'_id': u'E'}\n", + "{u'count': 159, u'_id': u'M'}\n", + "{u'count': 158, u'_id': u'Kate'}\n", + "{u'count': 158, u'_id': u'Michelle'}\n", + "{u'count': 158, u'_id': u'Bri'}\n", + "{u'count': 158, u'_id': u'Mercy Jobs'}\n", + "{u'count': 157, u'_id': u'Virtual Jukebox'}\n", + "{u'count': 157, u'_id': u'Jessica'}\n", + "{u'count': 156, u'_id': u'James Neva'}\n", + "{u'count': 156, u'_id': u'bri'}\n", + "{u'count': 155, u'_id': u'AvalonBay Jobs'}\n", + "{u'count': 153, u'_id': u'CompassUSAJobBoard'}\n", + "{u'count': 152, u'_id': u'Total Traffic NYC'}\n", + "{u'count': 152, u'_id': u'Regions Bank'}\n", + "{u'count': 151, u'_id': u'\\U0001f940'}\n", + "{u'count': 150, u'_id': u'Cintas Careers'}\n", + "{u'count': 149, u'_id': u'Meg'}\n", + "{u'count': 148, u'_id': u'Noodles Careers'}\n", + "{u'count': 147, u'_id': u'HMSHost Jobs'}\n", + "{u'count': 147, u'_id': u'Dan'}\n", + "{u'count': 147, u'_id': u'Kayla'}\n", + "{u'count': 146, u'_id': u\"BJ's Restaurants\"}\n", + "{u'count': 146, u'_id': u'LA Healthcare Jobs'}\n", + "{u'count': 146, u'_id': u'B.'}\n", + "{u'count': 145, u'_id': u'Scott'}\n", + "{u'count': 143, u'_id': u'Steve'}\n", + "{u'count': 143, u'_id': u'Nordstrom Jobs'}\n", + "{u'count': 143, u'_id': u'Baltimore City 311'}\n", + "{u'count': 142, u'_id': u'Denver Hospitality'}\n", + "{u'count': 142, u'_id': u'Mark'}\n", + "{u'count': 142, u'_id': u'...'}\n", + "{u'count': 142, u'_id': u'kay'}\n", + "{u'count': 142, u'_id': u'\\U0001f48b'}\n", + "{u'count': 141, u'_id': u'Kyle'}\n", + "{u'count': 141, u'_id': u'jordan'}\n", + "{u'count': 141, u'_id': u'Aaron'}\n", + "{u'count': 140, u'_id': u'@haircutteryjob'}\n", + "{u'count': 138, u'_id': u'Lisa'}\n", + "{u'count': 137, u'_id': u'US Hospitality Jobs'}\n", + "{u'count': 137, u'_id': u'meg'}\n", + "{u'count': 137, u'_id': u'\\u2122'}\n", + "{u'count': 136, u'_id': u'Jen'}\n", + "{u'count': 135, u'_id': u'kenz'}\n", + "{u'count': 135, u'_id': u'Robert'}\n", + "{u'count': 135, u'_id': u'\\U0001f5a4'}\n", + "{u'count': 135, u'_id': u'Kay'}\n", + "{u'count': 135, u'_id': u'Emma'}\n", + "{u'count': 134, u'_id': u'Paul'}\n", + "{u'count': 134, u'_id': u'jay'}\n", + "{u'count': 134, u'_id': u'ATL Hospitality Jobs'}\n", + "{u'count': 134, u'_id': u'Melissa'}\n", + "{u'count': 133, u'_id': u'Ty'}\n", + "{u'count': 131, u'_id': u'\\u3164\\u3164\\u3164'}\n", + "{u'count': 131, u'_id': u'Madison'}\n", + "{u'count': 131, u'_id': u'Vanessa'}\n", + "{u'count': 131, u'_id': u'katie'}\n", + "{u'count': 130, u'_id': u'Elizabeth'}\n", + "{u'count': 130, u'_id': u'Liz'}\n", + "{u'count': 129, u'_id': u'Brittany'}\n", + "{u'count': 129, u'_id': u'Portland Police log'}\n", + "{u'count': 129, u'_id': u'Rich'}\n", + "{u'count': 129, u'_id': u'Carl King'}\n", + "{u'count': 129, u'_id': u'Proviscalling'}\n", + "{u'count': 128, u'_id': u'amanda'}\n", + "{u'count': 128, u'_id': u'kat'}\n", + "{u'count': 128, u'_id': u'TMJ-CA HRTA Jobs'}\n", + "{u'count': 128, u'_id': u'nicole'}\n", + "{u'count': 128, u'_id': u'Drew'}\n", + "{u'count': 128, u'_id': u'megan'}\n", + "{u'count': 127, u'_id': u'TMJ-BOS HRTA Jobs'}\n", + "{u'count': 127, u'_id': u'han'}\n", + "{u'count': 126, u'_id': u'Brooke'}\n", + "{u'count': 125, u'_id': u'\\ufe0f'}\n", + "{u'count': 125, u'_id': u'TMJ-MSP HRTA Jobs'}\n", + "{u'count': 125, u'_id': u'Kat'}\n", + "{u'count': 125, u'_id': u'Erin'}\n", + "{u'count': 125, u'_id': u'Liv'}\n", + "{u'count': 124, u'_id': u'Mel'}\n", + "{u'count': 124, u'_id': u'haley'}\n", + "{u'count': 124, u'_id': u'Amy'}\n", + "{u'count': 123, u'_id': u'maurices careers'}\n", + "{u'count': 123, u'_id': u'$'}\n", + "{u'count': 122, u'_id': u'MENTOR Network Jobs'}\n", + "{u'count': 122, u'_id': u'Jeff'}\n", + "{u'count': 121, u'_id': u'vanessa'}\n", + "{u'count': 121, u'_id': u'Victoria'}\n", + "{u'count': 121, u'_id': u'Brad'}\n", + "{u'count': 121, u'_id': u'JP'}\n", + "{u'count': 121, u'_id': u'Han'}\n", + "{u'count': 121, u'_id': u'Dallas Hospitality'}\n", + "{u'count': 120, u'_id': u'TMJ-TX HRTA Jobs'}\n", + "{u'count': 120, u'_id': u'MJ'}\n", + "{u'count': 119, u'_id': u'Janie'}\n", + "{u'count': 119, u'_id': u'grace'}\n", + "{u'count': 118, u'_id': u'Courtney'}\n", + "{u'count': 118, u'_id': u'maddie'}\n", + "{u'count': 118, u'_id': u'k'}\n", + "{u'count': 118, u'_id': u'Danielle'}\n", + "{u'count': 118, u'_id': u'Lexi'}\n", + "{u'count': 118, u'_id': u'Sara'}\n", + "{u'count': 117, u'_id': u'morgan'}\n", + "{u'count': 117, u'_id': u'alexis'}\n", + "{u'count': 117, u'_id': u'Natalie'}\n", + "{u'count': 117, u'_id': u'Dom'}\n", + "{u'count': 116, u'_id': u'CTS Jobs'}\n", + "{u'count': 116, u'_id': u'V'}\n", + "{u'count': 115, u'_id': u'C'}\n", + "{u'count': 115, u'_id': u'Dave'}\n", + "{u'count': 115, u'_id': u'Jasmine'}\n", + "{u'count': 115, u'_id': u'Ken'}\n", + "{u'count': 115, u'_id': u'Ben'}\n", + "{u'count': 115, u'_id': u'nat'}\n", + "{u'count': 115, u'_id': u'Diana'}\n", + "{u'count': 114, u'_id': u'Jenna'}\n", + "{u'count': 114, u'_id': u'Jennifer'}\n", + "{u'count': 113, u'_id': u'Hunter'}\n", + "{u'count': 113, u'_id': u'Will'}\n", + "{u'count': 113, u'_id': u'Matthew'}\n", + "{u'count': 113, u'_id': u'tori'}\n", + "{u'count': 112, u'_id': u'liz'}\n", + "{u'count': 112, u'_id': u'\\U0001f33b'}\n", + "{u'count': 112, u'_id': u'A.'}\n", + "{u'count': 111, u'_id': u'Sydney'}\n", + "{u'count': 111, u'_id': u'-'}\n", + "{u'count': 111, u'_id': u'Amber'}\n", + "{u'count': 111, u'_id': u'Rob'}\n", + "{u'count': 111, u'_id': u'Danny'}\n", + "{u'count': 111, u'_id': u'Q'}\n", + "{u'count': 110, u'_id': u'madison'}\n", + "{u'count': 110, u'_id': u'Mads'}\n", + "{u'count': 110, u'_id': u'\\U0001f984'}\n", + "{u'count': 110, u'_id': u'al'}\n", + "{u'count': 110, u'_id': u'Cam'}\n", + "{u'count': 110, u'_id': u'Anna'}\n", + "{u'count': 109, u'_id': u'AJ'}\n", + "{u'count': 109, u'_id': u'TMJ-STL HRTA Jobs'}\n", + "{u'count': 108, u'_id': u'NYC Hospitality Jobs'}\n", + "{u'count': 108, u'_id': u'WHBM Careers'}\n", + "{u'count': 108, u'_id': u'Sean'}\n", + "{u'count': 108, u'_id': u'Joey'}\n", + "{u'count': 108, u'_id': u'Jacob'}\n", + "{u'count': 108, u'_id': u'S'}\n", + "{u'count': 107, u'_id': u'kt'}\n", + "{u'count': 107, u'_id': u'Ryder Jobs'}\n", + "{u'count': 107, u'_id': u'Adam'}\n", + "{u'count': 106, u'_id': u'kels'}\n", + "{u'count': 106, u'_id': u'Brianna'}\n", + "{u'count': 105, u'_id': u'Christian'}\n", + "{u'count': 105, u'_id': u'TMJ-ORL HRTA Jobs'}\n", + "{u'count': 105, u'_id': u'brooke'}\n", + "{u'count': 105, u'_id': u'Ally'}\n", + "{u'count': 105, u'_id': u'Abby'}\n", + "{u'count': 105, u'_id': u'abby'}\n", + "{u'count': 105, u'_id': u'sav'}\n", + "{u'count': 105, u'_id': u'michael'}\n", + "{u'count': 105, u'_id': u'Syd'}\n", + "{u'count': 104, u'_id': u'court'}\n", + "{u'count': 104, u'_id': u'Andrea'}\n", + "{u'count': 104, u'_id': u'Chicago Retail Jobs'}\n", + "{u'count': 104, u'_id': u'\\xaf\\\\_(\\u30c4)_/\\xaf'}\n", + "{u'count': 104, u'_id': u'Logan'}\n", + "{u'count': 104, u'_id': u'rach'}\n", + "{u'count': 104, u'_id': u'rachel'}\n", + "{u'count': 103, u'_id': u'steph'}\n", + "{u'count': 103, u'_id': u'Los Angeles Jobs'}\n", + "{u'count': 103, u'_id': u'Julie'}\n", + "{u'count': 103, u'_id': u'J.'}\n", + "{u'count': 103, u'_id': u'Jack'}\n", + "{u'count': 103, u'_id': u'cam'}\n", + "{u'count': 103, u'_id': u'emma'}\n", + "{u'count': 103, u'_id': u'Dani'}\n", + "{u'count': 103, u'_id': u'kate'}\n", + "{u'count': 103, u'_id': u'Haley'}\n", + "{u'count': 103, u'_id': u'\\U0001f410'}\n", + "{u'count': 102, u'_id': u'Erica'}\n", + "{u'count': 102, u'_id': u'TMJ-PHL HRTA Jobs'}\n", + "{u'count': 102, u'_id': u'samantha'}\n", + "{u'count': 102, u'_id': u'Heather'}\n", + "{u'count': 101, u'_id': u'One God Only'}\n", + "{u'count': 101, u'_id': u'Jon'}\n", + "{u'count': 101, u'_id': u\"Chico's Careers\"}\n", + "{u'count': 101, u'_id': u'Paige'}\n", + "{u'count': 100, u'_id': u'Newark Hosp/Rest/Tou'}\n", + "{u'count': 100, u'_id': u'K.'}\n", + "{u'count': 100, u'_id': u'TMJ-AR HRTA Jobs'}\n", + "{u'count': 100, u'_id': u'Monica'}\n", + "{u'count': 100, u'_id': u'Steph'}\n", + "{u'count': 100, u'_id': u'Lo'}\n", + "{u'count': 100, u'_id': u'RestaurantCareers'}\n", + "{u'count': 99, u'_id': u'olivia'}\n", + "{u'count': 99, u'_id': u'm'}\n", + "{u'count': 99, u'_id': u'G RACE'}\n", + "{u'count': 99, u'_id': u'Al'}\n", + "{u'count': 98, u'_id': u'jasmine'}\n", + "{u'count': 98, u'_id': u'Angel'}\n", + "{u'count': 98, u'_id': u'sydney'}\n", + "{u'count': 98, u'_id': u't'}\n", + "{u'count': 98, u'_id': u'Tony'}\n", + "{u'count': 98, u'_id': u'Joshua'}\n", + "{u'count': 97, u'_id': u'Jesse'}\n", + "{u'count': 97, u'_id': u'victoria'}\n", + "{u'count': 97, u'_id': u'Andy'}\n", + "{u'count': 96, u'_id': u'Total Traffic DFW'}\n", + "{u'count': 96, u'_id': u'Nate'}\n", + "{u'count': 96, u'_id': u'TMJ-WAS HRTA Jobs'}\n", + "{u'count': 96, u'_id': u'ken'}\n", + "{u'count': 96, u'_id': u'Maddie'}\n", + "{u'count': 96, u'_id': u'Jenn'}\n", + "{u'count': 96, u'_id': u'Bruno'}\n", + "{u'count': 95, u'_id': u'Nikki'}\n", + "{u'count': 95, u'_id': u'Ray'}\n", + "{u'count': 95, u'_id': u'Cameron Craig Group'}\n", + "{u'count': 94, u'_id': u'Kelly'}\n", + "{u'count': 94, u'_id': u'paige'}\n", + "{u'count': 94, u'_id': u'lyss'}\n", + "{u'count': 94, u'_id': u'UAMS Nursing Jobs'}\n", + "{u'count': 94, u'_id': u'chris'}\n", + "{u'count': 94, u'_id': u'TMJ-USA Cleric. Jobs'}\n", + "{u'count': 93, u'_id': u'KT'}\n", + "{u'count': 93, u'_id': u'Patrick'}\n", + "{u'count': 93, u'_id': u'Jules'}\n", + "{u'count': 93, u'_id': u'TMJ-BAL HRTA Jobs'}\n", + "{u'count': 93, u'_id': u'James Wolter'}\n", + "{u'count': 92, u'_id': u'britt'}\n", + "{u'count': 92, u'_id': u'Tweet3po'}\n", + "{u'count': 92, u'_id': u'Seattle Hospitality'}\n", + "{u'count': 92, u'_id': u'PFG Careers'}\n", + "{u'count': 92, u'_id': u'Mouton Cove Weather'}\n", + "{u'count': 91, u'_id': u'Dee'}\n", + "{u'count': 91, u'_id': u'maria'}\n", + "{u'count': 91, u'_id': u'JJ'}\n", + "{u'count': 91, u'_id': u'allison'}\n", + "{u'count': 91, u'_id': u'\\u2022'}\n", + "{u'count': 90, u'_id': u'danielle'}\n", + "{u'count': 90, u'_id': u'jen'}\n", + "{u'count': 90, u'_id': u'\\u2764\\ufe0f'}\n", + "{u'count': 90, u'_id': u'dani'}\n", + "{u'count': 90, u'_id': u'Jonathan'}\n", + "{u'count': 89, u'_id': u'Cass'}\n", + "{u'count': 89, u'_id': u'mel'}\n", + "{u'count': 89, u'_id': u'Boston, MA Jobs'}\n", + "{u'count': 89, u'_id': u'TMJ-CAP HRTA Jobs'}\n", + "{u'count': 88, u'_id': u'TMJ-BNA HRTA Jobs'}\n", + "{u'count': 88, u'_id': u'Mandarin Las Vegas'}\n", + "{u'count': 88, u'_id': u'attCAREERS'}\n", + "{u'count': 88, u'_id': u'Earth Rover Bot'}\n", + "{u'count': 88, u'_id': u'TCG Jobs'}\n", + "{u'count': 88, u'_id': u'Ishmael'}\n", + "{u'count': 87, u'_id': u'Des'}\n", + "{u'count': 87, u'_id': u'\\u2605\\u2605\\u2605Stephen Nix\\u2605\\u2605\\u2605'}\n", + "{u'count': 87, u'_id': u'Angela'}\n", + "{u'count': 87, u'_id': u'Mo'}\n", + "{u'count': 87, u'_id': u'TMJ-PIT HRTA Jobs'}\n", + "{u'count': 87, u'_id': u'Maria'}\n", + "{u'count': 87, u'_id': u'Einstein Bros. Jobs'}\n", + "{u'count': 87, u'_id': u'TMJ-LAX Legal Jobs'}\n", + "{u'count': 87, u'_id': u'TMJ-CLT HRTA Jobs'}\n", + "{u'count': 86, u'_id': u'erin'}\n", + "{u'count': 86, u'_id': u'TMJ-DFW Retail Jobs'}\n", + "{u'count': 86, u'_id': u'Providence Careers'}\n", + "{u'count': 86, u'_id': u'Chicago, IL Jobs'}\n", + "{u'count': 86, u'_id': u'Kim'}\n", + "{u'count': 85, u'_id': u'Z'}\n", + "{u'count': 85, u'_id': u'Evan'}\n", + "{u'count': 85, u'_id': u'nick'}\n", + "{u'count': 85, u'_id': u'NYC Jobs'}\n", + "{u'count': 85, u'_id': u'TMJ-AUS HRTA Jobs'}\n", + "{u'count': 85, u'_id': u'TMJ- BOS Health Jobs'}\n", + "{u'count': 85, u'_id': u'HCA'}\n", + "{u'count': 85, u'_id': u'Christina'}\n", + "{u'count': 85, u'_id': u'Sav'}\n", + "{u'count': 85, u'_id': u'Jo'}\n", + "{u'count': 85, u'_id': u'Court'}\n", + "{u'count': 84, u'_id': u'Aurora Careers'}\n", + "{u'count': 84, u'_id': u'\\U0001f338'}\n", + "{u'count': 84, u'_id': u'TMJ-STL Nursing Jobs'}\n", + "{u'count': 84, u'_id': u'Caris Health Jobs'}\n", + "{u'count': 84, u'_id': u'Ry'}\n", + "{u'count': 84, u'_id': u'L'}\n", + "{u'count': 84, u'_id': u'\\U0001f54a'}\n", + "{u'count': 84, u'_id': u'cass'}\n", + "{u'count': 84, u'_id': u'Chelsea'}\n", + "{u'count': 83, u'_id': u'TMJ-AZS HRTA Jobs'}\n", + "{u'count': 83, u'_id': u'Grace'}\n", + "{u'count': 83, u'_id': u'Baltimore Health Job'}\n", + "{u'count': 83, u'_id': u'SF Healthcare Jobs'}\n", + "{u'count': 83, u'_id': u'Linda'}\n", + "{u'count': 83, u'_id': u'P'}\n", + "{u'count': 83, u'_id': u'lexi'}\n", + "{u'count': 83, u'_id': u'Jackie'}\n", + "{u'count': 83, u'_id': u'jessica'}\n", + "{u'count': 83, u'_id': u'Rach'}\n", + "{u'count': 83, u'_id': u'Janet'}\n", + "{u'count': 83, u'_id': u'Dev'}\n", + "{u'count': 82, u'_id': u'princess'}\n", + "{u'count': 82, u'_id': u'madi'}\n", + "{u'count': 82, u'_id': u'Derek'}\n", + "{u'count': 82, u'_id': u'Jobs at Dressbarn'}\n", + "{u'count': 82, u'_id': u'Jamie'}\n", + "{u'count': 82, u'_id': u'Sandra'}\n", + "{u'count': 82, u'_id': u'CGI'}\n", + "{u'count': 82, u'_id': u'TMJ-AR Nursing Jobs'}\n", + "{u'count': 81, u'_id': u'bella'}\n", + "{u'count': 81, u'_id': u'Phoenix Hospitality'}\n", + "{u'count': 81, u'_id': u'TMJ-BOS Retail Jobs'}\n", + "{u'count': 81, u'_id': u'JB'}\n", + "{u'count': 81, u'_id': u'Karen'}\n", + "{u'count': 81, u'_id': u'S.'}\n", + "{u'count': 81, u'_id': u\"Brian Keith O'Hara\"}\n", + "{u'count': 81, u'_id': u'Daddy'}\n", + "{u'count': 81, u'_id': u'TMJ-USA Manuf Jobs'}\n", + "{u'count': 81, u'_id': u'Jenny'}\n", + "{u'count': 81, u'_id': u'Aroon Dani'}\n", + "{u'count': 80, u'_id': u'Mult Co Fire/EMS log'}\n", + "{u'count': 80, u'_id': u'Toronto Fire'}\n", + "{u'count': 80, u'_id': u'Allison'}\n", + "{u'count': 80, u'_id': u'Shannon'}\n", + "{u'count': 80, u'_id': u'd'}\n", + "{u'count': 80, u'_id': u'Meijer Jobs'}\n", + "{u'count': 80, u'_id': u'TMJ- PHL Health Jobs'}\n", + "{u'count': 80, u'_id': u'OC, CA Health Jobs'}\n", + "{u'count': 80, u'_id': u'Tim'}\n", + "{u'count': 80, u'_id': u'Marissa'}\n", + "{u'count': 79, u'_id': u'TMJ-SAT HRTA Jobs'}\n", + "{u'count': 79, u'_id': u'TMJ-GTA Jobs'}\n", + "{u'count': 79, u'_id': u'Mariah'}\n", + "{u'count': 79, u'_id': u'TMJ-PHL Jobs'}\n", + "{u'count': 79, u'_id': u'Bree'}\n", + "{u'count': 79, u'_id': u'julie'}\n", + "{u'count': 79, u'_id': u'Matthew Boicourt'}\n", + "{u'count': 79, u'_id': u'AMC Careers'}\n", + "{u'count': 79, u'_id': u'Christopher'}\n", + "{u'count': 79, u'_id': u'Judy'}\n", + "{u'count': 78, u'_id': u'TMJ-VAV HRTA Jobs'}\n", + "{u'count': 78, u'_id': u'TMJ-BOS Nursing Jobs'}\n", + "{u'count': 78, u'_id': u'Philly Nursing Jobs'}\n", + "{u'count': 78, u'_id': u'JOHN STRONG'}\n", + "{u'count': 78, u'_id': u'TMJ-FLS HRTA Jobs'}\n", + "{u'count': 78, u'_id': u'ryan'}\n", + "{u'count': 78, u'_id': u'Patricia'}\n", + "{u'count': 78, u'_id': u'Pat'}\n", + "{u'count': 78, u'_id': u'gabby'}\n", + "{u'count': 77, u'_id': u'TMJ-MKE HRTA Jobs'}\n", + "{u'count': 77, u'_id': u'..'}\n", + "{u'count': 77, u'_id': u'john beechy'}\n", + "{u'count': 77, u'_id': u'JT'}\n", + "{u'count': 77, u'_id': u'Olivia'}\n", + "{u'count': 77, u'_id': u'Susan'}\n", + "{u'count': 77, u'_id': u'\\U0001f352'}\n", + "{u'count': 77, u'_id': u'Ghirardelli Careers'}\n", + "{u'count': 77, u'_id': u'TMJ-IND HRTA Jobs'}\n", + "{u'count': 77, u'_id': u'Ed'}\n", + "{u'count': 77, u'_id': u'Nathan'}\n", + "{u'count': 76, u'_id': u'Bryan'}\n", + "{u'count': 76, u'_id': u'Tiffany'}\n", + "{u'count': 76, u'_id': u'Marcus'}\n", + "{u'count': 76, u'_id': u'TMJ - CHI Sales Jobs'}\n", + "{u'count': 76, u'_id': u'des'}\n", + "{u'count': 76, u'_id': u'Bailey'}\n", + "{u'count': 76, u'_id': u'ky'}\n", + "{u'count': 76, u'_id': u'Vincent E Ankner'}\n", + "{u'count': 75, u'_id': u'OhioHealth Jobs'}\n", + "{u'count': 75, u'_id': u'TMJ-LAX Nursing Jobs'}\n", + "{u'count': 75, u'_id': u'Sutter Health Jobs'}\n", + "{u'count': 75, u'_id': u'pat.'}\n", + "{u'count': 75, u'_id': u'Rick'}\n", + "{u'count': 75, u'_id': u'Kels'}\n", + "{u'count': 75, u'_id': u'Chicago Health Jobs'}\n", + "{u'count': 75, u'_id': u'Kristen'}\n", + "{u'count': 75, u'_id': u'Rebecca'}\n", + "{u'count': 75, u'_id': u'julia'}\n", + "{u'count': 75, u'_id': u'jon ewall'}\n", + "{u'count': 75, u'_id': u'Tom'}\n", + "{u'count': 75, u'_id': u'Julie Hale'}\n", + "{u'count': 74, u'_id': u'Dylan'}\n", + "{u'count': 74, u'_id': u'Florida Nursing Jobs'}\n", + "{u'count': 74, u'_id': u'Ali'}\n", + "{u'count': 74, u'_id': u'natalie'}\n", + "{u'count': 74, u'_id': u'TMJ-WAT Nursing Jobs'}\n", + "{u'count': 74, u'_id': u'MTC Jobs'}\n", + "{u'count': 74, u'_id': u'Ebb Tide Bot'}\n", + "{u'count': 74, u'_id': u'KC'}\n", + "{u'count': 74, u'_id': u'TM-STL Health Jobs'}\n", + "{u'count': 74, u'_id': u'TJ'}\n", + "{u'count': 74, u'_id': u'TMJ-CA-US Nursing'}\n", + "{u'count': 74, u'_id': u'Julia'}\n", + "{u'count': 73, u'_id': u'Golden Corral Jobs'}\n", + "{u'count': 73, u'_id': u'Carlos'}\n", + "{u'count': 73, u'_id': u'Atlanta, GA Jobs'}\n", + "{u'count': 73, u'_id': u'Cameron'}\n", + "{u'count': 73, u'_id': u'Luke'}\n", + "{u'count': 73, u'_id': u'\\U0001f608'}\n", + "{u'count': 73, u'_id': u'Nat'}\n", + "{u'count': 73, u'_id': u'TMJ-HOU Mgmt. Jobs'}\n", + "{u'count': 73, u'_id': u'United Rentals Jobs'}\n", + "{u'count': 73, u'_id': u'Britt'}\n", + "{u'count': 72, u'_id': u'Leah'}\n", + "{u'count': 72, u'_id': u'Citi Trends Jobs'}\n", + "{u'count': 72, u'_id': u'Steven'}\n", + "{u'count': 72, u'_id': u'claire'}\n", + "{u'count': 72, u'_id': u'UNC Lenoir Careers'}\n", + "{u'count': 72, u'_id': u'Nassau Hospitality'}\n", + "{u'count': 72, u'_id': u'Jerry'}\n", + "{u'count': 72, u'_id': u'Tori'}\n", + "{u'count': 72, u'_id': u'TMJ-PDX HRTA Jobs'}\n", + "{u'count': 72, u'_id': u'Mychel Russell Ward'}\n", + "{u'count': 72, u'_id': u'Connor'}\n", + "{u'count': 71, u'_id': u'jules'}\n", + "{u'count': 71, u'_id': u'CarpoolWorld'}\n", + "{u'count': 71, u'_id': u'g'}\n", + "{u'count': 71, u'_id': u'TMJ-OKC HRTA Jobs'}\n", + "{u'count': 71, u'_id': u'TMJ-CAO Jobs'}\n", + "{u'count': 71, u'_id': u'Max'}\n", + "{u'count': 71, u'_id': u'Jeremy'}\n", + "{u'count': 71, u'_id': u'jas'}\n", + "{u'count': 71, u'_id': u'CHOMP'}\n", + "{u'count': 71, u'_id': u'Miranda'}\n", + "{u'count': 71, u'_id': u'Milwaukee News'}\n", + "{u'count': 71, u'_id': u'Annie'}\n", + "{u'count': 71, u'_id': u'ally'}\n", + "{u'count': 71, u'_id': u'Israel Carbuckle'}\n", + "{u'count': 70, u'_id': u'TMJ-LAX Retail Jobs'}\n", + "{u'count': 70, u'_id': u'CJ'}\n", + "{u'count': 70, u'_id': u'Jimmy'}\n", + "{u'count': 70, u'_id': u'chlo'}\n", + "{u'count': 70, u'_id': u'Dallas, TX Jobs'}\n", + "{u'count': 70, u'_id': u'c'}\n", + "{u'count': 70, u'_id': u'KJ'}\n", + "{u'count': 70, u'_id': u'Caroline'}\n", + "{u'count': 70, u'_id': u'Ky'}\n", + "{u'count': 70, u'_id': u'\\U0001f319'}\n", + "{u'count': 70, u'_id': u'amber'}\n", + "{u'count': 70, u'_id': u'mariah'}\n", + "{u'count': 69, u'_id': u'Bill'}\n", + "{u'count': 69, u'_id': u'a'}\n", + "{u'count': 69, u'_id': u'TMJ-HOU Retail Jobs'}\n", + "{u'count': 69, u'_id': u'stephanie'}\n", + "{u'count': 69, u'_id': u'Cognizant Careers US'}\n", + "{u'count': 69, u'_id': u'Leslie'}\n", + "{u'count': 69, u'_id': u'KB'}\n", + "{u'count': 69, u'_id': u'T.'}\n", + "{u'count': 69, u'_id': u'Jared'}\n", + "{u'count': 69, u'_id': u'\\U0001f334 Ashley Perkins \\U0001f334'}\n", + "{u'count': 69, u'_id': u'TMJ-HOU Educ. Jobs'}\n", + "{u'count': 69, u'_id': u'Sunstate Jobs'}\n", + "{u'count': 69, u'_id': u'anna'}\n", + "{u'count': 69, u'_id': u'Lindsey'}\n", + "{u'count': 68, u'_id': u'Jake Hamby'}\n", + "{u'count': 68, u'_id': u'Stephanie Collins'}\n", + "{u'count': 68, u'_id': u'Richard'}\n", + "{u'count': 68, u'_id': u'josh'}\n", + "{u'count': 68, u'_id': u'TMJ-MIT HRTA Jobs'}\n", + "{u'count': 68, u'_id': u'Brenda'}\n", + "{u'count': 68, u'_id': u'Kelsey'}\n", + "{u'count': 68, u'_id': u'Johnny'}\n", + "{u'count': 68, u'_id': u'TMJ-RDU HRTA Jobs'}\n", + "{u'count': 68, u'_id': u'\\u26a1\\ufe0f'}\n", + "{u'count': 68, u'_id': u'511NY - Long Island'}\n", + "{u'count': 68, u'_id': u'SRHS Careers'}\n", + "{u'count': 68, u'_id': u'Cody'}\n", + "{u'count': 68, u'_id': u'Chase'}\n", + "{u'count': 68, u'_id': u'Kimberly'}\n", + "{u'count': 68, u'_id': u'TMJ-SFO Jobs'}\n", + "{u'count': 68, u'_id': u'Sabrina'}\n", + "{u'count': 67, u'_id': u'_'}\n", + "{u'count': 67, u'_id': u'Nick Moreno'}\n", + "{u'count': 67, u'_id': u'Statewide CTDOT'}\n", + "{u'count': 67, u'_id': u'\\u265b'}\n", + "{u'count': 67, u'_id': u'andrea'}\n", + "{u'count': 67, u'_id': u'NYC Retail Jobs'}\n", + "{u'count': 67, u'_id': u'GRACE HOLMES'}\n", + "{u'count': 67, u'_id': u'TMJ-CHI Transp. Jobs'}\n", + "{u'count': 67, u'_id': u'soph'}\n", + "{u'count': 67, u'_id': u'jenna'}\n", + "{u'count': 67, u'_id': u'Joel'}\n", + "{u'count': 67, u'_id': u'OC, CA Nursing Jobs'}\n", + "{u'count': 67, u'_id': u'marissa'}\n", + "{u'count': 67, u'_id': u'Christine'}\n", + "{u'count': 66, u'_id': u'Emerson'}\n", + "{u'count': 66, u'_id': u'RH Legal Jobs'}\n", + "{u'count': 66, u'_id': u'sara'}\n", + "{u'count': 66, u'_id': u'caroline'}\n", + "{u'count': 66, u'_id': u'TMJ-DEN Nursing Jobs'}\n", + "{u'count': 66, u'_id': u'courtney'}\n", + "{u'count': 66, u'_id': u'TravelNursesPHP'}\n", + "{u'count': 66, u'_id': u'Fresenius Careers'}\n", + "{u'count': 66, u'_id': u'Charlie'}\n", + "{u'count': 66, u'_id': u'Jas'}\n", + "{u'count': 66, u'_id': u'KP'}\n", + "{u'count': 66, u'_id': u'TMJ-LAS HRTA Jobs'}\n", + "{u'count': 66, u'_id': u'TampaBay Health Job'}\n", + "{u'count': 66, u'_id': u'MSC Jobs'}\n", + "{u'count': 66, u'_id': u'Tommy'}\n", + "{u'count': 66, u'_id': u'Adrian'}\n", + "{u'count': 65, u'_id': u'jo'}\n", + "{u'count': 65, u'_id': u'Deb'}\n", + "{u'count': 65, u'_id': u'TMJ-MS HRTA Jobs'}\n", + "{u'count': 65, u'_id': u'Troy'}\n", + "{u'count': 65, u'_id': u'TMJ-MO HRTA Jobs'}\n", + "{u'count': 65, u'_id': u'linds'}\n", + "{u'count': 65, u'_id': u'CCA'}\n", + "{u'count': 65, u'_id': u'Denise'}\n", + "{u'count': 65, u'_id': u'Charles'}\n", + "{u'count': 65, u'_id': u'Trump Hotels Jobs'}\n", + "{u'count': 65, u'_id': u'Carolyn'}\n", + "{u'count': 64, u'_id': u'CO Hospitality Jobs'}\n", + "{u'count': 64, u'_id': u'Michael Obrien'}\n", + "{u'count': 64, u'_id': u'\\U0001f31e'}\n", + "{u'count': 64, u'_id': u'Soma Careers'}\n", + "{u'count': 64, u'_id': u'Memorial Hermann TA'}\n", + "{u'count': 64, u'_id': u'Patricia Snyder'}\n", + "{u'count': 64, u'_id': u'ari'}\n", + "{u'count': 64, u'_id': u'William'}\n", + "{u'count': 64, u'_id': u'TMJ-KAN HRTA Jobs'}\n", + "{u'count': 63, u'_id': u'maddy'}\n", + "{u'count': 63, u'_id': u'Jobs at Hobsons'}\n", + "{u'count': 63, u'_id': u'TMJ-LAS Jobs'}\n", + "{u'count': 63, u'_id': u'Crystal'}\n", + "{u'count': 63, u'_id': u'tyler'}\n", + "{u'count': 63, u'_id': u'D.'}\n", + "{u'count': 63, u'_id': u'TMJ-FLF HRTA Jobs'}\n", + "{u'count': 63, u'_id': u'TMJ-CIN HRTA Jobs'}\n", + "{u'count': 63, u'_id': u'Frank'}\n", + "{u'count': 63, u'_id': u'Dallas Sales Jobs'}\n", + "{u'count': 63, u'_id': u'Riley'}\n", + "{u'count': 63, u'_id': u'Molly'}\n", + "{u'count': 63, u'_id': u'lil mama'}\n", + "{u'count': 62, u'_id': u'Meredith'}\n", + "{u'count': 62, u'_id': u'Alicia'}\n", + "{u'count': 62, u'_id': u's'}\n", + "{u'count': 62, u'_id': u'Kenz'}\n", + "{u'count': 62, u'_id': u'Shawn'}\n", + "{u'count': 62, u'_id': u'Teresa Morris'}\n", + "{u'count': 62, u'_id': u'Gabby'}\n", + "{u'count': 62, u'_id': u'Erika'}\n", + "{u'count': 62, u'_id': u'TMJ-PHL Retail Jobs'}\n", + "{u'count': 62, u'_id': u'Vic'}\n", + "{u'count': 62, u'_id': u'Stephen'}\n", + "{u'count': 62, u'_id': u'Rose'}\n", + "{u'count': 62, u'_id': u'Central Garden & Pet'}\n", + "{u'count': 62, u'_id': u'Alexandra'}\n", + "{u'count': 62, u'_id': u'brianna'}\n", + "{u'count': 62, u'_id': u'Noah'}\n", + "{u'count': 62, u'_id': u'Kenny'}\n", + "{u'count': 62, u'_id': u'Joseph'}\n", + "{u'count': 61, u'_id': u'chels'}\n", + "{u'count': 61, u'_id': u'Rae'}\n", + "{u'count': 61, u'_id': u'#FREEGATES'}\n", + "{u'count': 61, u'_id': u'594 Graffiti'}\n", + "{u'count': 61, u'_id': u'Sierra'}\n", + "{u'count': 61, u'_id': u'kenzie'}\n", + "{u'count': 61, u'_id': u'TMJ-HOU Jobs'}\n", + "{u'count': 61, u'_id': u'Aly'}\n", + "{u'count': 61, u'_id': u'Atlanta Nursing Jobs'}\n", + "{u'count': 61, u'_id': u'Madi'}\n", + "{u'count': 61, u'_id': u'Nassau Retail'}\n", + "{u'count': 61, u'_id': u'Ian'}\n", + "{u'count': 61, u'_id': u'matt'}\n", + "{u'count': 61, u'_id': u'BH Media Jobs'}\n", + "{u'count': 61, u'_id': u'Lyss'}\n", + "{u'count': 61, u'_id': u'JONATHON'}\n", + "{u'count': 61, u'_id': u'Zlicepromoteam'}\n", + "{u'count': 61, u'_id': u'TMJ-OK HRTA Jobs'}\n", + "{u'count': 61, u'_id': u'TMJ-TUL HRTA Jobs'}\n", + "{u'count': 61, u'_id': u'Kev'}\n", + "{u'count': 61, u'_id': u'Shay'}\n", + "{u'count': 60, u'_id': u'allie'}\n", + "{u'count': 60, u'_id': u'M.'}\n", + "{u'count': 60, u'_id': u'zach'}\n", + "{u'count': 60, u'_id': u'Tara'}\n", + "{u'count': 60, u'_id': u'michelle'}\n", + "{u'count': 60, u'_id': u'shelbs'}\n", + "{u'count': 60, u'_id': u'Matthew Lopez'}\n", + "{u'count': 60, u'_id': u'Kaplan Test Prep'}\n", + "{u'count': 60, u'_id': u'KING BRYON SHARPE'}\n", + "{u'count': 60, u'_id': u'Allie'}\n", + "{u'count': 60, u'_id': u'X'}\n", + "{u'count': 60, u'_id': u'Ethan'}\n", + "{u'count': 60, u'_id': u'MK'}\n", + "{u'count': 60, u'_id': u'molly'}\n", + "{u'count': 60, u'_id': u'Cait'}\n", + "{u'count': 60, u'_id': u'Val'}\n", + "{u'count': 60, u'_id': u'TMJ-PA Health Jobs'}\n", + "{u'count': 60, u'_id': u'destiny'}\n", + "{u'count': 60, u'_id': u'Kam'}\n", + "{u'count': 60, u'_id': u'Alan'}\n", + "{u'count': 60, u'_id': u'jake'}\n", + "{u'count': 60, u'_id': u'Jade'}\n", + "{u'count': 60, u'_id': u'k.'}\n", + "{u'count': 60, u'_id': u'Bash Org'}\n", + "{u'count': 60, u'_id': u'Ron'}\n", + "{u'count': 59, u'_id': u'Sheri Lynn Pritchett'}\n", + "{u'count': 59, u'_id': u'TMJ-GTA HRTA Jobs'}\n", + "{u'count': 59, u'_id': u'babygirl'}\n", + "{u'count': 59, u'_id': u'OG'}\n", + "{u'count': 59, u'_id': u'cait'}\n", + "{u'count': 59, u'_id': u'Maggie'}\n", + "{u'count': 59, u'_id': u'Robert Haviland'}\n", + "{u'count': 59, u'_id': u'Corey'}\n", + "{u'count': 59, u'_id': u'jade'}\n", + "{u'count': 59, u'_id': u'bailey'}\n", + "{u'count': 59, u'_id': u'hailey'}\n", + "{u'count': 59, u'_id': u'TMJ-SJC Jobs'}\n", + "{u'count': 59, u'_id': u'JD'}\n", + "{u'count': 59, u'_id': u'Ramapo Hospitality'}\n", + "{u'count': 59, u'_id': u'Melanie'}\n", + "{u'count': 59, u'_id': u'Casey'}\n", + "{u'count': 59, u'_id': u'christian'}\n", + "{u'count': 59, u'_id': u'TMJ-CLT Jobs'}\n", + "{u'count': 58, u'_id': u'xavier'}\n", + "{u'count': 58, u'_id': u'Milwaukee Health'}\n", + "{u'count': 58, u'_id': u'Charlotte Now'}\n", + "{u'count': 58, u'_id': u'Garrett'}\n", + "{u'count': 58, u'_id': u'Tiffeny Luvs MJ & 3T'}\n", + "{u'count': 58, u'_id': u'TMJ-LAJ HRTA Jobs'}\n", + "{u'count': 58, u'_id': u'Sacramento Health'}\n", + "{u'count': 58, u'_id': u'Michaela'}\n", + "{u'count': 58, u'_id': u'Zack'}\n", + "{u'count': 58, u'_id': u'Swedish Careers'}\n", + "{u'count': 58, u'_id': u'Veronica'}\n", + "{u'count': 58, u'_id': u'Savannah'}\n", + "{u'count': 58, u'_id': u'TCC Careers'}\n", + "{u'count': 58, u'_id': u'Mac'}\n", + "{u'count': 58, u'_id': u'TMJ-MKE Nursing Jobs'}\n", + "{u'count': 58, u'_id': u'TMJ- PHX Health Jobs'}\n", + "{u'count': 57, u'_id': u'Premise Health'}\n", + "{u'count': 57, u'_id': u'Total Traffic SEA'}\n", + "{u'count': 57, u'_id': u'TMJ-SAN HRTA Jobs'}\n", + "{u'count': 57, u'_id': u'Kris'}\n", + "{u'count': 57, u'_id': u'kaitlyn'}\n", + "{u'count': 57, u'_id': u'TMJ-HOU Cleric. Jobs'}\n", + "{u'count': 57, u'_id': u'miranda'}\n", + "{u'count': 57, u'_id': u'laur'}\n", + "{u'count': 57, u'_id': u'kait'}\n", + "{u'count': 57, u'_id': u'Gabe'}\n", + "{u'count': 57, u'_id': u'MHCD Careers'}\n", + "{u'count': 57, u'_id': u'sky'}\n", + "{u'count': 57, u'_id': u'Marie'}\n", + "{u'count': 57, u'_id': u'Jobs at Continuum'}\n", + "{u'count': 57, u'_id': u'Jody'}\n", + "{u'count': 57, u'_id': u'jackie'}\n", + "{u'count': 56, u'_id': u'Chuck'}\n", + "{u'count': 56, u'_id': u'Devin'}\n", + "{u'count': 56, u'_id': u'TMJ-SFO HRTA Jobs'}\n", + "{u'count': 56, u'_id': u'Baltimore Now'}\n", + "{u'count': 56, u'_id': u'JC'}\n", + "{u'count': 56, u'_id': u'FREE HUGS \\U0001f1e7\\U0001f1e6'}\n", + "{u'count': 56, u'_id': u'mo'}\n", + "{u'count': 56, u'_id': u'e'}\n", + "{u'count': 56, u'_id': u'Dave Morrison'}\n", + "{u'count': 56, u'_id': u'Seattle CP'}\n", + "{u'count': 56, u'_id': u'Boston Sales Jobs'}\n", + "{u'count': 56, u'_id': u'TMJ-TX Retail Jobs'}\n", + "{u'count': 56, u'_id': u'Beth'}\n", + "{u'count': 56, u'_id': u'Lee'}\n", + "{u'count': 56, u'_id': u'TMJ-CAO Retail Jobs'}\n", + "{u'count': 56, u'_id': u'Kent Palmer'}\n", + "{u'count': 56, u'_id': u'TM-KAN Health Jobs'}\n", + "{u'count': 55, u'_id': u'KG'}\n", + "{u'count': 55, u'_id': u'Mari'}\n", + "{u'count': 55, u'_id': u'Columbus Health Jobs'}\n", + "{u'count': 55, u'_id': u'Debbie'}\n", + "{u'count': 55, u'_id': u'King'}\n", + "{u'count': 55, u'_id': u'shan'}\n", + "{u'count': 55, u'_id': u'Denver Now'}\n", + "{u'count': 55, u'_id': u'Jose'}\n", + "{u'count': 55, u'_id': u'Washington Press'}\n", + "{u'count': 55, u'_id': u'Tookie Trilliams'}\n", + "{u'count': 55, u'_id': u'cat'}\n", + "{u'count': 55, u'_id': u'Thomas'}\n", + "{u'count': 55, u'_id': u'You'}\n", + "{u'count': 55, u'_id': u'TMJ-SDF HRTA Jobs'}\n", + "{u'count': 55, u'_id': u'TMJ-CLE HRTA Jobs'}\n", + "{u'count': 55, u'_id': u'Seattle Health Jobs'}\n", + "{u'count': 55, u'_id': u'Nancy'}\n", + "{u'count': 55, u'_id': u'anthony'}\n", + "{u'count': 55, u'_id': u'TMJ-RIP Jobs'}\n", + "{u'count': 55, u'_id': u'Ant'}\n", + "{u'count': 55, u'_id': u'Tina'}\n", + "{u'count': 55, u'_id': u'Las Vegas Press'}\n", + "{u'count': 55, u'_id': u'kelsey'}\n", + "{u'count': 55, u'_id': u'IG & SC: Zztro'}\n", + "{u'count': 55, u'_id': u'Lori'}\n", + "{u'count': 55, u'_id': u'TMJ-TN HRTA Jobs'}\n", + "{u'count': 55, u'_id': u'vic'}\n", + "{u'count': 54, u'_id': u'brittany'}\n", + "{u'count': 54, u'_id': u'Mitch'}\n", + "{u'count': 54, u'_id': u'Mar'}\n", + "{u'count': 54, u'_id': u'jacob'}\n", + "{u'count': 54, u'_id': u'Newark Other'}\n", + "{u'count': 54, u'_id': u'TTN Houston'}\n", + "{u'count': 54, u'_id': u'Cory'}\n", + "{u'count': 54, u'_id': u'#NotMyPresident'}\n", + "{u'count': 54, u'_id': u'TMJ-CHH HRTA Jobs'}\n", + "{u'count': 54, u'_id': u'kc'}\n", + "{u'count': 54, u'_id': u'Caitlin'}\n", + "{u'count': 54, u'_id': u'kass'}\n", + "{u'count': 54, u'_id': u'Lithia Careers'}\n", + "{u'count': 54, u'_id': u'Dennis S Brotman'}\n", + "{u'count': 54, u'_id': u'NYC Sales Jobs'}\n", + "{u'count': 54, u'_id': u'Karina'}\n", + "{u'count': 54, u'_id': u'Kathy'}\n", + "{u'count': 54, u'_id': u'KRH Careers'}\n", + "{u'count': 54, u'_id': u'Angie'}\n", + "{u'count': 54, u'_id': u'abigail'}\n", + "{u'count': 54, u'_id': u'nina'}\n", + "{u'count': 54, u'_id': u'mom'}\n", + "{u'count': 54, u'_id': u'Mario'}\n", + "{u'count': 54, u'_id': u'Shane'}\n", + "{u'count': 54, u'_id': u'Iveygirl08'}\n", + "{u'count': 54, u'_id': u'\\u3164\\u3164'}\n", + "{u'count': 53, u'_id': u'PUTA'}\n", + "{u'count': 53, u'_id': u'TMJ-DFW Transp. Jobs'}\n", + "{u'count': 53, u'_id': u'SF Sales Jobs'}\n", + "{u'count': 53, u'_id': u'Blake'}\n", + "{u'count': 53, u'_id': u'Shelby'}\n", + "{u'count': 53, u'_id': u'KD'}\n", + "{u'count': 53, u'_id': u'TMJ-CHI CstSrv Jobs'}\n", + "{u'count': 53, u'_id': u'TMJ-CHI Nursing Jobs'}\n", + "{u'count': 53, u'_id': u'George'}\n", + "{u'count': 53, u'_id': u'NetCat Summaries'}\n", + "{u'count': 53, u'_id': u'faith'}\n", + "{u'count': 53, u'_id': u'Destiny'}\n", + "{u'count': 53, u'_id': u'KM'}\n", + "{u'count': 53, u'_id': u'\\U0001f48e'}\n", + "{u'count': 53, u'_id': u'DJ'}\n", + "{u'count': 52, u'_id': u'DTBY/jajaw \\U0001f49bFM2RJ\\u264a\\ufe0f'}\n", + "{u'count': 52, u'_id': u'Linds'}\n", + "{u'count': 52, u'_id': u'mal'}\n", + "{u'count': 52, u'_id': u'Madeline'}\n", + "{u'count': 52, u'_id': u'SIMON Careers'}\n", + "{u'count': 52, u'_id': u'Los Angeles Now'}\n", + "{u'count': 52, u'_id': u'Travis'}\n", + "{u'count': 52, u'_id': u'Newark Retail'}\n", + "{u'count': 52, u'_id': u'TMJ-ATL Retail Jobs'}\n", + "{u'count': 52, u'_id': u'Dre'}\n", + "{u'count': 52, u'_id': u'melissa'}\n", + "{u'count': 52, u'_id': u'ty'}\n", + "{u'count': 52, u'_id': u'Greg'}\n", + "{u'count': 52, u'_id': u'Jobs at Roush'}\n", + "{u'count': 52, u'_id': u'Denver Health Jobs'}\n", + "{u'count': 52, u'_id': u'TMJ-TX Nursing Jobs'}\n", + "{u'count': 52, u'_id': u'Bobby'}\n", + "{u'count': 52, u'_id': u'RHMR Jobs'}\n", + "{u'count': 52, u'_id': u'\\U0001f5e3Politics Are Trash'}\n", + "{u'count': 52, u'_id': u'nikki'}\n", + "{u'count': 52, u'_id': u'AB'}\n", + "{u'count': 52, u'_id': u'erica'}\n", + "{u'count': 52, u'_id': u'Sophia'}\n", + "{u'count': 52, u'_id': u'erlindaandrada'}\n", + "{u'count': 52, u'_id': u'alexandra'}\n", + "{u'count': 52, u'_id': u'Eddie'}\n", + "{u'count': 52, u'_id': u'TMJ-IA Retail Jobs'}\n", + "{u'count': 52, u'_id': u'morg'}\n", + "{u'count': 52, u'_id': u\"Saint Luke's Careers\"}\n", + "{u'count': 52, u'_id': u'TMJ-SEA Nursing Jobs'}\n", + "{u'count': 52, u'_id': u'Kenzie'}\n", + "{u'count': 52, u'_id': u'Sharon Dennis'}\n", + "{u'count': 52, u'_id': u'Maddy'}\n", + "{u'count': 52, u'_id': u'TMJ-BAL Nursing Jobs'}\n", + "{u'count': 52, u'_id': u'Elise Young'}\n", + "{u'count': 51, u'_id': u'shannon'}\n", + "{u'count': 51, u'_id': u'v'}\n", + "{u'count': 51, u'_id': u'maggie'}\n", + "{u'count': 51, u'_id': u'val'}\n", + "{u'count': 51, u'_id': u'Kait'}\n", + "{u'count': 51, u'_id': u'Doug'}\n", + "{u'count': 51, u'_id': u'MedExpress Jobs'}\n", + "{u'count': 51, u'_id': u'Melton Truck Lines'}\n", + "{u'count': 51, u'_id': u'Eli'}\n", + "{u'count': 51, u'_id': u'jack'}\n", + "{u'count': 51, u'_id': u'Spencer'}\n", + "{u'count': 51, u'_id': u'TMJ-JAX HRTA Jobs'}\n", + "{u'count': 51, u'_id': u'AMD'}\n", + "{u'count': 51, u'_id': u'Vincent Steele'}\n", + "{u'count': 51, u'_id': u'TMJ-MSP Jobs'}\n", + "{u'count': 51, u'_id': u'CORT Careers'}\n", + "{u'count': 51, u'_id': u'shelby'}\n", + "{u'count': 51, u'_id': u'Fiserv Careers'}\n", + "{u'count': 51, u'_id': u'\\U0001f3f3\\ufe0f\\u200d\\U0001f308'}\n", + "{u'count': 51, u'_id': u'TMJ-USA PM Jobs'}\n", + "{u'count': 51, u'_id': u'TMJ-SFO Retail Jobs'}\n", + "{u'count': 51, u'_id': u'TMJ-CHI Cosmo Jobs'}\n", + "{u'count': 51, u'_id': u'Felix P. Nater'}\n", + "{u'count': 51, u'_id': u'bre'}\n", + "{u'count': 51, u'_id': u'elizabeth'}\n", + "{u'count': 50, u'_id': u'Alexandria'}\n", + "{u'count': 50, u'_id': u'FL Non-Metro Jobs'}\n", + "{u'count': 50, u'_id': u'Every Earthquake'}\n", + "{u'count': 50, u'_id': u'\\U0001f478\\U0001f3fd'}\n", + "{u'count': 50, u'_id': u'Michigan Automotive'}\n", + "{u'count': 50, u'_id': u'Abigail'}\n", + "{u'count': 50, u'_id': u'Brett'}\n", + "{u'count': 50, u'_id': u'dad'}\n", + "{u'count': 50, u'_id': u'james'}\n", + "{u'count': 50, u'_id': u'Justice'}\n", + "{u'count': 50, u'_id': u'Deplorable Me'}\n", + "{u'count': 50, u'_id': u'Florida Automotive'}\n", + "{u'count': 50, u'_id': u'TMJ - HOU Sales Jobs'}\n", + "{u'count': 50, u'_id': u'alexa'}\n", + "{u'count': 50, u'_id': u'\\U0001f4b0'}\n", + "{u'count': 50, u'_id': u'megs'}\n", + "{u'count': 50, u'_id': u'sierra'}\n", + "{u'count': 50, u'_id': u'San Diego Press'}\n", + "{u'count': 50, u'_id': u'Dallas Now'}\n", + "{u'count': 50, u'_id': u'Gary'}\n", + "{u'count': 50, u'_id': u'TMJ-WAT HRTA Jobs'}\n", + "{u'count': 50, u'_id': u'Bella'}\n", + "{u'count': 49, u'_id': u'William Owen'}\n", + "{u'count': 49, u'_id': u'me'}\n", + "{u'count': 49, u'_id': u'TMJ-ATL Cosmo Jobs'}\n", + "{u'count': 49, u'_id': u'andrew'}\n", + "{u'count': 49, u'_id': u'Keith'}\n", + "{u'count': 49, u'_id': u'mia'}\n", + "{u'count': 49, u'_id': u'Teresa'}\n", + "{u'count': 49, u'_id': u'TMJ-LA HRTA Jobs'}\n", + "{u'count': 49, u'_id': u'angel'}\n", + "{u'count': 49, u'_id': u'TMJ-COB HRTA Jobs'}\n", + "{u'count': 49, u'_id': u':)'}\n", + "{u'count': 49, u'_id': u'gab'}\n", + "{u'count': 49, u'_id': u'\\U0001f5e3'}\n", + "{u'count': 49, u'_id': u'Katelyn'}\n", + "{u'count': 49, u'_id': u'City of Hope Jobs'}\n", + "{u'count': 49, u'_id': u'TTN Oklahoma City'}\n", + "{u'count': 49, u'_id': u'Princess'}\n", + "{u'count': 49, u'_id': u'Queen'}\n", + "{u'count': 49, u'_id': u'Cole'}\n", + "{u'count': 49, u'_id': u'Austin Now'}\n", + "{u'count': 49, u'_id': u'TMJ-FL Retail Jobs'}\n", + "{u'count': 49, u'_id': u'Nassau Other'}\n", + "{u'count': 49, u'_id': u'jenn'}\n", + "{u'count': 49, u'_id': u'CheckOutStore'}\n", + "{u'count': 49, u'_id': u'every lot nyc'}\n", + "{u'count': 49, u'_id': u'TMJ- SJC Health Jobs'}\n", + "{u'count': 49, u'_id': u'My Info'}\n", + "{u'count': 48, u'_id': u'dan'}\n", + "{u'count': 48, u'_id': u'Ana'}\n", + "{u'count': 48, u'_id': u'Royal Tire Jobs'}\n", + "{u'count': 48, u'_id': u'austin'}\n", + "{u'count': 48, u'_id': u'\\U0001f49b'}\n", + "{u'count': 48, u'_id': u'adam'}\n", + "{u'count': 48, u'_id': u'Philadelphia Now'}\n", + "{u'count': 48, u'_id': u'Kara'}\n", + "{u'count': 48, u'_id': u'nick price'}\n", + "{u'count': 48, u'_id': u'Carly'}\n", + "{u'count': 48, u'_id': u'Splendid Savage'}\n", + "{u'count': 48, u'_id': u'Caleb'}\n", + "{u'count': 48, u'_id': u\"Bob's Jobs\"}\n", + "{u'count': 48, u'_id': u'TMJ-PA Retail Jobs'}\n", + "{u'count': 48, u'_id': u'Wash. DC Mgmt. Jobs'}\n", + "{u'count': 48, u'_id': u'TMJ-USA SocSci Jobs'}\n", + "{u'count': 48, u'_id': u'JoinTeamHealth'}\n", + "{u'count': 48, u'_id': u'None.'}\n", + "{u'count': 48, u'_id': u'Jim'}\n", + "{u'count': 48, u'_id': u'dev'}\n", + "{u'count': 48, u'_id': u'hails'}\n", + "{u'count': 48, u'_id': u'Becca'}\n", + "{u'count': 48, u'_id': u'Bob'}\n", + "{u'count': 48, u'_id': u'Bryce'}\n", + "{u'count': 48, u'_id': u'Jane'}\n", + "{u'count': 48, u'_id': u'TMJ-WAT Health Jobs'}\n", + "{u'count': 48, u'_id': u'TMJ-ATL Transp. Jobs'}\n", + "{u'count': 47, u'_id': u'$$$'}\n", + "{u'count': 47, u'_id': u'Ari'}\n", + "{u'count': 47, u'_id': u'jan'}\n", + "{u'count': 47, u'_id': u'JR'}\n", + "{u'count': 47, u'_id': u'\\U0001f478\\U0001f3fe'}\n", + "{u'count': 47, u'_id': u'cp'}\n", + "{u'count': 47, u'_id': u'Plastipak Jobs'}\n", + "{u'count': 47, u'_id': u'TTWN Detroit'}\n", + "{u'count': 47, u'_id': u'Chad'}\n", + "{u'count': 47, u'_id': u'Janet Heinsler'}\n", + "{u'count': 47, u'_id': u'TMJ-SFO Cleric. Jobs'}\n", + "{u'count': 47, u'_id': u'Noble Hospital Jobs'}\n", + "{u'count': 47, u'_id': u'christina'}\n", + "{u'count': 47, u'_id': u'Tum Tum'}\n", + "{u'count': 47, u'_id': u'p'}\n", + "{u'count': 47, u'_id': u'Ricky'}\n", + "{u'count': 47, u'_id': u'Cynthia'}\n", + "{u'count': 47, u'_id': u'ben'}\n" + ] + } + ], + "source": [ + "for element in db.tweet_subset.aggregate(pipeline):\n", + " print element" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "deletable": true, + "editable": true + }, + "source": [ + "## Basic Features of Linguistic Style\n", + "\n", + "1. Bag of Words Model (Word Count)\n", + "\n", + "2. Text Length\n", + "\n", + "3. Stance Markers\n", + "\n", + "..." + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": { + "collapsed": true, + "deletable": true, + "editable": true + }, + "outputs": [], + "source": [ + "match = {'$match': {}} # match a group of your interest\n", + "\n", + "unwind = {'$unwind': '$words'}\n", + "\n", + "group = {'$group': {'_id': '$words', 'count': {'$sum': 1}}}\n", + "\n", + "sort = {'$sort': {'count': -1}}\n", + "\n", + "limit = {'$limit': 1000}\n", + "\n", + "pipeline = [match, unwind, group, sort, limit]" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": { + "collapsed": false, + "deletable": true, + "editable": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{u'count': 291655, u'_id': u'the'}\n", + "{u'count': 275782, u'_id': u'i'}\n", + "{u'count': 264514, u'_id': u'to'}\n", + "{u'count': 212552, u'_id': u'a'}\n", + "{u'count': 177003, u'_id': u'you'}\n", + "{u'count': 160562, u'_id': u'in'}\n", + "{u'count': 155971, u'_id': u'and'}\n", + "{u'count': 134292, u'_id': u'for'}\n", + "{u'count': 132118, u'_id': u'my'}\n", + "{u'count': 125645, u'_id': u'is'}\n", + "{u'count': 121012, u'_id': u'this'}\n", + "{u'count': 115160, u'_id': u'of'}\n", + "{u'count': 87154, u'_id': u'on'}\n", + "{u'count': 87022, u'_id': u'me'}\n", + "{u'count': 84363, u'_id': u'co'}\n", + "{u'count': 83995, u'_id': u't'}\n", + "{u'count': 83727, u'_id': u'it'}\n", + "{u'count': 82075, u'_id': u'https'}\n", + "{u'count': 76042, u'_id': u'that'}\n", + "{u'count': 74252, u'_id': u'be'}\n", + "{u'count': 68655, u'_id': u'so'}\n", + "{u'count': 68095, u'_id': u'at'}\n", + "{u'count': 65238, u'_id': u\"i'm\"}\n", + "{u'count': 58313, u'_id': u'with'}\n", + "{u'count': 56741, u'_id': u'just'}\n", + "{u'count': 54924, u'_id': u'-'}\n", + "{u'count': 50208, u'_id': u'have'}\n", + "{u'count': 48564, u'_id': u'like'}\n", + "{u'count': 47479, u'_id': u'but'}\n", + "{u'count': 45610, u'_id': u'not'}\n", + "{u'count': 43863, u'_id': u'are'}\n", + "{u'count': 43185, u'_id': u'was'}\n", + "{u'count': 42825, u'_id': u'all'}\n", + "{u'count': 42229, u'_id': u'your'}\n", + "{u'count': 41452, u'_id': u'up'}\n", + "{u'count': 40793, u'_id': u'out'}\n", + "{u'count': 40534, u'_id': u'if'}\n", + "{u'count': 39349, u'_id': u'get'}\n", + "{u'count': 39284, u'_id': u'amp'}\n", + "{u'count': 38624, u'_id': u'we'}\n", + "{u'count': 37065, u'_id': u'our'}\n", + "{u'count': 37012, u'_id': u'can'}\n", + "{u'count': 36658, u'_id': u\"don't\"}\n", + "{u'count': 34742, u'_id': u\"it's\"}\n", + "{u'count': 34481, u'_id': u'about'}\n", + "{u'count': 34297, u'_id': u'what'}\n", + "{u'count': 34236, u'_id': u'when'}\n", + "{u'count': 34152, u'_id': u'love'}\n", + "{u'count': 33937, u'_id': u'@'}\n", + "{u'count': 33632, u'_id': u'do'}\n", + "{u'count': 29838, u'_id': u'they'}\n", + "{u'count': 29566, u'_id': u'want'}\n", + "{u'count': 29356, u'_id': u'see'}\n", + "{u'count': 28175, u'_id': u'one'}\n", + "{u'count': 27973, u'_id': u'work'}\n", + "{u'count': 27710, u'_id': u'go'}\n", + "{u'count': 27523, u'_id': u'no'}\n", + "{u'count': 27460, u'_id': u'from'}\n", + "{u'count': 27346, u'_id': u'he'}\n", + "{u'count': 26759, u'_id': u'good'}\n", + "{u'count': 26495, u'_id': u'now'}\n", + "{u'count': 26476, u'_id': u'day'}\n", + "{u'count': 25962, u'_id': u'how'}\n", + "{u'count': 25500, u'_id': u'time'}\n", + "{u'count': 25254, u'_id': u'great'}\n", + "{u'count': 24799, u'_id': u'know'}\n", + "{u'count': 23686, u'_id': u'will'}\n", + "{u'count': 23438, u'_id': u'as'}\n", + "{u'count': 23250, u'_id': u'here'}\n", + "{u'count': 22824, u'_id': u'people'}\n", + "{u'count': 22447, u'_id': u'got'}\n", + "{u'count': 21823, u'_id': u'or'}\n", + "{u'count': 21692, u'_id': u'today'}\n", + "{u'count': 21542, u'_id': u'happy'}\n", + "{u'count': 21120, u'_id': u'lol'}\n", + "{u'count': 20828, u'_id': u'latest'}\n", + "{u'count': 20653, u'_id': u'by'}\n", + "{u'count': 20499, u'_id': u'who'}\n", + "{u'count': 19748, u'_id': u'need'}\n", + "{u'count': 19445, u'_id': u'why'}\n", + "{u'count': 19428, u'_id': u\"can't\"}\n", + "{u'count': 19032, u'_id': u'an'}\n", + "{u'count': 18923, u'_id': u'more'}\n", + "{u'count': 18824, u'_id': u\"we're\"}\n", + "{u'count': 18798, u'_id': u'u'}\n", + "{u'count': 18333, u'_id': u'back'}\n", + "{u'count': 18257, u'_id': u'really'}\n", + "{u'count': 18257, u'_id': u'some'}\n", + "{u'count': 17892, u'_id': u\"you're\"}\n", + "{u'count': 16991, u'_id': u'new'}\n", + "{u'count': 16972, u'_id': u'been'}\n", + "{u'count': 16876, u'_id': u'going'}\n", + "{u'count': 16787, u'_id': u'too'}\n", + "{u'count': 16652, u'_id': u'think'}\n", + "{u'count': 16453, u'_id': u'click'}\n", + "{u'count': 16219, u'_id': u'her'}\n", + "{u'count': 16215, u'_id': u'has'}\n", + "{u'count': 16180, u'_id': u'she'}\n", + "{u'count': 15898, u'_id': u'opening'}\n", + "{u'count': 15798, u'_id': u'shit'}\n", + "{u'count': 15623, u'_id': u'right'}\n", + "{u'count': 15585, u'_id': u'much'}\n", + "{u'count': 15294, u'_id': u'his'}\n", + "{u'count': 15281, u'_id': u'still'}\n", + "{u'count': 15063, u'_id': u'anyone'}\n", + "{u'count': 14851, u'_id': u'never'}\n", + "{u'count': 14770, u'_id': u'life'}\n", + "{u'count': 14550, u'_id': u'would'}\n", + "{u'count': 14522, u'_id': u'2'}\n", + "{u'count': 14465, u'_id': u'had'}\n", + "{u'count': 14336, u'_id': u'them'}\n", + "{u'count': 14179, u'_id': u'there'}\n", + "{u'count': 14163, u'_id': u'make'}\n", + "{u'count': 13987, u'_id': u'could'}\n", + "{u'count': 13821, u'_id': u'only'}\n", + "{u'count': 13544, u'_id': u\"that's\"}\n", + "{u'count': 13457, u'_id': u'trump'}\n", + "{u'count': 13060, u'_id': u'even'}\n", + "{u'count': 12915, u'_id': u'am'}\n", + "{u'count': 12895, u'_id': u'us'}\n", + "{u'count': 12731, u'_id': u'off'}\n", + "{u'count': 12574, u'_id': u'night'}\n", + "{u'count': 12560, u'_id': u'best'}\n", + "{u'count': 12441, u'_id': u'birthday'}\n", + "{u'count': 12284, u'_id': u'thank'}\n", + "{u'count': 12252, u'_id': u'over'}\n", + "{u'count': 12012, u'_id': u'come'}\n", + "{u'count': 11978, u'_id': u'him'}\n", + "{u'count': 11868, u'_id': u'man'}\n", + "{u'count': 11841, u'_id': u'did'}\n", + "{u'count': 11738, u'_id': u'tonight'}\n", + "{u'count': 11678, u'_id': u'last'}\n", + "{u'count': 11677, u'_id': u'always'}\n", + "{u'count': 11637, u'_id': u'way'}\n", + "{u'count': 11478, u'_id': u'these'}\n", + "{u'count': 11144, u'_id': u'fit'}\n", + "{u'count': 11115, u'_id': u'take'}\n", + "{u'count': 11064, u'_id': u'down'}\n", + "{u'count': 11057, u'_id': u'team'}\n", + "{u'count': 10905, u'_id': u'say'}\n", + "{u'count': 10899, u'_id': u'game'}\n", + "{u'count': 10805, u'_id': u'than'}\n", + "{u'count': 10796, u'_id': u'then'}\n", + "{u'count': 10743, u'_id': u'thanks'}\n", + "{u'count': 10734, u'_id': u'someone'}\n", + "{u'count': 10665, u'_id': u'because'}\n", + "{u'count': 10628, u'_id': u'being'}\n", + "{u'count': 10621, u'_id': u'apply'}\n", + "{u'count': 10527, u'_id': u'fuck'}\n", + "{u'count': 10474, u'_id': u'ever'}\n", + "{u'count': 10428, u'_id': u'recommend'}\n", + "{u'count': 10390, u'_id': u'their'}\n", + "{u'count': 10305, u'_id': u'looking'}\n", + "{u'count': 10299, u'_id': u'feel'}\n", + "{u'count': 10135, u'_id': u'oh'}\n", + "{u'count': 10074, u'_id': u'should'}\n", + "{u'count': 9976, u'_id': u'better'}\n", + "{u'count': 9976, u'_id': u'first'}\n", + "{u'count': 9887, u'_id': u\"i've\"}\n", + "{u'count': 9805, u'_id': u'3'}\n", + "{u'count': 9760, u'_id': u'look'}\n", + "{u'count': 9739, u'_id': u'gt'}\n", + "{u'count': 9649, u'_id': u'w'}\n", + "{u'count': 9519, u'_id': u'im'}\n", + "{u'count': 9414, u'_id': u'check'}\n", + "{u'count': 9364, u'_id': u'home'}\n", + "{u'count': 9330, u'_id': u'gonna'}\n", + "{u'count': 9096, u'_id': u'hate'}\n", + "{u'count': 9059, u'_id': u'after'}\n", + "{u'count': 9026, u'_id': u'ass'}\n", + "{u'count': 9002, u'_id': u'might'}\n", + "{u'count': 8913, u'_id': u'wanna'}\n", + "{u'count': 8829, u'_id': u\"y'all\"}\n", + "{u'count': 8785, u'_id': u'girl'}\n", + "{u'count': 8782, u'_id': u'getting'}\n", + "{u'count': 8779, u'_id': u'year'}\n", + "{u'count': 8721, u'_id': u'well'}\n", + "{u'count': 8680, u'_id': u'every'}\n", + "{u'count': 8673, u'_id': u'1'}\n", + "{u'count': 8570, u'_id': u'hope'}\n", + "{u'count': 8538, u'_id': u'miss'}\n", + "{u'count': 8528, u'_id': u'next'}\n", + "{u'count': 8430, u'_id': u'god'}\n", + "{u'count': 8355, u'_id': u'read'}\n", + "{u'count': 8295, u'_id': u\"i'll\"}\n", + "{u'count': 8270, u'_id': u'thing'}\n", + "{u'count': 8265, u'_id': u'where'}\n", + "{u'count': 8253, u'_id': u'stop'}\n", + "{u'count': 8217, u'_id': u'bad'}\n", + "{u'count': 8172, u'_id': u'said'}\n", + "{u'count': 8060, u'_id': u'4'}\n", + "{u'count': 8010, u'_id': u'again'}\n", + "{u'count': 7957, u'_id': u'let'}\n", + "{u'count': 7952, u'_id': u\"didn't\"}\n", + "{u'count': 7927, u'_id': u'wait'}\n", + "{u'count': 7880, u'_id': u'real'}\n", + "{u'count': 7729, u'_id': u'week'}\n", + "{u'count': 7673, u'_id': u'were'}\n", + "{u'count': 7660, u'_id': u'please'}\n", + "{u'count': 7655, u'_id': u'ca'}\n", + "{u'count': 7547, u'_id': u'friends'}\n", + "{u'count': 7459, u'_id': u'into'}\n", + "{u'count': 7406, u'_id': u'lmao'}\n", + "{u'count': 7398, u'_id': u'fucking'}\n", + "{u'count': 7262, u'_id': u'keep'}\n", + "{u'count': 7234, u'_id': u'something'}\n", + "{u'count': 7223, u'_id': u'made'}\n", + "{u'count': 7178, u'_id': u'before'}\n", + "{u'count': 7057, u'_id': u'same'}\n", + "{u'count': 7014, u'_id': u'tomorrow'}\n", + "{u'count': 6992, u'_id': u'everyone'}\n", + "{u'count': 6967, u'_id': u'little'}\n", + "{u'count': 6955, u'_id': u'tell'}\n", + "{u'count': 6930, u'_id': u'show'}\n", + "{u'count': 6861, u'_id': u'watch'}\n", + "{u'count': 6850, u'_id': u'school'}\n", + "{u'count': 6802, u'_id': u'morning'}\n", + "{u'count': 6745, u'_id': u'join'}\n", + "{u'count': 6719, u'_id': u'big'}\n", + "{u'count': 6564, u'_id': u'give'}\n", + "{u'count': 6561, u'_id': u'things'}\n", + "{u'count': 6548, u'_id': u'its'}\n", + "{u'count': 6513, u'_id': u'vote'}\n", + "{u'count': 6511, u'_id': u\"ain't\"}\n", + "{u'count': 6478, u'_id': u'yes'}\n", + "{u'count': 6439, u'_id': u'other'}\n", + "{u'count': 6418, u'_id': u'any'}\n", + "{u'count': 6377, u'_id': u'play'}\n", + "{u'count': 6335, u'_id': u'5'}\n", + "{u'count': 6321, u'_id': u'many'}\n", + "{u'count': 6320, u'_id': u'days'}\n", + "{u'count': 6252, u'_id': u\"he's\"}\n", + "{u'count': 6242, u'_id': u'does'}\n", + "{u'count': 6234, u'_id': u'done'}\n", + "{u'count': 6211, u'_id': u'doing'}\n", + "{u'count': 6206, u'_id': u'world'}\n", + "{u'count': 6171, u'_id': u'damn'}\n", + "{u'count': 6150, u'_id': u'view'}\n", + "{u'count': 6107, u'_id': u'most'}\n", + "{u'count': 6106, u'_id': u'already'}\n", + "{u'count': 6025, u'_id': u'baby'}\n", + "{u'count': 5949, u'_id': u'very'}\n", + "{u'count': 5846, u'_id': u'years'}\n", + "{u'count': 5797, u'_id': u'long'}\n", + "{u'count': 5795, u'_id': u'two'}\n", + "{u'count': 5784, u'_id': u'interested'}\n", + "{u'count': 5774, u'_id': u'put'}\n", + "{u'count': 5764, u'_id': u'live'}\n", + "{u'count': 5764, u'_id': u'another'}\n", + "{u'count': 5761, u'_id': u'gotta'}\n", + "{u'count': 5753, u'_id': u'bitch'}\n", + "{u'count': 5710, u'_id': u'sleep'}\n", + "{u'count': 5710, u'_id': u'nothing'}\n", + "{u'count': 5687, u'_id': u'sure'}\n", + "{u'count': 5629, u'_id': u'win'}\n", + "{u'count': 5626, u'_id': u'ready'}\n", + "{u'count': 5595, u'_id': u'everything'}\n", + "{u'count': 5587, u'_id': u'wish'}\n", + "{u'count': 5586, u'_id': u'hard'}\n", + "{u'count': 5544, u'_id': u'trying'}\n", + "{u'count': 5518, u'_id': u'details'}\n", + "{u'count': 5497, u'_id': u'start'}\n", + "{u'count': 5471, u'_id': u'ya'}\n", + "{u'count': 5465, u'_id': u'myself'}\n", + "{u'count': 5453, u'_id': u'house'}\n", + "{u'count': 5445, u'_id': u'old'}\n", + "{u'count': 5441, u'_id': u'those'}\n", + "{u'count': 5340, u'_id': u'talk'}\n", + "{u'count': 5311, u'_id': u'help'}\n", + "{u'count': 5309, u'_id': u'guys'}\n", + "{u'count': 5283, u'_id': u'care'}\n", + "{u'count': 5272, u'_id': u\"doesn't\"}\n", + "{u'count': 5266, u'_id': u'also'}\n", + "{u'count': 5257, u'_id': u'tx'}\n", + "{u'count': 5226, u'_id': u'thought'}\n", + "{u'count': 5142, u'_id': u'makes'}\n", + "{u'count': 5138, u'_id': u'rn'}\n", + "{u'count': 5123, u'_id': u'find'}\n", + "{u'count': 5112, u'_id': u'actually'}\n", + "{u'count': 5105, u'_id': u'mom'}\n", + "{u'count': 5102, u'_id': u'yeah'}\n", + "{u'count': 5087, u'_id': u'call'}\n", + "{u'count': 5063, u'_id': u'beautiful'}\n", + "{u'count': 5036, u'_id': u'coming'}\n", + "{u'count': 5024, u'_id': u'weekend'}\n", + "{u'count': 5015, u'_id': u\"let's\"}\n", + "{u'count': 5015, u'_id': u'watching'}\n", + "{u'count': 4983, u'_id': u'class'}\n", + "{u'count': 4982, u'_id': u'nice'}\n", + "{u'count': 4956, u'_id': u'10'}\n", + "{u'count': 4925, u'_id': u'literally'}\n", + "{u'count': 4923, u'_id': u'friend'}\n", + "{u'count': 4916, u'_id': u'fun'}\n", + "{u'count': 4907, u'_id': u'pretty'}\n", + "{u'count': 4903, u'_id': u'having'}\n", + "{u'count': 4886, u'_id': u'nigga'}\n", + "{u'count': 4836, u'_id': u'guy'}\n", + "{u'count': 4835, u'_id': u'cause'}\n", + "{u'count': 4822, u'_id': u'around'}\n", + "{u'count': 4815, u'_id': u'ok'}\n", + "{u'count': 4809, u'_id': u'while'}\n", + "{u'count': 4798, u'_id': u'person'}\n", + "{u'count': 4765, u'_id': u'money'}\n", + "{u'count': 4726, u'_id': u'family'}\n", + "{u'count': 4659, u'_id': u'high'}\n", + "{u'count': 4644, u'_id': u'through'}\n", + "{u'count': 4641, u'_id': u'left'}\n", + "{u'count': 4639, u'_id': u'since'}\n", + "{u'count': 4634, u'_id': u'white'}\n", + "{u'count': 4632, u'_id': u'bro'}\n", + "{u'count': 4541, u'_id': u'anything'}\n", + "{u'count': 4523, u'_id': u'away'}\n", + "{u'count': 4499, u'_id': u'amazing'}\n", + "{u'count': 4498, u'_id': u'twitter'}\n", + "{u'count': 4473, u'_id': u'lot'}\n", + "{u'count': 4436, u'_id': u'stay'}\n", + "{u'count': 4415, u'_id': u'until'}\n", + "{u'count': 4414, u'_id': u'such'}\n", + "{u'count': 4396, u'_id': u'7'}\n", + "{u'count': 4354, u'_id': u'ur'}\n", + "{u'count': 4350, u'_id': u'free'}\n", + "{u'count': 4347, u'_id': u'favorite'}\n", + "{u'count': 4308, u'_id': u'bc'}\n", + "{u'count': 4290, u'_id': u'black'}\n", + "{u'count': 4287, u'_id': u'heart'}\n", + "{u'count': 4286, u'_id': u'omg'}\n", + "{u'count': 4265, u'_id': u'believe'}\n", + "{u'count': 4251, u'_id': u'music'}\n", + "{u'count': 4243, u'_id': u'both'}\n", + "{u'count': 4236, u'_id': u'mean'}\n", + "{u'count': 4211, u'_id': u'making'}\n", + "{u'count': 4210, u'_id': u'job'}\n", + "{u'count': 4196, u'_id': u'6'}\n", + "{u'count': 4194, u'_id': u'season'}\n", + "{u'count': 4188, u'_id': u'hey'}\n", + "{u'count': 4142, u'_id': u'wow'}\n", + "{u'count': 4142, u'_id': u'president'}\n", + "{u'count': 4138, u'_id': u'try'}\n", + "{u'count': 4118, u'_id': u'whole'}\n", + "{u'count': 4118, u'_id': u'talking'}\n", + "{u'count': 4111, u'_id': u'hair'}\n", + "{u'count': 4099, u'_id': u'crazy'}\n", + "{u'count': 4092, u'_id': u'end'}\n", + "{u'count': 4061, u'_id': u'0'}\n", + "{u'count': 4058, u'_id': u'state'}\n", + "{u'count': 4044, u'_id': u'own'}\n", + "{u'count': 4042, u'_id': u'wrong'}\n", + "{u'count': 4038, u'_id': u\"there's\"}\n", + "{u'count': 4026, u'_id': u\"isn't\"}\n", + "{u'count': 4014, u'_id': u'looks'}\n", + "{u'count': 4009, u'_id': u'30'}\n", + "{u'count': 4007, u'_id': u'hell'}\n", + "{u'count': 4004, u'_id': u'boy'}\n", + "{u'count': 4003, u'_id': u\"what's\"}\n", + "{u'count': 3925, u'_id': u'phone'}\n", + "{u'count': 3911, u'_id': u'girls'}\n", + "{u'count': 3910, u'_id': u'tho'}\n", + "{u'count': 3903, u'_id': u'went'}\n", + "{u'count': 3881, u'_id': u'told'}\n", + "{u'count': 3862, u'_id': u'sad'}\n", + "{u'count': 3844, u'_id': u'wind'}\n", + "{u'count': 3844, u'_id': u\"won't\"}\n", + "{u'count': 3842, u'_id': u'party'}\n", + "{u'count': 3827, u'_id': u'food'}\n", + "{u'count': 3808, u'_id': u'ny'}\n", + "{u'count': 3802, u'_id': u'cute'}\n", + "{u'count': 3788, u'_id': u'true'}\n", + "{u'count': 3739, u'_id': u'hit'}\n", + "{u'count': 3732, u'_id': u'yet'}\n", + "{u'count': 3731, u'_id': u'though'}\n", + "{u'count': 3722, u'_id': u'via'}\n", + "{u'count': 3713, u'_id': u'st'}\n", + "{u'count': 3693, u'_id': u'name'}\n", + "{u'count': 3663, u'_id': u'video'}\n", + "{u'count': 3659, u'_id': u'remember'}\n", + "{u'count': 3656, u'_id': u'place'}\n", + "{u'count': 3652, u'_id': u'car'}\n", + "{u'count': 3645, u'_id': u'face'}\n", + "{u'count': 3645, u'_id': u'part'}\n", + "{u'count': 3644, u'_id': u'excited'}\n", + "{u'count': 3634, u'_id': u'gone'}\n", + "{u'count': 3630, u'_id': u'head'}\n", + "{u'count': 3594, u'_id': u'america'}\n", + "{u'count': 3591, u'_id': u'use'}\n", + "{u'count': 3590, u'_id': u'seen'}\n", + "{u'count': 3586, u'_id': u'soon'}\n", + "{u'count': 3582, u'_id': u'finally'}\n", + "{u'count': 3577, u'_id': u'eat'}\n", + "{u'count': 3576, u'_id': u'maybe'}\n", + "{u'count': 3574, u'_id': u'8'}\n", + "{u'count': 3562, u'_id': u'sorry'}\n", + "{u'count': 3549, u'_id': u'tweet'}\n", + "{u'count': 3549, u'_id': u'hours'}\n", + "{u'count': 3543, u'_id': u'bed'}\n", + "{u'count': 3538, u'_id': u'times'}\n", + "{u'count': 3528, u'_id': u'playing'}\n", + "{u'count': 3528, u'_id': u'run'}\n", + "{u'count': 3522, u'_id': u'country'}\n", + "{u'count': 3519, u'_id': u'change'}\n", + "{u'count': 3514, u'_id': u'friday'}\n", + "{u'count': 3512, u'_id': u'dude'}\n", + "{u'count': 3505, u'_id': u'yo'}\n", + "{u'count': 3498, u'_id': u'enough'}\n", + "{u'count': 3489, u'_id': u'cool'}\n", + "{u'count': 3466, u'_id': u'point'}\n", + "{u'count': 3464, u'_id': u'college'}\n", + "{u'count': 3463, u'_id': u\"she's\"}\n", + "{u'count': 3444, u'_id': u'funny'}\n", + "{u'count': 3442, u'_id': u'without'}\n", + "{u'count': 3435, u'_id': u'fl'}\n", + "{u'count': 3428, u'_id': u'guess'}\n", + "{u'count': 3428, u'_id': u'city'}\n", + "{u'count': 3418, u'_id': u'niggas'}\n", + "{u'count': 3409, u'_id': u'break'}\n", + "{u'count': 3387, u'_id': u\"i'd\"}\n", + "{u'count': 3386, u'_id': u'full'}\n", + "{u'count': 3384, u'_id': u'dont'}\n", + "{u'count': 3383, u'_id': u'may'}\n", + "{u'count': 3372, u'_id': u'okay'}\n", + "{u'count': 3370, u'_id': u'needs'}\n", + "{u'count': 3368, u'_id': u'must'}\n", + "{u'count': 3365, u'_id': u'song'}\n", + "{u'count': 3360, u'_id': u'lost'}\n", + "{u'count': 3343, u'_id': u'hillary'}\n", + "{u'count': 3341, u'_id': u'manager'}\n", + "{u'count': 3334, u'_id': u'leave'}\n", + "{u'count': 3331, u'_id': u'kids'}\n", + "{u'count': 3326, u'_id': u'election'}\n", + "{u'count': 3326, u'_id': u'support'}\n", + "{u'count': 3303, u'_id': u'b'}\n", + "{u'count': 3295, u'_id': u'n'}\n", + "{u'count': 3248, u'_id': u'follow'}\n", + "{u'count': 3241, u'_id': u'says'}\n", + "{u'count': 3241, u'_id': u'saying'}\n", + "{u'count': 3213, u'_id': u'gets'}\n", + "{u'count': 3208, u'_id': u'probably'}\n", + "{u'count': 3206, u'_id': u'feeling'}\n", + "{u'count': 3177, u'_id': u'photo'}\n", + "{u'count': 3168, u'_id': u's'}\n", + "{u'count': 3164, u'_id': u'mad'}\n", + "{u'count': 3154, u'_id': u'working'}\n", + "{u'count': 3146, u'_id': u'awesome'}\n", + "{u'count': 3139, u'_id': u'hear'}\n", + "{u'count': 3135, u'_id': u'news'}\n", + "{u'count': 3120, u'_id': u'ask'}\n", + "{u'count': 3106, u'_id': u'else'}\n", + "{u'count': 3101, u'_id': u'mind'}\n", + "{u'count': 3092, u'_id': u'took'}\n", + "{u'count': 3087, u'_id': u\"they're\"}\n", + "{u'count': 3080, u'_id': u'early'}\n", + "{u'count': 3046, u'_id': u'honestly'}\n", + "{u'count': 3038, u'_id': u'almost'}\n", + "{u'count': 3030, u'_id': u'together'}\n", + "{u'count': 3026, u'_id': u'dead'}\n", + "{u'count': 3015, u'_id': u'which'}\n", + "{u'count': 3015, u'_id': u\"haven't\"}\n", + "{u'count': 3007, u'_id': u'idk'}\n", + "{u'count': 3004, u'_id': u'drinking'}\n", + "{u'count': 3001, u'_id': u'taking'}\n", + "{u'count': 2992, u'_id': u'saw'}\n", + "{u'count': 2978, u'_id': u'proud'}\n", + "{u'count': 2973, u'_id': u'sick'}\n", + "{u'count': 2943, u'_id': u'few'}\n", + "{u'count': 2940, u'_id': u'halloween'}\n", + "{u'count': 2930, u'_id': u'tired'}\n", + "{u'count': 2911, u'_id': u'women'}\n", + "{u'count': 2910, u'_id': u'half'}\n", + "{u'count': 2891, u'_id': u'open'}\n", + "{u'count': 2884, u'_id': u'room'}\n", + "{u'count': 2865, u'_id': u'dog'}\n", + "{u'count': 2864, u'_id': u'11'}\n", + "{u'count': 2857, u'_id': u'r'}\n", + "{u'count': 2845, u'_id': u'came'}\n", + "{u'count': 2838, u'_id': u'humidity'}\n", + "{u'count': 2832, u'_id': u'lil'}\n", + "{u'count': 2826, u'_id': u'dad'}\n", + "{u'count': 2820, u'_id': u'bring'}\n", + "{u'count': 2807, u'_id': u'af'}\n", + "{u'count': 2804, u'_id': u'move'}\n", + "{u'count': 2784, u'_id': u'buy'}\n", + "{u'count': 2783, u'_id': u'thinking'}\n", + "{u'count': 2772, u'_id': u'weather'}\n", + "{u'count': 2767, u'_id': u'top'}\n", + "{u'count': 2758, u'_id': u'used'}\n", + "{u'count': 2754, u'_id': u'wants'}\n", + "{u'count': 2748, u'_id': u'media'}\n", + "{u'count': 2730, u'_id': u'smh'}\n", + "{u'count': 2729, u'_id': u'thanksgiving'}\n", + "{u'count': 2725, u'_id': u'once'}\n", + "{u'count': 2705, u'_id': u'9'}\n", + "{u'count': 2697, u'_id': u'yourself'}\n", + "{u'count': 2685, u'_id': u'ago'}\n", + "{u'count': 2684, u'_id': u'listen'}\n", + "{u'count': 2677, u'_id': u'glad'}\n", + "{u'count': 2675, u'_id': u'understand'}\n", + "{u'count': 2667, u'_id': u'late'}\n", + "{u'count': 2657, u'_id': u'hot'}\n", + "{u'count': 2649, u'_id': u'movie'}\n", + "{u'count': 2643, u'_id': u'called'}\n", + "{u'count': 2639, u'_id': u'line'}\n", + "{u'count': 2631, u'_id': u'story'}\n", + "{u'count': 2621, u'_id': u'far'}\n", + "{u'count': 2618, u'_id': u'least'}\n", + "{u'count': 2613, u'_id': u'rain'}\n", + "{u'count': 2608, u'_id': u'sometimes'}\n", + "{u'count': 2601, u'_id': u'bout'}\n", + "{u'count': 2596, u'_id': u'posted'}\n", + "{u'count': 2586, u'_id': u\"wasn't\"}\n", + "{u'count': 2577, u'_id': u'against'}\n", + "{u'count': 2576, u'_id': u'waiting'}\n", + "{u'count': 2573, u'_id': u'obama'}\n", + "{u'count': 2566, u'_id': u'park'}\n", + "{u'count': 2561, u'_id': u'ppl'}\n", + "{u'count': 2558, u'_id': u'fall'}\n", + "{u'count': 2550, u'_id': u'health'}\n", + "{u'count': 2550, u'_id': u'boys'}\n", + "{u'count': 2542, u'_id': u'found'}\n", + "{u'count': 2538, u'_id': u'wtf'}\n", + "{u'count': 2519, u'_id': u'wanted'}\n", + "{u'count': 2519, u'_id': u'goes'}\n", + "{u'count': 2515, u'_id': u'seeing'}\n", + "{u'count': 2508, u'_id': u'swear'}\n", + "{u'count': 2504, u'_id': u'anymore'}\n", + "{u'count': 2500, u'_id': u'reason'}\n", + "{u'count': 2492, u'_id': u'lit'}\n", + "{u'count': 2487, u'_id': u'2017'}\n", + "{u'count': 2482, u'_id': u'hour'}\n", + "{u'count': 2481, u'_id': u'o'}\n", + "{u'count': 2472, u'_id': u'il'}\n", + "{u'count': 2455, u'_id': u'post'}\n", + "{u'count': 2454, u'_id': u'minutes'}\n", + "{u'count': 2448, u'_id': u'street'}\n", + "{u'count': 2428, u'_id': u'different'}\n", + "{u'count': 2425, u'_id': u'pay'}\n", + "{u'count': 2423, u'_id': u'stupid'}\n", + "{u'count': 2416, u'_id': u'christmas'}\n", + "{u'count': 2413, u'_id': u'perfect'}\n", + "{u'count': 2395, u'_id': u'saturday'}\n", + "{u'count': 2393, u'_id': u'side'}\n", + "{u'count': 2392, u'_id': u'worst'}\n", + "{u'count': 2389, u'_id': u'la'}\n", + "{u'count': 2381, u'_id': u'beat'}\n", + "{u'count': 2379, u'_id': u'fake'}\n", + "{u'count': 2370, u'_id': u'stuff'}\n", + "{u'count': 2335, u'_id': u'store'}\n", + "{u'count': 2329, u'_id': u'2016'}\n", + "{u'count': 2328, u'_id': u'won'}\n", + "{u'count': 2315, u'_id': u'york'}\n", + "{u'count': 2312, u'_id': u'turn'}\n", + "{u'count': 2302, u'_id': u'started'}\n", + "{u'count': 2301, u'_id': u'pa'}\n", + "{u'count': 2294, u'_id': u'super'}\n", + "{u'count': 2281, u'_id': u'ma'}\n", + "{u'count': 2269, u'_id': u'nc'}\n", + "{u'count': 2266, u'_id': u'text'}\n", + "{u'count': 2262, u'_id': u'drive'}\n", + "{u'count': 2259, u'_id': u'center'}\n", + "{u'count': 2255, u'_id': u'sales'}\n", + "{u'count': 2247, u'_id': u'lt'}\n", + "{u'count': 2237, u'_id': u'future'}\n", + "{u'count': 2231, u'_id': u'service'}\n", + "{u'count': 2229, u'_id': u'heard'}\n", + "{u'count': 2229, u'_id': u'forget'}\n", + "{u'count': 2227, u'_id': u'set'}\n", + "{u'count': 2225, u'_id': u\"couldn't\"}\n", + "{u'count': 2217, u'_id': u'games'}\n", + "{u'count': 2217, u'_id': u'nobody'}\n", + "{u'count': 2216, u'_id': u'comes'}\n", + "{u'count': 2215, u'_id': u'matter'}\n", + "{u'count': 2215, u'_id': u'12'}\n", + "{u'count': 2214, u'_id': u'vs'}\n", + "{u'count': 2208, u'_id': u'yesterday'}\n", + "{u'count': 2203, u'_id': u'congrats'}\n", + "{u'count': 2200, u'_id': u'cold'}\n", + "{u'count': 2187, u'_id': u'sweet'}\n", + "{u'count': 2184, u'_id': u'definitely'}\n", + "{u'count': 2179, u'_id': u'forever'}\n", + "{u'count': 2178, u'_id': u'young'}\n", + "{u'count': 2168, u'_id': u'feels'}\n", + "{u'count': 2166, u'_id': u'brother'}\n", + "{u'count': 2158, u'_id': u\"wouldn't\"}\n", + "{u'count': 2158, u'_id': u'kind'}\n", + "{u'count': 2156, u'_id': u'chance'}\n", + "{u'count': 2155, u'_id': u'somebody'}\n", + "{u'count': 2149, u'_id': u'enjoy'}\n", + "{u'count': 2148, u'_id': u'fight'}\n", + "{u'count': 2148, u'_id': u'second'}\n", + "{u'count': 2147, u'_id': u'business'}\n", + "{u'count': 2145, u'_id': u'lose'}\n", + "{u'count': 2143, u'_id': u'either'}\n", + "{u'count': 2136, u'_id': u'seriously'}\n", + "{u'count': 2134, u'_id': u'happen'}\n", + "{u'count': 2131, u'_id': u'tryna'}\n", + "{u'count': 2128, u'_id': u'fan'}\n", + "{u'count': 2115, u'_id': u'send'}\n", + "{u'count': 2114, u'_id': u'20'}\n", + "{u'count': 2113, u'_id': u'past'}\n", + "{u'count': 2106, u'_id': u'close'}\n", + "{u'count': 2096, u'_id': u'va'}\n", + "{u'count': 2095, u'_id': u'die'}\n", + "{u'count': 2083, u'_id': u'hurt'}\n", + "{u'count': 2079, u'_id': u'fire'}\n", + "{u'count': 2078, u'_id': u'sunday'}\n", + "{u'count': 2067, u'_id': u'each'}\n", + "{u'count': 2067, u'_id': u'knew'}\n", + "{u'count': 2062, u'_id': u'1st'}\n", + "{u'count': 2060, u'_id': u'between'}\n", + "{u'count': 2055, u'_id': u'fact'}\n", + "{u'count': 2055, u'_id': u'crying'}\n", + "{u'count': 2054, u'_id': u'mi'}\n", + "{u'count': 2045, u'_id': u'c'}\n", + "{u'count': 2044, u'_id': u'woman'}\n", + "{u'count': 2025, u'_id': u'single'}\n", + "{u'count': 2019, u'_id': u'hi'}\n", + "{u'count': 2012, u'_id': u'meet'}\n", + "{u'count': 2010, u'_id': u'thankful'}\n", + "{u'count': 2009, u'_id': u'month'}\n", + "{u'count': 2007, u'_id': u'spring'}\n", + "{u'count': 2007, u'_id': u'american'}\n", + "{u'count': 2006, u'_id': u'|'}\n", + "{u'count': 2006, u'_id': u'wake'}\n", + "{u'count': 2005, u'_id': u'case'}\n", + "{u'count': 2003, u'_id': u'temperature'}\n", + "{u'count': 2002, u'_id': u'picture'}\n", + "{u'count': 2002, u'_id': u'during'}\n", + "{u'count': 2002, u'_id': u'clinton'}\n", + "{u'count': 2001, u'_id': u'cry'}\n", + "{u'count': 2001, u'_id': u'voted'}\n", + "{u'count': 1995, u'_id': u\"'s\"}\n", + "{u'count': 1994, u'_id': u'under'}\n", + "{u'count': 1994, u'_id': u'till'}\n", + "{u'count': 1990, u'_id': u'cant'}\n", + "{u'count': 1986, u'_id': u'haha'}\n", + "{u'count': 1984, u'_id': u'nj'}\n", + "{u'count': 1970, u'_id': u'red'}\n", + "{u'count': 1970, u'_id': u'words'}\n", + "{u'count': 1968, u'_id': u'weeks'}\n", + "{u'count': 1955, u'_id': u'worth'}\n", + "{u'count': 1952, u'_id': u'dumb'}\n", + "{u'count': 1944, u'_id': u'book'}\n", + "{u'count': 1937, u'_id': u'rest'}\n", + "{u'count': 1937, u'_id': u'ball'}\n", + "{u'count': 1937, u'_id': u'ga'}\n", + "{u'count': 1930, u'_id': u'fine'}\n", + "{u'count': 1929, u'_id': u'walk'}\n", + "{u'count': 1924, u'_id': u'coffee'}\n", + "{u'count': 1923, u'_id': u'kid'}\n", + "{u'count': 1919, u'_id': u'welcome'}\n", + "{u'count': 1917, u'_id': u'word'}\n", + "{u'count': 1908, u'_id': u'alone'}\n", + "{u'count': 1908, u'_id': u'straight'}\n", + "{u'count': 1907, u'_id': u'less'}\n", + "{u'count': 1906, u'_id': u'everybody'}\n", + "{u'count': 1905, u'_id': u'tf'}\n", + "{u'count': 1905, u'_id': u'body'}\n", + "{u'count': 1903, u'_id': u'football'}\n", + "{u'count': 1900, u'_id': u'gave'}\n", + "{u'count': 1899, u'_id': u'months'}\n", + "{u'count': 1895, u'_id': u'idea'}\n", + "{u'count': 1890, u'_id': u'texas'}\n", + "{u'count': 1889, u'_id': u'mine'}\n", + "{u'count': 1881, u'_id': u'pick'}\n", + "{u'count': 1880, u'_id': u'wonder'}\n", + "{u'count': 1880, u'_id': u'shot'}\n", + "{u'count': 1878, u'_id': u'mo'}\n", + "{u'count': 1875, u'_id': u'learn'}\n", + "{u'count': 1875, u'_id': u'd'}\n", + "{u'count': 1874, u'_id': u'kinda'}\n", + "{u'count': 1874, u'_id': u\"who's\"}\n", + "{u'count': 1872, u'_id': u'living'}\n", + "{u'count': 1868, u'_id': u'instead'}\n", + "{u'count': 1867, u'_id': u'office'}\n", + "{u'count': 1866, u'_id': u'light'}\n", + "{u'count': 1864, u'_id': u'mood'}\n", + "{u'count': 1863, u'_id': u'happened'}\n", + "{u'count': 1858, u'_id': u'running'}\n", + "{u'count': 1855, u'_id': u'bitches'}\n", + "{u'count': 1854, u'_id': u'drink'}\n", + "{u'count': 1854, u'_id': u'forward'}\n", + "{u'count': 1845, u'_id': u'donald'}\n", + "{u'count': 1845, u'_id': u'trust'}\n", + "{u'count': 1844, u'_id': u'outside'}\n", + "{u'count': 1843, u'_id': u'fans'}\n", + "{u'count': 1839, u'_id': u'update'}\n", + "{u'count': 1831, u'_id': u'knows'}\n", + "{u'count': 1830, u'_id': u'stand'}\n", + "{u'count': 1829, u'_id': u'eyes'}\n", + "{u'count': 1811, u'_id': u'yall'}\n", + "{u'count': 1810, u'_id': u'cut'}\n", + "{u'count': 1809, u'_id': u'monday'}\n", + "{u'count': 1808, u'_id': u'giving'}\n", + "{u'count': 1807, u'_id': u'rt'}\n", + "{u'count': 1801, u'_id': u'problem'}\n", + "{u'count': 1793, u'_id': u'beach'}\n", + "{u'count': 1793, u'_id': u'act'}\n", + "{u'count': 1788, u'_id': u'kill'}\n", + "{u'count': 1787, u'_id': u'nurse'}\n", + "{u'count': 1780, u'_id': u'ima'}\n", + "{u'count': 1778, u'_id': u'woke'}\n", + "{u'count': 1778, u'_id': u\"aren't\"}\n", + "{u'count': 1777, u'_id': u'sister'}\n", + "{u'count': 1776, u'_id': u'lead'}\n", + "{u'count': 1776, u'_id': u'north'}\n", + "{u'count': 1773, u'_id': u'needed'}\n", + "{u'count': 1771, u'_id': u'fucked'}\n", + "{u'count': 1766, u'_id': u'everyday'}\n", + "{u'count': 1762, u'_id': u'sounds'}\n", + "{u'count': 1754, u'_id': u'road'}\n", + "{u'count': 1745, u'_id': u'west'}\n", + "{u'count': 1744, u'_id': u'weird'}\n", + "{u'count': 1743, u'_id': u'asked'}\n", + "{u'count': 1741, u'_id': u'starting'}\n", + "{u'count': 1740, u'_id': u'men'}\n", + "{u'count': 1737, u'_id': u'listening'}\n", + "{u'count': 1737, u'_id': u'agree'}\n", + "{u'count': 1729, u'_id': u'san'}\n", + "{u'count': 1725, u'_id': u'bar'}\n", + "{u'count': 1719, u'_id': u'special'}\n", + "{u'count': 1719, u'_id': u'luck'}\n", + "{u'count': 1717, u'_id': u'low'}\n", + "{u'count': 1717, u'_id': u'em'}\n", + "{u'count': 1715, u'_id': u'social'}\n", + "{u'count': 1714, u'_id': u'power'}\n", + "{u'count': 1710, u'_id': u'catch'}\n", + "{u'count': 1705, u'_id': u'able'}\n", + "{u'count': 1704, u'_id': u'water'}\n", + "{u'count': 1703, u'_id': u'player'}\n", + "{u'count': 1701, u'_id': u'tbh'}\n", + "{u'count': 1695, u'_id': u'date'}\n", + "{u'count': 1694, u'_id': u'group'}\n", + "{u'count': 1688, u'_id': u'course'}\n", + "{u'count': 1685, u'_id': u'eating'}\n", + "{u'count': 1681, u'_id': u'dinner'}\n", + "{u'count': 1680, u'_id': u'chicago'}\n", + "{u'count': 1676, u'_id': u'00'}\n", + "{u'count': 1672, u'_id': u'incident'}\n", + "{u'count': 1668, u'_id': u'tried'}\n", + "{u'count': 1662, u'_id': u'later'}\n", + "{u'count': 1662, u'_id': u'tv'}\n", + "{u'count': 1661, u'_id': u'forgot'}\n", + "{u'count': 1657, u'_id': u'nah'}\n", + "{u'count': 1657, u'_id': u'clear'}\n", + "{u'count': 1657, u'_id': u'means'}\n", + "{u'count': 1656, u'_id': u'bruh'}\n", + "{u'count': 1652, u'_id': u'wear'}\n", + "{u'count': 1649, u'_id': u'lie'}\n", + "{u'count': 1648, u'_id': u'south'}\n", + "{u'count': 1644, u'_id': u'three'}\n", + "{u'count': 1640, u'_id': u'missed'}\n", + "{u'count': 1637, u'_id': u'15'}\n", + "{u'count': 1632, u'_id': u'question'}\n", + "{u'count': 1629, u'_id': u'save'}\n", + "{u'count': 1628, u'_id': u'truth'}\n", + "{u'count': 1626, u'_id': u'hold'}\n", + "{u'count': 1622, u'_id': u'lady'}\n", + "{u'count': 1619, u'_id': u'broke'}\n", + "{u'count': 1619, u'_id': u'trip'}\n", + "{u'count': 1617, u'_id': u'front'}\n", + "{u'count': 1615, u'_id': u'az'}\n", + "{u'count': 1615, u'_id': u\"you'll\"}\n", + "{u'count': 1606, u'_id': u'cubs'}\n", + "{u'count': 1602, u'_id': u'shift'}\n", + "{u'count': 1601, u'_id': u'assistant'}\n", + "{u'count': 1599, u'_id': u'exactly'}\n", + "{u'count': 1592, u'_id': u'fast'}\n", + "{u'count': 1591, u'_id': u'parents'}\n", + "{u'count': 1587, u'_id': u'loved'}\n", + "{u'count': 1586, u'_id': u'ones'}\n", + "{u'count': 1586, u'_id': u'deal'}\n", + "{u'count': 1579, u'_id': u'voting'}\n", + "{u'count': 1577, u'_id': u'lmfao'}\n", + "{u'count': 1576, u'_id': u'f'}\n", + "{u'count': 1575, u'_id': u'sign'}\n", + "{u'count': 1564, u'_id': u'california'}\n", + "{u'count': 1562, u'_id': u'winning'}\n", + "{u'count': 1555, u'_id': u'behind'}\n", + "{u'count': 1555, u'_id': u'moment'}\n", + "{u'count': 1551, u'_id': u'drunk'}\n", + "{u'count': 1546, u'_id': u'son'}\n", + "{u'count': 1544, u'_id': u'series'}\n", + "{u'count': 1540, u'_id': u'blessed'}\n", + "{u'count': 1538, u'_id': u'takes'}\n", + "{u'count': 1537, u'_id': u'share'}\n", + "{u'count': 1536, u'_id': u'safe'}\n", + "{u'count': 1534, u'_id': u'blue'}\n", + "{u'count': 1532, u'_id': u'cuz'}\n", + "{u'count': 1528, u'_id': u'realize'}\n", + "{u'count': 1528, u'_id': u'cast'}\n", + "{u'count': 1528, u'_id': u'lord'}\n", + "{u'count': 1526, u'_id': u'dream'}\n", + "{u'count': 1525, u'_id': u'e'}\n", + "{u'count': 1523, u'_id': u'album'}\n", + "{u'count': 1523, u'_id': u'l'}\n", + "{u'count': 1520, u'_id': u'pic'}\n", + "{u'count': 1520, u'_id': u'nap'}\n", + "{u'count': 1519, u'_id': u'played'}\n", + "{u'count': 1516, u'_id': u'joke'}\n", + "{u'count': 1515, u'_id': u'thats'}\n", + "{u'count': 1515, u'_id': u'tweets'}\n", + "{u'count': 1514, u'_id': u'pass'}\n", + "{u'count': 1511, u'_id': u'hand'}\n", + "{u'count': 1509, u'_id': u'couple'}\n", + "{u'count': 1505, u'_id': u'throw'}\n", + "{u'count': 1505, u'_id': u'appreciate'}\n", + "{u'count': 1504, u'_id': u'jesus'}\n", + "{u'count': 1502, u'_id': u'respect'}\n", + "{u'count': 1499, u'_id': u'exit'}\n", + "{u'count': 1496, u'_id': u'easy'}\n", + "{u'count': 1490, u'_id': u'm'}\n", + "{u'count': 1489, u'_id': u'rock'}\n", + "{u'count': 1486, u'_id': u'history'}\n", + "{u'count': 1486, u'_id': u'closed'}\n", + "{u'count': 1485, u'_id': u'ugly'}\n", + "{u'count': 1484, u'_id': u'bit'}\n", + "{u'count': 1481, u'_id': u'absolutely'}\n", + "{u'count': 1480, u'_id': u'wa'}\n", + "{u'count': 1476, u'_id': u'important'}\n", + "{u'count': 1475, u'_id': u'club'}\n", + "{u'count': 1472, u'_id': u'pizza'}\n", + "{u'count': 1472, u'_id': u'driver'}\n", + "{u'count': 1472, u'_id': u\"you've\"}\n", + "{u'count': 1470, u'_id': u'walking'}\n", + "{u'count': 1465, u'_id': u'drop'}\n", + "{u'count': 1461, u'_id': u'current'}\n", + "{u'count': 1460, u'_id': u'mr'}\n", + "{u'count': 1460, u'_id': u'plan'}\n", + "{u'count': 1457, u'_id': u'2nd'}\n", + "{u'count': 1453, u'_id': u'pressure'}\n", + "{u'count': 1453, u'_id': u'town'}\n", + "{u'count': 1450, u'_id': u'field'}\n", + "{u'count': 1449, u'_id': u'seems'}\n", + "{u'count': 1447, u'_id': u'summer'}\n", + "{u'count': 1447, u'_id': u'accident'}\n", + "{u'count': 1445, u'_id': u'bless'}\n", + "{u'count': 1445, u'_id': u'bet'}\n", + "{u'count': 1440, u'_id': u'national'}\n", + "{u'count': 1439, u'_id': u'bday'}\n", + "{u'count': 1435, u'_id': u'missing'}\n", + "{u'count': 1429, u'_id': u'cannot'}\n", + "{u'count': 1425, u'_id': u'self'}\n", + "{u'count': 1425, u'_id': u'pm'}\n", + "{u'count': 1424, u'_id': u'lunch'}\n", + "{u'count': 1423, u'_id': u'order'}\n", + "{u'count': 1415, u'_id': u'tn'}\n", + "{u'count': 1414, u'_id': u'art'}\n", + "{u'count': 1410, u'_id': u'senior'}\n", + "{u'count': 1409, u'_id': u'shut'}\n", + "{u'count': 1404, u'_id': u'become'}\n", + "{u'count': 1394, u'_id': u'students'}\n", + "{u'count': 1393, u'_id': u'type'}\n", + "{u'count': 1391, u'_id': u'md'}\n", + "{u'count': 1390, u'_id': u'worse'}\n", + "{u'count': 1390, u'_id': u'florida'}\n", + "{u'count': 1387, u'_id': u'rather'}\n", + "{u'count': 1384, u'_id': u'ave'}\n", + "{u'count': 1381, u'_id': u'trash'}\n", + "{u'count': 1378, u'_id': u'ride'}\n", + "{u'count': 1378, u'_id': u'strong'}\n", + "{u'count': 1377, u'_id': u'gym'}\n", + "{u'count': 1377, u'_id': u'mn'}\n", + "{u'count': 1375, u'_id': u'hands'}\n", + "{u'count': 1363, u'_id': u'extra'}\n", + "{u'count': 1361, u'_id': u'small'}\n", + "{u'count': 1361, u'_id': u'using'}\n", + "{u'count': 1361, u'_id': u'rd'}\n", + "{u'count': 1360, u'_id': u'hoe'}\n", + "{u'count': 1358, u'_id': u'wearing'}\n", + "{u'count': 1357, u'_id': u'account'}\n", + "{u'count': 1356, u'_id': u'middle'}\n", + "{u'count': 1356, u'_id': u'number'}\n", + "{u'count': 1354, u'_id': u'16'}\n", + "{u'count': 1354, u'_id': u'ice'}\n", + "{u'count': 1353, u'_id': u'sound'}\n", + "{u'count': 1352, u'_id': u'fam'}\n", + "{u'count': 1352, u'_id': u'deserve'}\n", + "{u'count': 1351, u'_id': u'lets'}\n", + "{u'count': 1351, u'_id': u'bill'}\n", + "{u'count': 1350, u'_id': u'basketball'}\n", + "{u'count': 1349, u'_id': u'beer'}\n", + "{u'count': 1347, u'_id': u'dick'}\n", + "{u'count': 1346, u'_id': u'spend'}\n", + "{u'count': 1345, u'_id': u'bought'}\n", + "{u'count': 1344, u'_id': u'chill'}\n", + "{u'count': 1343, u'_id': u'tickets'}\n", + "{u'count': 1343, u'_id': u'24'}\n", + "{u'count': 1340, u'_id': u'sitting'}\n", + "{u'count': 1340, u'_id': u'sucks'}\n", + "{u'count': 1338, u'_id': u'telling'}\n", + "{u'count': 1336, u'_id': u'ugh'}\n", + "{u'count': 1334, u'_id': u'calling'}\n", + "{u'count': 1334, u'_id': u'watched'}\n", + "{u'count': 1327, u'_id': u'east'}\n", + "{u'count': 1326, u'_id': u'snow'}\n", + "{u'count': 1326, u'_id': u'sit'}\n", + "{u'count': 1321, u'_id': u'+'}\n", + "{u'count': 1321, u'_id': u'entire'}\n", + "{u'count': 1319, u'_id': u'dr'}\n", + "{u'count': 1317, u'_id': u'event'}\n", + "{u'count': 1315, u'_id': u'list'}\n", + "{u'count': 1314, u'_id': u'holy'}\n", + "{u'count': 1312, u'_id': u'episode'}\n", + "{u'count': 1312, u'_id': u'march'}\n", + "{u'count': 1311, u'_id': u'pictures'}\n", + "{u'count': 1310, u'_id': u'boyfriend'}\n", + "{u'count': 1309, u'_id': u'met'}\n", + "{u'count': 1309, u'_id': u'shows'}\n", + "{u'count': 1308, u'_id': u'traffic'}\n", + "{u'count': 1307, u'_id': u'happens'}\n", + "{u'count': 1302, u'_id': u'snapchat'}\n", + "{u'count': 1300, u'_id': u'coach'}\n", + "{u'count': 1298, u'_id': u'wit'}\n", + "{u'count': 1297, u'_id': u'level'}\n", + "{u'count': 1297, u'_id': u'wild'}\n", + "{u'count': 1296, u'_id': u'g'}\n", + "{u'count': 1295, u'_id': u'green'}\n", + "{u'count': 1295, u'_id': u'beauty'}\n", + "{u'count': 1294, u'_id': u'others'}\n", + "{u'count': 1293, u'_id': u'university'}\n", + "{u'count': 1291, u'_id': u'tuesday'}\n", + "{u'count': 1285, u'_id': u'3rd'}\n", + "{u'count': 1284, u'_id': u'truly'}\n", + "{u'count': 1280, u'_id': u'huge'}\n", + "{u'count': 1273, u'_id': u'relationship'}\n", + "{u'count': 1272, u'_id': u'test'}\n", + "{u'count': 1271, u'_id': u'p'}\n", + "{u'count': 1270, u'_id': u'quick'}\n", + "{u'count': 1270, u'_id': u'whatever'}\n", + "{u'count': 1270, u'_id': u'station'}\n", + "{u'count': 1264, u'_id': u'wins'}\n", + "{u'count': 1264, u'_id': u'registered'}\n", + "{u'count': 1259, u'_id': u'death'}\n", + "{u'count': 1259, u'_id': u'sc'}\n", + "{u'count': 1259, u'_id': u'visit'}\n", + "{u'count': 1258, u'_id': u'fr'}\n", + "{u'count': 1258, u'_id': u'17'}\n", + "{u'count': 1256, u'_id': u'sense'}\n", + "{u'count': 1252, u'_id': u'air'}\n", + "{u'count': 1247, u'_id': u'serious'}\n", + "{u'count': 1246, u'_id': u'wonderful'}\n", + "{u'count': 1245, u'_id': u'snap'}\n", + "{u'count': 1240, u'_id': u'cleared'}\n", + "{u'count': 1237, u'_id': u'scared'}\n", + "{u'count': 1237, u'_id': u'speak'}\n", + "{u'count': 1236, u'_id': u'wi'}\n", + "{u'count': 1232, u'_id': u'experience'}\n", + "{u'count': 1231, u'_id': u'chicken'}\n", + "{u'count': 1227, u'_id': u'fuckin'}\n", + "{u'count': 1226, u'_id': u'public'}\n", + "{u'count': 1225, u'_id': u'due'}\n", + "{u'count': 1224, u'_id': u'21'}\n", + "{u'count': 1223, u'_id': u'boo'}\n", + "{u'count': 1219, u'_id': u'racist'}\n", + "{u'count': 1217, u'_id': u'suck'}\n", + "{u'count': 1216, u'_id': u'laugh'}\n", + "{u'count': 1216, u'_id': u'associate'}\n", + "{u'count': 1214, u'_id': u'thursday'}\n", + "{u'count': 1213, u'_id': u'13'}\n", + "{u'count': 1213, u'_id': u'november'}\n", + "{u'count': 1210, u'_id': u'pull'}\n", + "{u'count': 1210, u'_id': u'sky'}\n", + "{u'count': 1207, u'_id': u'50'}\n", + "{u'count': 1206, u'_id': u'soul'}\n", + "{u'count': 1205, u'_id': u'imma'}\n", + "{u'count': 1202, u'_id': u'final'}\n", + "{u'count': 1201, u'_id': u'paid'}\n", + "{u'count': 1199, u'_id': u'yea'}\n", + "{u'count': 1197, u'_id': u'church'}\n", + "{u'count': 1197, u'_id': u'voice'}\n", + "{u'count': 1194, u'_id': u'inside'}\n", + "{u'count': 1193, u'_id': u'moving'}\n", + "{u'count': 1191, u'_id': u'hoes'}\n", + "{u'count': 1189, u'_id': u\"here's\"}\n", + "{u'count': 1186, u'_id': u'totally'}\n", + "{u'count': 1185, u'_id': u'attention'}\n", + "{u'count': 1182, u'_id': u'x'}\n", + "{u'count': 1179, u'_id': u'child'}\n", + "{u'count': 1174, u'_id': u'movies'}\n", + "{u'count': 1174, u'_id': u'goal'}\n", + "{u'count': 1174, u'_id': u'smoke'}\n", + "{u'count': 1169, u'_id': u'wife'}\n", + "{u'count': 1169, u'_id': u'mph'}\n", + "{u'count': 1168, u'_id': u'states'}\n", + "{u'count': 1166, u'_id': u'annoying'}\n", + "{u'count': 1166, u'_id': u'link'}\n", + "{u'count': 1164, u'_id': u'asking'}\n", + "{u'count': 1163, u'_id': u'human'}\n", + "{u'count': 1163, u'_id': u'pics'}\n", + "{u'count': 1161, u'_id': u'felt'}\n", + "{u'count': 1157, u'_id': u'deserves'}\n", + "{u'count': 1155, u'_id': u'cat'}\n", + "{u'count': 1153, u'_id': u'pls'}\n", + "{u'count': 1153, u'_id': u'control'}\n", + "{u'count': 1153, u'_id': u'john'}\n", + "{u'count': 1151, u'_id': u'biggest'}\n", + "{u'count': 1151, u'_id': u'feelings'}\n", + "{u'count': 1150, u'_id': u'piece'}\n", + "{u'count': 1143, u'_id': u'add'}\n", + "{u'count': 1143, u'_id': u'happening'}\n", + "{u'count': 1142, u'_id': u'supposed'}\n", + "{u'count': 1142, u'_id': u'driving'}\n" + ] + } + ], + "source": [ + "for element in db.tweet_subset.aggregate(pipeline):\n", + " print element" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": true, + "deletable": true, + "editable": true + }, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 2", + "language": "python", + "name": "python2" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 2 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython2", + "version": "2.7.14" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +}