PageSourceSearch

https://investigate.ai/search/

html investigate.ai collected 2026-10-03 21:37:11 UTC 51,947 bytes, 2,172 lines download raw bytes

1
2  <!doctype html>
3<html lang="en-US">
4
5
6
7<head>
8  <!-- Global site tag (gtag.js) - Google Analytics -->
vendor: 66 bytes, lines 8-9
8
9  <script async src="https://www.googletagmanager.com/gtag/js?id=
9UA-5541738-27
vendor: 14 bytes, lines 9-10
9"></script>
10  
10<script>
11    
vendor: 140 bytes, lines 11-15
11window.dataLayer = window.dataLayer || [];
12    function gtag(){dataLayer.push(arguments);}
13    gtag('js', new Date());
14
15    gtag('config', '
15UA-5541738-27
vendor: 6 bytes, lines 15-16
15');
16  
16</script>
16
17
18  <meta charset="utf-8">
19  <title>Search investigate.ai | Data Science for Journalism</title>
20  <link href="/font-awesome/css/all.min.css?v=500d1a92f875b1d96d37a3a3f8f0438c" rel="stylesheet">
21  <!-- <link href="https://cdnjs.cloudflare.com/ajax/libs/bulma/0.7.5/css/bulma.min.css" rel="stylesheet">
22        <link href="https://fonts.googleapis.com/css?family=Raleway:400,700|Open+Sans:400,700&display=swap" rel="stylesheet"> -->
23  <link rel="stylesheet" href="/css/spectre.min.css?v=5cd401d486f79e82913923fe7d7f47ff">
24  <link rel="stylesheet" href="/css/spectre-exp.min.css?v=5909d80638a6ae6aa3a455b6f6a6d768">
25  <link rel="stylesheet" href="/css/spectre-icons.min.css?v=56b1bd38b79450b37939f8adb811d4cd">
26
27  <link rel="stylesheet" href="/css/tocbot.css?v=e8f0173e7c5216e5359587a88a570b77">
28
29  <!-- 
29<script src="https://unpkg.com/lunr/lunr.js"></script>
29 -->
30  
30<script src="/js/lunr.js?v=b93de9e9609074d666f5123e866e25ed"></script>
30
31  <!-- 
31<script src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.6/require.min.js"></script>
31 -->
32  
32<script src="/js/require.min.js?v=18823f6a6d208ee1e361bb266ab794d5"></script>
32
33
34  <meta name="viewport" content="width=device-width, initial-scale=1">
35  <link href="/css/style.css?v=10420579fc48bad7c182d7d5e44a2cbb" rel="stylesheet">
36  <link href="/css/highlight.css?v=bdd372d828c6988b6071bb877211ebcb" rel="stylesheet">
37
38  <meta name="description" content="Search for data science + journalism information at investigate.ai">
39  <meta content="investigate.ai: Data Science for Journalists" property="og:site_name">
40
41  <meta name="twitter:creator" content="@dangerscarf">
42  <meta name="twitter:title" content="Search investigate.ai | Data Science for Journalism">
43  <meta name="twitter:description" content="Search for data science + journalism information at investigate.ai">
44  <meta name="twitter:image" content="https://investigate.ai/images/flame/flame-searching.png">
45  <meta name="twitter:image:alt" content="A person metaphorically examining data">
46  <meta name="twitter:card" content="summary" />
47
48  <meta property="og:type" content="website" />
49  <meta property="og:url" content="https://investigate.ai/search/" />
50  <meta property="og:title" content="Search investigate.ai | Data Science for Journalism" />
51  <meta property="og:description" content="Search for data science + journalism information at investigate.ai" />
52  <meta property="og:image" content="https://investigate.ai/images/flame/flame-searching.png" />
53  <meta property="og:image:height" content="912" />
54  <meta property="og:image:width" content="921" />
55  <meta property="fb:admins" content="1504164"/>
56
57  <link rel="apple-touch-icon" sizes="180x180" href="/apple-touch-icon.png">
58  <link rel="icon" type="image/png" sizes="32x32" href="/favicon-32x32.png">
59  <link rel="icon" type="image/png" sizes="16x16" href="/favicon-16x16.png">
60  <link rel="manifest" href="/site.webmanifest">
61  <link rel="mask-icon" href="/safari-pinned-tab.svg" color="#5bbad5">
62  <meta name="msapplication-TileColor" content="#da532c">
63  <meta name="theme-color" content="#ffffff">
64
65</head>
66
67<body class="">
68  <div>
69      <div class="content-main">
70        <div class="nav-holder bg-secondary">
71  <div class='content'>
72    <header class="navbar">
73      <a href="#" class="sidebar-opener" aria-label="Sidebar opener"><i class="fas fa-bars fa-2x"></i></a>
74      <section class="navbar-section">
75        <a href="/" class="btn btn-link">Home</a>
76        <a href="/projects/" class="btn btn-link">Projects</a>
77        <a href="/topics/" class="btn btn-link">Topics</a>
78        <a href="/search/" class="btn btn-link">Search</a>
79        <a href="/newsletter/" class="btn btn-link">Newsletter</a>
80        <a href="/about/" class="btn btn-link">About</a>
81      </section>
82    </header>
83  </div>
84</div>
85        
86  
87    <div class="hero">
88      <div class="hero-body">
89        <div class="content">
90          <h1>Search investigate.ai</h1>
91        </div>
92      </div>
93    </div>
94    <div class="content" id="page-content">
95      <p><link href="/css/search.css" rel="stylesheet" type="text/css">
96<script src="/js/lunr_index.js"></script>
vendor: 1 bytes, line 96
96
97<script src="/js/lunrclient.js"></script>
97</p>
98<p>Enter a search term, e.g., cat</p>
99
100<form id="lunrSearchForm" name="lunrSearchForm">
101    <input class="search-input" name="q" placeholder="Enter search term" type="text"> <input type="submit" value="Search">
102</form>
103
104<div class="loading" id="loading-div">
105    <i class="fa fa-spinner fa-pulse fa-3x fa-fw"></i>
106    <span class="sr-only">Loading...</span>
107</div>
108
109<p>Search results will be written below:</p>
110
111<div class="resultCount" id="resultCount"></div>
112
113<div id="searchResults"></div>
114    </div>
115  
116
117        <div class="footer bg-secondary">
118  <div class="content">
119    <div class="columns">
120      <div class="column col-8 col-sm-12">
121        <p><strong>About the site</strong></p>
122        <p>Hi, I'm <a href="https://twitter.com/dangerscarf">Soma</a>, welcome to Data Science for Journalism a.k.a. investigate.ai!</p>
123        <p>There's been a lot of buzz about machine learning and "artificial intelligence" being used in stories over the past few years. It's mostly not that complicated - a little stats, a classifier here or there - but it's hard to know where to start without a little help.</p>
124        <p>If you know a little Python programming, hopefully this site can be that help! <a href="/about">Learn more about this project here.</a></p>
125        <p><strong>Our newsletter</strong></p>
126        <form action="https://littlecolumns.us12.list-manage.com/subscribe/post?u=ecdebf156be0b7e068fac7c25&amp;id=16537e7c90" method="post" role="form" target="_blank" novalidate>
127          <div class="input-group">
128            <input name="EMAIL" type="email" class="form-input" placeholder="Enter your Email" required="">
129            <div style="position: absolute; left: -5000px;" aria-hidden="true"><input type="text" name="b_ecdebf156be0b7e068fac7c25_16537e7c90" tabindex="-1" value=""></div>
130            <div class="input-group-append">
131              <button class="btn btn-primary input-group-btn" type="submit" aria-label="Email signup submit button">
132                <i class="fas fa-envelope"></i>
133                Sign up
134              </button>
135            </div>
136          </div>
137        </form>
138        
139      </div>
140      <div class="column col-4 col-sm-12">
141        <p><strong>Links</strong></p>
142        <ul>
143          <li><a href="mailto:[email protected]">[email protected]</a></li>
144          <li><a href="https://twitter.com/dangerscarf">@dangerscarf</a></li>
145          <li><a href="/privacy-policy/">Privacy policy</a></li>
146          <li><a href="/newsletter/">Newsletter</a></li>
147          <li>Images via <a href="https://icons8.com/">icons8</a></li>
148        </ul>
149        <p>Thanks to <a href="https://journalism.columbia.edu/">Columbia Journalism School</a>, the <a href="https://knightfoundation.org/">Knight Foundation</a>, and <a href="/about#thankyou">many others</a>.</p>
150      </div>
151    </div>
152  </div>
153</div>
154<script src="/js/scripts.js?v=e9d8cec8fc9221c9dd15f6e0314372b3" type="text/javascript"></script>
154
155      </div>
156      <div class="bg-dark content-sidebar">
157        <div class="sidebar-holder">
158  <div class="brand">
159    <a href="/">investigate.ai</a>
160    <br>
161    data science for everybody
162  </div>
163  
164  <div class="accordion-container">
165    <div class="accordion">
166      <div class="form-group sidebar-sticky">
167        <form method="GET" action="/search/" class="search-form">
168          <div class="input-group">
169            <input type="text" class="form-input input-sm" name="q" placeholder="Search investigate.ai">
170            <button class="btn btn-primary input-group-btn btn-sm">Search</button>
171          </div>
172          </form>
173      </div>
174    
175        
176          <h4 id="textanalysis" class="sidebar-sticky">
177            <a href="#textanalysis">Text analysis</a>
178          </h4>
179          <ol class="menu menu-nav">
180            
181              <li class="menu-item">
182                
183  <a href="/text-analysis/types-of-text-analysis/">        
184      Types of text analysis
185  </a>
186  <div class="toc"></div>
187
188
189
190              </li>
191            
192              <li class="menu-item">
193                
194
195
196  <input id="accordion-countingwords" type="checkbox" name="accordion-checkbox" hidden="">
197  <label class="accordion-header c-hand" for="accordion-countingwords">
198      <i class="icon icon-arrow-right mr-1"></i>
199      Counting words
200  </label>
201  <div class="accordion-body">
202      <ol class="menu menu-nav">
203      
204      <li class="menu-item">
205          
206  <a href="/text-analysis/counting-words-with-pythons-counter/">        
207      Simple word counting
208  </a>
209  <div class="toc"></div>
210
211
212
213      </li>
214      
215      <li class="menu-item">
216          
217  <a href="/text-analysis/counting-words-with-scikit-learns-countvectorizer/">        
218      Counting words across many documents
219  </a>
220  <div class="toc"></div>
221
222
223
224      </li>
225      
226      <li class="menu-item">
227          
228  <a href="/text-analysis/splitting-words-in-east-asian-languages/">        
229      Segmenting words in East Asian languages
230  </a>
231  <div class="toc"></div>
232
233
234
235      </li>
236      
237      <li class="menu-item">
238          
239  <a href="/caixin-museum-word-count/counting-words-in-chinese-museum-names/">        
240      Project: Caixin museums
241  </a>
242  <div class="toc"></div>
243
244
245
246      </li>
247      
248      <li class="menu-item">
249          
250  <a href="/text-analysis/how-to-make-scikit-learn-natural-language-processing-work-with-japanese-chinese/">        
251      Using scikit-learn vectorizers with East Asian languages
252  </a>
253  <div class="toc"></div>
254
255
256
257      </li>
258      
259    </ol>
260  </div>
261
262              </li>
263            
264              <li class="menu-item">
265                
266
267
268  <input id="accordion-advancedwordanalysis" type="checkbox" name="accordion-checkbox" hidden="">
269  <label class="accordion-header c-hand" for="accordion-advancedwordanalysis">
270      <i class="icon icon-arrow-right mr-1"></i>
271      Advanced word analysis
272  </label>
273  <div class="accordion-body">
274      <ol class="menu menu-nav">
275      
276      <li class="menu-item">
277          
278  <a href="/text-analysis/a-simple-explanation-of-tf-idf/">        
279      Upgraded word counts with TF-IDF
280  </a>
281  <div class="toc"></div>
282
283
284
285      </li>
286      
287      <li class="menu-item">
288          
289  <a href="/text-analysis/explaining-n-grams-in-natural-language-processing/">        
290      Multi-word phrases and n-grams
291  </a>
292  <div class="toc"></div>
293
294
295
296      </li>
297      
298      <li class="menu-item">
299          
300  <a href="/text-analysis/stemming-and-lemmatization/">        
301      Standardizing text with stemming and lemmatization
302  </a>
303  <div class="toc"></div>
304
305
306
307      </li>
308      
309      <li class="menu-item">
310          
311  <a href="/text-analysis/using-tf-idf-with-chinese/">        
312      Using TF-IDF with Chinese text
313  </a>
314  <div class="toc"></div>
315
316
317
318      </li>
319      
320    </ol>
321  </div>
322
323              </li>
324            
325              <li class="menu-item">
326                
327
328
329  <input id="accordion-sentimentanalysis" type="checkbox" name="accordion-checkbox" hidden="">
330  <label class="accordion-header c-hand" for="accordion-sentimentanalysis">
331      <i class="icon icon-arrow-right mr-1"></i>
332      Sentiment analysis
333  </label>
334  <div class="accordion-body">
335      <ol class="menu menu-nav">
336      
337      <li class="menu-item">
338          
339  <a href="/investigating-sentiment-analysis/comparing-sentiment-analysis-tools/">        
340      Comparing sentiment analysis tools
341  </a>
342  <div class="toc"></div>
343
344
345
346      </li>
347      
348      <li class="menu-item">
349          
350  <a href="/investigating-sentiment-analysis/designing-your-own-sentiment-analysis-tool/">        
351      Design your own sentiment analyzer
352  </a>
353  <div class="toc"></div>
354
355
356
357      </li>
358      
359      <li class="menu-item">
360          
361  <a href="/investigating-sentiment-analysis/more-data-to-train-our-sentiment-analysis-tool/">        
362      Improving your tool
363  </a>
364  <div class="toc"></div>
365
366
367
368      </li>
369      
370      <li class="menu-item">
371          
372  <a href="/upshot-trump-emolex/nrc-emotional-lexicon/">        
373      NRC Emotional Lexicon
374  </a>
375  <div class="toc"></div>
376
377
378
379      </li>
380      
381      <li class="menu-item">
382          
383  <a href="/upshot-trump-emolex/trump-vs-state-of-the-union-addresses/">        
384      Project: UpShot State of the Union
385  </a>
386  <div class="toc"></div>
387
388
389
390      </li>
391      
392      <li class="menu-item">
393          
394  <a href="/nyt-trump-tweets/">        
395      Project: NYT Trump tweets
396  </a>
397  <div class="toc"></div>
398
399
400
401      </li>
402      
403    </ol>
404  </div>
405
406              </li>
407            
408              <li class="menu-item">
409                
410
411
412  <input id="accordion-documentstotext" type="checkbox" name="accordion-checkbox" hidden="">
413  <label class="accordion-header c-hand" for="accordion-documentstotext">
414      <i class="icon icon-arrow-right mr-1"></i>
415      Documents to text
416  </label>
417  <div class="accordion-body">
418      <ol class="menu menu-nav">
419      
420      <li class="menu-item">
421          
422  <a href="/text-analysis/processing-documents-with-apache-tika/">        
423      Converting documents to text (English)
424  </a>
425  <div class="toc"></div>
426
427
428
429      </li>
430      
431      <li class="menu-item">
432          
433  <a href="/text-analysis/processing-documents-with-apache-tika-greek/">        
434      Converting documents to text (non-English)
435  </a>
436  <div class="toc"></div>
437
438
439
440      </li>
441      
442    </ol>
443  </div>
444
445              </li>
446            
447              <li class="menu-item">
448                
449
450
451  <input id="accordion-conceptspeopleandplaces" type="checkbox" name="accordion-checkbox" hidden="">
452  <label class="accordion-header c-hand" for="accordion-conceptspeopleandplaces">
453      <i class="icon icon-arrow-right mr-1"></i>
454      Concepts, people and places
455  </label>
456  <div class="accordion-body">
457      <ol class="menu menu-nav">
458      
459      <li class="menu-item">
460          
461  <a href="/text-analysis/introduction-to-topic-modeling/">        
462      Extracting topics from documents
463  </a>
464  <div class="toc"></div>
465
466
467
468      </li>
469      
470      <li class="menu-item">
471          
472  <a href="/text-analysis/choosing-the-right-number-of-topics-for-a-scikit-learn-topic-model/">        
473      Choosing the right number of topics
474  </a>
475  <div class="toc"></div>
476
477
478
479      </li>
480      
481      <li class="menu-item">
482          
483  <a href="/text-analysis/topic-models-with-gensim/">        
484      Topic models with Gensim
485  </a>
486  <div class="toc"></div>
487
488
489
490      </li>
491      
492      <li class="menu-item">
493          
494  <a href="/text-analysis/topic-modeling-and-clustering/">        
495      Topic models vs clustering
496  </a>
497  <div class="toc"></div>
498
499
500
501      </li>
502      
503      <li class="menu-item">
504          
505  <a href="/text-analysis/named-entity-recognition/">        
506      Entity recognition
507  </a>
508  <div class="toc"></div>
509
510
511
512      </li>
513      
514      <li class="menu-item">
515          
516  <a href="/text-analysis/word-embeddings/">        
517      Intro to word embeddings
518  </a>
519  <div class="toc"></div>
520
521
522
523      </li>
524      
525      <li class="menu-item">
526          
527  <a href="/text-analysis/document-similarity-using-word-embeddings/">        
528      Conceptual document similarity
529  </a>
530  <div class="toc"></div>
531
532
533
534      </li>
535      
536      <li class="menu-item">
537          
538  <a href="/text-analysis/comparing-documents-in-different-languages/">        
539      Comparing documents in different languages
540  </a>
541  <div class="toc"></div>
542
543
544
545      </li>
546      
547    </ol>
548  </div>
549
550              </li>
551            
552          </ol>
553        
554          <h4 id="puttingthingsincategoriesautomatically" class="sidebar-sticky">
555            <a href="#puttingthingsincategoriesautomatically">Putting things in categories automatically</a>
556          </h4>
557          <ol class="menu menu-nav">
558            
559              <li class="menu-item">
560                
561  <a href="/classification/intro-to-classification/">        
562      Introduction to Classification
563  </a>
564  <div class="toc"></div>
565
566
567
568              </li>
569            
570              <li class="menu-item">
571                
572
573
574  <input id="accordion-techniques" type="checkbox" name="accordion-checkbox" hidden="">
575  <label class="accordion-header c-hand" for="accordion-techniques">
576      <i class="icon icon-arrow-right mr-1"></i>
577      Techniques
578  </label>
579  <div class="accordion-body">
580      <ol class="menu menu-nav">
581      
582      <li class="menu-item">
583          
584  <a href="/classification/evaluating-classifiers/">        
585      Evaluating classifiers
586  </a>
587  <div class="toc"></div>
588
589
590
591      </li>
592      
593      <li class="menu-item">
594          
595  <a href="/classification/scikit-learn-and-categorical-features/">        
596      Categorical features
597  </a>
598  <div class="toc"></div>
599
600
601
602      </li>
603      
604      <li class="menu-item">
605          
606  <a href="/classification/using-classification-algorithms-with-text/">        
607      Classifiers with text
608  </a>
609  <div class="toc"></div>
610
611
612
613      </li>
614      
615      <li class="menu-item">
616          
617  <a href="/classification/correcting-for-imbalanced-datasets/">        
618      Correcting for imbalanced datasets
619  </a>
620  <div class="toc"></div>
621
622
623
624      </li>
625      
626    </ol>
627  </div>
628
629              </li>
630            
631              <li class="menu-item">
632                
633
634
635  <input id="accordion-projects" type="checkbox" name="accordion-checkbox" hidden="">
636  <label class="accordion-header c-hand" for="accordion-projects">
637      <i class="icon icon-arrow-right mr-1"></i>
638      Projects
639  </label>
640  <div class="accordion-body">
641      <ol class="menu menu-nav">
642      
643      <li class="menu-item">
644          
645  <a href="/buzzfeed-spy-planes/buzzfeed-surveillance-planes-random-forests/">        
646      BuzzFeed: Spy planes
647  </a>
648  <div class="toc"></div>
649
650
651
652      </li>
653      
654      <li class="menu-item">
655          
656  <a href="/wapo-app-reviews/predict-reviews/">        
657      WaPo chat: App reviews
658  </a>
659  <div class="toc"></div>
660
661
662
663      </li>
664      
665      <li class="menu-item">
666          
667  <a href="/nyt-takata-airbags/nyt-takata-completed/">        
668      NYT: Faulty airbag search
669  </a>
670  <div class="toc"></div>
671
672
673
674      </li>
675      
676      <li class="menu-item">
677          
678  <a href="/latimes-crime-classification/using-a-classifier-to-find-misclassified-crimes/">        
679      LA Times: crime classifier
680  </a>
681  <div class="toc"></div>
682
683
684
685      </li>
686      
687    </ol>
688  </div>
689
690              </li>
691            
692          </ol>
693        
694          <h4 id="howxaffectsy" class="sidebar-sticky">
695            <a href="#howxaffectsy">How X affects Y</a>
696          </h4>
697          <ol class="menu menu-nav">
698            
699              <li class="menu-item">
700                
701  <a href="/regression/what-is-regression/">        
702      Finding relationships with regression
703  </a>
704  <div class="toc"></div>
705
706
707
708              </li>
709            
710              <li class="menu-item">
711                
712
713
714  <input id="accordion-linearregression" type="checkbox" name="accordion-checkbox" hidden="">
715  <label class="accordion-header c-hand" for="accordion-linearregression">
716      <i class="icon icon-arrow-right mr-1"></i>
717      Linear Regression
718  </label>
719  <div class="accordion-body">
720      <ol class="menu menu-nav">
721      
722      <li class="menu-item">
723          
724  <a href="/regression/linear-regression-quickstart/">        
725      Linear regression (Quickstart)
726  </a>
727  <div class="toc"></div>
728
729
730
731      </li>
732      
733      <li class="menu-item">
734          
735  <a href="/regression/linear-regression/">        
736      Linear regression for humans
737  </a>
738  <div class="toc"></div>
739
740
741
742      </li>
743      
744      <li class="menu-item">
745          
746  <a href="/regression/linear-regression-part-two/">        
747      Putting regression to use
748  </a>
749  <div class="toc"></div>
750
751
752
753      </li>
754      
755      <li class="menu-item">
756          
757  <a href="/regression/linear-regression-evaluation/">        
758      Evaluating regressions
759  </a>
760  <div class="toc"></div>
761
762
763
764      </li>
765      
766      <li class="menu-item">
767          
768  <a href="/ap-regression-unemployment/simple-regression-with-census-data-statsmodels-with-formulas/">        
769      Associated Press: Life expectancy and unemployment
770  </a>
771  <div class="toc"></div>
772
773
774
775      </li>
776      
777    </ol>
778  </div>
779
780              </li>
781            
782              <li class="menu-item">
783                
784
785
786  <input id="accordion-logisticregression" type="checkbox" name="accordion-checkbox" hidden="">
787  <label class="accordion-header c-hand" for="accordion-logisticregression">
788      <i class="icon icon-arrow-right mr-1"></i>
789      Logistic Regression
790  </label>
791  <div class="accordion-body">
792      <ol class="menu menu-nav">
793      
794      <li class="menu-item">
795          
796  <a href="/regression/logistic-regression-quickstart/">        
797      Logistic regression (Quickstart)
798  </a>
799  <div class="toc"></div>
800
801
802
803      </li>
804      
805      <li class="menu-item">
806          
807  <a href="/regression/logistic-regression/">        
808      Logistic regression for humans
809  </a>
810  <div class="toc"></div>
811
812
813
814      </li>
815      
816      <li class="menu-item">
817          
818  <a href="/regression/logistic-regression-part-two/">        
819      More complex logistic regressions
820  </a>
821  <div class="toc"></div>
822
823
824
825      </li>
826      
827      <li class="menu-item">
828          
829  <a href="/regression/evaluating-logistic-regressions/">        
830      Evaluating logistic regressions
831  </a>
832  <div class="toc"></div>
833
834
835
836      </li>
837      
838      <li class="menu-item">
839          
840  <a href="/boston-globe-tickets/boston-globe-ticketing-regression/">        
841      Boston Globe: Speeding tickets
842  </a>
843  <div class="toc"></div>
844
845
846
847      </li>
848      
849      <li class="menu-item">
850          
851  <a href="/apm-reports-jury-bias/in-the-dark-alternative-formula-methods/">        
852      APM Reports: Jury selection
853  </a>
854  <div class="toc"></div>
855
856
857
858      </li>
859      
860    </ol>
861  </div>
862
863              </li>
864            
865          </ol>
866        
867          <h4 id="pythondatasciencereference" class="sidebar-sticky">
868            <a href="#pythondatasciencereference">Python data science reference</a>
869          </h4>
870          <ol class="menu menu-nav">
871            
872              <li class="menu-item">
873                
874  <a href="/reference/">        
875      Introduction
876  </a>
877  <div class="toc"></div>
878
879
880
881              </li>
882            
883              <li class="menu-item">
884                
885  <a href="/reference/vectorizing/">        
886      Vectorizing
887  </a>
888  <div class="toc"></div>
889
890
891
892              </li>
893            
894              <li class="menu-item">
895                
896  <a href="/reference/text-analysis/">        
897      Text Analysis
898  </a>
899  <div class="toc"></div>
900
901
902
903              </li>
904            
905              <li class="menu-item">
906                
907  <a href="/reference/regression/">        
908      Regression
909  </a>
910  <div class="toc"></div>
911
912
913
914              </li>
915            
916              <li class="menu-item">
917                
918  <a href="/reference/classification/">        
919      Classification
920  </a>
921  <div class="toc"></div>
922
923
924
925              </li>
926            
927          </ol>
928        
929          <h4 id="allprojects" class="sidebar-sticky">
930            <a href="#allprojects">All Projects</a>
931          </h4>
932          <ol class="menu menu-nav">
933            
934              <li class="menu-item">
935                
936  <a href="/projects/">        
937      Project Summaries
938  </a>
939  <div class="toc"></div>
940
941
942
943              </li>
944            
945              <li class="menu-item">
946                
947
948
949  <input id="accordion-strongnytstrongtakataairbagsearch" type="checkbox" name="accordion-checkbox" hidden="">
950  <label class="accordion-header c-hand" for="accordion-strongnytstrongtakataairbagsearch">
951      <i class="icon icon-arrow-right mr-1"></i>
952      <strong>NYT:</strong>  Takata airbag search
953  </label>
954  <div class="accordion-body">
955      <ol class="menu menu-nav">
956      
957      <li class="menu-item">
958          
959  <a href="/nyt-takata-airbags/">        
960      Summary
961  </a>
962  <div class="toc"></div>
963
964
965
966      </li>
967      
968      <li class="menu-item">
969          
970  <a href="/nyt-takata-airbags/airbag-classifier-search-binary/">        
971      A simplistic reproduction of the NYT's research using logistic regression
972  </a>
973  <div class="toc"></div>
974
975
976
977      </li>
978      
979      <li class="menu-item">
980          
981  <a href="/nyt-takata-airbags/airbag-classifier-search-decision-tree/">        
982      A decision-tree reproduction of the NYT's research
983  </a>
984  <div class="toc"></div>
985
986
987
988      </li>
989      
990      <li class="menu-item">
991          
992  <a href="/nyt-takata-airbags/airbag-classifier-search-countvectorizer/">        
993      Combining a text vectorizer and a classifier to track down suspicious complaints
994  </a>
995  <div class="toc"></div>
996
997
998
999      </li>
1000      
1001    </ol>
1002  </div>
1003
1004              </li>
1005            
1006              <li class="menu-item">
1007                
1008
1009
1010  <input id="accordion-stronglatimesstrongcrimeclassification" type="checkbox" name="accordion-checkbox" hidden="">
1011  <label class="accordion-header c-hand" for="accordion-stronglatimesstrongcrimeclassification">
1012      <i class="icon icon-arrow-right mr-1"></i>
1013      <strong>LA Times:</strong>  Crime classification
1014  </label>
1015  <div class="accordion-body">
1016      <ol class="menu menu-nav">
1017      
1018      <li class="menu-item">
1019          
1020  <a href="/latimes-crime-classification/">        
1021      Summary
1022  </a>
1023  <div class="toc"></div>
1024
1025
1026
1027      </li>
1028      
1029      <li class="menu-item">
1030          
1031  <a href="/latimes-crime-classification/using-a-classifier-to-find-misclassified-crimes/">        
1032      Predicting downgraded assaults with machine learning
1033  </a>
1034  <div class="toc"></div>
1035
1036
1037
1038      </li>
1039      
1040      <li class="menu-item">
1041          
1042  <a href="/latimes-crime-classification/inspecting-classifications/">        
1043      Taking a closer look at our classifier and its misclassifications
1044  </a>
1045  <div class="toc"></div>
1046
1047
1048
1049      </li>
1050      
1051      <li class="menu-item">
1052          
1053  <a href="/latimes-crime-classification/trying-out-different-classifiers/">        
1054      Trying out and combining different classifiers
1055  </a>
1056  <div class="toc"></div>
1057
1058
1059
1060      </li>
1061      
1062    </ol>
1063  </div>
1064
1065              </li>
1066            
1067              <li class="menu-item">
1068                
1069
1070
1071  <input id="accordion-strongcaixinstrongmuseumnames" type="checkbox" name="accordion-checkbox" hidden="">
1072  <label class="accordion-header c-hand" for="accordion-strongcaixinstrongmuseumnames">
1073      <i class="icon icon-arrow-right mr-1"></i>
1074      <strong>Caixin:</strong>  Museum names
1075  </label>
1076  <div class="accordion-body">
1077      <ol class="menu menu-nav">
1078      
1079      <li class="menu-item">
1080          
1081  <a href="/caixin-museum-word-count/">        
1082      Summary
1083  </a>
1084  <div class="toc"></div>
1085
1086
1087
1088      </li>
1089      
1090      <li class="menu-item">
1091          
1092  <a href="/caixin-museum-word-count/chinese-museum-dataset-cleanup/">        
1093      Chinese museum dataset cleanup
1094  </a>
1095  <div class="toc"></div>
1096
1097
1098
1099      </li>
1100      
1101      <li class="menu-item">
1102          
1103  <a href="/caixin-museum-word-count/chinese-museums-per-capita-analysis/">        
1104      Chinese museums per capita analysis
1105  </a>
1106  <div class="toc"></div>
1107
1108
1109
1110      </li>
1111      
1112      <li class="menu-item">
1113          
1114  <a href="/caixin-museum-word-count/counting-words-in-chinese-museum-names/">        
1115      Counting words in Chinese museum names
1116  </a>
1117  <div class="toc"></div>
1118
1119
1120
1121      </li>
1122      
1123    </ol>
1124  </div>
1125
1126              </li>
1127            
1128              <li class="menu-item">
1129                
1130
1131
1132  <input id="accordion-strongwapostrongrandomchatappsafety" type="checkbox" name="accordion-checkbox" hidden="">
1133  <label class="accordion-header c-hand" for="accordion-strongwapostrongrandomchatappsafety">
1134      <i class="icon icon-arrow-right mr-1"></i>
1135      <strong>WaPo:</strong>  Random chat app safety
1136  </label>
1137  <div class="accordion-body">
1138      <ol class="menu menu-nav">
1139      
1140      <li class="menu-item">
1141          
1142  <a href="/wapo-app-reviews/">        
1143      Summary
1144  </a>
1145  <div class="toc"></div>
1146
1147
1148
1149      </li>
1150      
1151      <li class="menu-item">
1152          
1153  <a href="/wapo-app-reviews/scrape-app-store-reviews/">        
1154      Scrape and combine app store reviews
1155  </a>
1156  <div class="toc"></div>
1157
1158
1159
1160      </li>
1161      
1162      <li class="menu-item">
1163          
1164  <a href="/wapo-app-reviews/predict-reviews/">        
1165      Build a classifier to detect reviews about bad behavior
1166  </a>
1167  <div class="toc"></div>
1168
1169
1170
1171      </li>
1172      
1173    </ol>
1174  </div>
1175
1176              </li>
1177            
1178              <li class="menu-item">
1179                
1180  <a href="/ajc-doctors-abuse/">        
1181      <strong>AJC:</strong>  Doctors and sex abuse
1182  </a>
1183  <div class="toc"></div>
1184
1185
1186
1187              </li>
1188            
1189              <li class="menu-item">
1190                
1191
1192
1193  <input id="accordion-strongtheupshotstrongtrumpspeeches" type="checkbox" name="accordion-checkbox" hidden="">
1194  <label class="accordion-header c-hand" for="accordion-strongtheupshotstrongtrumpspeeches">
1195      <i class="icon icon-arrow-right mr-1"></i>
1196      <strong>The UpShot:</strong>  Trump speeches
1197  </label>
1198  <div class="accordion-body">
1199      <ol class="menu menu-nav">
1200      
1201      <li class="menu-item">
1202          
1203  <a href="/upshot-trump-emolex/">        
1204      Summary
1205  </a>
1206  <div class="toc"></div>
1207
1208
1209
1210      </li>
1211      
1212      <li class="menu-item">
1213          
1214  <a href="/upshot-trump-emolex/nrc-emotional-lexicon/">        
1215      An introduction to the NRC Emotional Lexicon
1216  </a>
1217  <div class="toc"></div>
1218
1219
1220
1221      </li>
1222      
1223      <li class="menu-item">
1224          
1225  <a href="/upshot-trump-emolex/trump-vs-state-of-the-union-addresses/">        
1226      Reproducing The UpShot's Trump State of the Union visualization
1227  </a>
1228  <div class="toc"></div>
1229
1230
1231
1232      </li>
1233      
1234    </ol>
1235  </div>
1236
1237              </li>
1238            
1239              <li class="menu-item">
1240                
1241
1242
1243  <input id="accordion-strongusatodaystrongmodellegislation" type="checkbox" name="accordion-checkbox" hidden="">
1244  <label class="accordion-header c-hand" for="accordion-strongusatodaystrongmodellegislation">
1245      <i class="icon icon-arrow-right mr-1"></i>
1246      <strong>USA Today:</strong>  Model legislation
1247  </label>
1248  <div class="accordion-body">
1249      <ol class="menu menu-nav">
1250      
1251      <li class="menu-item">
1252          
1253  <a href="/azcentral-text-reuse-model-legislation/">        
1254      Summary
1255  </a>
1256  <div class="toc"></div>
1257
1258
1259
1260      </li>
1261      
1262      <li class="menu-item">
1263          
1264  <a href="/azcentral-text-reuse-model-legislation/01-downloading-one-million-pieces-of-legislation-from-legiscan/">        
1265      Downloading one million pieces of legislation from LegiScan
1266  </a>
1267  <div class="toc"></div>
1268
1269
1270
1271      </li>
1272      
1273      <li class="menu-item">
1274          
1275  <a href="/azcentral-text-reuse-model-legislation/02-taking-a-mill
1275ion-pieces-of-legislation-from-a-csv-and-inserting-them-into-postgres/">        
1276      Taking a million pieces of legislation from a CSV and inserting them into Postgres
1277  </a>
1278  <div class="toc"></div>
1279
1280
1281
1282      </li>
1283      
1284      <li class="menu-item">
1285          
1286  <a href="/azcentral-text-reuse-model-legislation/03-download-word-pdf-and-html-content-and-process-it-into-text-with-tika/">        
1287      Download Word, PDF and HTML content and process it into text with Tika
1288  </a>
1289  <div class="toc"></div>
1290
1291
1292
1293      </li>
1294      
1295      <li class="menu-item">
1296          
1297  <a href="/azcentral-text-reuse-model-legislation/04-import-content-into-solr-for-advanced-text-searching/">        
1298      Import content into Solr for advanced text searching
1299  </a>
1300  <div class="toc"></div>
1301
1302
1303
1304      </li>
1305      
1306      <li class="menu-item">
1307          
1308  <a href="/azcentral-text-reuse-model-legislation/05-checking-for-legislative-text-reuse-using-python-solr-and-ngrams/">        
1309      Checking for legislative text reuse using Python, Solr, and ngrams
1310  </a>
1311  <div class="toc"></div>
1312
1313
1314
1315      </li>
1316      
1317      <li class="menu-item">
1318          
1319  <a href="/azcentral-text-reuse-model-legislation/05-checking-for-legislative-text-reuse-using-python-solr-and-simple-text-search/">        
1320      Checking for legislative text reuse using Python, Solr, and simple text search
1321  </a>
1322  <div class="toc"></div>
1323
1324
1325
1326      </li>
1327      
1328      <li class="menu-item">
1329          
1330  <a href="/azcentral-text-reuse-model-legislation/06-search-for-model-legislation-in-over-one-million-bills-using-postgres-and-solr/">        
1331      Search for model legislation in over one million bills using Postgres and Solr
1332  </a>
1333  <div class="toc"></div>
1334
1335
1336
1337      </li>
1338      
1339      <li class="menu-item">
1340          
1341  <a href="/azcentral-text-reuse-model-legislation/using-topic-modeling-to-categorize-legislation/">        
1342      Using topic modeling to categorize legislation
1343  </a>
1344  <div class="toc"></div>
1345
1346
1347
1348      </li>
1349      
1350    </ol>
1351  </div>
1352
1353              </li>
1354            
1355              <li class="menu-item">
1356                
1357  <a href="/fcc-comments/">        
1358      FCC comment bots
1359  </a>
1360  <div class="toc"></div>
1361
1362
1363
1364              </li>
1365            
1366              <li class="menu-item">
1367                
1368
1369
1370  <input id="accordion-strongbloombergstrongdemocraticcandidatetweets" type="checkbox" name="accordion-checkbox" hidden="">
1371  <label class="accordion-header c-hand" for="accordion-strongbloombergstrongdemocraticcandidatetweets">
1372      <i class="icon icon-arrow-right mr-1"></i>
1373      <strong>Bloomberg:</strong>  Democratic Candidate Tweets
1374  </label>
1375  <div class="accordion-body">
1376      <ol class="menu menu-nav">
1377      
1378      <li class="menu-item">
1379          
1380  <a href="/bloomberg-tweet-topics/">        
1381      Summary
1382  </a>
1383  <div class="toc"></div>
1384
1385
1386
1387      </li>
1388      
1389      <li class="menu-item">
1390          
1391  <a href="/bloomberg-tweet-topics/scrape-tweets-from-presidential-primary-candidates/">        
1392      Downloading all 2019 tweets from Democratic presidential candidates
1393  </a>
1394  <div class="toc"></div>
1395
1396
1397
1398      </li>
1399      
1400      <li class="menu-item">
1401          
1402  <a href="/bloomberg-tweet-topics/topic-modeling-for-tweets/">        
1403      Using topic modeling to analyze presidential candidate tweets
1404  </a>
1405  <div class="toc"></div>
1406
1407
1408
1409      </li>
1410      
1411      <li class="menu-item">
1412          
1413  <a href="/bloomberg-tweet-topics/assigning-categories-to-text-using-keyword-matching/">        
1414      Assigning categories to tweets using keyword matching
1415  </a>
1416  <div class="toc"></div>
1417
1418
1419
1420      </li>
1421      
1422      <li class="menu-item">
1423          
1424  <a href="/bloomberg-tweet-topics/building-streamgraphs-from-candidate-tweets/">        
1425      Building streamgraphs from categorized and dated datasets
1426  </a>
1427  <div class="toc"></div>
1428
1429
1430
1431      </li>
1432      
1433    </ol>
1434  </div>
1435
1436              </li>
1437            
1438              <li class="menu-item">
1439                
1440  <a href="/nyt-trump-tweets/">        
1441      <strong>NYT:</strong>  Trump tweets
1442  </a>
1443  <div class="toc"></div>
1444
1445
1446
1447              </li>
1448            
1449              <li class="menu-item">
1450                
1451
1452
1453  <input id="accordion-strongapstronglifeexpectancy" type="checkbox" name="accordion-checkbox" hidden="">
1454  <label class="accordion-header c-hand" for="accordion-strongapstronglifeexpectancy">
1455      <i class="icon icon-arrow-right mr-1"></i>
1456      <strong>AP:</strong>  Life expectancy
1457  </label>
1458  <div class="accordion-body">
1459      <ol class="menu menu-nav">
1460      
1461      <li class="menu-item">
1462          
1463  <a href="/ap-regression-unemployment/">        
1464      Summary
1465  </a>
1466  <div class="toc"></div>
1467
1468
1469
1470      </li>
1471      
1472      <li class="menu-item">
1473          
1474  <a href="/ap-regression-unemployment/simple-regression-with-census-data-statsmodels-with-formulas/">        
1475      Simple logistic regression using statsmodels (formula version)
1476  </a>
1477  <div class="toc"></div>
1478
1479
1480
1481      </li>
1482      
1483      <li class="menu-item">
1484          
1485  <a href="/ap-regression-unemployment/simple-regression-with-census-data-statsmodels-with-dataframes/">        
1486      Simple logistic regression using statsmodels (dataframes version)
1487  </a>
1488  <div class="toc"></div>
1489
1490
1491
1492      </li>
1493      
1494    </ol>
1495  </div>
1496
1497              </li>
1498            
1499              <li class="menu-item">
1500                
1501  <a href="/fivethirtyeight-p-hacking/">        
1502      <strong>FiveThirtyEight:</strong>  P-values
1503  </a>
1504  <div class="toc"></div>
1505
1506
1507
1508              </li>
1509            
1510              <li class="menu-item">
1511                
1512
1513
1514  <input id="accordion-strongmilwaukeejournalsentinelstrongpotholes" type="checkbox" name="accordion-checkbox" hidden="">
1515  <label class="accordion-header c-hand" for="accordion-strongmilwaukeejournalsentinelstrongpotholes">
1516      <i class="icon icon-arrow-right mr-1"></i>
1517      <strong>Milwaukee Journal-Sentinel:</strong>  Potholes
1518  </label>
1519  <div class="accordion-body">
1520      <ol class="menu menu-nav">
1521      
1522      <li class="menu-item">
1523          
1524  <a href="/milwaukee-potholes/">        
1525      Summary
1526  </a>
1527  <div class="toc"></div>
1528
1529
1530
1531      </li>
1532      
1533      <li class="menu-item">
1534          
1535  <a href="/milwaukee-potholes/milwaukee-journal-sentinel-and-potholes-full-walkthrough/">        
1536      Pothole geographic analysis and linear regression, complete walkthrough
1537  </a>
1538  <div class="toc"></div>
1539
1540
1541
1542      </li>
1543      
1544      <li class="menu-item">
1545          
1546  <a href="/milwaukee-potholes/milwaukee-journal-sentinel-and-potholes-without-merging/">        
1547      Pothole demographics linear regression, no spatial analysis
1548  </a>
1549  <div class="toc"></div>
1550
1551
1552
1553      </li>
1554      
1555    </ol>
1556  </div>
1557
1558              </li>
1559            
1560              <li class="menu-item">
1561                
1562
1563
1564  <input id="accordion-strongdallasmorningnewsstrongcheatingschools" type="checkbox" name="accordion-checkbox" hidden="">
1565  <label class="accordion-header c-hand" for="accordion-strongdallasmorningnewsstrongcheatingschools">
1566      <i class="icon icon-arrow-right mr-1"></i>
1567      <strong>Dallas Morning News:</strong>  Cheating schools
1568  </label>
1569  <div class="accordion-body">
1570      <ol class="menu menu-nav">
1571      
1572      <li class="menu-item">
1573          
1574  <a href="/dmn-texas-school-cheating/">        
1575      Summary
1576  </a>
1577  <div class="toc"></div>
1578
1579
1580
1581      </li>
1582      
1583      <li class="menu-item">
1584          
1585  <a href="/dmn-texas-school-cheating/texas-school-cheating-finding-outliers-with-standard-deviation-and-regression/">        
1586      Finding outliers with standard deviation and regression
1587  </a>
1588  <div class="toc"></div>
1589
1590
1591
1592      </li>
1593      
1594      <li class="menu-item">
1595          
1596  <a href="/dmn-texas-school-cheating/texas-school-cheating-finding-outliers-with-regression-residuals/">        
1597      Finding outliers with regression residuals (short version)
1598  </a>
1599  <div class="toc"></div>
1600
1601
1602
1603      </li>
1604      
1605      <li class="menu-item">
1606          
1607  <a href="/dmn-texas-school-cheating/texas-school-cheating-graph-reproductions/">        
1608      Reproducing the graphics from The Dallas Morning News piece
1609  </a>
1610  <div class="toc"></div>
1611
1612
1613
1614      </li>
1615      
1616    </ol>
1617  </div>
1618
1619              </li>
1620            
1621              <li class="menu-item">
1622                
1623
1624
1625  <input id="accordion-strongtampabaytimesstrongfailurefactories" type="checkbox" name="accordion-checkbox" hidden="">
1626  <label class="accordion-header c-hand" for="accordion-strongtampabaytimesstrongfailurefactories">
1627      <i class="icon icon-arrow-right mr-1"></i>
1628      <strong>Tampa Bay Times:</strong>  Failure factories
1629  </label>
1630  <div class="accordion-body">
1631      <ol class="menu menu-nav">
1632      
1633      <li class="menu-item">
1634          
1635  <a href="/tampa-bay-times-schools/">        
1636      Summary
1637  </a>
1638  <div class="toc"></div>
1639
1640
1641
1642      </li>
1643      
1644      <li class="menu-item">
1645          
1646  <a href="/tampa-bay-times-schools/linear-regression-on-florida-schools/">        
1647      Linear regression on Florida schools, complete walkthrough
1648  </a>
1649  <div class="toc"></div>
1650
1651
1652
1653      </li>
1654      
1655      <li class="menu-item">
1656          
1657  <a href="/tampa-bay-times-schools/linear-regression-on-florida-schools-no-cleaning/">        
1658      Linear regression on Florida schools, no cleaning
1659  </a>
1660  <div class="toc"></div>
1661
1662
1663
1664      </li>
1665      
1666    </ol>
1667  </div>
1668
1669              </li>
1670            
1671              <li class="menu-item">
1672                
1673
1674
1675  <input id="accordion-caraccidentsandcarweight" type="checkbox" name="accordion-checkbox" hidden="">
1676  <label class="accordion-header c-hand" for="accordion-caraccidentsandcarweight">
1677      <i class="icon icon-arrow-right mr-1"></i>
1678      Car accidents and car weight
1679  </label>
1680  <div class="accordion-body">
1681      <ol class="menu menu-nav">
1682      
1683      <li class="menu-item">
1684          
1685  <a href="/car-crashes-weight-regression/">        
1686      Summary
1687  </a>
1688  <div class="toc"></div>
1689
1690
1691
1692      </li>
1693      
1694      <li class="menu-item">
1695          
1696  <a href="/car-crashes-weight-regression/car-crashes-feature-selection-and-engineering/">        
1697      Feature selection and engineering
1698  </a>
1699  <div class="toc"></div>
1700
1701
1702
1703      </li>
1704      
1705      <li class="menu-item">
1706          
1707  <a href="/car-crashes-weight-regression/01-combine-excel-files-across-multiple-sheets-and-save-as-csv-files/">        
1708      Combine Excel files across multiple sheets and save as CSV files
1709  </a>
1710  <div class="toc"></div>
1711
1712
1713
1714      </li>
1715      
1716      <li class="menu-item">
1717          
1718  <a href="/car-crashes-weight-regression/02-create-make-model-weights-csv/">        
1719      Create make model weights csv
1720  </a>
1721  <div class="toc"></div>
1722
1723
1724
1725      </li>
1726      
1727      <li class="menu-item">
1728          
1729  <a href="/car-crashes-weight-regression/03-find-car-data-from-vins/">        
1730      Find car data from VINs
1731  </a>
1732  <div class="toc"></div>
1733
1734
1735
1736      </li>
1737      
1738      <li class="menu-item">
1739          
1740  <a href="/car-crashes-weight-regression/04-combine-vins-and-weights/">        
1741      Combine VINs and weights
1742  </a>
1743  <div class="toc"></div>
1744
1745
1746
1747      </li>
1748      
1749      <li class="menu-item">
1750          
1751  <a href="/car-crashes-weight-regression/05-clean-combine-and-filter-data/">        
1752      Clean combine and filter data
1753  </a>
1754  <div class="toc"></div>
1755
1756
1757
1758      </li>
1759      
1760    </ol>
1761  </div>
1762
1763              </li>
1764            
1765              <li class="menu-item">
1766                
1767  <a href="/propublica-opportunity-gap/">        
1768      <strong>ProPublica:</strong>  Opportunity Gap
1769  </a>
1770  <div class="toc"></div>
1771
1772
1773
1774              </li>
1775            
1776              <li class="menu-item">
1777                
1778
1779
1780  <input id="accordion-strongbostonglobestrongticketingbias" type="checkbox" name="accordion-checkbox" hidden="">
1781  <label class="accordion-header c-hand" for="accordion-strongbostonglobestrongticketingbias">
1782      <i class="icon icon-arrow-right mr-1"></i>
1783      <strong>Boston Globe:</strong>  Ticketing bias
1784  </label>
1785  <div class="accordion-body">
1786      <ol class="menu menu-nav">
1787      
1788      <li class="menu-item">
1789          
1790  <a href="/boston-globe-tickets/">        
1791      Summary
1792  </a>
1793  <div class="toc"></div>
1794
1795
1796
1797      </li>
1798      
1799      <li class="menu-item">
1800          
1801  <a href="/boston-globe-tickets/boston-globe-ticketing-regression/">        
1802      Logistic regression for speeding tickets
1803  </a>
1804  <div class="toc"></div>
1805
1806
1807
1808      </li>
1809      
1810    </ol>
1811  </div>
1812
1813              </li>
1814            
1815              <li class="menu-item">
1816                
1817  <a href="/stanford-open-policing/">        
1818      <strong>Stanford:</strong>  Open Policing Data
1819  </a>
1820  <div class="toc"></div>
1821
1822
1823
1824              </li>
1825            
1826              <li class="menu-item">
1827                
1828
1829
1830  <input id="accordion-strongbuzzfeedstrongsurveillanceplanes" type="checkbox" name="accordion-checkbox" hidden="">
1831  <label class="accordion-header c-hand" for="accordion-strongbuzzfeedstrongsurveillanceplanes">
1832      <i class="icon icon-arrow-right mr-1"></i>
1833      <strong>BuzzFeed:</strong>  Surveillance planes
1834  </label>
1835  <div class="accordion-body">
1836      <ol class="menu menu-nav">
1837      
1838      <li class="menu-item">
1839          
1840  <a href="/buzzfeed-spy-planes/">        
1841      Summary
1842  </a>
1843  <div class="toc"></div>
1844
1845
1846
1847      </li>
1848      
1849      <li class="menu-item">
1850          
1851  <a href="/buzzfeed-spy-planes/feature-engineering-buzzfeed-spy-planes/">        
1852      Feature engineering - BuzzFeed spy planes
1853  </a>
1854  <div class="toc"></div>
1855
1856
1857
1858      </li>
1859      
1860      <li class="menu-item">
1861          
1862  <a href="/buzzfeed-spy-planes/drawing-flight-paths-on-maps-with-cartopy/">        
1863      Drawing flight paths on maps with cartopy
1864  </a>
1865  <div class="toc"></div>
1866
1867
1868
1869      </li>
1870      
1871      <li class="menu-item">
1872          
1873  <a href="/buzzfeed-spy-planes/buzzfeed-surveillance-planes-random-forests/">        
1874      Finding surveillance planes using random forests
1875  </a>
1876  <div class="toc"></div>
1877
1878
1879
1880      </li>
1881      
1882    </ol>
1883  </div>
1884
1885              </li>
1886            
1887              <li class="menu-item">
1888                
1889
1890
1891  <input id="accordion-strongrevealstrongmortgagelendingbias" type="checkbox" name="accordion-checkbox" hidden="">
1892  <label class="accordion-header c-hand" for="accordion-strongrevealstrongmortgagelendingbias">
1893      <i class="icon icon-arrow-right mr-1"></i>
1894      <strong>Reveal:</strong>  Mortgage lending bias
1895  </label>
1896  <div class="accordion-body">
1897      <ol class="menu menu-nav">
1898      
1899      <li class="menu-item">
1900          
1901  <a href="/reveal-mortgages/">        
1902      Summary
1903  </a>
1904  <div class="toc"></div>
1905
1906
1907
1908      </li>
1909      
1910      <li class="menu-item">
1911          
1912  <a href="/reveal-mortgages/reveal-mortgage-analysis-cleaning-and-combining-data/">        
1913      Cleaning and combining data for the Reveal Mortgage Analysis
1914  </a>
1915  <div class="toc"></div>
1916
1917
1918
1919      </li>
1920      
1921      <li class="menu-item">
1922          
1923  <a href="/reveal-mortgages/reveal-mortgage-analysis-wild-formulas-in-statsmodels-using-patsy-short-version/">        
1924      Wild formulas in statsmodels using Patsy (short version)
1925  </a>
1926  <div class="toc"></div>
1927
1928
1929
1930      </li>
1931      
1932      <li class="menu-item">
1933          
1934  <a href="/reveal-mortgages/reveal-mortgage-analysis-logistic-regression-using-statsmodels-formulas/">        
1935      Reveal Mortgage Analysis - Logistic Regression using statsmodels formulas
1936  </a>
1937  <div class="toc"></div>
1938
1939
1940
1941      </li>
1942      
1943      <li class="menu-item">
1944          
1945  <a href="/reveal-mortgages/reveal-mortgage-analysis-logistic-regression/">        
1946      Reveal Mortgage Analysis - Logistic Regression
1947  </a>
1948  <div class="toc"></div>
1949
1950
1951
1952      </li>
1953      
1954    </ol>
1955  </div>
1956
1957              </li>
1958            
1959              <li class="menu-item">
1960                
1961
1962
1963  <input id="accordion-strongapmreportsstrongjuryselectionbias" type="checkbox" name="accordion-checkbox" hidden="">
1964  <label class="accordion-header c-hand" for="accordion-strongapmreportsstrongjuryselectionbias">
1965      <i class="icon icon-arrow-right mr-1"></i>
1966      <strong>APM Reports:</strong>  Jury selection bias
1967  </label>
1968  <div class="accordion-body">
1969      <ol class="menu menu-nav">
1970      
1971      <li class="menu-item">
1972          
1973  <a href="/apm-reports-jury-bias/">        
1974      Summary
1975  </a>
1976  <div class="toc"></div>
1977
1978
1979
1980      </li>
1981      
1982      <li class="menu-item">
1983          
1984  <a href="/apm-reports-jury-bias/in-the-dark-combining-datasets-and-cleaning-the-data/">        
1985      Combining and cleaning the initial dataset
1986  </a>
1987  <div class="toc"></div>
1988
1989
1990
1991      </li>
1992      
1993      <li class="menu-item">
1994          
1995  <a href="/apm-reports-jury-bias/in-the-dark-feature-selection-with-p-values/">        
1996      Picking what matters and what doesn't in a regression
1997  </a>
1998  <div class="toc"></div>
1999
2000
2001
2002      </li>
2003      
2004      <li class="menu-item">
2005          
2006  <a href="/apm-reports-jury-bias/in-the-dark-jury-selection-regression-walkthrough/">        
2007      Analyzing data using statsmodels formulas
2008  </a>
2009  <div class="toc"></div>
2010
2011
2012
2013      </li>
2014      
2015      <li class="menu-item">
2016          
2017  <a href="/apm-reports-jury-bias/in-the-dark-alternative-formula-methods/">        
2018      Alternative techniques with statsmodels formulas
2019  </a>
2020  <div class="toc"></div>
2021
2022
2023
2024      </li>
2025      
2026    </ol>
2027  </div>
2028
2029              </li>
2030            
2031              <li class="menu-item">
2032                
2033
2034
2035  <input id="accordion-strongreutersstrongasylumdenials" type="checkbox" name="accordion-checkbox" hidden="">
2036  <label class="accordion-header c-hand" for="accordion-strongreutersstrongasylumdenials">
2037      <i class="icon icon-arrow-right mr-1"></i>
2038      <strong>Reuters:</strong>  Asylum denials
2039  </label>
2040  <div class="accordion-body">
2041      <ol class="menu menu-nav">
2042      
2043      <li class="menu-item">
2044          
2045  <a href="/reuters-asylum/">        
2046      Summary
2047  </a>
2048  <div class="toc"></div>
2049
2050
2051
2052      </li>
2053      
2054      <li class="menu-item">
2055          
2056  <a href="/reuters-asylum/cleaning-the-eoir-immigration-court-dataset/">        
2057      Preparing the EOIR immigration court data for analysis
2058  </a>
2059  <div class="toc"></div>
2060
2061
2062
2063      </li>
2064      
2065      <li class="menu-item">
2066          
2067  <a href="/reuters-asylum/using-regression-to-analyze-asylum-cases/">        
2068      How nationality and judges affect your chance of asylum in immigration court
2069  </a>
2070  <div class="toc"></div>
2071
2072
2073
2074      </li>
2075      
2076    </ol>
2077  </div>
2078
2079              </li>
2080            
2081              <li class="menu-item">
2082                
2083  <a href="/propublica-pardons/">        
2084      <strong>ProPublica:</strong>  Presidential pardons
2085  </a>
2086  <div class="toc"></div>
2087
2088
2089
2090              </li>
2091            
2092              <li class="menu-item">
2093                
2094
2095
2096  <input id="accordion-strongpropublicastrongcriminalsentencing" t
2096ype="checkbox" name="accordion-checkbox" hidden="">
2097  <label class="accordion-header c-hand" for="accordion-strongpropublicastrongcriminalsentencing">
2098      <i class="icon icon-arrow-right mr-1"></i>
2099      <strong>ProPublica:</strong>  Criminal sentencing
2100  </label>
2101  <div class="accordion-body">
2102      <ol class="menu menu-nav">
2103      
2104      <li class="menu-item">
2105          
2106  <a href="/propublica-criminal-sentencing/">        
2107      Summary
2108  </a>
2109  <div class="toc"></div>
2110
2111
2112
2113      </li>
2114      
2115      <li class="menu-item">
2116          
2117  <a href="/propublica-criminal-sentencing/week-5-1-machine-bias-class/">        
2118      Breaking down machine bias
2119  </a>
2120  <div class="toc"></div>
2121
2122
2123
2124      </li>
2125      
2126    </ol>
2127  </div>
2128
2129              </li>
2130            
2131              <li class="menu-item">
2132                
2133  <a href="/foia-predictor/">        
2134      <strong>data.world:</strong>  The FOIA Predictor
2135  </a>
2136  <div class="toc"></div>
2137
2138
2139
2140              </li>
2141            
2142          </ol>
2143        
2144    </div>
2145  </div>
2146</div>
2147      </div>
2148    </div>
2149  </div>
2150    
2150<script src="/js/tocbot.js"></script>
2150
2151
2152  
2152<script>
2153    // Add the div to hold the table of contents
2154    try {
2155      let toc = document.createElement("div")
2156      toc.setAttribute('class', 'js-toc')
2157      document.querySelector(".reading-options").parentNode.appendChild(toc)
2158    } catch (err) {
2159
2160    }
2161
2162    let slugSelector = "/search/"
2163    
2164      let contentSelector = '.content'
2165    
2166  </script>
2166
2167
2168  
2168<script src="/js/main.js?v=1edd6b72f7227d977df2bf125e3b6e55"></script>
2168
2169
2170</body>
2171
2172</html>

Line numbers count LF bytes from the start of the resource, as the search results do. Vendor segments are library code the classifier recognised; they are stored but not indexed. Bytes are shown as Latin1 characters, one per byte.