[{"data":1,"prerenderedAt":933},["ShallowReactive",2],{"content-query-rXLWF2J44w":3},{"_path":4,"_dir":5,"_draft":6,"_partial":6,"_locale":7,"title":8,"description":7,"tags":9,"body":10,"_type":927,"_id":928,"_source":929,"_file":930,"_stem":931,"_extension":932},"/tutorials/data-ocelot","tutorials",false,"","Corpus data on Ocelot","bash",{"type":11,"children":12,"toc":925},"root",[13,75,79,166,169,668,671,919],{"type":14,"tag":15,"props":16,"children":17},"element","ul",{},[18,25,39,64],{"type":14,"tag":19,"props":20,"children":21},"li",{},[22],{"type":23,"value":24},"text","Written by Mauricio Gruppi on Jan 26, 2024",{"type":14,"tag":19,"props":26,"children":27},{},[28,30,37],{"type":23,"value":29},"Here you will find information about the corpus data in ",{"type":14,"tag":31,"props":32,"children":34},"code",{"className":33},[],[35],{"type":23,"value":36},"Ocelot",{"type":23,"value":38}," and how to access it using the shell.",{"type":14,"tag":19,"props":40,"children":41},{},[42,48,50,56,58],{"type":14,"tag":43,"props":44,"children":45},"strong",{},[46],{"type":23,"value":47},"Note",{"type":23,"value":49},": Once you sign in through ",{"type":14,"tag":31,"props":51,"children":53},{"className":52},[],[54],{"type":23,"value":55},"ssh",{"type":23,"value":57},", you be in your home folder, the absolute path for which is ",{"type":14,"tag":31,"props":59,"children":61},{"className":60},[],[62],{"type":23,"value":63},"/home/\u003Cyour_username>/",{"type":14,"tag":19,"props":65,"children":66},{},[67,69],{"type":23,"value":68},"The corpus data resides in ",{"type":14,"tag":31,"props":70,"children":72},{"className":71},[],[73],{"type":23,"value":74},"/data/corpora",{"type":14,"tag":76,"props":77,"children":78},"hr",{},[],{"type":14,"tag":15,"props":80,"children":81},{},[82,95,154],{"type":14,"tag":19,"props":83,"children":84},{},[85,87,93],{"type":23,"value":86},"Run ",{"type":14,"tag":31,"props":88,"children":90},{"className":89},[],[91],{"type":23,"value":92},"cd /data/corpora",{"type":23,"value":94}," to change the working directory to the data folder.",{"type":14,"tag":19,"props":96,"children":97},{},[98,100,105,107],{"type":23,"value":99},"E.g.: changing the working directory to ",{"type":14,"tag":31,"props":101,"children":103},{"className":102},[],[104],{"type":23,"value":74},{"type":23,"value":106},":\n",{"type":14,"tag":108,"props":109,"children":112},"pre",{"className":110,"code":111,"language":9,"meta":7,"style":7},"language-bash shiki shiki-themes github-light monokai monokai github-light monokai","mgouveag@ocelot:~$ cd /data/corpora \nmgouveag@ocelot:/data/corpora$ \n",[113],{"type":14,"tag":31,"props":114,"children":115},{"__ignoreMap":7},[116,145],{"type":14,"tag":117,"props":118,"children":121},"span",{"class":119,"line":120},"line",1,[122,128,134,139],{"type":14,"tag":117,"props":123,"children":125},{"style":124},"--shiki-default:#6F42C1;--shiki-dark-mode:#A6E22E;--shiki-sky-dark-mode:#A6E22E;--shiki-light-mode:#6F42C1;--shiki-blue-mode:#A6E22E",[126],{"type":23,"value":127},"mgouveag@ocelot:~$",{"type":14,"tag":117,"props":129,"children":131},{"style":130},"--shiki-default:#032F62;--shiki-dark-mode:#E6DB74;--shiki-sky-dark-mode:#E6DB74;--shiki-light-mode:#032F62;--shiki-blue-mode:#E6DB74",[132],{"type":23,"value":133}," cd",{"type":14,"tag":117,"props":135,"children":136},{"style":130},[137],{"type":23,"value":138}," /data/corpora",{"type":14,"tag":117,"props":140,"children":142},{"style":141},"--shiki-default:#24292E;--shiki-dark-mode:#F8F8F2;--shiki-sky-dark-mode:#F8F8F2;--shiki-light-mode:#24292E;--shiki-blue-mode:#F8F8F2",[143],{"type":23,"value":144}," \n",{"type":14,"tag":117,"props":146,"children":148},{"class":119,"line":147},2,[149],{"type":14,"tag":117,"props":150,"children":151},{"style":124},[152],{"type":23,"value":153},"mgouveag@ocelot:/data/corpora$\n",{"type":14,"tag":19,"props":155,"children":156},{},[157,159,164],{"type":23,"value":158},"Your terminal is now pointed to the directory ",{"type":14,"tag":31,"props":160,"children":162},{"className":161},[],[163],{"type":23,"value":74},{"type":23,"value":165}," - you can think of it as \"opening\" the folder using a graphical interface",{"type":14,"tag":76,"props":167,"children":168},{},[],{"type":14,"tag":15,"props":170,"children":171},{},[172,573,578,622,627,640,653,658,663],{"type":14,"tag":19,"props":173,"children":174},{},[175,177,183,185],{"type":23,"value":176},"To list all the files and folders in the current directory, run ",{"type":14,"tag":31,"props":178,"children":180},{"className":179},[],[181],{"type":23,"value":182},"ls -lh",{"type":23,"value":184},". E.g.:\n",{"type":14,"tag":108,"props":186,"children":188},{"className":110,"code":187,"language":9,"meta":7,"style":7},"mgouveag@ocelot:/data/corpora$ ls -lh\ntotal 32K\ndrwxrwxr-x  4 mgouveag data 4.0K Jan 24 19:34 coca\ndrwxrwxr-x  3 mgouveag data 4.0K Jan 24 19:28 coha\ndrwxrwxr-x  2 mgouveag data 4.0K Jan 24 19:27 compressed\ndrwxrwxr-x 11 mgouveag data 4.0K Jan 25 10:59 congress_text\ndrwxr-xr-x  2 mgouveag data 4.0K Jan 24 12:55 english-us-uk\ndrwxrwxr-x  3 mgouveag data 4.0K Jan 24 18:45 gutenberg\ndrwxr-xr-x  2 mgouveag data 4.0K Jan 24 13:00 nela\ndrwxr-xr-x  6 mgouveag data 4.0K Jan 24 12:53 semeval-2020-task1\n",[189],{"type":14,"tag":31,"props":190,"children":191},{"__ignoreMap":7},[192,211,224,273,316,359,403,446,488,530],{"type":14,"tag":117,"props":193,"children":194},{"class":119,"line":120},[195,200,205],{"type":14,"tag":117,"props":196,"children":197},{"style":124},[198],{"type":23,"value":199},"mgouveag@ocelot:/data/corpora$",{"type":14,"tag":117,"props":201,"children":202},{"style":130},[203],{"type":23,"value":204}," ls",{"type":14,"tag":117,"props":206,"children":208},{"style":207},"--shiki-default:#005CC5;--shiki-dark-mode:#AE81FF;--shiki-sky-dark-mode:#AE81FF;--shiki-light-mode:#005CC5;--shiki-blue-mode:#AE81FF",[209],{"type":23,"value":210}," -lh\n",{"type":14,"tag":117,"props":212,"children":213},{"class":119,"line":147},[214,219],{"type":14,"tag":117,"props":215,"children":216},{"style":124},[217],{"type":23,"value":218},"total",{"type":14,"tag":117,"props":220,"children":221},{"style":130},[222],{"type":23,"value":223}," 32K\n",{"type":14,"tag":117,"props":225,"children":227},{"class":119,"line":226},3,[228,233,238,243,248,253,258,263,268],{"type":14,"tag":117,"props":229,"children":230},{"style":124},[231],{"type":23,"value":232},"drwxrwxr-x",{"type":14,"tag":117,"props":234,"children":235},{"style":207},[236],{"type":23,"value":237},"  4",{"type":14,"tag":117,"props":239,"children":240},{"style":130},[241],{"type":23,"value":242}," mgouveag",{"type":14,"tag":117,"props":244,"children":245},{"style":130},[246],{"type":23,"value":247}," data",{"type":14,"tag":117,"props":249,"children":250},{"style":130},[251],{"type":23,"value":252}," 4.0K",{"type":14,"tag":117,"props":254,"children":255},{"style":130},[256],{"type":23,"value":257}," Jan",{"type":14,"tag":117,"props":259,"children":260},{"style":207},[261],{"type":23,"value":262}," 24",{"type":14,"tag":117,"props":264,"children":265},{"style":130},[266],{"type":23,"value":267}," 19:34",{"type":14,"tag":117,"props":269,"children":270},{"style":130},[271],{"type":23,"value":272}," coca\n",{"type":14,"tag":117,"props":274,"children":276},{"class":119,"line":275},4,[277,281,286,290,294,298,302,306,311],{"type":14,"tag":117,"props":278,"children":279},{"style":124},[280],{"type":23,"value":232},{"type":14,"tag":117,"props":282,"children":283},{"style":207},[284],{"type":23,"value":285},"  3",{"type":14,"tag":117,"props":287,"children":288},{"style":130},[289],{"type":23,"value":242},{"type":14,"tag":117,"props":291,"children":292},{"style":130},[293],{"type":23,"value":247},{"type":14,"tag":117,"props":295,"children":296},{"style":130},[297],{"type":23,"value":252},{"type":14,"tag":117,"props":299,"children":300},{"style":130},[301],{"type":23,"value":257},{"type":14,"tag":117,"props":303,"children":304},{"style":207},[305],{"type":23,"value":262},{"type":14,"tag":117,"props":307,"children":308},{"style":130},[309],{"type":23,"value":310}," 19:28",{"type":14,"tag":117,"props":312,"children":313},{"style":130},[314],{"type":23,"value":315}," coha\n",{"type":14,"tag":117,"props":317,"children":319},{"class":119,"line":318},5,[320,324,329,333,337,341,345,349,354],{"type":14,"tag":117,"props":321,"children":322},{"style":124},[323],{"type":23,"value":232},{"type":14,"tag":117,"props":325,"children":326},{"style":207},[327],{"type":23,"value":328},"  2",{"type":14,"tag":117,"props":330,"children":331},{"style":130},[332],{"type":23,"value":242},{"type":14,"tag":117,"props":334,"children":335},{"style":130},[336],{"type":23,"value":247},{"type":14,"tag":117,"props":338,"children":339},{"style":130},[340],{"type":23,"value":252},{"type":14,"tag":117,"props":342,"children":343},{"style":130},[344],{"type":23,"value":257},{"type":14,"tag":117,"props":346,"children":347},{"style":207},[348],{"type":23,"value":262},{"type":14,"tag":117,"props":350,"children":351},{"style":130},[352],{"type":23,"value":353}," 19:27",{"type":14,"tag":117,"props":355,"children":356},{"style":130},[357],{"type":23,"value":358}," compressed\n",{"type":14,"tag":117,"props":360,"children":362},{"class":119,"line":361},6,[363,367,372,376,380,384,388,393,398],{"type":14,"tag":117,"props":364,"children":365},{"style":124},[366],{"type":23,"value":232},{"type":14,"tag":117,"props":368,"children":369},{"style":207},[370],{"type":23,"value":371}," 11",{"type":14,"tag":117,"props":373,"children":374},{"style":130},[375],{"type":23,"value":242},{"type":14,"tag":117,"props":377,"children":378},{"style":130},[379],{"type":23,"value":247},{"type":14,"tag":117,"props":381,"children":382},{"style":130},[383],{"type":23,"value":252},{"type":14,"tag":117,"props":385,"children":386},{"style":130},[387],{"type":23,"value":257},{"type":14,"tag":117,"props":389,"children":390},{"style":207},[391],{"type":23,"value":392}," 25",{"type":14,"tag":117,"props":394,"children":395},{"style":130},[396],{"type":23,"value":397}," 10:59",{"type":14,"tag":117,"props":399,"children":400},{"style":130},[401],{"type":23,"value":402}," congress_text\n",{"type":14,"tag":117,"props":404,"children":406},{"class":119,"line":405},7,[407,412,416,420,424,428,432,436,441],{"type":14,"tag":117,"props":408,"children":409},{"style":124},[410],{"type":23,"value":411},"drwxr-xr-x",{"type":14,"tag":117,"props":413,"children":414},{"style":207},[415],{"type":23,"value":328},{"type":14,"tag":117,"props":417,"children":418},{"style":130},[419],{"type":23,"value":242},{"type":14,"tag":117,"props":421,"children":422},{"style":130},[423],{"type":23,"value":247},{"type":14,"tag":117,"props":425,"children":426},{"style":130},[427],{"type":23,"value":252},{"type":14,"tag":117,"props":429,"children":430},{"style":130},[431],{"type":23,"value":257},{"type":14,"tag":117,"props":433,"children":434},{"style":207},[435],{"type":23,"value":262},{"type":14,"tag":117,"props":437,"children":438},{"style":130},[439],{"type":23,"value":440}," 12:55",{"type":14,"tag":117,"props":442,"children":443},{"style":130},[444],{"type":23,"value":445}," english-us-uk\n",{"type":14,"tag":117,"props":447,"children":449},{"class":119,"line":448},8,[450,454,458,462,466,470,474,478,483],{"type":14,"tag":117,"props":451,"children":452},{"style":124},[453],{"type":23,"value":232},{"type":14,"tag":117,"props":455,"children":456},{"style":207},[457],{"type":23,"value":285},{"type":14,"tag":117,"props":459,"children":460},{"style":130},[461],{"type":23,"value":242},{"type":14,"tag":117,"props":463,"children":464},{"style":130},[465],{"type":23,"value":247},{"type":14,"tag":117,"props":467,"children":468},{"style":130},[469],{"type":23,"value":252},{"type":14,"tag":117,"props":471,"children":472},{"style":130},[473],{"type":23,"value":257},{"type":14,"tag":117,"props":475,"children":476},{"style":207},[477],{"type":23,"value":262},{"type":14,"tag":117,"props":479,"children":480},{"style":130},[481],{"type":23,"value":482}," 18:45",{"type":14,"tag":117,"props":484,"children":485},{"style":130},[486],{"type":23,"value":487}," gutenberg\n",{"type":14,"tag":117,"props":489,"children":491},{"class":119,"line":490},9,[492,496,500,504,508,512,516,520,525],{"type":14,"tag":117,"props":493,"children":494},{"style":124},[495],{"type":23,"value":411},{"type":14,"tag":117,"props":497,"children":498},{"style":207},[499],{"type":23,"value":328},{"type":14,"tag":117,"props":501,"children":502},{"style":130},[503],{"type":23,"value":242},{"type":14,"tag":117,"props":505,"children":506},{"style":130},[507],{"type":23,"value":247},{"type":14,"tag":117,"props":509,"children":510},{"style":130},[511],{"type":23,"value":252},{"type":14,"tag":117,"props":513,"children":514},{"style":130},[515],{"type":23,"value":257},{"type":14,"tag":117,"props":517,"children":518},{"style":207},[519],{"type":23,"value":262},{"type":14,"tag":117,"props":521,"children":522},{"style":130},[523],{"type":23,"value":524}," 13:00",{"type":14,"tag":117,"props":526,"children":527},{"style":130},[528],{"type":23,"value":529}," nela\n",{"type":14,"tag":117,"props":531,"children":533},{"class":119,"line":532},10,[534,538,543,547,551,555,559,563,568],{"type":14,"tag":117,"props":535,"children":536},{"style":124},[537],{"type":23,"value":411},{"type":14,"tag":117,"props":539,"children":540},{"style":207},[541],{"type":23,"value":542},"  6",{"type":14,"tag":117,"props":544,"children":545},{"style":130},[546],{"type":23,"value":242},{"type":14,"tag":117,"props":548,"children":549},{"style":130},[550],{"type":23,"value":247},{"type":14,"tag":117,"props":552,"children":553},{"style":130},[554],{"type":23,"value":252},{"type":14,"tag":117,"props":556,"children":557},{"style":130},[558],{"type":23,"value":257},{"type":14,"tag":117,"props":560,"children":561},{"style":207},[562],{"type":23,"value":262},{"type":14,"tag":117,"props":564,"children":565},{"style":130},[566],{"type":23,"value":567}," 12:53",{"type":14,"tag":117,"props":569,"children":570},{"style":130},[571],{"type":23,"value":572}," semeval-2020-task1\n",{"type":14,"tag":19,"props":574,"children":575},{},[576],{"type":23,"value":577},"Here is a brief explanation of what this list means:",{"type":14,"tag":19,"props":579,"children":580},{},[581,583,588,590,596,598,604,606,612,614,620],{"type":23,"value":582},"The leftmost sequence of characters, such as ",{"type":14,"tag":31,"props":584,"children":586},{"className":585},[],[587],{"type":23,"value":232},{"type":23,"value":589}," indicates permissions of the respective file. The leading ",{"type":14,"tag":31,"props":591,"children":593},{"className":592},[],[594],{"type":23,"value":595},"d",{"type":23,"value":597}," indicates the item is a directory, ",{"type":14,"tag":31,"props":599,"children":601},{"className":600},[],[602],{"type":23,"value":603},"r",{"type":23,"value":605}," ,",{"type":14,"tag":31,"props":607,"children":609},{"className":608},[],[610],{"type":23,"value":611},"w,",{"type":23,"value":613}," and ",{"type":14,"tag":31,"props":615,"children":617},{"className":616},[],[618],{"type":23,"value":619},"x",{"type":23,"value":621}," indicate read, write and execute permissions for the owner, the group and all users in the system (you do not need to worry about these right now).",{"type":14,"tag":19,"props":623,"children":624},{},[625],{"type":23,"value":626},"The second number is the number of hard links to the file (not relevant here)",{"type":14,"tag":19,"props":628,"children":629},{},[630,632,638],{"type":23,"value":631},"The third column is the owner of the file. Here, it is myself (",{"type":14,"tag":31,"props":633,"children":635},{"className":634},[],[636],{"type":23,"value":637},"mgouveag",{"type":23,"value":639},").",{"type":14,"tag":19,"props":641,"children":642},{},[643,645,651],{"type":23,"value":644},"The fourth column is the group of the folder. We are all part of group ",{"type":14,"tag":31,"props":646,"children":648},{"className":647},[],[649],{"type":23,"value":650},"data",{"type":23,"value":652},", which allows us to access these files.",{"type":14,"tag":19,"props":654,"children":655},{},[656],{"type":23,"value":657},"The fifth column is the size of the file (folders are always 4KB in Unix).",{"type":14,"tag":19,"props":659,"children":660},{},[661],{"type":23,"value":662},"The sixth column is the date and time of creation.",{"type":14,"tag":19,"props":664,"children":665},{},[666],{"type":23,"value":667},"The seventh and final column is the name of the file. Note that folders are also considered files.",{"type":14,"tag":76,"props":669,"children":670},{},[],{"type":14,"tag":15,"props":672,"children":673},{},[674,679,753,781,803,825],{"type":14,"tag":19,"props":675,"children":676},{},[677],{"type":23,"value":678},"In this section, I will briefly explain each of the corpora.",{"type":14,"tag":19,"props":680,"children":681},{},[682,689],{"type":14,"tag":683,"props":684,"children":686},"h3",{"id":685},"coca-corpus-of-contemporary-american-english",[687],{"type":23,"value":688},"COCA - Corpus of Contemporary American English",{"type":14,"tag":15,"props":690,"children":691},{},[692,697,710,731],{"type":14,"tag":19,"props":693,"children":694},{},[695],{"type":23,"value":696},"This corpus contains texts from the year 1990 through 2012 across different categories: academic, spoken, fiction, magazine, and news.",{"type":14,"tag":19,"props":698,"children":699},{},[700,702,708],{"type":23,"value":701},"The folder ",{"type":14,"tag":31,"props":703,"children":705},{"className":704},[],[706],{"type":23,"value":707},"coca/text_files",{"type":23,"value":709}," holds all such text files",{"type":14,"tag":19,"props":711,"children":712},{},[713,715,721,723,729],{"type":23,"value":714},"To peek a file you can use the ",{"type":14,"tag":31,"props":716,"children":718},{"className":717},[],[719],{"type":23,"value":720},"head",{"type":23,"value":722}," command. For instance, the following will print the first few lines of file ",{"type":14,"tag":31,"props":724,"children":726},{"className":725},[],[727],{"type":23,"value":728},"w_acad_2010.txt",{"type":23,"value":730},":",{"type":14,"tag":19,"props":732,"children":733},{},[734],{"type":14,"tag":108,"props":735,"children":737},{"className":110,"code":736,"language":9,"meta":7,"style":7},"head coca/text_files/w_acad_2010.txt\n",[738],{"type":14,"tag":31,"props":739,"children":740},{"__ignoreMap":7},[741],{"type":14,"tag":117,"props":742,"children":743},{"class":119,"line":120},[744,748],{"type":14,"tag":117,"props":745,"children":746},{"style":124},[747],{"type":23,"value":720},{"type":14,"tag":117,"props":749,"children":750},{"style":130},[751],{"type":23,"value":752}," coca/text_files/w_acad_2010.txt\n",{"type":14,"tag":19,"props":754,"children":755},{},[756,762],{"type":14,"tag":683,"props":757,"children":759},{"id":758},"coha-corpus-of-historical-american-english",[760],{"type":23,"value":761},"COHA - Corpus of Historical American English",{"type":14,"tag":15,"props":763,"children":764},{},[765,770],{"type":14,"tag":19,"props":766,"children":767},{},[768],{"type":23,"value":769},"Similar to COCA, except that it includes data from a longer period (from 1820-2010).",{"type":14,"tag":19,"props":771,"children":772},{},[773,775],{"type":23,"value":774},"Files are in ",{"type":14,"tag":31,"props":776,"children":778},{"className":777},[],[779],{"type":23,"value":780},"coha/text_files",{"type":14,"tag":19,"props":782,"children":783},{},[784,790],{"type":14,"tag":683,"props":785,"children":787},{"id":786},"nela-news-landscape",[788],{"type":23,"value":789},"NELA - News Landscape",{"type":14,"tag":15,"props":791,"children":792},{},[793,798],{"type":14,"tag":19,"props":794,"children":795},{},[796],{"type":23,"value":797},"A corpus of contemporary news, containing millions of news articles from hundreds of news outlets from years 2018-2023.",{"type":14,"tag":19,"props":799,"children":800},{},[801],{"type":23,"value":802},"This corpus is in a database, not plain text files",{"type":14,"tag":19,"props":804,"children":805},{},[806,812],{"type":14,"tag":683,"props":807,"children":809},{"id":808},"congressional-record-congress_text",[810],{"type":23,"value":811},"Congressional Record (congress_text)",{"type":14,"tag":15,"props":813,"children":814},{},[815,820],{"type":14,"tag":19,"props":816,"children":817},{},[818],{"type":23,"value":819},"Transcripts of the congressional speeches from the 43rd through the 114th US congress.",{"type":14,"tag":19,"props":821,"children":822},{},[823],{"type":23,"value":824},"Years 1873 - 2017",{"type":14,"tag":19,"props":826,"children":827},{},[828,834],{"type":14,"tag":683,"props":829,"children":831},{"id":830},"project-gutenberg",[832],{"type":23,"value":833},"Project Gutenberg",{"type":14,"tag":15,"props":835,"children":836},{},[837,842,853,858,863,908],{"type":14,"tag":19,"props":838,"children":839},{},[840],{"type":23,"value":841},"Over 71,000 books ranging including fiction and non-fiction",{"type":14,"tag":19,"props":843,"children":844},{},[845,847],{"type":23,"value":846},"Data in: ",{"type":14,"tag":31,"props":848,"children":850},{"className":849},[],[851],{"type":23,"value":852},"gutenberg/data/raw/",{"type":14,"tag":19,"props":854,"children":855},{},[856],{"type":23,"value":857},"Metadata for each book is available",{"type":14,"tag":19,"props":859,"children":860},{},[861],{"type":23,"value":862},"E.g.: to take a peek into the first 100 lines of Lewis Carrol's Alice's Adventures in Wonderland:",{"type":14,"tag":19,"props":864,"children":865},{},[866,895],{"type":14,"tag":108,"props":867,"children":869},{"className":110,"code":868,"language":9,"meta":7,"style":7},"head -n 100 gutenberg/data/raw/PG11_raw.txt\n",[870],{"type":14,"tag":31,"props":871,"children":872},{"__ignoreMap":7},[873],{"type":14,"tag":117,"props":874,"children":875},{"class":119,"line":120},[876,880,885,890],{"type":14,"tag":117,"props":877,"children":878},{"style":124},[879],{"type":23,"value":720},{"type":14,"tag":117,"props":881,"children":882},{"style":207},[883],{"type":23,"value":884}," -n",{"type":14,"tag":117,"props":886,"children":887},{"style":207},[888],{"type":23,"value":889}," 100",{"type":14,"tag":117,"props":891,"children":892},{"style":130},[893],{"type":23,"value":894}," gutenberg/data/raw/PG11_raw.txt\n",{"type":14,"tag":15,"props":896,"children":897},{},[898],{"type":14,"tag":19,"props":899,"children":900},{},[901,903],{"type":23,"value":902},"Make sure your current directory is ",{"type":14,"tag":31,"props":904,"children":906},{"className":905},[],[907],{"type":23,"value":74},{"type":14,"tag":19,"props":909,"children":910},{},[911,913],{"type":23,"value":912},"The metadata about all the books is in ",{"type":14,"tag":31,"props":914,"children":916},{"className":915},[],[917],{"type":23,"value":918},"gutenberg/metadata/metadata.csv",{"type":14,"tag":920,"props":921,"children":922},"style",{},[923],{"type":23,"value":924},"html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark-mode .shiki span {color: var(--shiki-dark-mode);background: var(--shiki-dark-mode-bg);font-style: var(--shiki-dark-mode-font-style);font-weight: var(--shiki-dark-mode-font-weight);text-decoration: var(--shiki-dark-mode-text-decoration);}html.dark-mode .shiki span {color: var(--shiki-dark-mode);background: var(--shiki-dark-mode-bg);font-style: var(--shiki-dark-mode-font-style);font-weight: var(--shiki-dark-mode-font-weight);text-decoration: var(--shiki-dark-mode-text-decoration);}html .sky-dark-mode .shiki span {color: var(--shiki-sky-dark-mode);background: var(--shiki-sky-dark-mode-bg);font-style: var(--shiki-sky-dark-mode-font-style);font-weight: var(--shiki-sky-dark-mode-font-weight);text-decoration: var(--shiki-sky-dark-mode-text-decoration);}html.sky-dark-mode .shiki span {color: var(--shiki-sky-dark-mode);background: var(--shiki-sky-dark-mode-bg);font-style: var(--shiki-sky-dark-mode-font-style);font-weight: var(--shiki-sky-dark-mode-font-weight);text-decoration: var(--shiki-sky-dark-mode-text-decoration);}html .light-mode .shiki span {color: var(--shiki-light-mode);background: var(--shiki-light-mode-bg);font-style: var(--shiki-light-mode-font-style);font-weight: var(--shiki-light-mode-font-weight);text-decoration: var(--shiki-light-mode-text-decoration);}html.light-mode .shiki span {color: var(--shiki-light-mode);background: var(--shiki-light-mode-bg);font-style: var(--shiki-light-mode-font-style);font-weight: var(--shiki-light-mode-font-weight);text-decoration: var(--shiki-light-mode-text-decoration);}html .blue-mode .shiki span {color: var(--shiki-blue-mode);background: var(--shiki-blue-mode-bg);font-style: var(--shiki-blue-mode-font-style);font-weight: var(--shiki-blue-mode-font-weight);text-decoration: var(--shiki-blue-mode-text-decoration);}html.blue-mode .shiki span {color: var(--shiki-blue-mode);background: var(--shiki-blue-mode-bg);font-style: var(--shiki-blue-mode-font-style);font-weight: var(--shiki-blue-mode-font-weight);text-decoration: var(--shiki-blue-mode-text-decoration);}",{"title":7,"searchDepth":147,"depth":147,"links":926},[],"markdown","content:tutorials:data-ocelot.md","content","tutorials/data-ocelot.md","tutorials/data-ocelot","md",1793934184825]