{"id":54058,"date":"2019-12-17T00:00:00","date_gmt":"2019-12-16T21:00:00","guid":{"rendered":"https:\/\/prohoster.info\/blog\/blog_prohoster\/14-open-source-proektov-dlya-prokachki-data-science-masterstva-easy-normal-hard"},"modified":"2020-02-18T14:02:02","modified_gmt":"2020-02-18T11:02:02","slug":"14-open-source-proektov-dlya-prokachki-data-science-masterstva-easy-normal-hard","status":"publish","type":"post","link":"https:\/\/prohoster.info\/lv\/blog\/news\/14-open-source-proektov-dlya-prokachki-data-science-masterstva-easy-normal-hard","title":{"rendered":"14 open-source projekti datu zin\u0101tnes prasmju att\u012bst\u012b\u0161anai (viegli, norm\u0101li, gr\u016bti)","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"<p><i> Datu zin\u0101tne s\u0101kumam<\/i><\/p>\n<h3>1. Noska\u0146ojuma anal\u012bze (Teksta anal\u012bze, lai noteiktu noska\u0146ojumus)<\/h3>\n<p>\n<img decoding=\"async\" alt=\"14 open-source projekti datu zin\u0101tnes prasmju att\u012bst\u012b\u0161anai (viegli, norm\u0101li, gr\u016bti)\" src=\"\/wp-content\/uploads\/2019\/12\/1a3bd6118b09790564840e749909b9bb.jpg\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<br \/>\nApskatiet pilnu Datu zin\u0101tnes projekta realiz\u0101ciju, izmantojot avota kodu \u2014 <noindex><a rel=\"nofollow\" href=\"https:\/\/data-flair.training\/blogs\/data-science-r-sentiment-analysis-project\/\">Noska\u0146ojuma anal\u012bzes projekts R valod\u0101<\/a><\/noindex>.<\/p>\n<p>Sentiment Analysis \u2014 ir v\u0101rdu anal\u012bze, lai noteiktu noska\u0146ojumus un viedok\u013cus, kas var b\u016bt pozit\u012bvi vai negat\u012bvi. Tas ir klasifik\u0101cijas veids, kur\u0101 klases var b\u016bt bin\u0101ras (pozit\u012bvas un negat\u012bvas) vai daudzveid\u012bgas (priec\u012bgas, dusm\u012bgas, skumjas, nepat\u012bkamas ...). M\u0113s \u012bstenosim \u0161o Data Science projektu valod\u0101 R un izmantosim datu kopu no pakotnes \"janeaustenR\". M\u0113s izmantosim visp\u0101r\u0113j\u0101s lieto\u0161anas v\u0101rdn\u012bcas, piem\u0113ram, AFINN, bing un loughran, veiksim iek\u0161\u0113jo savienojumu, un beig\u0101s izveidosim v\u0101rdu m\u0101ko\u0146a att\u0113lu, lai par\u0101d\u012btu rezult\u0101tu.<\/p>\n<p><b>Valoda:<\/b> R<br \/>\n<b>Datu kopas \/ Pakotne:<\/b> janeaustenR<br \/>\n<noindex><a rel=\"nofollow\" name=\"habracut\"><\/a><\/noindex><\/p>\n<blockquote><p><noindex><a rel=\"nofollow\" href=\"https:\/\/www.edsd.ru\/\" title=\"EDISON Software - web-att\u012bst\u012bba\"><img decoding=\"async\" alt=\"14 open-source projekti datu zin\u0101tnes prasmju att\u012bst\u012b\u0161anai (viegli, norm\u0101li, gr\u016bti)\" src=\"\/wp-content\/uploads\/2019\/12\/ae4e0cd04c9fb71d127fb28c2c9bc91d.jpg\" style=\"display:block;margin: 0 auto;\" \/><\/a><\/noindex><br clear=\"right\"><br \/>\nRaksts tulkots ar EDISON Software atbalstu, kas <noindex><a rel=\"nofollow\" href=\"https:\/\/www.edsd.ru\/virtualnaya-primerochnaya\">izveido virtu\u0101las pielaiko\u0161anas telpas daudzu z\u012bmolu veikaliem<\/a><\/noindex>, k\u0101 ar\u012b <noindex><a rel=\"nofollow\" href=\"https:\/\/www.edsd.ru\/ru\/uslugi\/testirovanie_po\">test\u0113 programmat\u016bru<\/a><\/noindex>.<\/p><\/blockquote>\n<h3>2. Viltus zi\u0146u atkl\u0101\u0161ana (Fake News Detection)<\/h3>\n<p>\nIepaz\u012bstieties ar sav\u0101m prasm\u0113m, str\u0101d\u0101jot pie Datu zin\u0101tnes projekta s\u0101kumam \u2014 <noindex><a rel=\"nofollow\" href=\"https:\/\/data-flair.training\/blogs\/advanced-python-project-detecting-fake-news\/\">viltus zi\u0146u atkl\u0101\u0161ana ar Python<\/a><\/noindex>.<\/p>\n<p><img decoding=\"async\" alt=\"14 open-source projekti datu zin\u0101tnes prasmju att\u012bst\u012b\u0161anai (viegli, norm\u0101li, gr\u016bti)\" src=\"\/wp-content\/uploads\/2019\/12\/811e1a87f46944d5c153f2dafe04ff87.jpg\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<br \/>\nViltus zi\u0146as ir nepatiesa inform\u0101cija, kas tiek izplat\u012bta caur soci\u0101lajiem t\u012bkliem un citiem t\u012bmek\u013ca pla\u0161sazi\u0146as l\u012bdzek\u013ciem, lai sasniegtu politiskus m\u0113r\u0137us. \u0160aj\u0101 Datu zin\u0101tnes projekta idej\u0101 m\u0113s izmantosim Python, lai izveidotu modeli, kas prec\u012bzi noteiktu, vai zi\u0146a ir \u012bsta vai viltota. M\u0113s izveidosim TfidfVectorizer un izmantosim PassiveAggressiveClassifier, lai klasific\u0113tu zi\u0146as par \"\u012bst\u0101m\" un \"viltot\u0101m\". M\u0113s izmantosim datu kopu ar 7796 \u00d7 4 form\u0101tu un veiksim visu Jupyter Lab.<\/p>\n<p><b>Valoda:<\/b> Python<\/p>\n<p><b>Datu kopas \/ Pakotne:<\/b> news.csv<\/p>\n<h3>3. Parkinsona slim\u012bbas atkl\u0101\u0161ana (Detecting Parkinson\u2019s Disease)<\/h3>\n<p>\nVirzieties uz priek\u0161u, str\u0101d\u0101jot pie Datu zin\u0101tnes projekta idejas \u2014 <noindex><a rel=\"nofollow\" href=\"https:\/\/data-flair.training\/blogs\/python-machine-learning-project-detecting-parkinson-disease\/\">Parkinsona slim\u012bbas atkl\u0101\u0161ana ar XGBoost<\/a><\/noindex>.<\/p>\n<p><img decoding=\"async\" alt=\"14 open-source projekti datu zin\u0101tnes prasmju att\u012bst\u012b\u0161anai (viegli, norm\u0101li, gr\u016bti)\" src=\"\/wp-content\/uploads\/2019\/12\/a4a106cc5bab8370a483dab609213ff1.jpg\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<br \/>\nM\u0113s esam s\u0101ku\u0161i izmantot Datu zin\u0101tni, lai uzlabotu vesel\u012bbas apr\u016bpi un pakalpojumus \u2014 ja m\u0113s varam prognoz\u0113t slim\u012bbu agr\u012bn\u0101 stadij\u0101, mums b\u016bs daudz priek\u0161roc\u012bbu. T\u0101tad, \u0161aj\u0101 Datu zin\u0101tnes projekta idej\u0101 m\u0113s iem\u0101c\u012bsimies noteikt Parkinsona slim\u012bbu, izmantojot Python. T\u0101 ir neirode\u0123enerat\u012bva, progres\u0113jo\u0161a centr\u0101l\u0101s nervu sist\u0113mas slim\u012bba, kas ietekm\u0113 kust\u012bbu un izraisa tr\u012bci un st\u012bvumu. T\u0101 ietekm\u0113 dopam\u012bnu ra\u017eojo\u0161os neuronus smadzen\u0113s, un katru gadu t\u0101 skar vair\u0101k nek\u0101 1 miljonu cilv\u0113ku Indij\u0101.<\/p>\n<p><b>Valoda:<\/b> Python<\/p>\n<p><b>Datu kopas \/ Pakotne:<\/b> UCI ML Parkinsons datu kopums<\/p>\n<p><i>Vid\u0113j\u0101 gr\u016bt\u012bbas pak\u0101pe Datu zin\u0101tnes projektiem<\/i><\/p>\n<h3>4. Runas emociju atpaz\u012b\u0161ana (Speech Emotion Recognition)<\/h3>\n<p>\nIepaz\u012bstieties ar piln\u012bgu Data Science projekta piem\u0113ra realiz\u0101ciju \u2014 <noindex><a rel=\"nofollow\" href=\"https:\/\/data-flair.training\/blogs\/python-mini-project-speech-emotion-recognition\/\">balss atpaz\u012b\u0161ana, izmantojot Librosa<\/a><\/noindex>.<\/p>\n<p><img decoding=\"async\" alt=\"14 open-source projekti datu zin\u0101tnes prasmju att\u012bst\u012b\u0161anai (viegli, norm\u0101li, gr\u016bti)\" src=\"\/wp-content\/uploads\/2019\/12\/7be955cede12e04fbd1e6c5e7760be8f.jpg\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<br \/>\nTagad m\u0113s iem\u0101c\u012bsimies izmantot da\u017e\u0101das bibliot\u0113kas. \u0160is Data Science projekts izmanto librosa, lai veiktu balss atpaz\u012b\u0161anu. SER ir process, kas nosaka cilv\u0113ku emocijas un afekt\u012bv\u0101s st\u0101vok\u013cus p\u0113c balss. T\u0101 k\u0101 m\u0113s izmatojam toni un to\u0146u augstumu, lai izteiktu emocijas ar balsi, SER ir svar\u012bgs. Tom\u0113r, \u0146emot v\u0113r\u0101 emociju subjektivit\u0101ti, ska\u0146as anot\u0101cija ir sare\u017e\u0123\u012bta uzdevums. M\u0113s izmantosim funkcijas mfcc, chroma un mel un izmantosim RAVDESS datu kopu, lai atpaz\u012btu emocijas. M\u0113s izveidosim MLPC klasifikatoru \u0161im modelim.<\/p>\n<p><b>Valoda:<\/b> Python<\/p>\n<p><b>Datu kopas \/ Pakotne:<\/b> RAVDESS datu kopums<\/p>\n<h3>5. Dzimuma un vecuma noteik\u0161ana (Gender and Age Detection)<\/h3>\n<p>\nP\u0101rsteidziet darba dev\u0113jus ar jauno Data Science projektu \u2014 <noindex><a rel=\"nofollow\" href=\"https:\/\/data-flair.training\/blogs\/python-project-gender-age-detection\/\">dzimuma un vecuma noteik\u0161ana, izmantojot OpenCV<\/a><\/noindex>.<\/p>\n<p><img decoding=\"async\" alt=\"14 open-source projekti datu zin\u0101tnes prasmju att\u012bst\u012b\u0161anai (viegli, norm\u0101li, gr\u016bti)\" src=\"\/wp-content\/uploads\/2019\/12\/202a0a823626e5ccd9c4a28487328a40.jpg\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<br \/>\nTas ir interesants Data Science projekts ar Python. Izmantojot tikai vienu att\u0113lu, j\u016bs iem\u0101c\u012bsieties paredz\u0113t cilv\u0113ka dzimumu un vecumu. \u0160aj\u0101 projekt\u0101 j\u016bs iepaz\u012bstin\u0101sim ar datorredzi un t\u0101s principiem. M\u0113s uzb\u016bv\u0113sim <noindex><a rel=\"nofollow\" href=\"https:\/\/data-flair.training\/blogs\/convolutional-neural-networks-tutorial\/\">konvol\u016bciju neironu t\u012bklu<\/a><\/noindex> un izmantosim modeli, ko apm\u0101c\u012bjusi Tal Hassner un Gil Levi Adience datu kopai. Ce\u013cojuma laik\u0101 m\u0113s izmantosim da\u017eus .pb, .pbtxt, .prototxt un .caffemodel failus.<\/p>\n<p><b>Valoda:<\/b> Python<\/p>\n<p><b>Datu kopas \/ Pakotne:<\/b> Adience<\/p>\n<h3>6. Uber datu anal\u012bze (Uber Data Analysis)<\/h3>\n<p>\nPaskatieties pilnu Data Science projekta realiz\u0101ciju ar avota kodu \u2014 <noindex><a rel=\"nofollow\" href=\"https:\/\/data-flair.training\/blogs\/r-data-science-project-uber-data-analysis\/\">Uber datu anal\u012bze projekt\u0101 R<\/a><\/noindex>.<\/p>\n<p><img decoding=\"async\" alt=\"14 open-source projekti datu zin\u0101tnes prasmju att\u012bst\u012b\u0161anai (viegli, norm\u0101li, gr\u016bti)\" src=\"\/wp-content\/uploads\/2019\/12\/1547e93b846e76ef7a13c3126c61ccd7.jpg\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<br \/>\nTas ir datu vizualiz\u0101cijas projekts ar ggplot2, kur\u0101 m\u0113s izmantosim R un t\u0101 bibliot\u0113kas, analiz\u0113jot da\u017e\u0101dus parametrus. M\u0113s izmantosim Uber Pickups datu kopu \u0145ujork\u0101 un veidosim vizualiz\u0101cijas da\u017e\u0101diem gada laikiem. Tas noregul\u0113 laika ietekmi uz klientu braucieniem.<\/p>\n<p><b>Valoda:<\/b> R<\/p>\n<p><b>Datu kopas \/ Pakotne:<\/b> Uber Pickups in New York City datu kopums<\/p>\n<h3>7. Vad\u012bt\u0101ja miegain\u012bbas noteik\u0161ana (Driver Drowsiness detection)<\/h3>\n<p>\nUzlabojiet savas prasmes, str\u0101d\u0101jot pie Top Data Science projekta \u2014 <noindex><a rel=\"nofollow\" href=\"https:\/\/data-flair.training\/blogs\/python-project-driver-drowsiness-detection-system\/\">miegain\u012bbas noteik\u0161anas sist\u0113mas ar OpenCV &amp; Keras<\/a><\/noindex>.<\/p>\n<p><img decoding=\"async\" alt=\"14 open-source projekti datu zin\u0101tnes prasmju att\u012bst\u012b\u0161anai (viegli, norm\u0101li, gr\u016bti)\" src=\"\/wp-content\/uploads\/2019\/12\/3969a34093ea1c95dd6732f44bfecc90.jpg\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<br \/>\nMiegains brauciens ir \u0101rk\u0101rt\u012bgi b\u012bstams, un katru gadu notiek ap t\u016bksto\u0161 negad\u012bjumu, kad vad\u012bt\u0101ji aizmieg brauciena laik\u0101. \u0160aj\u0101 Python projekt\u0101 m\u0113s izveidosim sist\u0113mu, kas sp\u0113s noteikt miegainus vad\u012bt\u0101jus un br\u012bdin\u0101t vi\u0146us ar ska\u0146as sign\u0101lu.<\/p>\n<p>\u0160is projekts tiek \u012bstenots, izmantojot Keras un OpenCV. M\u0113s izmantosim OpenCV, lai atkl\u0101tu sejas un acis, bet, izmantojot Keras, m\u0113s klasific\u0113sim acu st\u0101vokli (Atv\u0113rta vai Aizv\u0113rta), izmantojot dzi\u013co neira t\u012bklu metodes.<\/p>\n<h3>8. \u010catbots<\/h3>\n<p>\nIzveidojiet \u010datbotu, izmantojot Python, un speriet soli uz priek\u0161u sav\u0101 karjer\u0101 \u2014 <noindex><a rel=\"nofollow\" href=\"https:\/\/data-flair.training\/blogs\/python-chatbot-project\/\">\u010catbots ar NLTK &amp; Keras<\/a><\/noindex>.<\/p>\n<p><img decoding=\"async\" alt=\"14 open-source projekti datu zin\u0101tnes prasmju att\u012bst\u012b\u0161anai (viegli, norm\u0101li, gr\u016bti)\" src=\"\/wp-content\/uploads\/2019\/12\/293f92b84332d5065d97e712ebb2e223.jpg\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<br \/>\n\u010catboti ir neat\u0146emama da\u013ca no biznesa. Daudziem uz\u0146\u0113mumiem ir j\u0101sniedz pakalpojumi saviem klientiem, un to apkalpo\u0161anai ir nepiecie\u0161ama liela darba sp\u0113ka, laika un p\u016b\u013cu izlietojums. \u010catboti var automatiz\u0113t liel\u0101ko da\u013cu mijiedarb\u012bbas ar klientiem, atbildot uz da\u017eiem bie\u017ei uzdotajiem jaut\u0101jumiem. Galvenok\u0101rt ir divi \u010datbotu veidi: specifisk\u0101 joma un atv\u0113rta joma. Specifisk\u0101s jomas \u010datbots bie\u017ei tiek izmantots konkr\u0113tas probl\u0113mas risin\u0101\u0161anai. T\u0101p\u0113c j\u016bs to j\u0101piel\u0101go efekt\u012bvai darb\u012bbai j\u016bsu jom\u0101. Atv\u0113rt\u0101s jomas \u010datbotiem var uzdot jebkurus jaut\u0101jumus, t\u0101p\u0113c to apm\u0101c\u012bbai ir nepiecie\u0161ami milz\u012bgi dati.<\/p>\n<p><b>Datu kopums:<\/b> Intents json fails<\/p>\n<p><b>Valoda:<\/b> Python<\/p>\n<p><i>Augstas klases datu zin\u0101tnes projekti<\/i><\/p>\n<h3>9. Att\u0113la aprakstu \u0123enerators<\/h3>\n<p>\nP\u0101rbaudiet pilnu projekta realiz\u0101ciju ar avota kodu \u2014 <noindex><a rel=\"nofollow\" href=\"https:\/\/data-flair.training\/blogs\/python-based-project-image-caption-generator-cnn\/\">Att\u0113la aprakstu \u0123enerators ar CNN &amp; LSTM<\/a><\/noindex>.<\/p>\n<p><img decoding=\"async\" alt=\"14 open-source projekti datu zin\u0101tnes prasmju att\u012bst\u012b\u0161anai (viegli, norm\u0101li, gr\u016bti)\" src=\"\/wp-content\/uploads\/2019\/12\/ab80a69d28f3acdfa9231a91911490ef.jpg\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<br \/>\nAprakst\u012bt, kas att\u0113l\u0101 ir, cilv\u0113kiem ir vienk\u0101r\u0161a, bet datoriem att\u0113ls ir tikai skait\u013cu kopums, kas att\u0113lo katra pikse\u013ca kr\u0101sas v\u0113rt\u012bbu. Tas ir gr\u016bts uzdevums datoriem. Saprast, kas atrodas att\u0113l\u0101, un p\u0113c tam izveidot aprakstu dabiskaj\u0101 valod\u0101 (piem\u0113ram, ang\u013cu valod\u0101) ir cits gr\u016bts uzdevums. \u0160is projekts izmanto dzi\u013c\u0101s m\u0101c\u012b\u0161an\u0101s metodes, kur m\u0113s realiz\u0113sim konvol\u016bcijas neira t\u012bklu (CNN) ar atk\u0101rtotu neira t\u012bklu (LSTM), lai izveidotu att\u0113la aprakstu \u0123eneratoru.<\/p>\n<p><b>Datu kopums:<\/b> Flickr 8K<\/p>\n<p><b>Valoda:<\/b> Python<\/p>\n<p><b>R\u0101mis:<\/b> Keras<\/p>\n<h3>10. Kred\u012btkartes kr\u0101p\u0161anas atkl\u0101\u0161ana<\/h3>\n<p>\nIzdariet visu iesp\u0113jamo, str\u0101d\u0101jot pie datu zin\u0101tnes projekta idejas \u2014 <noindex><a rel=\"nofollow\" href=\"https:\/\/data-flair.training\/blogs\/data-science-machine-learning-project-credit-card-fraud-detection\/\">kred\u012btkartes kr\u0101p\u0161anas atkl\u0101\u0161ana, izmantojot ma\u0161\u012bnm\u0101c\u012b\u0161anos<\/a><\/noindex>.<\/p>\n<p><img decoding=\"async\" alt=\"14 open-source projekti datu zin\u0101tnes prasmju att\u012bst\u012b\u0161anai (viegli, norm\u0101li, gr\u016bti)\" src=\"\/wp-content\/uploads\/2019\/12\/755bed019f95df54f7e75ba3da6a20ce.jpg\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<br \/>\nL\u012bdz \u0161im j\u016bs esat s\u0101ku\u0161i saprast metodes un koncepcijas. P\u0101rsl\u0113gsimies pie da\u017eiem augst\u0101kajiem datu zin\u0101tnes projektiem. \u0160aj\u0101 projekt\u0101 m\u0113s izmantosim R valodu ar t\u0101diem algoritmiem k\u0101 <noindex><a rel=\"nofollow\" href=\"https:\/\/data-flair.training\/blogs\/r-decision-trees\/\">l\u0113mumu koki<\/a><\/noindex>, lo\u0123istikas regresija, m\u0101ksl\u012bgie neironu t\u012bkli un gradienta palielin\u0101\u0161anas klasifikators. M\u0113s izmantosim dar\u012bjumu ar kart\u0113m datu kopu, lai klasific\u0113tu kred\u012btkar\u0161u dar\u012bjumus par kr\u0101pnieciskiem un \u012bstiem. M\u0113s izv\u0113l\u0113simies da\u017e\u0101dus mode\u013cus un izveidosim veiktsp\u0113jas l\u012bknes.<\/p>\n<p><b>Valoda:<\/b> R<\/p>\n<p><b>Datu kopas \/ Pakotne:<\/b> Kartes dar\u012bjumu datu kopas<\/p>\n<h3>11. Filmu ieteikumu sist\u0113ma<\/h3>\n<p>\nIepaz\u012bstieties ar lab\u0101k\u0101 Data Science projekta realiz\u0101ciju ar Avota kodu \u2014 <noindex><a rel=\"nofollow\" href=\"https:\/\/data-flair.training\/blogs\/data-science-r-movie-recommendation\/\">Filmu ieteikumu sist\u0113ma R valod\u0101<\/a><\/noindex><\/p>\n<p><img decoding=\"async\" alt=\"14 open-source projekti datu zin\u0101tnes prasmju att\u012bst\u012b\u0161anai (viegli, norm\u0101li, gr\u016bti)\" src=\"\/wp-content\/uploads\/2019\/12\/d9649913c8a254dd5b2dbc4f3de56397.jpg\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<br \/>\n\u0160aj\u0101 Data Science projekt\u0101 m\u0113s izmantosim R, lai veiktu filmu ieteikumus, izmantojot ma\u0161\u012bnm\u0101c\u012b\u0161anos. Ieteikumu sist\u0113ma pied\u0101v\u0101 lietot\u0101jiem ieteikumus, balstoties uz citu lietot\u0101ju izv\u0113l\u0113m un skat\u012b\u0161an\u0101s v\u0113sturi. Ja A un B pat\u012bk \"M\u0101j\u0101s vieni\", bet B m\u012bl \"Meitenes no Mean\", tad A var\u0113tu tikt ieteikts \u2014 vi\u0146am tas var\u0113tu patikt. Tas \u013cauj klientiem mijiedarboties ar platformu.<\/p>\n<p><b>Valoda:<\/b> R<\/p>\n<p><b>Datu kopas \/ Pakotne:<\/b> MovieLens datu kopa<\/p>\n<h3>12. Klientu segment\u0101cija<\/h3>\n<p>\nAizraujiet darba dev\u0113jus ar Data Science projekta pal\u012bdz\u012bbu (ietverot avota kodu) \u2014 <noindex><a rel=\"nofollow\" href=\"https:\/\/data-flair.training\/blogs\/r-data-science-project-customer-segmentation\/\">Klientu segment\u0101cija, izmantojot ma\u0161\u012bnm\u0101c\u012b\u0161anos<\/a><\/noindex>.<\/p>\n<p><img decoding=\"async\" alt=\"14 open-source projekti datu zin\u0101tnes prasmju att\u012bst\u012b\u0161anai (viegli, norm\u0101li, gr\u016bti)\" src=\"\/wp-content\/uploads\/2019\/12\/726c3aef4702afe5fa6c60b9c7016066.jpg\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<br \/>\nKlientu segment\u0101cija ir popul\u0101ra <noindex><a rel=\"nofollow\" href=\"https:\/\/en.wikipedia.org\/wiki\/Unsupervised_learning\">neuzraudz\u012bt\u0101 m\u0101c\u012b\u0161an\u0101s<\/a><\/noindex>. Izmantojot klasteriz\u0101ciju, uz\u0146\u0113mumi nosaka klientu segmentus, ar kuriem str\u0101d\u0101t ar potenci\u0101lo lietot\u0101ju b\u0101zi. Vi\u0146i sadala klientus grup\u0101s, pamatojoties uz kop\u012bg\u0101m iez\u012bm\u0113m, piem\u0113ram, dzimumu, vecumu, interes\u0113m un izdevumu paradumiem, lai efekt\u012bvi tirgotu sava produkta katrai grupai. M\u0113s izmantosim <noindex><a rel=\"nofollow\" href=\"https:\/\/data-flair.training\/blogs\/k-means-clustering-tutorial\/\">K-vid\u0113ji klasteriz\u0101ciju<\/a><\/noindex>, k\u0101 ar\u012b vizualiz\u0113sim sadal\u012bjumu p\u0113c dzimuma un vecuma. Tad m\u0113s analiz\u0113sim vi\u0146u gada ien\u0101kumus un izdevumu l\u012bmeni.<\/p>\n<p><b>Valoda:<\/b> R<\/p>\n<p><b>Datu kopas \/ Pakotne:<\/b> Mall_Customers datu kopa<\/p>\n<h3>13. Kr\u016bts v\u0113\u017ea klasifik\u0101cija<\/h3>\n<p>\nIzskatiet pilnu Data Science projekta realiz\u0101ciju Python valod\u0101 \u2014 <noindex><a rel=\"nofollow\" href=\"https:\/\/data-flair.training\/blogs\/project-in-python-breast-cancer-classification\/\">Kr\u016bts v\u0113\u017ea klasifik\u0101cija, izmantojot dzi\u013co m\u0101c\u012b\u0161anos<\/a><\/noindex>.<\/p>\n<p><img decoding=\"async\" alt=\"14 open-source projekti datu zin\u0101tnes prasmju att\u012bst\u012b\u0161anai (viegli, norm\u0101li, gr\u016bti)\" src=\"\/wp-content\/uploads\/2019\/12\/0f17da321e3de2f01c12f277635cd7fa.jpg\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<br \/>\nAtgrie\u017eoties pie medic\u012bnas datu zin\u0101tnes ieguld\u012bjuma, m\u0101c\u012bsimies atkl\u0101t kr\u016bts v\u0113zi, izmantojot Python. M\u0113s izmantosim IDC_regular datu kopu, lai identific\u0113tu invaz\u012bvo ductal karcinomu, visizplat\u012bt\u0101ko kr\u016bts v\u0113\u017ea formu. T\u0101 att\u012bst\u0101s piena kan\u0101los, ieaugot piena dziedzeru saistaudu vai tauku audos \u0101rpus kan\u0101la. \u0160aj\u0101 datu v\u0101k\u0161anas zin\u0101tnisk\u0101 projekta idej\u0101 m\u0113s izmantosim <noindex><a rel=\"nofollow\" href=\"https:\/\/data-flair.training\/blogs\/deep-learning-tutorial\/\">Deep Learning<\/a><\/noindex> un Keras bibliot\u0113ku klasifik\u0101cijai.<\/p>\n<p><b>Valoda:<\/b> Python<\/p>\n<p><b>Datu kopas \/ Pakotne:<\/b> IDC_regular<\/p>\n<h3>14. Ce\u013cu z\u012bmju atpaz\u012b\u0161ana<\/h3>\n<p>\nLai sasniegtu precizit\u0101ti automa\u0161\u012bnas autonomaj\u0101 brauk\u0161anas tehnolo\u0123ij\u0101, izmantojot datu zin\u0101tnes projektu par <noindex><a rel=\"nofollow\" href=\"https:\/\/data-flair.training\/blogs\/python-project-traffic-signs-recognition\/\">ce\u013cu z\u012bmju atpaz\u012b\u0161anu, izmantojot CNN<\/a><\/noindex> ar atv\u0113rt\u0101 koda risin\u0101jumiem.<\/p>\n<p><img decoding=\"async\" alt=\"14 open-source projekti datu zin\u0101tnes prasmju att\u012bst\u012b\u0161anai (viegli, norm\u0101li, gr\u016bti)\" src=\"\/wp-content\/uploads\/2019\/12\/c6560afe67f13996bf2047db498065f4.jpg\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<br \/>\nCe\u013cu z\u012bmes un ce\u013cu satiksmes noteikumi ir \u013coti svar\u012bgi ikvienam autovad\u012bt\u0101jam, lai izvair\u012btos no negad\u012bjumiem. Lai iev\u0113rotu noteikumu, vispirms j\u0101izprot, k\u0101 izskat\u0101s ce\u013cu z\u012bme. Cilv\u0113kam j\u0101iem\u0101c\u0101s visas ce\u013cu z\u012bmes, pirms vi\u0146am tiek dotas ties\u012bbas vad\u012bt jebkuru transportl\u012bdzekli. Tom\u0113r \u0161obr\u012bd autonoma transportl\u012bdzek\u013cu skaits pieaug, un tuv\u0101kaj\u0101 n\u0101kotn\u0113 cilv\u0113ks vairs nevad\u012bs automa\u0161\u012bnu pats. Projekt\u0101 \u201cCe\u013cu z\u012bmju atpaz\u012b\u0161ana\u201d j\u016bs uzzin\u0101siet, k\u0101 programma var atpaz\u012bt ce\u013cu z\u012bmju tipu, pie\u0146emot att\u0113lu k\u0101 ieejas sign\u0101lu. V\u0101cijas ce\u013cu z\u012bmju atpaz\u012b\u0161anas datu kopa (GTSRB) tiek izmantota, lai izveidotu dzi\u013co neironu t\u012bklu ce\u013cu z\u012bmes klases atpaz\u012b\u0161anai. M\u0113s ar\u012b izveidojam vienk\u0101r\u0161u grafisko saskarni mijiedarb\u012bbai ar lietojumprogrammu.<\/p>\n<p><b>Valoda:<\/b> Python<\/p>\n<p><b>Datu kopums:<\/b> GTSRB (V\u0101cijas ce\u013cu z\u012bmju atpaz\u012b\u0161anas nov\u0113rt\u0113jums)<\/p>\n<h3>Las\u012bt vair\u0101k<\/h3>\n<p><\/p>\n<ul>\n<li><noindex><a rel=\"nofollow\" href=\"https:\/\/habr.com\/ru\/company\/edison\/blog\/480408\/\">52 datu kopas apm\u0101c\u012bbas projektiem<\/a><\/noindex><\/li>\n<li><noindex><a rel=\"nofollow\" href=\"https:\/\/habr.com\/ru\/company\/edison\/blog\/479100\/\">Front-end dojos: projekti izstr\u0101d\u0101t\u0101ja prasmju apg\u016b\u0161anai (5 jauni + 43 veci)<\/a><\/noindex><\/li>\n<li><noindex><a rel=\"nofollow\" href=\"https:\/\/habr.com\/ru\/company\/edison\/blog\/479650\/\">Top-12 interesant\u0101k\u0101s IT dinamisk\u0101s infografikas<\/a><\/noindex><\/li>\n<\/ul>\n<p>Avots: <a content=\"nofollow\" rel=\"nofollow\" href=\"https:\/\/habr.com\/ru\/company\/edison\/blog\/480378\/\">habr.com<\/a><\/p>","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"excerpt":{"rendered":"<p>Data Science \u0434\u043b\u044f \u043d\u0430\u0447\u0438\u043d\u0430\u044e\u0449\u0438\u0445 1. Sentiment Analysis (\u0410\u043d\u0430\u043b\u0438\u0437 \u043d\u0430\u0441\u0442\u0440\u043e\u0435\u043d\u0438\u0439 \u0447\u0435\u0440\u0435\u0437 \u0442\u0435\u043a\u0441\u0442) \u041f\u043e\u0441\u043c\u043e\u0442\u0440\u0438\u0442\u0435 \u043f\u043e\u043b\u043d\u0443\u044e \u0440\u0435\u0430\u043b\u0438\u0437\u0430\u0446\u0438\u044e \u043f\u0440\u043e\u0435\u043a\u0442\u0430 Data Science \u0441 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043d\u0438\u0435\u043c \u0438\u0441\u0445\u043e\u0434\u043d\u043e\u0433\u043e \u043a\u043e\u0434\u0430 \u2014 Sentiment Analysis Project \u0432 R. Sentiment Analysis \u2014 \u044d\u0442\u043e \u0430\u043d\u0430\u043b\u0438\u0437 \u0441\u043b\u043e\u0432 \u0434\u043b\u044f \u043e\u043f\u0440\u0435\u0434\u0435\u043b\u0435\u043d\u0438\u044f \u043d\u0430\u0441\u0442\u0440\u043e\u0435\u043d\u0438\u0439 \u0438 \u043c\u043d\u0435\u043d\u0438\u0439, \u043a\u043e\u0442\u043e\u0440\u044b\u0435 \u043c\u043e\u0433\u0443\u0442 \u0431\u044b\u0442\u044c \u043f\u043e\u043b\u043e\u0436\u0438\u0442\u0435\u043b\u044c\u043d\u044b\u043c\u0438 \u0438\u043b\u0438 \u043e\u0442\u0440\u0438\u0446\u0430\u0442\u0435\u043b\u044c\u043d\u044b\u043c\u0438. \u042d\u0442\u043e \u0442\u0438\u043f \u043a\u043b\u0430\u0441\u0441\u0438\u0444\u0438\u043a\u0430\u0446\u0438\u0438, \u043f\u0440\u0438 \u043a\u043e\u0442\u043e\u0440\u043e\u043c \u043a\u043b\u0430\u0441\u0441\u044b \u043c\u043e\u0433\u0443\u0442 \u0431\u044b\u0442\u044c \u0434\u0432\u043e\u0438\u0447\u043d\u044b\u043c\u0438 (\u043f\u043e\u043b\u043e\u0436\u0438\u0442\u0435\u043b\u044c\u043d\u044b\u043c\u0438 \u0438 [&hellip;]<\/p>\n","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[702],"tags":[],"class_list":["post-54058","post","type-post","status-publish","format-standard","hentry","category-news"],"aioseo_notices":[],"aioseo_head":"\n\t\t<!-- All in One SEO 5.0.5 - aioseo.com -->\n\t<meta name=\"description\" content=\"Data Science \u0434\u043b\u044f \u043d\u0430\u0447\u0438\u043d\u0430\u044e\u0449\u0438\u0445 1.\" \/>\n\t<meta name=\"robots\" content=\"max-image-preview:large\" \/>\n\t<meta name=\"author\" content=\"Yuri Gagarin\"\/>\n\t<link rel=\"canonical\" href=\"https:\/\/prohoster.info\/lv\/blog\/news\/14-open-source-proektov-dlya-prokachki-data-science-masterstva-easy-normal-hard\" \/>\n\t\t<meta name=\"generator\" content=\"All in One SEO (AIOSEO) 5.0.5\" \/>\n\t\t<meta property=\"og:locale\" content=\"lv_LV\" \/>\n\t\t<meta property=\"og:site_name\" content=\"ProHoster | \u041a\u0443\u043f\u0438\u0442\u044c \u043d\u0430\u0434\u0435\u0436\u043d\u044b\u0439 \u0445\u043e\u0441\u0442\u0438\u043d\u0433 \u0434\u043b\u044f \u0441\u0430\u0439\u0442\u043e\u0432 \u0441 \u0437\u0430\u0449\u0438\u0442\u043e\u0439 \u043e\u0442 DDoS, VPS VDS \u0441\u0435\u0440\u0432\u0435\u0440\u044b\" \/>\n\t\t<meta property=\"og:type\" content=\"article\" \/>\n\t\t<meta property=\"og:title\" content=\"\ud83e\udd4714 open-source \u043f\u0440\u043e\u0435\u043a\u0442\u043e\u0432 \u0434\u043b\u044f \u043f\u0440\u043e\u043a\u0430\u0447\u043a\u0438 Data Science \u043c\u0430\u0441\u0442\u0435\u0440\u0441\u0442\u0432\u0430 (easy, normal, hard) | ProHoster\" \/>\n\t\t<meta property=\"og:description\" content=\"Data Science \u0434\u043b\u044f \u043d\u0430\u0447\u0438\u043d\u0430\u044e\u0449\u0438\u0445 1.\" \/>\n\t\t<meta property=\"og:url\" content=\"https:\/\/prohoster.info\/lv\/blog\/news\/14-open-source-proektov-dlya-prokachki-data-science-masterstva-easy-normal-hard\" \/>\n\t\t<meta property=\"og:image\" content=\"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg\" \/>\n\t\t<meta property=\"og:image:secure_url\" content=\"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg\" \/>\n\t\t<meta property=\"og:image:width\" content=\"350\" \/>\n\t\t<meta property=\"og:image:height\" content=\"350\" \/>\n\t\t<meta property=\"article:published_time\" content=\"2019-12-16T21:00:00+00:00\" \/>\n\t\t<meta property=\"article:modified_time\" content=\"2020-02-18T11:02:02+00:00\" \/>\n\t\t<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/prohoster\" \/>\n\t\t<meta property=\"article:author\" content=\"https:\/\/www.facebook.com\/prohoster\" \/>\n\t\t<!-- All in One SEO -->\n\n","aioseo_head_json":{"title":"\ud83e\udd4714 atv\u0113rt\u0101 koda projekti datu zin\u0101tnes prasmju uzlabo\u0161anai (viegli, norm\u0101li, gr\u016bti) | ProHoster","description":"Datu zin\u0101tne ies\u0101c\u0113jiem 1.","canonical_url":"https:\/\/prohoster.info\/lv\/blog\/news\/14-open-source-proektov-dlya-prokachki-data-science-masterstva-easy-normal-hard","robots":"max-image-preview:large","keywords":"","webmasterTools":{"miscellaneous":""},"schema":null,"og:locale":"lv_LV","og:site_name":"ProHoster | \u041a\u0443\u043f\u0438\u0442\u044c \u043d\u0430\u0434\u0435\u0436\u043d\u044b\u0439 \u0445\u043e\u0441\u0442\u0438\u043d\u0433 \u0434\u043b\u044f \u0441\u0430\u0439\u0442\u043e\u0432 \u0441 \u0437\u0430\u0449\u0438\u0442\u043e\u0439 \u043e\u0442 DDoS, VPS VDS \u0441\u0435\u0440\u0432\u0435\u0440\u044b","og:type":"article","og:title":"\ud83e\udd4714 open-source \u043f\u0440\u043e\u0435\u043a\u0442\u043e\u0432 \u0434\u043b\u044f \u043f\u0440\u043e\u043a\u0430\u0447\u043a\u0438 Data Science \u043c\u0430\u0441\u0442\u0435\u0440\u0441\u0442\u0432\u0430 (easy, normal, hard) | ProHoster","og:description":"Data Science \u0434\u043b\u044f \u043d\u0430\u0447\u0438\u043d\u0430\u044e\u0449\u0438\u0445 1.","og:url":"https:\/\/prohoster.info\/lv\/blog\/news\/14-open-source-proektov-dlya-prokachki-data-science-masterstva-easy-normal-hard","og:image":"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg","og:image:secure_url":"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg","og:image:width":350,"og:image:height":350,"article:published_time":"2019-12-16T21:00:00+00:00","article:modified_time":"2020-02-18T11:02:02+00:00","article:publisher":"https:\/\/www.facebook.com\/prohoster","article:author":"https:\/\/www.facebook.com\/prohoster"},"aioseo_meta_data":{"post_id":"54058","title":null,"description":null,"keywords":null,"keyphrases":null,"primary_term":null,"canonical_url":null,"og_title":null,"og_description":null,"og_object_type":"default","og_image_type":"default","og_image_url":null,"og_image_width":null,"og_image_height":null,"og_image_custom_url":null,"og_image_custom_fields":null,"og_video":null,"og_custom_url":null,"og_article_section":null,"og_article_tags":null,"twitter_use_og":false,"twitter_card":"default","twitter_image_type":"default","twitter_image_url":null,"twitter_image_custom_url":null,"twitter_image_custom_fields":null,"twitter_title":null,"twitter_description":null,"schema":{"blockGraphs":[],"customGraphs":[],"default":{"data":{"Article":[],"Course":[],"Dataset":[],"FAQPage":[],"Movie":[],"Person":[],"Product":[],"ProductReview":[],"Car":[],"Recipe":[],"Service":[],"SoftwareApplication":[],"WebPage":[]},"graphName":"","isEnabled":true},"graphs":[]},"schema_type":null,"schema_type_options":null,"pillar_content":false,"robots_default":true,"robots_noindex":false,"robots_noarchive":false,"robots_nosnippet":false,"robots_nofollow":false,"robots_noimageindex":false,"robots_noodp":false,"robots_notranslate":false,"robots_max_snippet":null,"robots_max_videopreview":null,"robots_max_imagepreview":"large","priority":null,"frequency":null,"local_seo":null,"seo_analyzer_scan_date":"2026-01-24 09:53:20","breadcrumb_settings":null,"limit_modified_date":false,"reviewed_by":null,"ai":null,"created":"2021-02-28 20:12:24","updated":"2026-01-24 09:53:20","focus_keyword":null,"additional_keywords":null,"truseo_locale":null},"gt_translate_keys":[{"key":"link","format":"url"}],"_links":{"self":[{"href":"https:\/\/prohoster.info\/lv\/wp-json\/wp\/v2\/posts\/54058","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/prohoster.info\/lv\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/prohoster.info\/lv\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/prohoster.info\/lv\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/prohoster.info\/lv\/wp-json\/wp\/v2\/comments?post=54058"}],"version-history":[{"count":0,"href":"https:\/\/prohoster.info\/lv\/wp-json\/wp\/v2\/posts\/54058\/revisions"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/lv\/wp-json\/wp\/v2\/media?parent=54058"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/lv\/wp-json\/wp\/v2\/categories?post=54058"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/lv\/wp-json\/wp\/v2\/tags?post=54058"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}