Data Science rau Beginners
1. Sentiment Analysis (Sentimment Analysis through Text)
Txheeb xyuas qhov ua tiav Data Science qhov kev ua tiav siv qhov chaws- .
Sentiment Analysis yog kev tshuaj xyuas cov lus los txiav txim siab txog kev xav thiab kev xav, uas tuaj yeem ua tau zoo lossis tsis zoo. Qhov no yog ib hom kev faib nyob rau hauv cov chav kawm yuav ua tau binary (zoo thiab tsis zoo) los yog plural (zoo siab, npau taws, tu siab, phem ...). Peb yuav siv qhov project Data Science hauv R thiab yuav siv cov ntaub ntawv hauv pob "janeaustenR". Peb yuav siv phau ntawv txhais lus dav dav xws li AFINN, bing thiab loughran, ua ib qho kev koom nrog sab hauv, thiab thaum kawg peb yuav tsim ib lo lus huab los qhia qhov tshwm sim.
Hais lus: Lus R
Cov ntaub ntawv / Pob: JaneaustenR
Tsab ntawv tau muab txhais nrog kev txhawb nqa ntawm EDISON Software, uas Thiab .
2. Kev Tshawb Nrhiav Fake News
Coj koj cov txuj ci mus rau qib tom ntej los ntawm kev ua haujlwm ntawm Data Science project rau cov pib tshiab - .
Cov xov xwm cuav yog cov ntaub ntawv tsis tseeb tshaj tawm los ntawm kev tshaj xov xwm thiab lwm yam xov xwm hauv online kom ua tiav cov hom phiaj kev nom kev tswv. Hauv lub tswv yim ntawm Kev Tshawb Fawb Txog Kev Tshawb Fawb no, peb yuav siv Python los tsim tus qauv uas tuaj yeem txiav txim siab seb cov xov xwm yog qhov tseeb lossis cuav. Peb yuav tsim TfidfVectorizer thiab siv PassiveAggressiveClassifier los faib cov xov xwm rau hauv "tiag" thiab "fake". Peb yuav siv cov ntaub ntawv ntawm cov duab 7796 Γ 4 thiab khiav txhua yam hauv Jupyter Lab.
Hais lus: Lus Nab hab sej
Cov ntaub ntawv / Pob: xov.csv
3. Txheeb xyuas tus kab mob Parkinson
Mus rau pem hauv ntej nrog koj cov ntaub ntawv Science Project Tswv yim - .
Peb tau pib siv Kev Tshawb Fawb Txog Kev Tshawb Fawb los txhim kho kev noj qab haus huv thiab kev pabcuam - yog tias peb tuaj yeem kwv yees tus kabmob thaum ntxov, ces peb yuav muaj ntau yam zoo. Yog li, hauv lub tswv yim ntawm Kev Tshawb Fawb Txog Kev Tshawb Fawb no, peb yuav kawm paub yuav ua li cas txhawm rau kuaj Parkinson tus kab mob siv Python. Nws yog ib tug neurodegenerative, kev loj hlob kab mob ntawm lub hauv paus paj hlwb uas cuam tshuam rau kev txav thiab ua rau tremors thiab txhav. Nws cuam tshuam rau dopamine-tsim neurons hauv lub hlwb, thiab txhua xyoo, nws cuam tshuam ntau dua 1 lab tus tib neeg hauv Is Nrias teb.
Hais lus: Lus Nab hab sej
Cov ntaub ntawv / Pob: UCI ML Parkinson cov ntaub ntawv
Data Science tej yaam num ntawm nruab nrab complexity
4. Kev paub txog kev hais lus
Txheeb xyuas qhov ua tiav ntawm Kev Tshawb Fawb Cov Qauv piv txwv project β .
Tam sim no cia peb kawm paub siv cov tsev qiv ntawv sib txawv. Qhov project Data Science no siv librosa rau kev paub hais lus. SER yog tus txheej txheem ntawm kev txheeb xyuas tib neeg txoj kev xav thiab lub xeev muaj kev cuam tshuam los ntawm kev hais lus. Txij li thaum peb siv lub suab thiab suab los qhia kev xav nrog peb lub suab, SER yog qhov tseem ceeb. Tab sis txij li cov kev xav yog cov ntsiab lus, cov lus piav qhia suab yog ib txoj haujlwm nyuaj. Peb yuav siv mfcc, chroma thiab mel ua haujlwm thiab siv RAVDESS dataset rau kev paub txog kev xav. Peb yuav tsim ib qho MLPC classifier rau tus qauv no.
Hais lus: Lus Nab hab sej
Cov ntaub ntawv / Pob: RAVDESS cov ntaub ntawv
5. Kev txheeb xyuas poj niam txiv neej thiab hnub nyoog
Txaus siab rau cov tswv ntiav nrog qhov tseeb Data Science project - .
Qhov no yog ib qho nthuav Data Science nrog Python. Siv ib daim duab xwb, koj yuav kawm los kwv yees tus txiv neej thiab hnub nyoog. Hauv qhov no peb yuav qhia koj txog Computer Vision thiab nws cov hauv paus ntsiab lus. Peb yuav tsim thiab yuav siv cov qauv kawm los ntawm Tal Hassner thiab Gil Levy ntawm Adience dataset. Raws li peb yuav siv qee cov ntaub ntawv .pb, .pbtxt, .prototxt thiab .caffemodel.
Hais lus: Lus Nab hab sej
Cov ntaub ntawv / Pob: Adience
6. Uber Data Analysis
Txheeb xyuas qhov ua tiav Cov Ntaub Ntawv Kev Tshawb Fawb Kev Ua Haujlwm nrog rau qhov chaws β .
Qhov no yog ib qhov project visualization nrog ggplot2 uas peb yuav siv R thiab nws cov tsev qiv ntawv thiab txheeb xyuas ntau yam tsis. Peb yuav siv Uber Pickups New York City dataset thiab tsim kev pom rau lub sijhawm sib txawv ntawm lub xyoo. Qhov no qhia peb tias lub sijhawm cuam tshuam li cas rau cov neeg siv khoom mus ncig.
Hais lus: Lus R
Cov ntaub ntawv / Pob: Uber Pickups hauv New York City dataset
7. Tus tsav tsheb Drowsiness nrhiav kom pom
Txhim kho koj cov kev txawj ntse los ntawm kev ua haujlwm ntawm Cov Ntaub Ntawv Tshawb Fawb Top - .
Kev tsav tsheb tsaug zog yog qhov txaus ntshai heev, thiab ze li ib txhiab qhov xwm txheej tshwm sim txhua xyoo vim cov neeg tsav tsheb tsaug zog thaum tsav tsheb. Hauv qhov project Python no, peb yuav tsim lub kaw lus uas tuaj yeem ntes cov neeg tsav tsheb tsaug zog thiab tseem ceeb toom lawv nrog lub suab teeb liab.
Qhov project no yog siv los ntawm Keras thiab OpenCV. Peb yuav siv OpenCV rau lub ntsej muag thiab qhov muag kom pom thiab nrog Keras peb yuav faib lub qhov muag (Qhib lossis Kaw) siv cov tswv yim sib sib zog nqus neural network.
8. Cov Chatbot
Tsim Chatbot nrog Python thiab ua ib kauj ruam tom ntej hauv koj txoj haujlwm - .
Chatbots yog ib feem tseem ceeb ntawm kev lag luam. Ntau lub lag luam yuav tsum muab kev pabcuam rau lawv cov neeg siv khoom thiab nws yuav siv ntau lub zog, sijhawm thiab kev siv zog los pab lawv. Chatbots tuaj yeem ua haujlwm ntau ntawm koj cov neeg siv khoom sib cuam tshuam los ntawm kev teb qee cov lus nug uas cov neeg siv khoom nug. Yeej muaj ob hom chatbots: Domain-specific thiab Open-domain. Ib lub npe tshwj xeeb chatbot feem ntau siv los daws qhov teeb meem tshwj xeeb. Yog li, koj yuav tsum tau kho nws kom ua haujlwm zoo hauv koj daim teb. Qhib-domain chatbots tuaj yeem nug txhua yam lus nug, yog li kev cob qhia lawv yuav tsum muaj cov ntaub ntawv loj heev.
Cov ntaub ntawv teev: Intents json cov ntaub ntawv
Hais lus: Lus Nab hab sej
Advanced Data Science tej yaam num
9. Duab Caption Generator
Txheeb xyuas qhov ua tiav ntawm qhov project nrog qhov chaws- .
Piav txog dab tsi hauv daim duab yog ib txoj haujlwm yooj yim rau tib neeg, tab sis rau cov khoos phis tawj, cov duab tsuas yog cov lej uas sawv cev rau xim tus nqi ntawm txhua pixel. Qhov no yog ib txoj haujlwm nyuaj rau computers. To taub dab tsi hauv ib daim duab thiab tom qab ntawd tsim cov lus piav qhia hauv hom lus (xws li lus Askiv) yog lwm txoj haujlwm nyuaj. Qhov project no siv cov txheej txheem kev kawm tob uas peb siv Convolutional Neural Network (CNN) nrog Recurrent Neural Network (LSTM) los tsim cov duab piav qhia lub tshuab hluav taws xob.
Cov ntaub ntawv teev: Flickr 8K
Hais lus: Lus Nab hab sej
Framework: Keras
10. Daim npav rho nyiaj tsis raug cai
Ua koj qhov zoo tshaj plaws thaum ua haujlwm ntawm koj lub tswv yim Data Science project - .
Txog tam sim no koj tau pib nkag siab txog cov tswv yim thiab cov tswv yim. Cia peb mus rau qee qhov kev tshawb fawb cov ntaub ntawv qib siab. Hauv qhov project no peb yuav siv R hom lus nrog algorithms zoo li , logistic regression, artificial neural networks thiab gradient boosting classifier. Peb yuav siv cov ntaub ntawv ntawm daim npav rho nyiaj los faib cov credit card kev lag luam raws li kev dag lossis tiag. Peb yuav xaiv cov qauv sib txawv rau lawv thiab tsim kev ua haujlwm nkhaus.
Hais lus: Lus R
Cov ntaub ntawv / Pob: Daim npav rho nyiaj cov ntaub ntawv
11. Movie Recommendation System
Kawm txog kev siv qhov zoo tshaj plaws Data Science project nrog Source code -
Hauv qhov project Data Science no, peb yuav siv R los siv cov yeeb yaj kiab cov lus pom zoo los ntawm kev kawm tshuab. Lub kaw lus pom zoo xa cov lus qhia rau cov neeg siv los ntawm cov txheej txheem lim raws li lwm tus neeg siv cov kev nyiam thiab kev tshawb nrhiav keeb kwm. Yog tias A thiab B nyiam Lub Tsev Ib Leeg, thiab B nyiam Mean Cov Ntxhais, ces koj tuaj yeem hais A - lawv kuj nyiam nws thiab. Qhov no tso cai rau cov neeg siv khoom sib cuam tshuam nrog lub platform.
Hais lus: Lus R
Cov ntaub ntawv / Pob: MovieLens cov ntaub ntawv
12. Cov neeg siv khoom Segmentation
Txaus siab rau cov tswv ntiav nrog Data Science project (nrog rau qhov chaws) - .
Cov neeg yuav khoom segmentation yog ib daim ntawv thov nrov . Siv kev sib koom ua ke, tuam txhab lag luam txheeb xyuas cov neeg siv khoom lag luam txhawm rau tsom cov neeg siv peev txheej. Lawv faib cov neeg siv khoom ua pab pawg raws li cov yam ntxwv xws li poj niam txiv neej, hnub nyoog, kev nyiam thiab kev siv nyiaj kom lawv tuaj yeem ua lag luam lawv cov khoom lag luam zoo rau txhua pab pawg. Peb yuav siv , nrog rau pom qhov kev faib tawm los ntawm poj niam txiv neej thiab hnub nyoog. Tom qab ntawd peb yuav txheeb xyuas lawv cov nyiaj tau los thiab cov nuj nqis txhua xyoo.
Hais lus: Lus R
Cov ntaub ntawv / Pob: Mall_Customers dataset
13. Kev faib cov qog nqaij hlav mis
Txheeb xyuas qhov ua tiav ntawm Kev Tshawb Fawb Txog Kev Tshawb Fawb hauv Python β .
Rov qab los rau kev pab kho mob ntawm cov ntaub ntawv tshawb fawb, cia peb kawm yuav ua li cas txhawm rau kuaj mob qog noj ntshav siv Python. Peb yuav siv IDC_regular dataset los txheeb xyuas cov kab mob ductal carcinoma, feem ntau hom mob qog noj ntshav mis. Nws tsim nyob rau hauv cov mis nyuj ducts, burrowing mus rau hauv lub fibrous los yog fatty mis cov ntaub so ntswg sab nraum lub duct. Nyob rau hauv cov ntaub ntawv sau txog science project tswv yim peb yuav siv thiab lub tsev qiv ntawv Keras rau kev faib tawm.
Hais lus: Lus Nab hab sej
Cov ntaub ntawv / Pob: IDC_regular
14. Kev lees paub ntawm kev tsheb
Ua tiav qhov tseeb hauv kev tsav tsheb tus kheej nrog Data Science project qhib qhov chaw.
Cov paib txoj kev thiab cov kev cai tsheb yog ib qho tseem ceeb heev rau txhua tus neeg tsav tsheb kom tsis txhob muaj xwm txheej. Ua raws li txoj cai, thawj zaug koj yuav tsum nkag siab tias txoj kev kos npe zoo li cas. Ib tug neeg yuav tsum kawm tag nrho txoj kev kos npe ua ntej nws tau txais daim ntawv tso cai tsav tsheb. Tab sis tam sim no tus naj npawb ntawm cov tsheb autonomous tau loj hlob, thiab nyob rau yav tom ntej tus neeg yuav tsis tsav tsheb ntawm nws tus kheej. Nyob rau hauv txoj haujlwm Kos Npe Kev Pom Zoo, koj yuav kawm paub tias qhov kev zov me nyuam tuaj yeem paub txog hom kev kos npe ntawm txoj kev los ntawm kev thaij duab los ntawm kev nkag. Lub German Traffic Sign Recognition Benchmark (GTSRB) dataset yog siv los tsim kom muaj qhov sib sib zog nqus neural network kom paub txog cov chav kawm uas kos npe rau tsheb. Peb kuj tsim ib qho yooj yim GUI los cuam tshuam nrog daim ntawv thov.
Hais lus: Lus Nab hab sej
Cov ntaub ntawv teev: GTSRB (German Traffic Sign Recognition Benchmark)
Nyeem ntxiv
Tau qhov twg los: www.hab.com