![[PyTorch] 쉽고 빠르게 배우는 NLP강의 썸네일](https://cdn.inflearn.com/public/courses/325056/course_cover/b66025dd-43f5-4a96-8627-202b9ba9e038/pytorch-nlp-eng.png?w=420)
[PyTorch] 쉽고 빠르게 배우는 NLP
코코
기본적인 자연어처리 기법(Natural Language Processing)과 딥러닝을 활용한 다양한 텍스트 task에 대해 다룹니다.
중급이상
딥러닝, 인공신경망, PyTorch
Learn how to collect and manage all stocks listed on the stock market. Create a dashboard using shiny that automatically collects new stock prices every day and can also identify stock trends by industry.
Collection of all KOSPI/KOSDAQ stocks
Industry-specific stock data management
Understanding industry-specific stock trends
🙆🏻♀ Automate all stock data collection and management/industry-specific stock management 🙆🏻♂
Would you like to analyze a stock you are interested in or all stocks listed on KOSPI/KOSDAQ?
To do analysis, you need data .
This course collects and manages all stocks listed on our country's stock market.
Due to time constraints, the lecture collects data for the past three years for all subjects.
If you change 3 to 10, you can easily collect 10 years' worth of data.
Starting today, we will collect not only the last 10 years of data, but also new data, that is, data generated the next day.
Automation updates the stocks daily by collecting data on the day's transactions around 4 p.m., when the stock market closes.
Create a Shiny Dash Board like the address below.
https://leegt.shinyapps.io/shiny/
(Connection may not be possible if the number of people exceeds a certain number)
All companies (stocks) listed on the stock market have their own unique code.
Depending on this code, the address to be crawled will change.
So, first, we collect the unique code for each company.
Additionally, we preprocess the code so that it can be imported from Naver Finance.
After setting the Naver Financial address for each stock, data for the past three years is collected for all stocks.
It took about 4 hours to collect 3 years' worth, so I think 10 years' worth could be collected in about 12 hours.
After collecting daily stock data by stock, create a folder for each stock and save it in each folder.
Additionally, exception handling is provided in case an error occurs.
We can't scrape 10 years' worth of data like this every day. It's highly inefficient.
After today's stock trading is completed, automation proceeds by collecting only today's stock data and merging it with previously stored data.
Now we can automatically update all daily stock data every day at 4 PM.
From a mid- to long-term stock investment perspective, it is important to understand industry/theme trends.
We collect stock codes by industry, retrieve data on these stocks, identify trends, and visualize them.
After the stock market closes each day, we collect additional daily data and automate the entire process, from managing and visualizing stocks by industry.
This lecture is
The lecture assumes basic knowledge of the R language and crawling.
Who is this course right for?
Someone who knows the basics of R
Anyone who needs stock data
Anyone who wants to build up basic data for investing
8,299
Learners
501
Reviews
136
Answers
4.4
Rating
20
Courses
학부에서는 통계학을 전공하고 산업공학(인공지능) 박사를 받고 여전히 공부중인 백수입니다.
수상
ㆍ 제6회 빅콘테스트 게임유저이탈 알고리즘 개발 / 엔씨소프트상(2018)
ㆍ 제5회 빅콘테스트 대출 연체자 예측 알고리즘개발 / 한국정보통신진흥협회장상(2017)
ㆍ 2016 날씨 빅데이터 콘테스트/ 기상산업 진흥원장상(2016)
ㆍ 제4회 빅콘테스트 보험사기 예측 알고리즘 개발 / 본선진출(2016)
ㆍ 제3회 빅콘테스트 야구 경기 예측 알고리즘 개발 / 미래창조과학부 장관상(2015)
* blog : https://bluediary8.tistory.com
주로 연구하는 분야는 데이터 사이언스, 강화학습, 딥러닝 입니다.
크롤링과 텍스트마이닝은 현재는 취미로 하고있습니다 :)
크롤링을 이용해서 인기있는 커뮤니티 글만 수집해서 보여주는 마롱이라는 앱을 개발하였고
전국의 맛집리스트와 블로그를 수집해서 맛집 추천 앱도 만들었었죠 :) (시원하게 말아먹..)
지금은 인공지능을 연구하는 박사과정생입니다.
All
23 lectures ∙ (3hr 55min)
Course Materials:
All
8 reviews
4.9
8 reviews
Reviews 4
∙
Average Rating 5.0
Reviews 155
∙
Average Rating 5.0
Reviews 15
∙
Average Rating 5.0
Reviews 1
∙
Average Rating 5.0
Reviews 1
∙
Average Rating 4.0
$42.90
Check out other courses by the instructor!
Explore other courses in the same field!