[Boards: 3 / a / aco / adv / an / asp / b / biz / c / cgl / ck / cm / co / d / diy / e / fa / fit / g / gd / gif / h / hc / his / hm / hr / i / ic / int / jp / k / lgbt / lit / m / mlp / mu / n / news / o / out / p / po / pol / qa / r / r9k / s / s4s / sci / soc / sp / t / tg / toy / trash / trv / tv / u / v / vg / vp / vr / w / wg / wsg / wsr / x / y ] [Home]
4chanarchives logo
How to import online data, like the value of some stock for the
Images are sometimes not shown due to bandwidth/network limitations. Refreshing the page usually helps.

You are currently reading a thread in /g/ - Technology

Thread replies: 18
Thread images: 1
File: marisaBacktest_02.png (89 KB, 560x420) Image search: [Google]
marisaBacktest_02.png
89 KB, 560x420
How to import online data, like the value of some stock for the past 500 days, to MATLAB?

Someone please post a tutorial or something.
>>
Look for an api that provides what you want.failing that, scrape it yourself with python or something
>>
Download .csv from online

Import .csv into matlab
>>
>>53752653
Alright, so yahoo finance let's me download stock prices as a .csv file.

I take it there is something in MATLAB that let's me convert it to two vectors so I can plot it on my own?
>>
>>53753159
yup, irc its called csvread, you can specify the number what columns and rows you wanna take.

its funny, i am also dealing with an assignment on matlab with financial data. Are you by any chance UvA econometrics?
>>
>>53753159
>>53754049
http://nl.mathworks.com/help/matlab/ref/csvread.html

and just cause i am feeling nice XP
>>
>>53751871

Right click and save duh?
>>
>>53754049
>UvA
University of Amsterdam?
>>
>>53751871
>mfw doing this exact thing with python and sentiment analysis for my final uni project
>mfw not helping at all
>mfw no face
>>
>>53754452
I actually recently turned in a research proposal for researching event extraction combined with fine-grained implicit sentiment analysis for economic news text.
>>
>>53754762
Me and a bro are just bullshiting our work. It's maybe 500 lines for a bastardized gradient descent and sentiment analysis of yahoo news RSS feeds for NASDAQ corportations, and another 300 lines for pulling opening and closing and correlating with words from those RSS feeds.
>>
>>53754895
So it's all lexicon-based sentiment analysis? That's weak if you're not at least machine learning the dictionary yourself. My NLP and IR research group takes a data-driven ML approach which also incorporated sentiment lexicon information in the feature vectors.
>>
>>53754941
What are you studying, senpai? I am working on my masters in public policy, looking at voting behaviour and I'm in love with data ever since my first statistics course. I would love to branch out into machine learning approaches for my PhD and am wondering what other people are doing.
>>
>>53754941
We're training the dictionary ourselves for the most part, though I have written a function to train the dictionary using the dictionary itself. It's iterative, but my partner needs to do the training first so that the dictionary is reasonably accurate first.
>>
>>53755029
Doing project work as a doctoral researcher in natural language processing and information retrieval.

I got a BA in English and Spanish Linguistics and Literature, an MA in Computational and Formal Linguistics and an advanced MSc in Artificial Intelligence: Speech and Language Technologies.

Keep up the work. Coming from the humanities to a CS field is not easy but keep learning and reading and you'll get there.
>>
>>53755085
Nice, that approach is usually called bootstrapping and completely valid. But you knew that already. Start with seeds and iterate using an unsupervised approach.
>>
>>53755150
that's the idea. I'm in a machine learning course but it's basic and I have a propensity to forget technical words
>>
>>53755111
Thanks for the kind words, lad. Glad to see I am not the only one who made the switch. Good luck on your PhD!
Thread replies: 18
Thread images: 1

banner
banner
[Boards: 3 / a / aco / adv / an / asp / b / biz / c / cgl / ck / cm / co / d / diy / e / fa / fit / g / gd / gif / h / hc / his / hm / hr / i / ic / int / jp / k / lgbt / lit / m / mlp / mu / n / news / o / out / p / po / pol / qa / r / r9k / s / s4s / sci / soc / sp / t / tg / toy / trash / trv / tv / u / v / vg / vp / vr / w / wg / wsg / wsr / x / y] [Home]

All trademarks and copyrights on this page are owned by their respective parties. Images uploaded are the responsibility of the Poster. Comments are owned by the Poster.
If a post contains personal/copyrighted/illegal content you can contact me at [email protected] with that post and thread number and it will be removed as soon as possible.
DMCA Content Takedown via dmca.com
All images are hosted on imgur.com, send takedown notices to them.
This is a 4chan archive - all of the content originated from them. If you need IP information for a Poster - you need to contact them. This website shows only archived content.