TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Why you don't need much math to learn data science

3 点作者 SharpSightLabs将近 7 年前

2 条评论

nanis将近 7 年前
Math is the easy part. Having the intellect to understand what the numbers coming out of the sausage machine is harder. As always, the incentive is to ignore all that difficult stuff ... Look ma, I am soooo machine learned!
iagovar将近 7 年前
Sometimes I feel strange in the &quot;data science&quot; field. I did a sociology degree in a small Spanish university (UDC) and I found the Multivariate Statistics course way harder than almost anything out there.<p>I do struggle with programming though. Not really the logical part, but even in R plotting something that would be simple in Excel or SPSS is quite tricky. Maybe it is because I&#x27;m not a native english speaker but how stuff is named is weird and doesn&#x27;t make much sense to me, so it becomes harder to memorize.<p>For example, why did they choose str() for a quick view of data frames? To me that reads naturally like &quot;string()&quot;, so it would make sense to use it for doing stuff with strings.<p>That&#x27;s why, while I do use R, I really love tools like KNIME above all. Maybe it&#x27;s just a matter of keep doing it, but while other people seems &quot;fluent&quot; with R o Python I really can&#x27;t do much without documentation, and some trial and error.