Finding Answers

Loading...

Do curso por Johns Hopkins University

As Ferramentas do Cientista de Dados

14676 ratings

Johns Hopkins University

As Ferramentas do Cientista de Dados

14676 ratings

Curso 1 de 10 em Specialization Data Science

Neste curso você receberá uma introdução às ferramentas e idéias mais importantes da "caixa de ferramenta do cientista". O curso dará uma visão geral de dados, perguntas e ferramentas utilizadas pelo cientista para a análise de dados. Este curso possui duas partes. A primeira é uma parte introdutória e conceitual às ideias por trás da transformação de dados em conhecimento. A segunda parte dará uma intrudução prática às ferramentas que serão utilizadas durante o programa (version control, markdown, git, GitHub, R e RStudio).

Na lição

Week 1

During Week 1, you'll learn about the goals and objectives of the Data Science Specialization and each of its components. You'll also get an overview of the field as well as instructions on how to install R.

Specialization Motivation12:03

The Data Scientist's Toolbox5:09

Getting Help8:52

Finding Answers4:35

R Programming Overview2:12

Getting Data Overview1:34

Exploratory Data Analysis Overview1:21

Reproducible Research Overview1:27

Statistical Inference Overview1:06

Regression Models Overview1:46

Practical Machine Learning Overview1:31

Building Data Products Overview1:19

Installing R on Windows {Roger Peng}3:19

Install R on a Mac {Roger Peng}2:02

Installing Rstudio {Roger Peng}1:36

Installing Outside Software on Mac (OS X Mavericks)1:19

Conheça os instrutores

Jeff Leek, PhD
Associate Professor, Biostatistics
Bloomberg School of Public Health
Roger D. Peng, PhD
Associate Professor, Biostatistics
Bloomberg School of Public Health
Brian Caffo, PhD
Professor, Biostatistics
Bloomberg School of Public Health

This is a brief follow-up video to getting help and it's about finding answers.

The reason why there are two videos about this

is because it's such a critical skill in data science.

So you can see one of the three fundamental sort of,

skills you see in the Venn diagram here is Hacking Skills.

And the reason why it's one of the

three fundamental skill is because almost of none

of the knowledge that you will need is

already sort of set in standardized text books.

It's often scattered in a bunch of different places and you have to be

able to sort of synthesize it or find the information that you need about.

Whether it's about which data set you need to be using, or the statistical analysis

you need to be doing, or the R Package that you need to be using.

All of this is sort of scattered around, and you have to be willing

to do a little bit of hard work and elbow grease to find it yourself.

Obviously we'll tell you as much as we can

in lectures, but we're necessarily limited by the amount of

time that we can lecture every week, and so

it's important to be able to find that information yourself.

So key, some key characteristics packers are that

they're willing to go out and find the answers

on their own even if it takes a little bit of time or a little bit of effort.

They're knowledgeable about where to find those answers

whether its Google, or stack over glow, or cat.

Cross validated or a message fo history of mailing lists.

They're unintimidated by new data types or packages.

It's very common as a data scientist to be thrown a new kind of

data or a new kind of Our package that you need to learn very quickly

to be able to analyze the data to being unintimidated by that is important

and then being unafraid to say that you don't know the answer to a question.

And so a key characteristic I would say the way

to summarize it up is being alive but relentless here.

Going after the answer and you just trying to

find it But you're very polite while doing it.

And so Google knows this too.

In their hiring practices they're looking for these sort of characteristics.

The kind of people that will go after these sorts of

things as it's described in this article, I'm linked to here.

[SOUND] So an important question is where

to look for, for different types of questions.

So for our programming you might want to go

straight to the the archive of the class forums.

Where the class you're taking will focus on very specific questions or functions.

And there'll be a large group of interested people.

You could read the manual or help files

like I showed you in the getting help lecture.

You can search on the web.

That's actually one of the best ways to do it.

You can ask a skilled friend.

That's even better if you've got a person that you

know that already is a bit of a data scientist.

They can often help you out.

And then you can post to the class forums and try to get your answers.

Remember to be specific with your questions.

You can also post to forums outside of the class.

The R Mailing List or Stackoverflow, if you have R questions.

For data analysis or statistics type questions, you want to go to start

again with the class forums, and then go to the web or to friends.

And then there's another outside forum called CrossValidated

where you can ask these types of questions.

Brother software you might have to go to software specific websites.

So forget HUB, they have a lot of tutorials and

nice information that you can use to get answers there.

[SOUND] So an important point to know is that Googling

data science questions isn't always the easiest thing in the world.

So, the best place to start with if you

have a pretty general question is often in the forums.

And if people can direct you to where you should be searching outside of the forums.

Keep in mind that Stackoverflow with the tag R

is a really good place to get information about R.

And, so, you have to use this tag because if you just use

the letter R, it obviously is, sometimes, a little bit hard to search for.

You can also try the R mailing list

for software questions or CrossValidated for more general questions.

Usually what I've found is that if I'm going

to work in Google, searching Google, I use usually type

something like the data type and then data analysis or

I type the data type and then the R package.

I found that data type R package often works a

little bit better than data type, data analysis when Googling things.

Another thing to keep in mind is that data

analysis or data science is often called something different depending

on what kind of data you are looking at,

so for example medical data it might be called biostatistics.

For data from the web it might be data science.

For data in computer vision it might be machine learning

or natural language processing for data from text and so on.

So, knowing what the right word to Google is, is often half the battle.

And so, you can often find that out by posting to forums and

people will let you know what the right word to be googling is.

[SOUND] Again the credits for this go to Roger's Getting Help Video.

And it was inspired by Eric Raymond's How to Ask Questions the Right Way.

Explore nosso catálogo

Registre-se gratuitamente e obtenha recomendações, atualizações e ofertas personalizadas.

O Coursera proporciona acesso universal à melhor educação do mundo fazendo parcerias com as melhores universidades e organizações para oferecer cursos on-line.

© 2018 Coursera Inc. Todos os direitos reservados.

Baixar na App Store

Baixar no Google Play