So let me give you an example that comes from whitten that’s used pretty ubiquitously to explain some of the concepts of machine learning and we won’t use this example too much but it’s it is useful for a variety of purposes so imagine you’re trying to predict when someone is going to play golf

Or play tennis or do some other outdoor activity and we imagine that it’s a function of the weather and so we take in inputs like the outlook whether it’s sunny or overcast or rainy the temperature whether it’s hot cool mild the humidity how windy it is and

We want to learn a function that takes in those inputs and produces a yes or no answer whether or not we play say golf okay and so the simplest version of this you might do just intuitively is just try to predict it with a simple rule so you might say look

Maybe we only play when it’s sunny you know is this true or not well no it’s not true because we find we can find examples where we did indeed play when it was overcast okay you might say well maybe we don’t play if it’s rainy and windy

And that turns out to be true but there’s also other times that we don’t play as well so the pattern that you know if a function exists that can predict this output well it’s perhaps not something that we can express in just one simple rule

Which is kind of the limit of what we can do you know mentally just through intuition so the idea is we need some principled way of coming up with more complex models when when they’re needed okay so fine so this some terminology this problem is an example of a classification problem where there’s

A learned attribute and it’s categorical it can take two values in this case zero or one uh if the learned attribute is more of a numeric value for example what our score at golf was you know as a function of the weather if you want to try to predict that that’d

Be more of a regression case okay and really not just learned attributes probably when all the attributes in americans becomes more of a classical regression case although there’s ways to handle this and so we’ve talked about regression in terms of you know fitting a curve to data but when you use that

Fit curve to actually make predictions that’s when it sort of you can see that it’s analogous to the classification problem over categorical data okay so more terminology the the golf example we just gave is an example of supervised learning where you’re given examples of inputs and the desired outputs and we’re trying to

Learn the relationship between them so we train a model to do this and there’s also notion of unsupervised learning which is you’re not given any labels whatsoever you’re just given the data and you’re trying to understand the underlying structure in that data okay so this is things like clustering Algorithms or dimension reduction

Algorithms if you’ve heard those terms before let me give you an example with that can be sort of cast as either supervised learning or unsupervised learning but it’s instructive as an unsupervised learning case uh for right now so imagine you’re just giving a big corpus of documents and you’re trying to figure out

You want to make a prediction of what topic a given document pertains to and so you know if you see the phrase the falcons trounce the saints on sunday you might guess that this document is about sports while if you see that the mars rover discovered organic molecules

On sunday you might guess that this document is about science and so you know how do you set this problem up as a machine learning problem you know what are the rows and columns we just had an example where there’s sort of rows and columns we said for one for one record we’re

Trying to predict the output given the inputs what are the rows and columns here well this shouldn’t be too bad since you’ve seen this before in a couple of assignments now You

Link to this course:

Simple Examples – Practical Predictive Analytics: Models and Methods

Data Science at Scale Specialization

Statistical experiment design and Analytics are at the heart of data science. In this course you will design statistical experiments and analyze the results using modern methods. You will also explore the common pitfalls in interpreting statistical arguments, especially those associated with big data. Collectively, this course will help you internalize a core set of practical and effective machine learning methods and concepts, and apply them to solve some real world problems.

Learning Goals: After completing this course, you will be able to:

1. Design effective experiments and analyze the results

2. Use resampling methods to make clear and bulletproof statistical arguments without invoking esoteric notation

3. Explain and apply a core set of classification methods of increasing complexity (rules, trees, random forests), and associated optimization methods (gradient descent and variants)

4. Explain and apply a set of unsupervised learning concepts and methods

5. Describe the common idioms of large-scale graph analytics, including structural query, traversals and recursive queries, PageRank, and community detection

Random Forest, Predictive Analytics, Machine Learning, R Programming

The topic the professor covers are awesome. Going from statistics to machine learning is something very awesome about this course,Nive that the course covered a broad range of topics. And good to get pushed to do some kaggle competition and peer review.

Follow a tour through the important methods, algorithms, and techniques in machine learning. You will learn how these methods build upon each other and can be combined into practical algorithms that perform well on a variety of tasks. Learn how to evaluate machine learning methods and the pitfalls to avoid.

Simple Examples – Practical Predictive Analytics: Models and Methods

Copyright Disclaimer under Section 107 of the copyright act 1976, allowance is made for fair use for purposes such as criticism, comment, news reporting, scholarship, and research. Fair use is a use permitted by copyright statute that might otherwise be infringing. Non-profit, educational or personal use tips the balance in favour of fair use.

00:03 so let me give you an example that comes

00:05 from

00:05 whitten that’s used pretty ubiquitously

00:07 to explain some of the concepts of

00:09 machine learning and

00:10 we won’t use this example too much but

00:12 it’s it is useful for a variety of

00:14 purposes

00:15 so imagine you’re trying to predict when

00:17 someone is going to play golf

00:18 or play tennis or do some other outdoor

00:20 activity and we imagine that it’s a

00:22 function of the weather and so we take

00:24 in inputs like

00:25 the outlook whether it’s sunny or

00:27 overcast or rainy the temperature

00:28 whether it’s hot cool mild

00:30 the humidity how windy it is and

00:34 we want to learn a function that takes

00:36 in those inputs and produces

00:37 a yes or no answer whether or not we

00:39 play say golf

00:41 okay and so the simplest version of this

00:44 you might do just intuitively is just

00:46 try to predict it with a

00:48 simple rule so you might say look

00:52 maybe we only play when it’s sunny you

00:54 know is this true or not

00:56 well no it’s not true because we find we

00:58 can find examples where we did indeed

00:59 play when it was overcast

01:01 okay you might say well maybe we don’t

01:03 play if it’s rainy and windy

01:04 and that turns out to be true but

01:06 there’s also other times that we don’t

01:07 play as well so

01:09 the pattern that you know if a function

01:11 exists that can predict this output

01:13 well it’s perhaps not something that we

01:16 can express in just one simple rule

01:17 which is kind of the limit of what we

01:19 can do

01:20 you know mentally just through intuition

01:22 so the idea is we need some

01:24 principled way of coming up with more

01:26 complex models

01:27 when when they’re needed okay

01:31 so fine so this some terminology this

01:34 problem is an example of a

01:35 classification problem where there’s

01:37 a learned attribute and it’s categorical

01:40 it can take two values in this case zero

01:41 or one

01:42 uh if the learned attribute is more of a

01:44 numeric value for example what our score

01:47 at golf was

01:48 you know as a function of the weather if

01:50 you want to try to predict that that’d

01:51 be more of a regression

01:53 case okay and really not just learned

01:56 attributes probably when all the

01:57 attributes in americans becomes more of

01:58 a classical regression case although

02:00 there’s ways to

02:01 handle this and so we’ve talked about

02:02 regression in terms of you know fitting

02:04 a curve to data but when you use that

02:06 fit curve to actually make predictions

02:08 that’s when it sort of you can see that

02:10 it’s

02:13 analogous to the classification problem

02:14 over categorical data

02:16 okay so more terminology the

02:20 the golf example we just gave is an

02:22 example of supervised learning where

02:23 you’re given examples of inputs and the

02:25 desired outputs and we’re trying to

02:26 learn the relationship between them so

02:28 we train a model to do this

02:30 and there’s also notion of unsupervised

02:31 learning which is you’re not given any

02:33 labels whatsoever you’re just given the

02:35 data and you’re trying to

02:36 understand the underlying structure in

02:39 that data

02:40 okay so this is things like clustering

02:42 algorithms or dimension reduction

02:44 algorithms if

02:44 you’ve heard those terms before let me

02:46 give you an example

02:48 with that can be sort of cast as either

02:50 supervised learning or unsupervised

02:52 learning but

02:53 it’s instructive as an unsupervised

02:54 learning case uh

02:56 for right now so imagine you’re just

02:58 giving a big corpus of documents

03:00 and you’re trying to figure out

03:04 you want to make a prediction of what

03:07 topic a given document pertains to and

03:10 so

03:10 you know if you see the phrase the

03:12 falcons trounce the saints on sunday you

03:13 might

03:15 guess that this document is about sports

03:17 while if you see that the

03:18 mars rover discovered organic molecules

03:20 on sunday you might guess that this

03:22 document is about

03:24 science and so you know how do you set

03:25 this problem up as a machine learning

03:27 problem

03:28 you know what are the rows and columns

03:29 we just had an example where there’s

03:31 sort of rows and columns

03:32 we said for one for one record we’re

03:33 trying to predict the output given the

03:35 inputs

03:35 what are the rows and columns here well

03:37 this shouldn’t be

03:39 too bad since you’ve seen this before in

03:41 a couple of assignments now

03:46 [Music]

03:46 you

PredictiveAnalyticsModels