Story behind Meghan Markle's shocked face: Duchess's priceless reaction
'Come here!' Astonished Meghan finally embraces student she encouraged not to drop out of university despite gruelling hospital treatment with messages and support videos on Instagram
A young woman who confided about her health battle with Meghan Markle has met the astonished Duchess of Sussex in person after she spotted her among the crowds in New Zealand
Hannah Sergel was among the huge crowd that turned out to greet Meghan and Prince Harry at the Viaduct Harbour in Auckland, on the country's North Island Tuesday
The 20-year-old and Meghan used to message one another on Instagram before the Duchess deleted her account following her engagement to Prince Harry
Before she got together with her now husband, Meghan sent the young woman a short video clip and messages of inspiration encouraging her to be herself and work hard at university
Hannah, who talks about her battle with mental health on Instagram, was left in tears of joy when the Duchess, in a £1,728 custom cream dress by Brandon Maxwell, recognised her among the thousands of adoring royal fans
It came at the end of the final day of their visit, during which the couple were also gifted Maori coats in a traditional ceremony and visited a Kiwi hatchery before taking part in a redwood walk
Meghan was also seen playing with a little girl in an adorable floral print dress while meeting the crowds in Rotorua
It nearly brings to a close a jam-packed 16-day visit, which has seen the royal couple welcomed in Australia, New Zealand, Tonga and Fiji
They will fly back to London from Auckland tomorrow
Meghan's jaw dropped the moment she spotted Hannah, who had flown across the country for the chance to meet her idol
'Oh my god', the Duchess exclaimed as she rushed over to greet Hannah, who was holding a 'It's Hannah from Instagram' sign
The Duchess gave Hannah a warm hug and accepted a letter she had written
It was the first time the pair had met in person
'I was friends with her on Instagram before she had to deactivate her account
We used to have conversations and stuff on there,' Hannah told 1 News
'She would tell me to do well at university and encourage me to be myself'
Hannah said she was left 'so shaky and flustered' following the encounter, adding Meghan's jaw-dropping reaction 'means the world to me'
The Duchess told Hannah 'Thank you for getting in touch' and 'said she would read my letter that I gave her'
Hannah told 9Honey: 'She recognised me and knew who I was so that's why she came over'
She gave me a hug which was incredible - when I first saw her I cried
She's just such an incredible person and I'm just so glad she's happy with Harry,' she said
She later posted on Twitter how shocked she was to finally met her idol
'Can you believe Meghan Markle held me with both her hands then went in for a hug
I'm still in shock,' she wrote
'Meghan said "come here" before hugging me'
Hannah has been a fan of the Duchess long before she became a royal - she was the co-founder of the Meghan Markle Daily Twitter account in 2015, which bills itself as 'Your #1 source for all things about the Duchess of Sussex, Meghan Markle'
Hannah told Daily Mail Australia she first followed Meghan on Instagram in 2015 and the then actress followed her back in January 2016
She said their initial conversations 'were mainly just small comments on each other's photos, a couple of well wishes and other small direct messages'
Hannah said the Duchess has been an inspirational figure in her life
'She has inspired me to be the best version of myself that I can be,' she said
'She has inspired me to keep going when things get tough and to always be kind
'I admire her willingness to try new things, her intellect and how she uses her public platform to inspire change within the world'
More than two years ago, Hannah had posted a video to her Instagram page which was captured by a friend
The footage included a personal message for Hannah - 'sending you lots of love, hope I get to see you soon'
'Love you so much Meghan Markle - thank you for the lovely video and I hope I get to meet you soon too *cries of happiness*,' she wrote in a caption accompanying the video
New Zealand prime minister Jacinda Ardern had comforted Hannah following the encounter
She then personally sent her a photo of Meghan's priceless reaction through private message
'Can you believe I was such a mess that the prime minister of New Zealand had to comfort me,' Hannah posted on Twitter
The public walkabout in Auckland was held on Tuesday, the third day of the royal couple's tour of New Zealand
The Duke and Duchess are spending Wednesday in Rotorua before flying home to London
The day ended with a redwood walk, during which she wore a Norrona Oslo Lightweight jacket, which cost £391, a pair of Mother denim jeans and Blackbird flats, previously seen in 2016
It brings to an end a marathon 16-day tour of Australia, Fiji, Tonga and New Zealand - the first royal tour for the Duke and Duchess since their May wedding
Meghan Markle wears a traditional Maori cloak made from pheasant feathers to protect her during pregnancy as she and Prince Harry begin the final day of their marathon royal tour
The Duke and Duchess of Sussex have arrived in Rotorua, New Zealand for the final day of their mammoth first royal tour as a married couple
.Prince Harry and Meghan are spending the last day of their 16-day regional tour in the central North Island town taking in the local culture and nature
The sound of a conch shell signalled the start of the welcome ceremony at Te Papaiouru Marae - a Māori meeting house - for the royal couple before a powerful haka on the shores of Lake Rotorua
The Duchess wore a $3,873 (£2,159/US$2,743) navy midi dress by acclaimed British designer Stella McCartney and paired her chic ensemble with a traditional New Zealand necklace and her $882 (£556/US$625) navy Manolo Blahnik BB stilettos
In sparkling weather - the best they've encountered in New Zealand so far - the pair were gifted korowai, traditional Māori woven cloaks, which they wore over their attire
The korowai were presented by the people of Te Arawa, honouring Meghan's impending motherhood and the significance of female ancestors
The couple then passed through a procession of children and elders, before taking their shoes off to step into the meeting house
Prince Harry gave a speech in Māori - with clear pronunciation - thanking his hosts and saying the cloaks would be treasured by his family, adding he was pleased to be spending time in Rotorua
He then led a song, singing all of the words to 'Te Aroha' in Māori
The royal couple attended a lunch, including a traditional Māori steamed hangi meal, with their hosts, before heading off to their next engagement of the day
Next on the agenda was a visit to a kiwi bird hatchery where they got to name a pair of the rotund, flightless birds and meet conservationists protecting the species
The royals will later take a public stroll through Rotorua's gardens, go walking through a redwood forest and meet with the local mountain biking community before departing the country
The Queen previously visited Rotorua in 1954
New Zealand was the final stop on the couple's tour, after visiting Australia, Fiji and Tonga
The tour has been a memorable one for the Duke and Duchess, who announced on the day of their arrival in Australia they were expecting their first child in the northern Spring
Meghan's 'Diana moment': Duchess appears to flash her legs through her bespoke Givenchy skirt during walkabout in New Zealand - but all is not what it seems
The Duchess of Sussex appeared to have a 'Diana moment' in New Zealand today - as she looked to have flashed her legs through her Givenchy skirt
Meghan, 37, seemed to show off more than she bargained for in photographs taken during a walkabout in Rotorua today on the final day of the royal tour
However, it was in fact simply an optical illusion created by the skirt's heavy woven fabric 'strobing on camera'
Meanwhile, the stripe design of the skirt also created the illusion of Meghan's underwear - at the point where the lighter stripes become darker again
The images recall the famous photograph taken of the late Princess of Wales in 1980, in which her legs were revealed through her sheer lace skirt
Explaining what had caused the optical illusion, stylist Lucas Armitage told FEMAIL: 'Certain fabrics with a heavy woven effect can strobe on camera
Strobing is something you may have noticed on TV when someone is wearing stripes or check patterns and this causes an optical illusion which creates a moving flickering look
'I suspect this is what is happening here and the fabric is thick heavily woven piece creating a camera strobe and the illusion its sheer'
Meghan, who is expecting her first child in the Spring, teamed her bespoke Givenchy pleated skirt, which featured thick royal blue stripes and thinner white stripes, with a co-coordinating jumper, also by the French fashion house
She finished off her chic look with a pair of navy Manolo Blahnik BB heels, priced at £556, while wearing her locks in a messy bun
The Duchess looked in high spirits as she greeted crowds in Rotorua, on one of her final engagements of the royal tour
Following the walkabout, she and Harry visited the Redwoods Tree Walk in Rotorua for the final engagement of their 16-day long tour
The couple will now fly back to London tomorrow, following their 16-day tour of Australia, Fiji, Tonga and New Zealand
Meghan's apparent fashion mishap today came after she opted for a daring striped dress by US brand Reformation on Fraser Island last week, which featured a thigh-high split
Some compared Meghan's frock to Diana's white lace skirt, with the Duchess displaying her legs through the semi-sheer fabric
For more infomation >> Story behind Meghan Markle's shocked face: Duchess's priceless reaction - Duration: 10:05.-------------------------------------------
Alternative to Cable Ep. 4- Streaming Services - Duration: 7:07.
Hi everybody, this is Brad.
Welcome back to the series of alternatives to cable.
The previous three videos
focused on the three free choices
and this video will focus on
the two monthly subscription costs.
I was originally going to do
each one of these individually
but they're pretty much the same.
The only thing that differs is whether
you can watch live TV or not.
Next week we will have the hardware.
Our next episode we will have the hardware.
So let us start to go into this.
All right.
So, the most famous
and probably first
streaming service was Netflix.
They have agreements with most stations
to show
complete seasons,
up to the previous
season of the current show.
So that means if the show is still on
and...creating episodes,
they're not going to get that season,
until the next season starts.
For shows that are over
they have the complete season series or nothing.
They're constantly changing though
because they have to enter into agreements with
the studios that produce the TV shows and movies.
And so every month
it's a rotating list of shows
that drop off and
they add new shows and movies.
They have really started to ramp up
their original programming.
And I believe they want to have 50%
original programming by I want to say 2025.
I think something like that.
They have a pretty good selection.
The movies aren't fantastic.
And you can see any time, here,
if you have new episodes
it'll show you the new episodes.
And if I click play
you can see it goes to the episode.
and you can see a very similar kind of player
as we saw with
the network channels or the cable channels
all that kind of stuff.
You can still drag. you can pause.
Here's your volume control.
These are closed captions.
There's full screen.
Out of full screen.
One thing that's different here,
as you can see,
you can jump between the episodes
in the episode.
Which is something
that most of the network stations do not have.
I can go back to season 1.
and play from there.
So it's pretty simple.
You just have to
I would say look at what is there
and see if it's for you.
As far as pricing goes...
So this is actually a pretty good one
because you can actually get away
with this plan, this option,
without even having the internet connection.
So you can see I can I only have streaming.
but I can add at DVD plan.
That means this was how it originally was.
Where you can check out 2 discs at a time for $12
You could have both if you like.
I have my streaming plan, here.
So that's what it costs a month.
So it's it's fairly affordable all things considered.
As we get on to other ones,
you'll see how that is.
One thing you can do, here, is you can
create different profiles.
And that means that
different profiles can have different lists.
So you can see my wife and I have our own profiles.
So that's Netflix.
The next one I don't have a subscription.
So I will just mention the other ones.
Amazon has their Amazon Prime.
And that Prime is the same as
getting the free two-day shipping.
But you also get access to the movies and TV shows
that they have.
They also have their original programming.
They're also having to make agreements with
the TV shows and movie studios
and they're constantly dropping and adding.
So it's the same basic thing.
Just a different choice.
Hulu is a good one to transition from.
So, Hulu you have
the traditional
Netflix, Amazon Prime
on demand but not watching live TV.
But they also have now a live TV offering.
So you can see they have the same thing.
They have originals
and they have other movies and TV shows
that they have agreements with.
This is really the first option
that we're talking about that has sports.
So you can you can check that out.
The first live TV around
was something called Sling TV.
And 25 bucks a month
you can watch live TV.
And here are your shows.
For these plans
just give you different
TV packages for different channels
like cable does
And obviously the the more you pay
the more channels you get.
One thing that this doesn't have
it has sports but
it does not have NESN.
For NESN you would have to go to something like
Youtube TV.
You can see it getting kind of crazy here.
So it's $40 a month,
plus your internet connection.
But this does have NESN.
So that means that if your Boston sports fan.
Bruins and Patriot, non Patriots, Red Sox,
This, and you want to get rid of cable
This would be the option that you would want.
The last option
is something called
PlayStation Vue.
So this is a PlayStation gaming console.
And that also has NESN.
And you can see that it's getting even even pricier.
They have a lot more channels.
but, again, each one of these options
has to make the agreement with each of the TV shows,
the stations.
And this is live TV so you can see..
This one's interesting, right?
So it's showing you all the possible channels
that you would have.
But the low end doesn't have these
grayed out ones.
So you can see that the higher you go
the more channels you get.
This one has
movie channels.
Independent film channel
Stuff like that.
So that is it.
As far as
live and
on-demand
live streaming stations.
If these are interest to you
then just just check out...
I would go to each one of them
and check out what
channels they have
and see if those channels
have the shows you
want to watch.
Alright, that's it for this week.
iI you have any questions please
comment below or
you can get in touch with me at
BMcKenna@wilmlibrary.org
Or you just call the library.
I'm usually here.
Okay. Thanks, bye.
-------------------------------------------
Audi A4 2.0 TDI 150pk Innovation Edition S tronic | Virtual Cockpit | - Duration: 1:07.
For more infomation >> Audi A4 2.0 TDI 150pk Innovation Edition S tronic | Virtual Cockpit | - Duration: 1:07. -------------------------------------------
Volkswagen up! 1.0I Move Up! - Duration: 0:52.
For more infomation >> Volkswagen up! 1.0I Move Up! - Duration: 0:52. -------------------------------------------
Opel KARL 1.0 75pk ROCKS Online Edition *Navi Europa* - Duration: 1:08.
For more infomation >> Opel KARL 1.0 75pk ROCKS Online Edition *Navi Europa* - Duration: 1:08. -------------------------------------------
Opel Corsa 1.2 Twinport, 85pk 5 deurs, Business+ ** NAVI, ECC, LMV ** - Duration: 1:05.
For more infomation >> Opel Corsa 1.2 Twinport, 85pk 5 deurs, Business+ ** NAVI, ECC, LMV ** - Duration: 1:05. -------------------------------------------
КОРОЧЕ ГОВОРЯ, ХЭЛЛОУИН (МЁРТВЫЙ ДР, БАЛДИ, ГРЕННИ, МОМО, ХОРРОР) | Halloween - Duration: 30:49.
Топ
Лайк
-------------------------------------------
J Trudeau - Duration: 2:53.
it's like I just love stoner you know it's just like I just know it's bad but
it's just like can I rip off your bong and can we get a little higher 4:20 pipe smoki'
sitting alone in my dorm room tokin' all buzzed funny
wastin' mom and dad's money effects on my brain are more than minimal at least I'm
no longer a criminal to lit on these gases failing all my classes
every PM's against it though why is it even bad yo I just wanna smoke some dope
Good thing I voted for J Trudeau!
Baby let's get high J Trudeau!
So easy to access when it's right in front of ya could get marijuana induced schizophrenia
but at least I won't get arrested at least I'm not depressed eh? rent has to
wait when I'm running out not allowed to stay at my mom and dad's house
nowhere to go least I got the dank kush though my family won't look me in the
eye I've racked up a couple DUIs can't be happy without getting high
why was marijuana legalized?
Baby let's get high J Trudeau!
Baby let's get high J Trudeau!
here I go
To the end of this bag
so my skin stops to crawl
I'm shitting myself without it
I should probably go to rehab
and waste some tax dollars
baby let's get high J Trudeau
baby let's get high J Trudeau
-------------------------------------------
В.М.Зельдин-Творч.вечер ,02.03.2016г,Дом офицеров -СПб(J.St) - Duration: 48:02.
For more infomation >> В.М.Зельдин-Творч.вечер ,02.03.2016г,Дом офицеров -СПб(J.St) - Duration: 48:02. -------------------------------------------
Halloween in the D - Duration: 3:04.
For more infomation >> Halloween in the D - Duration: 3:04. -------------------------------------------
Hyundai i10 1.1 Pure 104851 KM, 5 Drs. - Duration: 1:05.
For more infomation >> Hyundai i10 1.1 Pure 104851 KM, 5 Drs. - Duration: 1:05. -------------------------------------------
Renault Grand Modus 1.6-16V Expression nieuwstaat, 22061 KM. - Duration: 1:06.
For more infomation >> Renault Grand Modus 1.6-16V Expression nieuwstaat, 22061 KM. - Duration: 1:06. -------------------------------------------
Doubts For Voice / Advice - WhatsApp - IberoPistacho - Duration: 1:36.
For more infomation >> Doubts For Voice / Advice - WhatsApp - IberoPistacho - Duration: 1:36. -------------------------------------------
Audi A6 Avant 2.0 TDI | NAVI | ECC | CRUISE | TREKHAAK | XENON - Duration: 1:07.
For more infomation >> Audi A6 Avant 2.0 TDI | NAVI | ECC | CRUISE | TREKHAAK | XENON - Duration: 1:07. -------------------------------------------
"Mystery Box" fun with 104.1 KRBE's Special K - Duration: 9:12.
For more infomation >> "Mystery Box" fun with 104.1 KRBE's Special K - Duration: 9:12. -------------------------------------------
Crimestoppers: $100K reward offered in Tamara Green's murder - Duration: 2:16.
For more infomation >> Crimestoppers: $100K reward offered in Tamara Green's murder - Duration: 2:16. -------------------------------------------
Mehboob ko apne pas bulane ka Amal || spell bring someone back you - do reconciliation spells work - Duration: 1:56.
plz subccribe my channle
-------------------------------------------
Supervised Machine Learning: Crash Course Statistics #36 - Duration: 11:51.
Hi, I'm Adriene Hill, and welcome back to Crash Course Statistics. We've covered a
lot of statistical models, from the matched pairs t-test to linear regression. And for
the most part, we've used them to model data that we already have so we can make inferences
about it.
But sometimes we want to predict future data. A model that predicts whether someone will
default on their loan could be very helpful to a bank employee. They're probably not
writing scientific papers about why people default on loans, but they do care about accurately
predicting who will.
Many types of Machine Learning (ML) do just that: build models to predict future outcomes.
And this field has exploded over the past few decades. Supervised Machine Learning takes
data that already has a correct answer, like images that have been labeled as "cat"
or "not a cat", or the current salary of a company's CEO, and tries to learn how
to predict it. It's supervised because we can tell the model what it got wrong.
It's called Machine Learning because instead of following strict rules and instructions
from humans, the computers (or machines) learn how to do things from data.
Today, we'll briefly cover a few types of supervised Machine Learning models, logistic
regression, Linear Discriminant Analysis, and K Nearest Neighbors.
Intro
Say you own a microloan company. Your goal is to give short term, low interest loans
to people around the world, so they can invest in their small businesses. You have everyone
fill out an application that asks them to specify things like their age, sex, annual
income, and the number of years they've been in business.
The microloan is not a donation, the recipient is supposed to pay it back. So you need to
figure out who is most likely to do that.
During the early days of your company, you reviewed each application by hand and made
that decision based on personal experience of who was likely to pay back the loan.
But now you have more money and applicants than you could possibly handle. You need a
model--or algorithm--to help you make these decisions efficiently.
Logistic regression is a simple twist on linear regression. It gets its name from the fact
that it is a regression that predicts what's called the log odds of an event occuring.
While log odds can be difficult, once we have them, we can use some quick calculations to
turn them into probabilities, which are a lot easier to work with. We can use these
probabilities to predict whether an individual will default on their loan.
Usually the cutoff is 50%. If someone is less than 50% likely to default on their loan,
we'll predict that they'll pay it off. Otherwise, we'll predict that they won't
pay off their loan.
We need to be able to test whether our model will be good at predicting data it's never
seen before. Data it doesn't have the correct answer for. So we need to pretend that some
of our data is "future" data for which we don't know the outcome.
One simple way to do that is to split your data into two parts.
The first portion of our data, called the training set, will be the data that we use
to create--or train--our model. The other portion, called the testing set, is the data
we're pretending is from the future. We don't use it to train our model.
Instead, to test how well our model works, we withhold the outcomes of the test set so
that the model doesn't know whether someone paid off their loan or not, and ask it to
make a prediction.
Then, we can compare these with the real outcomes that we ignored before.
We can do this using a what's called a Confusion Matrix. A Confusion Matrix is a chart that
tells us what actually happened--whether a person paid back a loan--and what the model
predicted would happen.
The diagonals of this matrix are times when the model got it right. Cases where the model
correctly predicted that the person will default on the loan is called a True Positive. "True"
because it got it right. "Positive" because the person defaulted on their loan.
Cases where the model correctly predicted that a person will pay back the loan are called
True Negatives. Again "true" because it made the correct prediction, and "negative"
because the person did not default.
Cases where the model was wrong are called False Negatives--if the model thought that
they would not default--and False Positives--if the model thought they would default.
Using current data and pretending it was future data allows us to see how this model performed
with data it had never seen before.
One simple way to measure how well the model did is to calculate its accuracy. Accuracy
is the total number of correct classifications--Our True Positives and True Negatives--divided
by the total number of cases. It's the percent of cases our model got correct.
Accuracy is important. But it's also pretty simplistic. It doesn't take into account
the fact that in different situations, we might care more about some mistakes than others.
We won't touch on other methods of measuring a model's accuracy here, but it's important
to recognize that in many situations, we want information above and beyond just an accuracy
percentage.
Logistic regression isn't the only way predict the future. Another common model is Linear
Discriminant Analysis or LDA for short. LDA uses Bayes' Theorem in order to help us
make predictions about data.
Let's say we wanna predict whether someone would get into our local state college based
on their high school GPA. The red dots represent people who did not
get in, green are people who did.
If we make a couple of assumptions, we can estimate the GPA distributions of people who
did, and did not get their acceptance letter.
If we find a new student who wants to know if they will get in to your local state school,
we use Bayes Rule and these distributions to calculate the probability of getting in
or not.
LDA just asks, "Which category is more likely?" If we draw a vertical line at their GPA, whichever
distribution has a higher value at that line is the group we'd guess.
Since this student, Analisa has a 3.2 GPA, we'd predict that she DOES get in. Since
it's more likely under the "got in" distribution.
But we all know that GPA isn't everything. What if we looked at SAT Scores as well.
Looking at the distributions of both GPA and SAT scores together can get a little more
complicated. And this is where LDA becomes really helpful.
We want to create a score, we'll call it Score X, that's a linear combination of
GPA and SAT scores. Something like this: We, or rather the computer, want to make it
so that the Score X value of the admitted students is as different as possible from
the Score X value of the people who weren't admitted.
This special way of combining variables to make a score that maximally separates the
two groups is what makes LDA really special.
So, Score X is a pretty good indicator of whether or not a student got in. AND that's
just one number that we have to keep track of, instead of two: GPA and SAT score.
For this sample, my computer told me that this is the correct formula:
Which means we can take the scatter plot of both GPA and SAT score and change it into
a one-dimensional graph of just Score X.
Then we can plot the distributions and use Bayes Rule to predict whether a new student,
Brad, is going to get into this school.
Brad's Score X is 8, so we predict that he won't get in, since with a score X of
8, it's more likely that you won't get in than that you will.
Creating a score like Score X can simplify things a lot. Here, we looked at two variables,
which we could have easily graphed. But, that's not the case if we have 100 variables for
each student. Trust me, you don't want your college admissions counselor making admissions
decisions based on a graph like that.
Using fewer numbers also means that on average, the computer can do faster calculations. So
if 5 million potential students ask you to predict whether they get in, using LDA to
simplify will speed things up.
Reducing the number of variables we have to deal with is called Dimensionality Reduction,
and it's really important in the world of "Big Data". It makes working with millions
of data points, each with thousands of variables, possible.
That's often the kind of data that companies like Google and Amazon have.
The last machine learning model we'll talk about is K-Nearest Neighbors.
K-Nearest Neighbors...or KNN for short...relies on the idea that data points will be similar
to other data points that are near it.
For example, let's plot the height and weight of a group of Golden Retrievers, and a group
of Huskies:
If someone tells us a height and weight for a dog--named Chase--whose breed we don't
know...we could plot it on our graph.
The four points closest to Chase are Golden Retrievers, so we would guess he's a Golden
Retriever.
That's the basic idea behind K-Nearest Neighbors! Whichever category--in this case dog breed--has
the more data points near our new data point is the category we pick.
In practice it is a tiny bit more complicated than that. One thing we need to do is decide
how many "neighboring" data points to look at.
The K in KNN is a variable representing the number of neighbors we'll look at for each
point--or dog--we want to classify.
When we wanted to know whether Chase was a Husky or a Golden Retriever, we looked at
the 4 closest data points. So K equals 4. But we can set K to be any number.
We could look at the 1 nearest neighbor. Or 15 nearest neighbors. As K changes, our classifications
can change. These graphs show how points in each area of the graph would be classified.
There are many ways to choose which k to use. One way is to split your data into two groups,
a training set and a test set. I'm going to take 20% of the data, and ignore
it for now.
Then I'm going to take the other 80% of the data and use it to train a KNN classifier.
A classifier basically just predicts which group something will be in. It classifies
it. We'll build it using k equals 5.
And we get this result: Where blue means Golden Retriever. And red means Husky.
As you can see, the boundaries between classes don't have to be one straight line. That's
one benefit of KNN. It can fit all kinds of data.
Now that we have trained our classifier using 80% of the data, we can test it using the
other 20%. We'll ask it to predict the classes of each of the data points in this 20% test
set. And again, we can calculate an accuracy score. This model has 66.25% accuracy. But
we can also try out other K's and pick the one that has the best accuracy.
It looks like using a k of 50 hits the sweet spot for us. Since the model with k equals
50 has the highest accuracy of predicting Husky vs. Golden Retriever. So, if we want
to build a KNN classifier to predict the breed of unknown dogs, we'd start with a K of
50.
Choosing model parameters--variables like k that can be different numbers--can be done
in much more complex ways than we showed here, or could be done using information about the
specific data set you're working with . We not going to get into alternative methods
now, but if you're ever going to build models for real, you should look it up.
Machine Learning focuses a lot on prediction. Instead of just accurately describing our
current data, we want it to pretty accurately predict future data.
And these days, data is BIG. By one estimate, we produce 2.5 QUINTILLION bytes of data per
day. And supervised machine learning can help us harness the strength of that data.
We can teach models or rather have the models teach themselves how to best distinguish between
groups like will pay off a loan and those that won't. Or people who will love watching
the new season of The Good Place `and those that won't.
We're affected by these models all the time. From online shopping, to streaming a new show
on Hulu, to a new song recommendation on Spotify. Machine learning affects our lives everyday.
And it doesn't always make it better we'll get to that. Thanks for watching. I'll see you next time.
No comments:
Post a Comment