﻿1
00:00:00,133 --> 00:00:01,500
That was my friends.

2
00:00:01,500 --> 00:00:03,300
Disillusion and congratulations.

3
00:00:03,300 --> 00:00:07,600
Really, if you got this right, because
you had to pay attention to two things.

4
00:00:07,600 --> 00:00:09,833
First, the right format of the 2D array

5
00:00:09,833 --> 00:00:13,733
here for your input
and then transforming that input.

6
00:00:13,766 --> 00:00:17,766
You know, those features to get the right
skill for your predict method.

7
00:00:18,033 --> 00:00:18,900
Okay. Perfect.

8
00:00:18,900 --> 00:00:21,600
So now we're actually ready to run this.

9
00:00:21,600 --> 00:00:24,833
But we'll actually get a better output,
you know, nicer one

10
00:00:25,100 --> 00:00:27,966
if we put all this into a print

11
00:00:27,966 --> 00:00:31,466
you know,
print that output of the predict method.

12
00:00:31,966 --> 00:00:33,833
And now let's press play.

13
00:00:33,833 --> 00:00:39,000
And remember let's see if our classifier
manages to predict the right outcome.

14
00:00:39,000 --> 00:00:42,866
Meaning the right purchase decision,
which according to the test set

15
00:00:42,866 --> 00:00:47,533
which contains the real result is zero,
meaning that first customer of age

16
00:00:47,533 --> 00:00:52,933
30 and $87,000
estimated salary doesn't buy that new SUV.

17
00:00:53,100 --> 00:00:58,133
Okay, so let's press play and let's
see if it is zero and great, it is zero.

18
00:00:58,200 --> 00:00:59,000
So good job.

19
00:00:59,000 --> 00:01:03,933
Our model did amazing here on this
single observation single customer.

20
00:01:04,600 --> 00:01:05,066
Great.

21
00:01:05,066 --> 00:01:05,566
So now

22
00:01:05,566 --> 00:01:09,433
we're going to move on to the next step
which will be to predict the test results.

23
00:01:09,600 --> 00:01:12,300
So that I'm sure you know
exactly how to do.

24
00:01:12,300 --> 00:01:14,633
Just make sure to figure out
if you need to apply feature

25
00:01:14,633 --> 00:01:17,633
scaling or not,
and you will get to the right solution.

26
00:01:18,066 --> 00:01:22,333
Also, I would like you to please display
you know, the vector of predictions.

27
00:01:22,333 --> 00:01:25,566
You know the vector of predicted
purchase decisions for the test set

28
00:01:25,833 --> 00:01:27,133
and the vector of the

29
00:01:27,133 --> 00:01:30,600
real purchase decisions at the same test
sit next to each other

30
00:01:30,933 --> 00:01:33,900
and you don't have to figure out
how to implement that.

31
00:01:33,900 --> 00:01:36,333
Again, remember
I want you to be efficient,

32
00:01:36,333 --> 00:01:39,300
so I encourage you
to take that little piece of code

33
00:01:39,300 --> 00:01:44,100
we made in many of the regression models
to display this efficiently.

34
00:01:44,100 --> 00:01:46,966
And that's exactly what we'll do together
in the next tutorial.

35
00:01:46,966 --> 00:01:48,966
So until then, enjoy machine learning.
