Would you like to inspect the original subtitles? These are the user uploaded subtitles that are being translated:
1
00:00:02,720 --> 00:00:06,645
From the videos, you've seen
supervised learning and
2
00:00:06,645 --> 00:00:10,000
unsupervised learning and
also examples of both.
3
00:00:10,000 --> 00:00:13,500
For you to more deeply
understand these concepts,
4
00:00:13,500 --> 00:00:16,560
I'll like to invite you
in this class to see,
5
00:00:16,560 --> 00:00:18,930
learn and maybe
later write codes
6
00:00:18,930 --> 00:00:21,615
yourself to implement
these concepts.
7
00:00:21,615 --> 00:00:24,480
The most widely used tool
by machine learning and
8
00:00:24,480 --> 00:00:27,910
data science practitioners
today is the Jupyter Notebook.
9
00:00:27,910 --> 00:00:30,980
This is the default
environments that a lot of us
10
00:00:30,980 --> 00:00:34,585
use to code up and experiment
and try things out.
11
00:00:34,585 --> 00:00:38,210
In this class, right here
in your web browser,
12
00:00:38,210 --> 00:00:41,060
you build a user Jupyter
Notebook environment
13
00:00:41,060 --> 00:00:44,515
to test out some of these
ideas for yourself as well.
14
00:00:44,515 --> 00:00:48,245
This is not some made up
simplified environment,
15
00:00:48,245 --> 00:00:50,479
this is the exact
same environments,
16
00:00:50,479 --> 00:00:53,345
the exact same tool,
the Jupyter Notebook
17
00:00:53,345 --> 00:00:54,860
that developers are using in
18
00:00:54,860 --> 00:00:56,890
many large countries right now.
19
00:00:56,890 --> 00:00:59,180
One type of lab that
you see throughout
20
00:00:59,180 --> 00:01:01,130
this class are optional labs,
21
00:01:01,130 --> 00:01:04,340
which are ones you can
open and run one line at
22
00:01:04,340 --> 00:01:09,235
a time with usually no need
to write any code yourself.
23
00:01:09,235 --> 00:01:13,175
Optional labs are
designed to be very easy
24
00:01:13,175 --> 00:01:16,370
and I can guarantee you
will get full marks,
25
00:01:16,370 --> 00:01:19,535
every single one of them
because there are no marks.
26
00:01:19,535 --> 00:01:21,650
All you need to do is open it up
27
00:01:21,650 --> 00:01:24,220
and just run the
code we've provided.
28
00:01:24,220 --> 00:01:26,150
By reading through and running
29
00:01:26,150 --> 00:01:27,740
the code in the optional labs,
30
00:01:27,740 --> 00:01:31,255
you see how machine
learning code runs.
31
00:01:31,255 --> 00:01:35,090
You should complete
them relatively
32
00:01:35,090 --> 00:01:37,085
quickly just by running it
33
00:01:37,085 --> 00:01:39,875
one line at a time
from top to bottom.
34
00:01:39,875 --> 00:01:42,440
Optional labs are
completely optional
35
00:01:42,440 --> 00:01:43,550
so you don't have to do
36
00:01:43,550 --> 00:01:45,370
them at all if you
don't want to,
37
00:01:45,370 --> 00:01:47,915
but I hope you will take a look
38
00:01:47,915 --> 00:01:49,550
because running through them
39
00:01:49,550 --> 00:01:50,960
will give you a deeper feel,
40
00:01:50,960 --> 00:01:53,015
give you a little
bit more experience
41
00:01:53,015 --> 00:01:55,115
with what machine
learning algorithms,
42
00:01:55,115 --> 00:01:58,265
what machine learning
code actually looks like.
43
00:01:58,265 --> 00:02:00,410
Starting next week,
there'll also be
44
00:02:00,410 --> 00:02:02,630
some practice labs
which would give you
45
00:02:02,630 --> 00:02:04,610
an opportunity to write
some of that code
46
00:02:04,610 --> 00:02:07,190
yourself but we'll get
to that next week.
47
00:02:07,190 --> 00:02:08,250
Don't worry about it for
48
00:02:08,250 --> 00:02:10,325
now and I hope you
just go through
49
00:02:10,325 --> 00:02:12,230
the next optional lab and get
50
00:02:12,230 --> 00:02:14,960
through the rest of the
content for this week.
51
00:02:14,960 --> 00:02:18,260
Let's take a look at an
example of a notebook.
52
00:02:18,260 --> 00:02:19,860
Here's what you see when you
53
00:02:19,860 --> 00:02:21,870
go to the first optional lab.
54
00:02:21,870 --> 00:02:25,820
Feel free to scroll up and
down and browse and mouseover
55
00:02:25,820 --> 00:02:27,620
the different menus and take
56
00:02:27,620 --> 00:02:30,520
a look at the different
options here.
57
00:02:30,520 --> 00:02:32,450
You might notice that there are
58
00:02:32,450 --> 00:02:34,160
two types of these blocks,
59
00:02:34,160 --> 00:02:36,080
also called cells in
60
00:02:36,080 --> 00:02:39,475
the notebook and there
are two types of cells.
61
00:02:39,475 --> 00:02:43,365
One is what's called
a Markdown cell,
62
00:02:43,365 --> 00:02:46,035
which means a bunch of tax.
63
00:02:46,035 --> 00:02:48,260
Here you can actually
edit the text
64
00:02:48,260 --> 00:02:50,785
if you don't like the
text that we wrote,
65
00:02:50,785 --> 00:02:54,540
but this is text that
describes the code.
66
00:02:54,540 --> 00:02:57,245
Then there's a
second type of block
67
00:02:57,245 --> 00:02:59,900
or cell which looks like this,
68
00:02:59,900 --> 00:03:02,335
which has a code cell.
69
00:03:02,335 --> 00:03:04,770
Here, we've already
provided the code
70
00:03:04,770 --> 00:03:07,160
and if you want to
run this code cell,
71
00:03:07,160 --> 00:03:09,470
hitting Shift Enter will run
72
00:03:09,470 --> 00:03:12,695
the code in this code
cell, and by the way,
73
00:03:12,695 --> 00:03:14,735
if you click on a markdown cell,
74
00:03:14,735 --> 00:03:17,300
so this showing all
this formatting,
75
00:03:17,300 --> 00:03:20,780
go ahead and hit Shift
Enter on your keyboard as
76
00:03:20,780 --> 00:03:22,805
well and that will also convert
77
00:03:22,805 --> 00:03:25,765
back to this nicely
formatted text.
78
00:03:25,765 --> 00:03:29,300
This optional lab shows
some common Python code,
79
00:03:29,300 --> 00:03:31,010
so you can go ahead and run this
80
00:03:31,010 --> 00:03:33,835
afterwards in your
own Jupyter notebook.
81
00:03:33,835 --> 00:03:36,360
When you jump into this
notebook yourself,
82
00:03:36,360 --> 00:03:38,270
what I'd like you
to do is select
83
00:03:38,270 --> 00:03:41,320
the cells and hit Shift Enter.
84
00:03:41,320 --> 00:03:44,010
Read through the code,
see if it makes sense,
85
00:03:44,010 --> 00:03:46,100
try to make a prediction
about what you
86
00:03:46,100 --> 00:03:48,710
think this code
would do and then
87
00:03:48,710 --> 00:03:51,080
hit Shift Enter and
88
00:03:51,080 --> 00:03:53,465
then see what the
code actually does,
89
00:03:53,465 --> 00:03:54,980
and if you like it,
90
00:03:54,980 --> 00:03:57,125
feel free to go in
and edit the code,
91
00:03:57,125 --> 00:04:00,415
change the code, and then
run it and see what happens.
92
00:04:00,415 --> 00:04:02,010
If you haven't played in
93
00:04:02,010 --> 00:04:04,010
the Jupyter Notebook
environment for,
94
00:04:04,010 --> 00:04:05,840
I hope you become
more familiar with
95
00:04:05,840 --> 00:04:08,330
Python in a Jupyter Notebook.
96
00:04:08,330 --> 00:04:10,790
I spend a lot of hours
playing around in
97
00:04:10,790 --> 00:04:12,470
Jupyter notebooks and so I
98
00:04:12,470 --> 00:04:14,680
hope you have fun with them too.
99
00:04:14,680 --> 00:04:17,090
After that, I look
forward to seeing you
100
00:04:17,090 --> 00:04:19,160
in the next video
where we'll take
101
00:04:19,160 --> 00:04:22,070
the supervised learning
problem as start to flesh
102
00:04:22,070 --> 00:04:25,535
out our first supervised
learning algorithm.
103
00:04:25,535 --> 00:04:26,960
I hope that will
be fun to you and
104
00:04:26,960 --> 00:04:29,190
look forward to
seeing you there.7506
Can't find what you're looking for?
Get subtitles in any language from opensubtitles.com, and translate them here.