0
1
00:00:00,510 --> 00:00:00,930
All right.
1

2
00:00:00,990 --> 00:00:06,660
So now that you know where the original data comes from and how to work with archive files and how to
2

3
00:00:06,660 --> 00:00:14,340
work with files that don't really have a good file extension, let's focus on how I would like you to work
3

4
00:00:14,430 --> 00:00:18,000
with the lesson resources that I've already included.
4

5
00:00:18,000 --> 00:00:23,520
These resources don't just include the spam emails, but also some image files and some fonts and I've
5

6
00:00:23,550 --> 00:00:28,180
organized everything very, very nicely for you in folders as well.
6

7
00:00:28,320 --> 00:00:30,470
So, you're welcome.
7

8
00:00:30,480 --> 00:00:35,780
Let's include the modules resources in Jupyter.
8

9
00:00:35,920 --> 00:00:36,240
All right.
9

10
00:00:36,270 --> 00:00:45,000
So on Windows, I've got my MLProject folder here in Jupyter and I have to pull up this folder here
10

11
00:00:45,540 --> 00:00:46,830
in Explorer.
11

12
00:00:47,490 --> 00:00:52,960
So this folder is located right here under "Users" and then my username,
12

13
00:00:53,130 --> 00:01:00,900
and if I open this up I can see that the same files that are listed here are here on Windows Explorer.
13

14
00:01:01,900 --> 00:01:04,250
So I've downloaded the lesson resources here.
14

15
00:01:04,330 --> 00:01:09,170
The "SpamData.zip" and if I double click on it,
15

16
00:01:09,310 --> 00:01:12,100
I open the "SpamData.
16

17
00:01:12,100 --> 00:01:13,180
zip" file.
17

18
00:01:13,300 --> 00:01:15,790
I have not extracted it.
18

19
00:01:15,790 --> 00:01:22,030
What you really need to do is right click on this thing and click "Extract All".
19

20
00:01:22,430 --> 00:01:23,150
OK.
20

21
00:01:23,200 --> 00:01:25,610
So now this is key.
21

22
00:01:26,050 --> 00:01:33,640
Let's see what happens if I leave the defaults and I just click "Extract". We'll twiddle our thumbs a bit
22

23
00:01:34,210 --> 00:01:38,200
and wait for this to complete.
23

24
00:01:38,200 --> 00:01:45,430
One thing you'll notice is that this works a lot faster with solid state drives than with regular hard
24

25
00:01:45,430 --> 00:01:47,620
drives. All right,
25

26
00:01:47,640 --> 00:01:50,440
now let's see what we've got.
26

27
00:01:50,440 --> 00:01:53,220
We've got SpamData.
27

28
00:01:53,230 --> 00:02:02,080
This is the extracted folder from here. If I double click on this, I have a nested folder here,
28

29
00:02:02,080 --> 00:02:09,730
"SpamData" and then I have this one here which we'll ignore or you can delete, but it's this folder here
29

30
00:02:09,730 --> 00:02:10,630
that you need.
30

31
00:02:10,630 --> 00:02:11,190
Right?
31

32
00:02:11,200 --> 00:02:15,740
So this is the one where you've got processing, training and testing.
32

33
00:02:15,820 --> 00:02:16,090
Right.
33

34
00:02:16,120 --> 00:02:25,990
So by default I've got a nested folder structure "SpamData" is inside another folder called "SpamData".
34

35
00:02:25,990 --> 00:02:33,720
Now, take this one here, the one inside and bring it over here.
35

36
00:02:33,730 --> 00:02:38,530
This thing here is just an artifact from me having zipped this file on a Mac.
36

37
00:02:38,620 --> 00:02:42,440
So you don't need to worry about this, you can just delete this file.
37

38
00:02:42,460 --> 00:02:44,370
It's not important.
38

39
00:02:44,370 --> 00:02:45,660
Now, here's the key.
39

40
00:02:45,700 --> 00:02:46,110
Right.
40

41
00:02:46,210 --> 00:02:52,470
Back in Jupyter notebook, we see the SpamData folder here come up and clicking on it,
41

42
00:02:52,600 --> 00:02:57,600
you see three folders. If you open this and you see another SpamData folder,
42

43
00:02:57,670 --> 00:03:03,010
then you've got a nested folder which you don't want and will cause problems later on.
43

44
00:03:03,010 --> 00:03:08,860
So this is the structure that we're really, really going for. The remainder of this module assumes that
44

45
00:03:08,860 --> 00:03:13,250
you've got this exactly the same way I'm doing this.
45

46
00:03:13,270 --> 00:03:15,220
You've got the same file names.
46

47
00:03:15,280 --> 00:03:16,690
You've got the same folder names.
47

48
00:03:16,780 --> 00:03:21,090
You've got the same folder structure and you've got the same location.
48

49
00:03:21,100 --> 00:03:23,260
This is how we're going to roll.
49

50
00:03:23,260 --> 00:03:31,150
So just double check that you're mirroring my setup here and that there is no accidental nested directories
50

51
00:03:31,270 --> 00:03:32,400
anywhere.
51

52
00:03:32,450 --> 00:03:37,200
And with that out of the way we're finally good to go.
52

53
00:03:37,270 --> 00:03:38,890
I'll see in the next lesson.
53

54
00:03:38,920 --> 00:03:39,420
Take care.