1
00:00:01,110 --> 00:00:06,660
In this session, we're going to talk about plots and what can we do with them here?

2
00:00:06,700 --> 00:00:08,570
They are just like command.

3
00:00:08,580 --> 00:00:12,860
If you remove this person sign, then you can see each of them.

4
00:00:12,870 --> 00:00:17,040
Let's see the plot histogram for running this plant.

5
00:00:17,790 --> 00:00:24,780
I'm going to just select it and then F and F nine to see the histogram.

6
00:00:26,180 --> 00:00:28,500
Look at the information that we can see here.

7
00:00:28,520 --> 00:00:33,170
I can see the zero error and that's the only information that I have.

8
00:00:33,680 --> 00:00:43,430
But if you select the plot list and then check the help for this point, just F in an F one, you can

9
00:00:43,430 --> 00:00:49,700
see some information like the scene, the difference in Texas that you can use with this plot histogram

10
00:00:50,060 --> 00:00:53,720
by default, it just use this spawn, which is a simple part.

11
00:00:53,990 --> 00:01:00,000
But here we can have different errors and then give it a name or two and the name.

12
00:01:00,620 --> 00:01:08,210
And here we have another syntax for this plot histogram, which are declaring their beans as well.

13
00:01:09,260 --> 00:01:15,170
There are some more information and some examples, and you can just review them back here.

14
00:01:15,180 --> 00:01:16,850
I'm going to change it a little bit.

15
00:01:17,090 --> 00:01:25,190
Since I already defined in recalculating training validation, I calculated the training errors and

16
00:01:25,190 --> 00:01:32,870
I just defined with a variable name train errors, the same for validation, errors and testing errors.

17
00:01:33,400 --> 00:01:34,850
Here is what we were going to do.

18
00:01:35,570 --> 00:01:43,850
Let's just call the train errors and then give it a name like train.

19
00:01:45,860 --> 00:01:54,910
Errors and also I want to see the testing part or let's see the validation part while errors.

20
00:01:54,980 --> 00:02:02,420
This is the name of the variable and then give it a name like validation errors.

21
00:02:03,110 --> 00:02:06,200
Selectees can't run it.

22
00:02:07,130 --> 00:02:15,950
OK, here we can see more information now we can see the validation error showed by color of green and

23
00:02:15,950 --> 00:02:22,490
training error, which is color of blue, and we can see their names as we defined it here.

24
00:02:23,090 --> 00:02:27,350
Since we have three, let's just add the past or as well.

25
00:02:29,460 --> 00:02:34,260
Just this time, I'm going to type air to see the differences.

26
00:02:36,090 --> 00:02:41,940
OK, here we can also see the test errors here in this part, and this is a name that I gave.

27
00:02:42,810 --> 00:02:51,510
There are several things that you can do, even you can define a new plot, for example, for the plot

28
00:02:51,510 --> 00:02:52,180
histogram.

29
00:02:52,200 --> 00:02:55,940
We have another, which is his tweet.

30
00:02:56,430 --> 00:03:04,260
So if we want to see the feet that can use Heyst Ft code for the highest feed, you can select and see

31
00:03:04,620 --> 00:03:05,090
what order?

32
00:03:05,340 --> 00:03:06,070
Texas.

33
00:03:07,290 --> 00:03:12,480
We have several syntaxes like the data and then the number of means.

34
00:03:12,490 --> 00:03:14,220
So let's just check it here.

35
00:03:15,570 --> 00:03:16,980
Training errors.

36
00:03:16,980 --> 00:03:21,480
I want to see four train errors and I want to see for ten.

37
00:03:23,710 --> 00:03:24,730
Now let's run.

38
00:03:25,090 --> 00:03:33,130
I can see the photograph on days, you can select any of these options to see the information and of

39
00:03:33,130 --> 00:03:37,120
course, you can change the colors and the markings.

40
00:03:38,230 --> 00:03:42,190
Murrayville, we have another plot here, which is plot regression.

41
00:03:42,400 --> 00:03:50,800
You can do the same for the rest of them, just selected and F and F one to see difference in taxes

42
00:03:50,800 --> 00:03:52,170
for the plot regression.

43
00:03:52,180 --> 00:03:57,010
You can also choose your target and then the output and give it a name.

44
00:03:57,880 --> 00:04:00,860
OK, that's all you need to know about the plot.

45
00:04:02,020 --> 00:04:08,740
Not even a job to advance a scrape to satisfy your needs and the applications that you're looking for

46
00:04:08,740 --> 00:04:10,240
you for writing a paper.

47
00:04:10,810 --> 00:04:17,110
This amount of information would be enough for you to analyze different data, train and network and

48
00:04:17,110 --> 00:04:18,220
see the output.