Would you like to inspect the original subtitles? These are the user uploaded subtitles that are being translated:
1
00:00:12,330 --> 00:00:14,310
Hi, everyone, and welcome in this new video.
2
00:00:14,940 --> 00:00:20,720
In this video, we're all going to see the main point of this chapter, which is the training of our
3
00:00:20,730 --> 00:00:27,930
linear regression, though we have already seen the theory behind the linear regression.
4
00:00:28,290 --> 00:00:40,310
And even for those of you which are not very comfortable with this notion, you will see that the practice,
5
00:00:40,320 --> 00:00:43,350
it's really much easier.
6
00:00:46,190 --> 00:00:56,030
To create a linear regression, we need to import the linear regression class from psychedelia to do
7
00:00:56,030 --> 00:00:56,300
it.
8
00:00:56,870 --> 00:01:00,900
We use the from import operator.
9
00:01:00,930 --> 00:01:13,160
So from psychic points linear model, we want to import the class linear regression.
10
00:01:19,950 --> 00:01:24,060
Then we need to initialize the class to do it.
11
00:01:24,090 --> 00:01:36,180
We're going to create a variable containing this class, and I have chosen to begin this course with
12
00:01:37,140 --> 00:01:44,750
their first model as a linear regression because we don't need to specify some parameter.
13
00:01:44,850 --> 00:01:54,360
So it's really much easier to you to understand your first machine learning algorithm so you don't need
14
00:01:54,360 --> 00:02:03,720
to put any parameters because the few parameters for this class is set by default.
15
00:02:04,560 --> 00:02:12,990
And then to fit the model, we just needed to use the function of the ranking class.
16
00:02:13,620 --> 00:02:26,490
So in parameters, we need to give the feature so extreme and the target because a linear regression
17
00:02:26,490 --> 00:02:29,190
is a supervised machine learning model.
18
00:02:29,490 --> 00:02:31,890
So it means that to between
19
00:02:35,010 --> 00:02:42,510
the algorithm needed extremes of the features and the target to compute and never function, and then
20
00:02:43,410 --> 00:02:48,760
change its parameters to minimize this error.
21
00:02:48,780 --> 00:02:58,360
So we need to put the target and then we are currently train or algorithm.
22
00:02:58,680 --> 00:03:07,020
And in the next video, we're going to do some prediction, some stock price prediction using this linear
23
00:03:07,020 --> 00:03:07,800
regression.
2462
Can't find what you're looking for?
Get subtitles in any language from opensubtitles.com, and translate them here.