1
00:00:00,730 --> 00:00:07,030
How that continue with our cost and in this video, we would always some explanation plus in the library

2
00:00:07,030 --> 00:00:09,280
and data, so.

3
00:00:11,310 --> 00:00:17,160
And you can say that we need to predict the market trends, depending the betting on the changes that

4
00:00:17,160 --> 00:00:17,990
are occurring.

5
00:00:18,480 --> 00:00:22,550
So to do this will run on neural network regression for what the data said.

6
00:00:22,890 --> 00:00:27,420
So the median values of owner occupied home are predicted for the test data.

7
00:00:28,200 --> 00:00:31,320
I said this right up there, no more properties of houses.

8
00:00:31,510 --> 00:00:39,860
But I suppose any concern with modelling the price of houses in endorsable in house turn up dollars

9
00:00:40,560 --> 00:00:43,890
and shot this year regression, predictive modelling.

10
00:00:44,970 --> 00:00:53,220
So in both actually include features such a crameri the proportion of non retail business asheesh chemical

11
00:00:53,220 --> 00:00:54,450
concentration and more.

12
00:00:55,520 --> 00:01:04,250
So I did draw on the explanation in here, so because we are free, because you only have two hours,

13
00:01:04,590 --> 00:01:11,140
so that's why instead of watching me typing everything for you so easy a.

14
00:01:12,840 --> 00:01:22,460
Lieshout showed all the variables with the smallest disruption here, so there's a number of instances

15
00:01:22,730 --> 00:01:31,320
is around five and six number of attributes, 14 continue at will, including the class attribute and

16
00:01:31,320 --> 00:01:34,120
one binary value attribute.

17
00:01:35,160 --> 00:01:38,070
So each of the detail attributes are listed in here.

18
00:01:38,580 --> 00:01:43,350
The first one is Green, which he copied from Right by Tao.

19
00:01:43,860 --> 00:01:45,060
The second one is that.

20
00:01:45,060 --> 00:01:52,430
And what is the proportion of residential and John for loss over twenty five thousand square feet.

21
00:01:52,920 --> 00:01:57,240
The next one in the US is a proportion of non retail business asheesh.

22
00:01:57,270 --> 00:02:07,190
But how the next one is just a Charles River dummy variable, which is why I struck by the river zero,

23
00:02:07,200 --> 00:02:08,790
which is otherwise.

24
00:02:09,840 --> 00:02:15,170
The next one is a ox which needs to be oxidised concentration.

25
00:02:17,100 --> 00:02:21,570
I think this what I did wrong, and we should be over.

26
00:02:23,470 --> 00:02:24,430
Ten million.

27
00:02:26,550 --> 00:02:29,310
So it is not over pa, pa.

28
00:02:32,300 --> 00:02:43,450
Ten, and so this one is Arrium, which is the average number of rooms, but welding, which a proportion

29
00:02:43,450 --> 00:02:48,090
of owner occupied units will be for 1940.

30
00:02:49,150 --> 00:02:53,860
This is a way to distances to find some employment centers.

31
00:02:54,460 --> 00:02:59,670
The next one is not indict of accessibility to the radio highways.

32
00:03:00,520 --> 00:03:09,130
But Utah is a pupil teacher ratio about how Blackwood is one thousand with a, b, k.

33
00:03:10,530 --> 00:03:16,140
Equals zero Victory Square, where Becae is the proportion of blacks, but how?

34
00:03:17,200 --> 00:03:25,960
House set is a portion of blower's that placed on a population map is a median value of owner who buy

35
00:03:25,960 --> 00:03:28,400
homes in one thousand dollar.

36
00:03:29,020 --> 00:03:32,830
So on this map.

37
00:03:34,250 --> 00:03:39,660
Is there is response variable wired to 13 variables are possible predictor.

38
00:03:40,130 --> 00:03:41,270
So the goal of this.

39
00:03:42,150 --> 00:03:48,450
Project is to fit a operation model that explain the variation in map.

40
00:03:49,040 --> 00:03:52,920
So is there a relationship between the first 13 column and the map?

41
00:03:53,400 --> 00:03:54,150
Variable variables?

42
00:03:55,260 --> 00:04:02,520
Can we predict the manpower value based on the tutted in both columns that we set before?

43
00:04:02,640 --> 00:04:07,830
The objective of this project is to predict the median value of owner occupied homes.

44
00:04:08,550 --> 00:04:19,530
So the data is available in the data by name housing, not data from the UCI that as I said so.

45
00:04:21,210 --> 00:04:24,180
To import the data we need to do dot.

46
00:04:25,830 --> 00:04:29,910
We need to you read underscores yes module upon this library.

47
00:04:31,190 --> 00:04:33,080
So these are DataDot.

48
00:04:35,310 --> 00:04:36,460
Rolling on the radar.

49
00:04:36,690 --> 00:04:40,230
And for us, we have to import a bandos library.

50
00:04:43,020 --> 00:04:43,710
So let.

51
00:04:45,630 --> 00:04:48,870
Import pandas as speedy.

52
00:04:51,610 --> 00:04:54,420
So in this project where you will go, we will collapse.

53
00:04:55,420 --> 00:05:05,520
This will be easier and from now on, Turei for any function containing a bandos library widjojo the

54
00:05:05,530 --> 00:05:14,180
string beedi, as we have Jane bandos library name and the asset class can be added to do that.

55
00:05:14,740 --> 00:05:17,470
So the bandos the library is an open source.

56
00:05:18,330 --> 00:05:23,410
And it's very easy to you it operate a structure and operation to manipulate.

57
00:05:24,860 --> 00:05:27,650
Numerical so.

58
00:05:28,980 --> 00:05:31,410
The available data are not contained.

59
00:05:31,860 --> 00:05:37,950
So is it necessary to retrieve the names of the variable is not contained in an audio file?

60
00:05:38,640 --> 00:05:41,040
So let make the head of.

61
00:05:43,500 --> 00:05:45,960
But we had to run the sale.

62
00:05:46,960 --> 00:05:48,810
And then we're happy, Hesh.

63
00:05:49,830 --> 00:05:51,630
Names equa.

64
00:05:54,980 --> 00:05:55,610
Graham.

65
00:06:00,190 --> 00:06:00,950
That and.

66
00:06:04,980 --> 00:06:05,700
In us.

67
00:06:09,090 --> 00:06:09,750
Just.

68
00:06:14,020 --> 00:06:14,680
Norks.

69
00:06:16,620 --> 00:06:17,430
I am.

70
00:06:19,540 --> 00:06:19,900
I.

71
00:06:23,110 --> 00:06:23,620
This.

72
00:06:27,320 --> 00:06:27,790
Right.

73
00:06:30,420 --> 00:06:30,960
Tocks.

74
00:06:34,570 --> 00:06:35,740
B Trottier.

75
00:06:44,370 --> 00:06:45,210
How's that?

76
00:06:46,660 --> 00:06:48,250
Sorry, Mr..

77
00:06:49,730 --> 00:06:51,410
And then the last one is a.

78
00:06:54,380 --> 00:06:57,140
And this right now is important.

79
00:06:57,380 --> 00:07:00,980
You are straight away so that one Azal.

80
00:07:03,420 --> 00:07:15,000
We don't need any mistakes or be they show data that do data equal, we don't create and underscore

81
00:07:15,010 --> 00:07:15,720
CISPA.

82
00:07:15,730 --> 00:07:17,780
So you can buy straight.

83
00:07:18,600 --> 00:07:18,960
You are.

84
00:07:20,680 --> 00:07:23,410
The limb lies by a quarter to.

85
00:07:24,940 --> 00:07:36,830
And then names equal the names so that one does hail and we do make any mistake, so it is how you imported

86
00:07:36,960 --> 00:07:37,130
it.

87
00:07:38,230 --> 00:07:42,830
So we zero it underscores that grey module of the bandos library.

88
00:07:43,150 --> 00:07:47,830
So in this function, instead of the fine and we can also enter the complete stream.

89
00:07:48,130 --> 00:07:51,820
You are provide content in the website respiratory.

90
00:07:52,930 --> 00:07:53,620
So.

91
00:07:54,890 --> 00:08:02,000
We have set to complete your hiring here and then this variable will bask in the sunshine and you say

92
00:08:02,010 --> 00:08:09,920
that data, you will reward us by straight in the reflection and we have to order bar that had been

93
00:08:09,920 --> 00:08:10,760
boss as well.

94
00:08:10,780 --> 00:08:13,150
So which is the name and names.

95
00:08:13,700 --> 00:08:17,480
So the first person, if or not, why would be use.

96
00:08:18,110 --> 00:08:19,280
The second one is.

97
00:08:19,430 --> 00:08:20,210
So this one.

98
00:08:21,550 --> 00:08:25,160
Is he tied up with you, the wife's away or not?

99
00:08:25,540 --> 00:08:35,200
The second one is specify a list of name to use and now we just playing the role of the frame to say

100
00:08:35,860 --> 00:08:40,070
that we impose a carefully because there might be some mistake.

101
00:08:40,390 --> 00:08:41,310
So just plain.

102
00:08:42,760 --> 00:08:48,720
DataDot had 20 soldier.

103
00:08:51,210 --> 00:08:55,410
And we did successfully bring the results are separate or.

104
00:08:56,290 --> 00:09:04,000
In here, we got out, so I mean, we did impose essentially bought the library, and so that is the

105
00:09:04,000 --> 00:09:05,050
end of this video.

106
00:09:05,260 --> 00:09:06,550
I hope you enjoy it.

107
00:09:06,760 --> 00:09:08,970
And I will see you in the next video.