1
00:00:00,790 --> 00:00:08,080
So here is the data that we are going to use in this course, the problem statement here is that you

2
00:00:08,080 --> 00:00:10,180
are a manager in a real estate company.

3
00:00:11,200 --> 00:00:18,970
You want to find out these selling potential of a property that is basically data of past property transactions.

4
00:00:19,660 --> 00:00:24,250
You want to predict whether the property will be sold within three months or not.

5
00:00:26,680 --> 00:00:34,840
So the sold variable here, which is the last variable of this day, will really be dependent variable

6
00:00:34,900 --> 00:00:35,770
in our analysis.

7
00:00:37,150 --> 00:00:43,360
And other factors which impact this old variable, which we identified, busiest primary and secondary

8
00:00:43,360 --> 00:00:46,150
search, are these independent variables.

9
00:00:48,390 --> 00:00:51,810
This dataset has values for all these variables.

10
00:00:52,800 --> 00:00:54,090
Whenever we collect data.

11
00:00:54,420 --> 00:00:57,120
Different parts of data come from different sources.

12
00:00:57,960 --> 00:01:02,070
And we need to collate this data into a single tabular format.

13
00:01:02,360 --> 00:01:02,990
As this.

14
00:01:05,190 --> 00:01:09,090
And this table, the header row is just the variable names.

15
00:01:11,210 --> 00:01:16,280
While keeping the video names, trying not to use space, instead using underscore.

16
00:01:17,840 --> 00:01:24,800
For example, an air quality variable we have used underscored this is because some software do not

17
00:01:24,800 --> 00:01:25,760
accept spaces.

18
00:01:28,420 --> 00:01:35,680
Secondly, try to keep names so that you can recognize the actual variable that is a whiteboarding,

19
00:01:35,680 --> 00:01:37,930
putting names like X1, x2, X3.

20
00:01:39,610 --> 00:01:45,550
Since post analysis, the results from software will also be showing these variable names.

21
00:01:45,760 --> 00:01:48,290
And then it will become difficult to make sense of the design.

22
00:01:50,990 --> 00:01:54,540
I will show you in a couple of minutes what each variable stands for.

23
00:01:54,950 --> 00:02:00,290
But even by just looking at the names, you'll get some idea of what this day is.

24
00:02:02,810 --> 00:02:08,540
So this data is about how transactions and other related variables to each house.

25
00:02:10,580 --> 00:02:16,590
We will look at these variables in detail in some time after this top head row.

26
00:02:17,090 --> 00:02:20,900
Each row contains values pertaining to one single observation.

27
00:02:22,640 --> 00:02:25,820
And we have a total of five hundred six observations.

28
00:02:29,050 --> 00:02:31,720
The total number of columns we have is 19.

29
00:02:33,370 --> 00:02:39,340
We may have received different parts of this data from different sources, probably one source gave

30
00:02:39,400 --> 00:02:42,100
us data of also address and its price.

31
00:02:43,330 --> 00:02:49,470
One source gave data of air quality in different neighborhoods into the case.

32
00:02:49,830 --> 00:02:54,570
We need to use a unique identifier which will help us match these two parts.

33
00:02:56,100 --> 00:03:04,170
So doing all these different parts of data and get the data into one single data set with the rows and

34
00:03:04,170 --> 00:03:09,780
columns, the columns contain each variable and rules contain each observation.

35
00:03:13,370 --> 00:03:18,500
Now, your data suggest 80, but whenever you are going to share your data, all your analysis with

36
00:03:18,530 --> 00:03:22,430
anyone, the data should be accompanied by data dignity.

37
00:03:25,650 --> 00:03:29,100
A data dictionary contains information about the variables.

38
00:03:29,140 --> 00:03:29,990
Indeed, do does it?

39
00:03:31,950 --> 00:03:35,190
So comprehensive data dictionary includes the following.

40
00:03:36,480 --> 00:03:39,720
It has definitions of all the variables of your d2c.

41
00:03:41,350 --> 00:03:45,520
Then it should tell about the unique identifier for each observation.

42
00:03:47,230 --> 00:03:52,990
This unique identifier is called the primary key to match the data from another table.

43
00:03:53,500 --> 00:03:56,540
If there is a magic key used, that should also be highlighted.

44
00:03:58,010 --> 00:04:03,650
If you want to learn more about primary, Antec and Ricki's you can look at our video here.

45
00:04:04,250 --> 00:04:05,870
We have shared the link in this presentation.

46
00:04:07,070 --> 00:04:11,500
This video is part of another course on database management using Escuela.

47
00:04:13,990 --> 00:04:20,900
Lastly, if there is a categorical variable in the data, all its values should also be explained.

48
00:04:23,550 --> 00:04:26,730
Now, let's define the variables of our host bracingly, does it?

49
00:04:31,550 --> 00:04:40,580
On the left is the variable limb, as indeed I say, on the right is a brief description of what that

50
00:04:40,580 --> 00:04:41,300
variable is.

51
00:04:43,190 --> 00:04:44,570
I'm going to read this one by one.

52
00:04:44,600 --> 00:04:44,930
No.

53
00:04:47,350 --> 00:04:51,330
So the price tells us the asking price of the property by the owner.

54
00:04:53,490 --> 00:04:56,820
That is not how much the owner is willing to sell the property.

55
00:04:59,810 --> 00:05:00,800
That's a NATO stance.

56
00:05:00,890 --> 00:05:02,900
What proportion of residential area in the town?

57
00:05:04,200 --> 00:05:08,120
It call Stanford index of quality of it in that neighborhood.

58
00:05:10,020 --> 00:05:14,140
Room them is the average number of rooms in the houses of that locality.

59
00:05:16,460 --> 00:05:21,650
It is how all is that house construction is that is all many years ago.

60
00:05:21,740 --> 00:05:22,660
It was constructed.

61
00:05:24,870 --> 00:05:31,740
This one, two, three, four are four distances of that hose from the nearest employment hub.

62
00:05:34,480 --> 00:05:40,120
Because we hypothesised that the ease of selling the house will depend on the employment opportunity

63
00:05:40,210 --> 00:05:41,110
available needed.

64
00:05:43,310 --> 00:05:47,720
Teachers stand for the number of teachers, but Ulgen population in that town.

65
00:05:53,130 --> 00:05:54,570
Then we have food probe.

66
00:05:55,860 --> 00:05:58,650
That is the proportion of world population in the town.

67
00:06:00,410 --> 00:06:01,700
Airport stands for.

68
00:06:02,390 --> 00:06:04,310
Is there any airport in the city or not?

69
00:06:04,880 --> 00:06:06,620
So this is a categorical variable.

70
00:06:07,370 --> 00:06:08,470
It has to Aleuts.

71
00:06:08,600 --> 00:06:09,290
Yes, I know.

72
00:06:09,680 --> 00:06:11,200
These are self explanatory.

73
00:06:12,560 --> 00:06:12,850
Yes.

74
00:06:12,860 --> 00:06:14,930
Means that there is an airport in the city.

75
00:06:15,170 --> 00:06:17,090
No means there is no airport in the city.

76
00:06:19,550 --> 00:06:22,970
And horse bed is giving us the number of hospital beds.

77
00:06:23,160 --> 00:06:25,100
But Teligent population in the down.

78
00:06:27,240 --> 00:06:31,780
And hard rooms, guilty number of hotel rooms, but out in public and indeed on.

79
00:06:34,000 --> 00:06:36,300
Waterboarding is another categorical variable.

80
00:06:37,170 --> 00:06:40,740
It has values like Lake River boat or none.

81
00:06:42,230 --> 00:06:46,670
Which is giving us whether there is a natural freshwater source within the city or not.

82
00:06:49,420 --> 00:06:52,710
Rainfall is giving us the average rainfall in centimeters.

83
00:06:54,890 --> 00:07:00,820
Buster is a categorical variable with this telling us whether there is a bus terminal in the city.

84
00:07:03,200 --> 00:07:07,190
Yes means that there is no means there is no bus terminal in the city.

85
00:07:09,890 --> 00:07:15,660
And Park's variable is giving us the proportion of land assigned as green land in that town.

86
00:07:17,630 --> 00:07:22,910
And lastly, we have the sole variable, which is our dependent variable, which is telling us whether

87
00:07:23,300 --> 00:07:27,720
that particular property was sold within three months of getting listed on or.

88
00:07:28,880 --> 00:07:36,350
By default, it will be having value zero and one one meaning that the house was sold within three months

89
00:07:36,860 --> 00:07:41,700
and zero means that the house was not sold within three months.

90
00:07:44,380 --> 00:07:44,920
So that does.

91
00:07:44,950 --> 00:07:49,990
Yes, wi fi and the PDA of PBT, a dash in the resource section of this lecture.

92
00:07:51,130 --> 00:07:53,890
You have the new the data we'll be using for analysis.

93
00:07:55,380 --> 00:08:01,050
No doubt this data is not real leader, and it's similar to Boston housing data set commonly used for

94
00:08:01,070 --> 00:08:01,650
analysis.

95
00:08:02,880 --> 00:08:05,780
But do not take the result of our analysis too seriously.

96
00:08:06,020 --> 00:08:07,310
This is not actually does it?

97
00:08:09,130 --> 00:08:13,560
In the next video, we will learn how to import this data, say, in our software package.
