1
00:00:03,210 --> 00:00:06,980
Now, we have imported data and our data is ready.

2
00:00:07,860 --> 00:00:10,300
So let's run data on this data.

3
00:00:11,630 --> 00:00:12,450
Duran unity.

4
00:00:13,330 --> 00:00:15,130
Just straight your variable name.

5
00:00:15,160 --> 00:00:17,620
That is beef don't describe.

6
00:00:25,600 --> 00:00:26,830
This is our unity.

7
00:00:27,280 --> 00:00:29,860
So let's go through all the variables.

8
00:00:29,930 --> 00:00:30,610
When wavin.

9
00:00:32,340 --> 00:00:37,960
As we calculated using the ship, the total number of records are 506.

10
00:00:38,580 --> 00:00:39,990
So for price, very well.

11
00:00:40,120 --> 00:00:42,190
Our total record is 506.

12
00:00:42,780 --> 00:00:46,800
And the mean price, house prices, twenty two point five to.

13
00:00:47,940 --> 00:00:50,450
We also have a standard deviation of this video.

14
00:00:50,750 --> 00:00:57,000
But the minimum value is five and the maximum value is 50.

15
00:00:57,420 --> 00:00:59,070
And the median is 21.

16
00:00:59,790 --> 00:01:03,510
Median is always represented as the four feet percentile value.

17
00:01:07,040 --> 00:01:10,640
On this information, you can see for all of the variables.

18
00:01:13,530 --> 00:01:20,100
There are two important values that we should look for, and then UDD first is the common variable.

19
00:01:22,410 --> 00:01:26,930
So on for almost all the variables, is 506.

20
00:01:28,640 --> 00:01:30,160
But for and horse backs.

21
00:01:30,530 --> 00:01:33,350
That is the number of hospital beds, but posehn.

22
00:01:34,720 --> 00:01:36,630
The number is not five zero six.

23
00:01:37,510 --> 00:01:42,160
This means that there are eight missing values in our data for this video.

24
00:01:42,190 --> 00:01:42,460
But.

25
00:01:44,480 --> 00:01:50,870
We will treat this missing values and the later part of the video, but at the moment we only want to

26
00:01:50,870 --> 00:01:54,170
look at what all the variables have a missing value in them.

27
00:01:54,950 --> 00:01:58,900
So it looks like on the end, Horsburgh missing.

28
00:01:58,900 --> 00:01:59,450
They lose.

29
00:02:01,320 --> 00:02:05,430
The second important thing, boom or bust, is the difference between the mean and median.

30
00:02:07,210 --> 00:02:13,090
If you see there is no significant difference and mean and median off price, there is a significant

31
00:02:13,090 --> 00:02:16,120
difference in the mean, then maybe enough time rate.

32
00:02:18,020 --> 00:02:19,330
You can also look at them.

33
00:02:20,370 --> 00:02:23,430
You, Maxwell, 25 percent dead and the 75.

34
00:02:23,510 --> 00:02:25,590
But son died of that variable.

35
00:02:26,340 --> 00:02:30,020
You get a sense of the distribution of data of that variable.

36
00:02:31,440 --> 00:02:38,710
If you see the minimum value is zero point zero zero six and the 25 percentile value is zero point zero

37
00:02:38,710 --> 00:02:39,450
is eight.

38
00:02:40,140 --> 00:02:47,120
This means that there is little difference between the zero percent and the minimum value and the 25

39
00:02:47,130 --> 00:02:48,150
percentile value.

40
00:02:48,870 --> 00:02:53,190
And there is a large difference between the 75 percentile value and the max value.

41
00:02:56,470 --> 00:03:02,680
This means that a word data for this variable is negatively skewed.

42
00:03:03,010 --> 00:03:08,850
Most of the values lies in the small range of zero to three point six.

43
00:03:10,040 --> 00:03:14,340
And the rest of values are dispersed from three to 88.

44
00:03:15,830 --> 00:03:19,840
This means that our data is skewed for this variable.

45
00:03:23,990 --> 00:03:30,390
If you look at the mean and median value of other variables, you will find out that for.

46
00:03:32,000 --> 00:03:38,630
And hotel rooms, the maximum value is significantly larger than the sum in the fifth.

47
00:03:38,920 --> 00:03:40,120
The mean value.

48
00:03:41,550 --> 00:03:43,140
The largest value is one zero one.

49
00:03:43,830 --> 00:03:44,480
Where does this end?

50
00:03:44,520 --> 00:03:46,170
Seventy fifth value is 14.

51
00:03:47,280 --> 00:03:50,460
And defended by Lewis on the 11:00.

52
00:03:52,530 --> 00:03:58,110
So data may be positively skewed or there may be some outliers in this data.

53
00:03:59,340 --> 00:04:02,460
Similarly for rainfall, also, we can see that.

54
00:04:03,540 --> 00:04:10,230
The minimum wage, Lewis three, then the five percentile, Lewis, 28, and them and then the maximum

55
00:04:10,230 --> 00:04:11,170
value is 60.

56
00:04:12,120 --> 00:04:18,990
So here I can see that the data is either negatively skewed or there is an outlier in this data.

57
00:04:19,650 --> 00:04:23,070
We'll discuss about outliers and missing value.

58
00:04:23,920 --> 00:04:24,240
And then what?

59
00:04:24,240 --> 00:04:25,020
Next videos.

60
00:04:25,230 --> 00:04:30,690
But at this point, we will use a duty display, identifiers, such variables.

61
00:04:33,390 --> 00:04:38,070
As you can see, we've identified this issues in our data using duty.

62
00:04:39,870 --> 00:04:44,310
And you should always look for a duty before starting your analysis.

63
00:04:48,150 --> 00:04:53,310
Since we identified problems with the word rainfall and added hotel room data.

64
00:04:54,740 --> 00:04:59,000
Will not scatterplot for this data to understand them completely.

65
00:05:03,220 --> 00:05:04,700
To Blätter Scatterplot.

66
00:05:05,430 --> 00:05:06,520
I will use as.

67
00:05:07,290 --> 00:05:09,650
That is Seabourne function joint block.

68
00:05:09,860 --> 00:05:11,270
As soon as don't join Lord.

69
00:05:13,200 --> 00:05:14,430
The expendible.

70
00:05:17,980 --> 00:05:19,560
It's my end or Delarue.

71
00:05:24,260 --> 00:05:27,110
Remember to put variable names in quotes.

72
00:05:30,800 --> 00:05:32,400
And then y equal to.

73
00:05:34,470 --> 00:05:42,540
Twice since my dependent variable is price and put by equal to price, and then they take away to be.

74
00:05:48,890 --> 00:05:49,260
Remember?

75
00:05:49,440 --> 00:05:51,630
Right, we're able limbs that at least.

76
00:05:56,780 --> 00:06:01,160
You can see on the top we have the highest program of any hotel rooms.

77
00:06:04,590 --> 00:06:08,070
And on the right, we have his program of price.

78
00:06:09,350 --> 00:06:10,310
And in between.

79
00:06:11,770 --> 00:06:16,410
In between the main plot, we have the scatter plot of Christ versus and hotel rooms.

80
00:06:17,280 --> 00:06:22,470
One thing you can quickly identify from this graph is the two outliers.

81
00:06:23,040 --> 00:06:27,690
These two points are at very large distance from the rest of the points.

82
00:06:28,320 --> 00:06:33,210
So most of my data lies between zero and twenty four and hotel rooms.

83
00:06:33,510 --> 00:06:38,390
But there are two points for which we have a value near to a, B and hundred.

84
00:06:40,520 --> 00:06:44,490
Similarly, will Blätter scatterplot for rainfall also right?

85
00:06:44,760 --> 00:06:46,370
Asanas don't join plot.

86
00:06:51,310 --> 00:06:51,940
You will, right?

87
00:06:52,080 --> 00:06:53,380
Exequatur rainfall.

88
00:06:57,280 --> 00:06:59,110
And by equal to price.

89
00:07:06,550 --> 00:07:08,270
And there details, details, Deth.

90
00:07:14,420 --> 00:07:17,600
Now, again, on the top, we have a stroke rahmah of rainfall.

91
00:07:17,720 --> 00:07:20,060
And on the right, we have a stroke Raam of Y.

92
00:07:20,600 --> 00:07:25,580
And in between we have a distribution or scatterplot of rainfall towards this place.

93
00:07:27,160 --> 00:07:31,210
Here you can see my rainfall values lies between 20 and 60.

94
00:07:31,300 --> 00:07:36,230
Most of my rainfall values lies between 20 and 16, but I can see one outlier.

95
00:07:36,400 --> 00:07:41,410
There is a single point for which the value is almost like four or five.

96
00:07:42,960 --> 00:07:49,590
This may be due to the some sampling error or calculation error or something else.

97
00:07:50,460 --> 00:07:53,700
And we'll learn more about outliers and our outlier videos.

98
00:07:57,150 --> 00:08:01,150
Now, we have only covered numerical variables.

99
00:08:01,510 --> 00:08:04,000
Now let's move on to categorical variables.

100
00:08:07,130 --> 00:08:12,520
So, again, we will take a sample of five values, will, right, B.F. Dopehead.

101
00:08:20,440 --> 00:08:26,080
And we tried to identify our categorical variables or first psychological variable variables airport.

102
00:08:28,830 --> 00:08:31,290
To analyze this will lower the bar.

103
00:08:31,400 --> 00:08:41,280
Lord Aurecon, Lord of Categorical, everyone will read as an assault on Lord and then exequatur to

104
00:08:43,860 --> 00:08:46,170
our categorical variable, which is airport.

105
00:08:50,900 --> 00:09:00,170
And then they take what it be, a bull run this now we have a lot of work, ecological way.

106
00:09:00,310 --> 00:09:03,980
Well, airport and you can see their distribution on this airport.

107
00:09:06,490 --> 00:09:08,920
There is nothing unusual in this data.

108
00:09:09,100 --> 00:09:11,620
So we'll move on to the next set of what he calls medieval.

109
00:09:15,030 --> 00:09:16,340
Is, though, what everybody.

110
00:09:21,030 --> 00:09:26,170
In Wheelwright, that's an assault on blood mommai exists waterboarding.

111
00:09:28,060 --> 00:09:29,760
The days of.

112
00:09:40,550 --> 00:09:43,250
Again, you can see there this region of waterboardings.

113
00:09:46,620 --> 00:09:49,420
And there is nothing unusual about that also.

114
00:09:49,560 --> 00:09:51,780
So we'll move on to the next variable.

115
00:09:55,770 --> 00:09:57,010
There is a bus terminal.

116
00:10:21,130 --> 00:10:25,990
Yet you can see my bus terminal is only taking one value that this.

117
00:10:26,200 --> 00:10:26,710
Yes.

118
00:10:28,370 --> 00:10:36,710
So this may not be useful in our data, since this will not brought any differentiating power for our

119
00:10:36,770 --> 00:10:37,790
dependent variable.

120
00:10:38,220 --> 00:10:40,670
And for all the values of dependent variables.

121
00:10:40,850 --> 00:10:41,860
This will be us.

122
00:10:42,500 --> 00:10:46,850
So and all the cases, this will not impact our model anyway.

123
00:10:47,270 --> 00:10:51,830
So we'll look at it in more detail in the later part of this court's.

124
00:10:53,450 --> 00:10:59,540
For now, we will just mark this variable and we'll write some of the observation that we have from

125
00:10:59,540 --> 00:11:07,750
looking at the duty and programs and Bartletts, our first observation is about the missing values in

126
00:11:07,830 --> 00:11:09,530
very well and also Broome's.

127
00:11:17,250 --> 00:11:24,420
Second observation was Skewness or all players in the variable, the crime rate.

128
00:11:30,690 --> 00:11:34,820
Or total obliteration was outliers and.

129
00:11:37,430 --> 00:11:40,160
Hotel rooms vary, but that is an outcomes.

130
00:11:47,050 --> 00:11:49,550
And also in the variables, rainfall.

131
00:11:51,650 --> 00:11:53,380
I our fourth observation.

132
00:11:56,520 --> 00:12:01,440
Was about the bus terminal where even it was only taking one value.

133
00:12:06,570 --> 00:12:10,020
We'll look at this observations in the later part of the sports.