1
00:00:01,860 --> 00:00:04,940
Now, let's start for missing value treatment in Python.

2
00:00:06,030 --> 00:00:08,850
So this photo, what observations from Oord EBD.

3
00:00:11,020 --> 00:00:15,080
We have discussed point two and three in our outlier video.

4
00:00:15,730 --> 00:00:20,650
Now we will be discussing about this other missing we are losing and Hause, but it's variable.

5
00:00:22,390 --> 00:00:32,830
The best way to identify missing value is just to take in full of our data frame will be if not in full.

6
00:00:37,910 --> 00:00:43,550
Here you will see the total number of values for all the variables.

7
00:00:43,970 --> 00:00:49,850
There is only one variable, which is an Herzberg's, where the total number of values is less than

8
00:00:49,850 --> 00:00:50,900
five zero six.

9
00:00:51,860 --> 00:00:57,590
Therefore, this confirms that and Horsburgh contain missing values.

10
00:00:59,270 --> 00:00:59,720
You can.

11
00:01:00,820 --> 00:01:04,390
Also, look at duty to identify missing values.

12
00:01:06,010 --> 00:01:07,960
But then a duty you only get.

13
00:01:08,200 --> 00:01:10,370
Values of numerical variables.

14
00:01:10,930 --> 00:01:14,020
This will give you details of categorical variables as one.

15
00:01:17,890 --> 00:01:21,640
Greeting missing, well, it was fairly easy in Biton.

16
00:01:27,280 --> 00:01:29,690
To impute missing values, we will use.

17
00:01:30,800 --> 00:01:32,030
Fail and they function.

18
00:01:32,930 --> 00:01:37,760
So we'll rate be, if not our column name, which is and also birds.

19
00:01:41,050 --> 00:01:41,310
And.

20
00:01:42,570 --> 00:01:42,720
We.

21
00:01:43,020 --> 00:01:50,880
Equal to since we want our imputed data to again change the original values in our data.

22
00:01:51,020 --> 00:01:51,180
So.

23
00:01:51,210 --> 00:01:54,960
All right, B.F. Dorte and his words.

24
00:01:57,990 --> 00:01:59,140
Don't philander.

25
00:02:03,240 --> 00:02:08,940
And since we want to replace this value with the mean of our hospital beds.

26
00:02:09,290 --> 00:02:11,790
All right, B.F. Dorte and husbands.

27
00:02:16,000 --> 00:02:21,990
Not mean what this function is actually doing is.

28
00:02:23,660 --> 00:02:30,550
Plus, it is calculating the mean awful what really well, which is B.F. and Herzberg's.

29
00:02:32,340 --> 00:02:41,460
Then whenever I would be, if Dorte and Oz Bags is Zettl or and then it is filling those blanks with

30
00:02:41,460 --> 00:02:42,540
this mean value.

31
00:02:43,860 --> 00:02:52,450
And after filling all the missing values, we are again saving this day and Bill are or reasonably Dufrene.

32
00:02:56,340 --> 00:02:57,260
If on this.

33
00:03:00,360 --> 00:03:02,130
Missing values are not imputed.

34
00:03:02,610 --> 00:03:07,110
If we take in full of our day Dufrene food, I'd be if not in full.

35
00:03:15,240 --> 00:03:15,930
You can see.

36
00:03:18,140 --> 00:03:22,030
Now, the count is five 06 and set off for 98.

37
00:03:22,460 --> 00:03:27,950
So we have faith, all of that missing, we're loose with the meaning of that column.

38
00:03:32,540 --> 00:03:36,650
Now, if you want to do missing, well, you're imputation for all of the columns.

39
00:03:40,540 --> 00:03:45,050
You have to right, B.F. Dot, fill in there and then record just right.

40
00:03:45,240 --> 00:03:46,120
F dot mean

41
00:03:48,840 --> 00:03:53,570
and again, we have to save this data frame again and go out business little frame.

42
00:03:53,620 --> 00:03:54,690
So we'll read BFE.

43
00:03:54,730 --> 00:03:55,980
Way to be if.

44
00:03:57,290 --> 00:04:05,060
Not feel this way, Lou, do for all the columns, but since we want a specific solution for each of

45
00:04:05,060 --> 00:04:10,340
our columns, as we mentioned, they know what to re elected, that for some variables, we won zero.

46
00:04:10,340 --> 00:04:11,780
For some variables we won.

47
00:04:11,780 --> 00:04:14,090
We mean for some variables.

48
00:04:14,120 --> 00:04:14,930
We want more.

49
00:04:15,440 --> 00:04:19,250
That's why we have we have used specific variables.

50
00:04:19,560 --> 00:04:20,990
They impute our missing value.

51
00:04:22,370 --> 00:04:28,460
This statement is not needed yet, as we have already imputed a lot of missing values.

52
00:04:30,150 --> 00:04:32,310
Now we'll see what to do about the notebook.

53
00:04:33,210 --> 00:04:36,580
Go on, change their title of offor notebook.

54
00:04:45,720 --> 00:04:54,930
And click on, say, streaming, and then you can see that so you're missing well, the imputation and

55
00:04:54,940 --> 00:04:55,450
Biton.

56
00:04:56,640 --> 00:04:57,120
Thanks.
