1
00:00:00,180 --> 00:00:03,930
Hello, welcome to the very first session of this project.

2
00:00:04,080 --> 00:00:10,680
So this is exactly my data set on which I have to do certain kind of analysis on which I have to do

3
00:00:10,830 --> 00:00:13,940
certain kind of privacy, lots of analysis.

4
00:00:14,160 --> 00:00:19,950
And at the end, I have to come up with some beautiful insights, some meaningful insight from this

5
00:00:19,950 --> 00:00:21,320
huge chunk of data.

6
00:00:21,660 --> 00:00:25,220
So you will see these are all different, different features in many different.

7
00:00:25,500 --> 00:00:29,610
So very first, I have to load this data frame in my Jupiter notebook.

8
00:00:30,120 --> 00:00:32,420
So this is exactly my general guide.

9
00:00:32,460 --> 00:00:36,580
And by force, I'm just going to report some basic models over here.

10
00:00:36,870 --> 00:00:42,310
So very first, let's say I'm just going to import my partner's module and I'm going to create Elías

11
00:00:42,330 --> 00:00:42,960
as Espina.

12
00:00:43,290 --> 00:00:51,000
So PARNAS is exactly that library that is extensively used in case of data manipulation, data extraction

13
00:00:51,150 --> 00:00:54,460
and data modification and much, much task as well.

14
00:00:54,870 --> 00:01:01,140
So after it, if you have to perform some numerical task on data, you guys can import no library as

15
00:01:01,140 --> 00:01:01,380
well.

16
00:01:01,740 --> 00:01:07,230
So here I'm going to say import number as ENPI after it for vacation stuff.

17
00:01:07,500 --> 00:01:13,440
I'm going to import my matplotlib and from this matplotlib, I'm going to import my daughter and I'm

18
00:01:13,440 --> 00:01:18,660
going to create a Elías BLT after it for better presentation.

19
00:01:18,660 --> 00:01:24,060
You guys can also import and interlibrary, which is exactly your Seabourne library.

20
00:01:24,060 --> 00:01:26,960
So I'm going to say import Seabourne SSME.

21
00:01:27,210 --> 00:01:32,450
So just executer using all this enter and it will execute this set.

22
00:01:32,700 --> 00:01:36,680
And after what you have to do very first, you have to read your data.

23
00:01:36,930 --> 00:01:38,580
So I'm going to say the speed.

24
00:01:38,850 --> 00:01:46,920
And here I have a function which is exactly my read underscore CSB and here you have to pass your where

25
00:01:46,920 --> 00:01:49,380
exactly your dataset is available.

26
00:01:49,530 --> 00:01:55,080
You will see over here, this is exactly my dataset and it is available at this spot.

27
00:01:55,080 --> 00:01:58,710
So I'm just going to copy this part and I'm just going to paste over here.

28
00:01:58,920 --> 00:02:04,890
And after it, if you will press tab, you will get all the stuff I will will add this particular part.

29
00:02:04,920 --> 00:02:08,610
So this is exactly the data fed that you need.

30
00:02:08,800 --> 00:02:15,570
So I'm just going to append are over it so that it will make us to get rid of all the issue that will

31
00:02:15,570 --> 00:02:19,190
come across after importing this data.

32
00:02:19,440 --> 00:02:27,150
So I'm just going to say it is exactly my div and let's see if I want our preview of it to just call

33
00:02:27,150 --> 00:02:28,860
had ordered that set.

34
00:02:28,860 --> 00:02:33,660
And you will see this is exactly the data frame that you need on this.

35
00:02:33,660 --> 00:02:41,550
You have to perform also preprocessing lots of analysis and at the end you have to conclude your visalo.

36
00:02:41,910 --> 00:02:48,870
So you will see for this particular session, I have this assignment in which I have to perform data

37
00:02:48,870 --> 00:02:55,650
planning on our data, as well as lots of data on our data, because whenever you are going to work

38
00:02:55,650 --> 00:03:00,210
for some real work project, your data will be always raw.

39
00:03:00,330 --> 00:03:03,110
You will always have your massive data.

40
00:03:03,390 --> 00:03:09,870
So you have to make radio data for the analysis, but for the modeling purposes, that's why you have

41
00:03:09,870 --> 00:03:13,520
to perform lots of data, including lots of people sitting on your data.

42
00:03:13,840 --> 00:03:18,150
So let's see if I'm going to check what exactly is the shape of my data frame.

43
00:03:18,160 --> 00:03:21,630
You will see it has that much rules and that much column.

44
00:03:21,840 --> 00:03:27,090
And let's see if I have to check whether I have any null value in the frame or not.

45
00:03:27,270 --> 00:03:34,680
So for this, I'm going to say this is null dot values dot any.

46
00:03:34,680 --> 00:03:42,900
And if I'm going to execute it, you will see it has to it means it has some kind of missing value available

47
00:03:42,900 --> 00:03:43,830
in your data.

48
00:03:44,340 --> 00:03:50,110
So let's say I'm going to say I just want summation of all the missing values over here.

49
00:03:50,130 --> 00:03:54,660
So for this, I'm just going to call this is Nelda's some.

50
00:03:54,660 --> 00:04:00,330
You will see this has all these types of different different values in your data available over here.

51
00:04:00,570 --> 00:04:01,440
You will see this.

52
00:04:01,590 --> 00:04:03,690
This country has that much missing value.

53
00:04:03,700 --> 00:04:08,070
This all these features has huge number of missing valleys over here.

54
00:04:08,520 --> 00:04:11,730
So if you will observe over here in this agent.

55
00:04:11,970 --> 00:04:23,160
So if Ajin is not given, so it means booking was most likely made by a person or you can see booking

56
00:04:23,160 --> 00:04:27,960
was mostly made without one and similarly were here incomplete.

57
00:04:28,290 --> 00:04:34,920
So if none is given or I can say wherever I have missing value, it means it is mostly like private.

58
00:04:34,920 --> 00:04:42,540
Similarly, and all the other features we can explain or I can say we can manage it according to our

59
00:04:42,780 --> 00:04:43,230
need.

60
00:04:43,530 --> 00:04:50,790
So here I'm going to say let's say I'm just going to say they've got Filani and here I'm going to say

61
00:04:51,150 --> 00:04:56,500
just fill it with zero and I'm just going to update my data frame as well.

62
00:04:56,520 --> 00:04:59,820
So here I have to pass my in-place parameter as.

63
00:05:00,040 --> 00:05:07,870
Troops were just executed and after it, if again, I'm going to call this some over there exactly this

64
00:05:07,870 --> 00:05:08,520
summer.

65
00:05:08,900 --> 00:05:12,820
Now, you will observe don't have any missing value in your data.

66
00:05:12,850 --> 00:05:19,430
It means up to some extent you data some already for your analysis purpose for the prepossessing purpose.

67
00:05:19,960 --> 00:05:26,110
So let's say let's say yeah, in this in this meeting feature, let's say in this middle feature, I'm

68
00:05:26,110 --> 00:05:28,010
just going to call ya.

69
00:05:28,270 --> 00:05:31,840
What exactly is account of each and every category in this?

70
00:05:32,110 --> 00:05:36,540
So for this, I'm just going to call this value on a school counselor there.

71
00:05:36,550 --> 00:05:41,250
And if you will execute the cell, you will see backfills and that number of count.

72
00:05:41,260 --> 00:05:45,570
Similarly, each and every category has that much number of count.

73
00:05:45,910 --> 00:05:52,690
So after it, let's say if I'm just going to access these children over there and in these children,

74
00:05:52,690 --> 00:06:00,370
if I'm going to call my unique or now you'll see it has all these unique, unique children available

75
00:06:00,370 --> 00:06:02,650
in your data frame in a similar way.

76
00:06:02,980 --> 00:06:08,890
Let's see if I'm going to call this adults, if I'm going to access this adult had on this, if I'm

77
00:06:08,890 --> 00:06:15,240
going to call my Unicode here, you will see it has this unique number of adults in a similar way.

78
00:06:15,250 --> 00:06:21,520
If I'm going to access my BBS and on this, if I'm going to call my Unicode unit, you will observe

79
00:06:21,520 --> 00:06:26,080
it has that unique number of babies available in your data frame.

80
00:06:26,290 --> 00:06:34,240
And from all the stuff that we have fach for here to form this, we can see in our data my children

81
00:06:34,240 --> 00:06:37,680
and adult and babies can't be zero at the time.

82
00:06:38,020 --> 00:06:41,130
So far, this what I'm going to do, I'm just going to create a filter.

83
00:06:41,170 --> 00:06:43,360
Let's end going to create a filter.

84
00:06:43,360 --> 00:06:46,840
And in this filter, I'm going to say very first I have to exit the children.

85
00:06:47,200 --> 00:06:52,650
For the children, it goes to zero so that if this is exactly my very first condition.

86
00:06:52,930 --> 00:06:58,120
So I'm going to say this is my very first condition and I'd say my second condition is the thing would

87
00:06:58,270 --> 00:07:01,520
be half of adults equally close to zero.

88
00:07:01,540 --> 00:07:04,270
So this is exactly my second condition.

89
00:07:04,270 --> 00:07:11,030
And my third condition is exactly where my babies are equally close to zero.

90
00:07:11,050 --> 00:07:13,750
So this is exactly my condition.

91
00:07:13,900 --> 00:07:20,320
And if I'm going to pass this filter, if I'm going to pass this filter in my data frame now, you will

92
00:07:20,320 --> 00:07:21,220
think over here.

93
00:07:21,250 --> 00:07:28,930
You will see over here, it has that much a number of rules and that it means these are exactly you're

94
00:07:29,080 --> 00:07:35,190
wrong entries in your data because you will observe at a time, at a time these values are going to

95
00:07:35,200 --> 00:07:35,580
be zero.

96
00:07:35,590 --> 00:07:39,240
It means you have to remove all these stuff for four days.

97
00:07:39,250 --> 00:07:43,570
What I'm going to do, let's say let's say I'm just going to store it somewhere else.

98
00:07:43,570 --> 00:07:47,460
Let's say this is the frame that I have to store very first or what you can do.

99
00:07:47,710 --> 00:07:51,570
You guys can call you guys can call negation of this filter.

100
00:07:51,580 --> 00:07:53,620
So I'm just going to copy from here.

101
00:07:53,950 --> 00:07:58,320
Just going to paste over here and if you will call negation of this.

102
00:07:58,510 --> 00:08:01,200
So in bonders, you have to use this operator over here.

103
00:08:01,300 --> 00:08:02,490
So just execute it.

104
00:08:02,500 --> 00:08:09,170
And it has that much number of rules in your data frame that doesn't contain any wrong entry.

105
00:08:09,490 --> 00:08:11,100
So that said, this is my letter.

106
00:08:11,110 --> 00:08:12,280
This is my final data frame.

107
00:08:12,280 --> 00:08:14,490
So I'm going to say this is exactly my data.

108
00:08:14,500 --> 00:08:15,940
So just executed.

109
00:08:16,120 --> 00:08:20,400
And if I'm going to call my hat over there, you will observe over here.

110
00:08:20,680 --> 00:08:28,330
This is a data frame on which you have to perform certain kind of analysis, because this data is almost

111
00:08:28,330 --> 00:08:31,780
I can say it is almost your preprocessed data.

112
00:08:31,780 --> 00:08:35,620
And on this data, you have to come up with some meaningful insight.

113
00:08:35,620 --> 00:08:38,290
You have to come up with some beautiful insights.

114
00:08:38,470 --> 00:08:40,210
So that is exactly what I mean.

115
00:08:40,570 --> 00:08:43,720
So that's all about the session hope of this session very much.

116
00:08:43,970 --> 00:08:44,610
Thank you.

117
00:08:44,620 --> 00:08:45,620
Have a nice day.

118
00:08:45,970 --> 00:08:46,780
Keep learning.

119
00:08:46,780 --> 00:08:47,620
Keep growing.

120
00:08:47,950 --> 00:08:48,670
Keep practicing.