1
00:00:05,810 --> 00:00:06,470
Hey everyone.

2
00:00:07,180 --> 00:00:12,200
So in this video we are going to learn something by which you will get to know that how on are used

3
00:00:12,440 --> 00:00:14,330
for data analyses.

4
00:00:14,380 --> 00:00:18,920
Now you have just learned the data frames and all that but you did not get the idea that how we can

5
00:00:18,920 --> 00:00:21,710
use this bound us to analyze any data.

6
00:00:22,460 --> 00:00:27,750
So that's what something we are going to do here by a topic that is known as data frames.

7
00:00:27,780 --> 00:00:29,040
So goodbye.

8
00:00:29,450 --> 00:00:32,020
So we are going to learn head goodbye.

9
00:00:32,240 --> 00:00:34,600
And let me begin first.

10
00:00:34,640 --> 00:00:41,840
I have an example dictionary that is something a person that is selling fruits may be having a fruit

11
00:00:41,840 --> 00:00:42,360
shop.

12
00:00:42,530 --> 00:00:44,590
Like we have bee stencil bugger.

13
00:00:46,130 --> 00:00:52,850
So Bulger is a fruit seller and Bulger have few items on his shop like we consider first

14
00:00:56,090 --> 00:00:57,250
like that money's app.

15
00:00:57,270 --> 00:01:07,830
But a guy selling Apple and they will use this twice that put I will tell you I have used this one twice.

16
00:01:07,840 --> 00:01:12,110
All right then second thing Bulger is selling orange.

17
00:01:12,620 --> 00:01:17,240
And then again copy that orange also come on and come on.

18
00:01:17,930 --> 00:01:20,480
And then there is also a smuggler.

19
00:01:20,480 --> 00:01:22,190
So he's selling consensus.

20
00:01:23,390 --> 00:01:25,530
So stay away from them.

21
00:01:26,820 --> 00:01:29,830
Now we have a list of items.

22
00:01:29,960 --> 00:01:33,340
This one is not supposed to be there.

23
00:01:33,410 --> 00:01:36,500
So this is the list of items that Bulger is selling.

24
00:01:36,800 --> 00:01:45,440
And now we have and at least here in the dictionary that is 150 days debugger is selling the items like

25
00:01:46,010 --> 00:01:51,440
Bulger have stock all at once on Monday Tuesday then Orange is on Bannister tested and guns on Friday

26
00:01:51,440 --> 00:01:53,980
Saturday and Sunday's awful Bulger.

27
00:01:54,140 --> 00:01:58,610
So here we have days maybe that was OK.

28
00:01:58,760 --> 00:02:12,420
Then we have in days like First Monday then Tuesday then to this day.

29
00:02:13,050 --> 00:02:24,370
After Tuesday we have an escape and then to this day then we have Friday and we have secured

30
00:02:28,650 --> 00:02:29,780
after that.

31
00:02:29,970 --> 00:02:34,920
This is the second thing that we need here now for third column.

32
00:02:34,980 --> 00:02:42,840
Require something like this sales that is we know if it sells because it's in any analyses you will

33
00:02:42,930 --> 00:02:51,240
either just go for sales or go for the ghost or we can see that revenue have generated.

34
00:02:51,240 --> 00:02:57,510
And that's what you analyze in the Ponderosa also also known one like something like to whom I have

35
00:02:57,600 --> 00:02:58,820
sold things.

36
00:02:58,870 --> 00:02:59,590
No.

37
00:02:59,880 --> 00:03:06,530
So here I have sales and that is like on Monday but I sold hundred cage of heifers.

38
00:03:06,560 --> 00:03:07,790
That's something possible.

39
00:03:08,130 --> 00:03:08,800
But he's.

40
00:03:08,850 --> 00:03:16,450
But his brother so other 20 after that on Tuesday he sold 80 gauging then oranges we have.

41
00:03:16,500 --> 00:03:19,520
And one thing I for digital that I have used this twice.

42
00:03:19,530 --> 00:03:23,870
So that's all you have use twice because I have to consider six days here.

43
00:03:24,600 --> 00:03:31,920
So I have done something like Epsilon two days orange on two days and guns on two days so that you will

44
00:03:31,920 --> 00:03:39,000
understand the good buy better then the oranges oranges are more popular than have great demand to bugger

45
00:03:39,090 --> 00:03:42,810
sell 200 kids your oranges on the first day and 100 gauge you next.

46
00:03:43,560 --> 00:03:45,270
Then smuggler.

47
00:03:45,870 --> 00:03:48,290
He sold five cagey.

48
00:03:48,410 --> 00:03:49,060
Not crazy.

49
00:03:49,260 --> 00:04:01,470
Five guns on Friday then pencil tested and that's over dictionaries now get in the beginning and you

50
00:04:01,580 --> 00:04:06,140
go hey this now should be done.

51
00:04:06,140 --> 00:04:11,980
And then this is a dictionary here.

52
00:04:11,980 --> 00:04:15,040
Items that are epaulets drop days and seeds.

53
00:04:15,280 --> 00:04:22,570
Now convert this one into our data frame that is def just do BD door data frame.

54
00:04:22,570 --> 00:04:25,620
Now you are expert in this one.

55
00:04:26,530 --> 00:04:28,320
Then we have B.

56
00:04:28,630 --> 00:04:31,330
And if you print b you will get this.

57
00:04:31,690 --> 00:04:38,780
So this is the list or we get the data from which we are going to analyze here.

58
00:04:39,440 --> 00:04:47,220
But something is known as Group by is a we can see that inbuilt function that do something like if I

59
00:04:47,220 --> 00:04:54,840
want to have the means of my sale the standard deviation of my C Let me do that then you will understand

60
00:04:54,840 --> 00:04:55,550
better.

61
00:04:55,740 --> 00:04:59,840
Like if I consider something like X any variable.

62
00:05:00,240 --> 00:05:08,370
And first I need to go buy this all so I will do something like the F note group by all in small case

63
00:05:08,370 --> 00:05:16,020
letters nothing is in capitalized then I will group according to anything like I want to group according

64
00:05:16,020 --> 00:05:22,700
to items because I have two types of item there and now she's done.

65
00:05:22,740 --> 00:05:28,040
Now if you tried to print x when you will get something like that one because there is not any value.

66
00:05:28,080 --> 00:05:34,320
This one is just I have group this data frame according to the items and what that means is something

67
00:05:34,320 --> 00:05:40,770
like if I want to have the mean of all these since then I will do something like X don't mean

68
00:05:43,880 --> 00:05:46,820
then which type of mean we like it.

69
00:05:46,820 --> 00:05:53,120
I will get according to the item because I have grouped the item according the item down like I have

70
00:05:53,120 --> 00:05:55,310
three items apple orange and guns.

71
00:05:55,310 --> 00:05:59,840
So it will automatically scan for the items that are common like apple apple orange or injured in guns

72
00:05:59,850 --> 00:06:00,550
guns.

73
00:06:00,740 --> 00:06:07,220
If I also add there a third one that is denoting the Saturday and again the guns like if I do the

74
00:06:11,260 --> 00:06:18,430
guns here and then the day will be like does that show maybe have some may

75
00:06:21,330 --> 00:06:26,670
then this is will be like in five.

76
00:06:27,340 --> 00:06:31,750
And then I learned that one I will get into the one that is Sunday.

77
00:06:32,530 --> 00:06:43,510
And now if I perform the mean I will get this thing that is at Pulse the mean of all the [REMOVED] like

78
00:06:43,580 --> 00:06:50,530
hundred on Monday it on Tuesday hundred plus eighty 180 half of that one ninety because they are two

79
00:06:50,960 --> 00:06:56,760
then if I go for oranges three hundred divided by two one 150 then I will go for guns that is twenty

80
00:06:56,760 --> 00:07:02,470
by three six point six because there are three not two because it just take the mean value.

81
00:07:02,800 --> 00:07:08,430
So for me we will add only values and divided by the total number of values.

82
00:07:08,500 --> 00:07:11,360
So here is how you can group the element.

83
00:07:11,380 --> 00:07:17,840
So that's what you can also do for the big scales like if you are working on like thousands of data.

84
00:07:18,070 --> 00:07:23,110
Then according to item you will still do it and you will find that each item is best on sale.

85
00:07:23,110 --> 00:07:28,690
Like if you as a fruit seller like brother and you will get like hey I'm selling thousand apples in

86
00:07:28,690 --> 00:07:34,180
a week five hundred oranges and like 80 burned out or like that one.

87
00:07:34,180 --> 00:07:37,750
So we'll find that this thing is largest in say.

88
00:07:37,750 --> 00:07:41,950
Like here I have orange do orange is something I am selling the most.

89
00:07:42,250 --> 00:07:49,330
So I will go for larger stock of oranges smaller stock of apples and even our most molars like guns

90
00:07:49,360 --> 00:07:57,640
number of guns they so that's how by using these thing you can have these talks and all that and can

91
00:07:57,640 --> 00:07:58,150
work on that.

92
00:07:58,150 --> 00:08:02,300
You can also make a table of like cost the rupees you have made.

93
00:08:02,320 --> 00:08:07,950
You can also consider this one as it BS so that you can also analyze the profit.

94
00:08:08,020 --> 00:08:11,110
There are a few more methods related to that one at this point.

95
00:08:11,140 --> 00:08:16,920
This is clear that how you guys use these goodbye to analyze the data now you will find the fundamentals

96
00:08:16,930 --> 00:08:23,870
like if I want to have some of the items that I just use X notes some I will get one eighty there 20

97
00:08:23,920 --> 00:08:30,100
guns because I have sold 20 guns and 300 oranges that is 200 plus 300.

98
00:08:30,700 --> 00:08:35,820
If you want to had have standard deviation you will get the standard definition.

99
00:08:35,830 --> 00:08:38,910
This is what you can calculate the with formula.

100
00:08:38,980 --> 00:08:41,810
That's what I'm not going to do here.

101
00:08:41,980 --> 00:08:52,060
After that if you need to count that how many of these are so selling like I am selling Apple on 2D

102
00:08:52,120 --> 00:08:58,240
guns on 3D oranges on base here I have taken the example of base but you can work on anything like you

103
00:08:58,240 --> 00:09:03,400
are selling the number of that particular item according to any particular condition or any particular

104
00:09:03,850 --> 00:09:04,990
item with that one.

105
00:09:04,990 --> 00:09:05,960
Something like that.

106
00:09:07,240 --> 00:09:14,650
You can also find the maximum and minimum values like X load maximum you will get there.

107
00:09:14,860 --> 00:09:19,020
This one like Apple I have sold Apple maximum on Tuesday.

108
00:09:19,060 --> 00:09:24,130
So here on these do Apple on Tuesday's hundred.

109
00:09:24,190 --> 00:09:28,770
This is sort of showing me Tuesday a hundred but I have done on Monday.

110
00:09:28,780 --> 00:09:31,270
Guns on Sunday.

111
00:09:31,270 --> 00:09:39,430
Maybe this one is showing the next day and since it's showing maximum says that is hundred of apples

112
00:09:40,460 --> 00:09:48,380
then of guns and you can see two hundred of all ages but it's showing days differently.

113
00:09:48,380 --> 00:09:50,430
Maybe is because of index.

114
00:09:50,480 --> 00:10:01,010
So if you try minimum also you will get the minimum like 80 Apple guns five and hundred oranges.

115
00:10:01,150 --> 00:10:07,760
Also if you need all the information regarding these things like if you want to completely describe

116
00:10:07,760 --> 00:10:11,250
the table then you have a matter that is known as describe.

117
00:10:11,360 --> 00:10:15,910
So you just use X not describe.

118
00:10:16,310 --> 00:10:22,470
And then the apprentice nothing in the barometer because you have already got the item with the item.

119
00:10:22,640 --> 00:10:28,210
And when you return that one you will get something like this one apples selling on two days.

120
00:10:28,280 --> 00:10:33,440
Their mean is this one the standard deviation this one minimum value sold it.

121
00:10:33,890 --> 00:10:39,090
And that one here you have percentages and maximum value under.

122
00:10:39,530 --> 00:10:44,560
And here we have guns all the values of a level for guns oranges.

123
00:10:44,660 --> 00:10:51,130
And this one is like something here horizontally you can make this one vertically also like here you

124
00:10:51,130 --> 00:11:00,750
can just use another method that is transpose because people prefer something like this one apples guns

125
00:11:00,880 --> 00:11:06,460
and oranges they want to compare them and it's easy to comparing vertical lines so that's how you can

126
00:11:06,460 --> 00:11:08,120
also convert that one vertically.

127
00:11:08,340 --> 00:11:11,890
I have to do because that one is horizontally there.

128
00:11:11,960 --> 00:11:15,580
So this is how you can analyze the data by using panels.

129
00:11:15,770 --> 00:11:21,020
And you have some few methods by which you can easily get these things because to analyze any data you

130
00:11:21,620 --> 00:11:29,060
I believe you just need all these things only you either need mean maximum aluminium value some and

131
00:11:29,120 --> 00:11:35,030
you are not going to do something like on value at analyzing any product sales and you are performing

132
00:11:35,030 --> 00:11:37,780
their integration that something maybe.

133
00:11:38,870 --> 00:11:41,150
So this is how you're going to group by the elements.

134
00:11:41,150 --> 00:11:45,470
And I hope you understand that one this one is an important video so I would suggest you to go through

135
00:11:45,470 --> 00:11:47,970
this one again if you do not understand anything there.

136
00:11:48,500 --> 00:11:49,520
So thanks for watching.

137
00:11:49,520 --> 00:11:53,150
And if you still have any doubts then ask me I will help you there.

138
00:11:54,140 --> 00:11:55,250
So see in the next video.