1
00:00:00,150 --> 00:00:06,150
Hello, in the previous session, we all have performed lots of analysis on our data from important

2
00:00:06,160 --> 00:00:09,930
data, are doing lots of analysis, you do completely module.

3
00:00:09,930 --> 00:00:12,540
We have solved a complex problem statement.

4
00:00:12,810 --> 00:00:16,290
And in this session we have this two problem statement.

5
00:00:16,290 --> 00:00:24,060
The very first one, we have to analyze which base number gets popular by Montani.

6
00:00:24,180 --> 00:00:30,010
It means I have to group my data on the basis of base number and one as well.

7
00:00:30,510 --> 00:00:34,470
So let me show you what exactly is a data frame here.

8
00:00:34,470 --> 00:00:36,270
So this is exactly why data frame.

9
00:00:36,600 --> 00:00:41,730
So on this what I have to do, I have two very first group it on the basis of base.

10
00:00:42,060 --> 00:00:45,200
After that, I have to group it on the basis of month.

11
00:00:45,480 --> 00:00:49,490
So I'm just going to say D.F. Dot group by.

12
00:00:49,530 --> 00:00:57,090
And here I have to say very first I had a group on the basis of base, then after I had a group on the

13
00:00:57,090 --> 00:01:05,340
basis of one that said once I have all this stuff, I have to simply access this data over here.

14
00:01:05,580 --> 00:01:14,220
And whatever the time I have over here on this, I have to simply perform this count operation that

15
00:01:14,400 --> 00:01:16,370
it just executed.

16
00:01:16,370 --> 00:01:22,740
It will take some couple of seconds and it will return to some beautiful stats you will see with respect

17
00:01:22,740 --> 00:01:23,130
to this.

18
00:01:23,130 --> 00:01:24,810
With no having this this month.

19
00:01:24,810 --> 00:01:26,250
You have this this values.

20
00:01:26,250 --> 00:01:32,190
Let's say I have to create its data form so far that I'm just going to call this reset on this index

21
00:01:32,190 --> 00:01:32,850
over here.

22
00:01:33,120 --> 00:01:35,970
And after doing this, I have to store it somewhere else.

23
00:01:36,180 --> 00:01:38,820
So this is exactly my base data frame.

24
00:01:38,820 --> 00:01:46,770
And after it, I have to just print money as it just get executed and it will definitely return as this

25
00:01:46,770 --> 00:01:48,360
beautiful little phrase.

26
00:01:48,390 --> 00:01:51,270
Now you will see this back to each and every base number.

27
00:01:51,510 --> 00:01:56,130
You have some kind of values that let's say what I'm going to do.

28
00:01:56,250 --> 00:02:01,950
I have to simply visualize which base number gets popular by month name.

29
00:02:01,990 --> 00:02:08,490
So for this, I'm just going to use my line plot that you can use your Lindberg's on Gartley.

30
00:02:08,490 --> 00:02:12,240
Either you can use from Metalocalypse, either you can use on Seabourne.

31
00:02:12,240 --> 00:02:13,170
It's all up to you.

32
00:02:13,440 --> 00:02:15,390
So let me use Likert from Seimone.

33
00:02:15,390 --> 00:02:24,660
So I'm going to say as an dot line plot and just shift Gustav and all your costs about Iapetus in front

34
00:02:24,660 --> 00:02:25,080
of you.

35
00:02:25,530 --> 00:02:27,930
So here are the very first on X axis.

36
00:02:27,930 --> 00:02:33,120
I just need my mind and definitely on Y axis.

37
00:02:33,390 --> 00:02:37,430
I just want my count, which is exactly my time.

38
00:02:37,920 --> 00:02:44,520
Once I have all the stuff, let's say I have to split my line plot on the basis of base.

39
00:02:44,530 --> 00:02:48,030
So I'm going to say on the basis of base, I have to split it.

40
00:02:48,420 --> 00:02:51,450
Then I have to measure what exactly mine it are famous.

41
00:02:51,930 --> 00:02:54,000
So my data frame is exactly my base.

42
00:02:54,710 --> 00:02:59,820
I have to customize my fit because the thought is I have to set my own trigger site.

43
00:03:00,060 --> 00:03:08,280
So I am going to split dot figure and here I have to set my own finger side like the size of Stankonia

44
00:03:08,290 --> 00:03:11,760
six, whatever side you want, just executed.

45
00:03:11,760 --> 00:03:17,610
It will take some couple of seconds, but now you will see where here this is with respect to each and

46
00:03:17,610 --> 00:03:20,670
every piece number and this green line.

47
00:03:20,670 --> 00:03:27,150
You can definitely come up with this cantus and yeah, this base number, which is exactly be zero to

48
00:03:27,150 --> 00:03:31,140
six and seven, gets popular bi monthly.

49
00:03:31,470 --> 00:03:35,730
That's a type of conclusion you can fetch from this visit.

50
00:03:36,060 --> 00:03:43,200
So let's go ahead with our next problem, a statement in which you have to perform cross analysis using

51
00:03:43,200 --> 00:03:44,370
your heat map.

52
00:03:44,370 --> 00:03:49,320
And if you guys are not that much of it, what exactly is a heat map?

53
00:03:49,680 --> 00:03:57,360
So heat map is advance level of radiation, which definitely uses my data or my magic.

54
00:03:57,450 --> 00:04:04,410
And wherever the value of that particular data add, that particular index will be high and heat map

55
00:04:04,410 --> 00:04:08,760
will rate on that particular index as a higher density.

56
00:04:08,760 --> 00:04:10,380
That's what my heat map will do.

57
00:04:10,800 --> 00:04:14,790
So here what I am going to do, I'm just going to where it goes.

58
00:04:14,820 --> 00:04:16,410
I have to define some functions.

59
00:04:16,410 --> 00:04:17,070
So let me check.

60
00:04:17,070 --> 00:04:18,750
What exactly is the problem statement?

61
00:04:18,750 --> 00:04:19,710
The very first one.

62
00:04:19,950 --> 00:04:21,030
Yeah, the very first one.

63
00:04:21,030 --> 00:04:28,140
I have to perform a heat map between this hour and then it means I have to group my data on the basis

64
00:04:28,140 --> 00:04:30,210
of this week and hour.

65
00:04:30,510 --> 00:04:38,370
So for this what you guys can do very us, I'm just going to say dot gloopy and here I have to group

66
00:04:38,370 --> 00:04:40,740
my data on the basis of the day.

67
00:04:41,160 --> 00:04:45,480
After that, I have to group my data on the basis of this hour.

68
00:04:45,900 --> 00:04:50,130
Once I have all this stuff, let's say very first I have defined some functions.

69
00:04:50,130 --> 00:04:52,680
I'm just going to define a function using that keyword.

70
00:04:52,980 --> 00:04:58,560
And here my function name is like, say, count on the school rules that count my number of rules.

71
00:04:58,830 --> 00:04:59,730
And here.

72
00:05:00,020 --> 00:05:07,460
It will exactly receive some barometer and on the basis of barometer here, I'm going to say just return

73
00:05:07,460 --> 00:05:07,820
land.

74
00:05:08,210 --> 00:05:14,810
So here I'm going to say return land of whatever parameter in this function will receive.

75
00:05:14,840 --> 00:05:16,980
So here I'm going to say it is my rules.

76
00:05:17,420 --> 00:05:24,630
So this function, this does so now I have just executed and now here I have to just apply this count

77
00:05:24,650 --> 00:05:25,750
and a squirrel's function.

78
00:05:26,000 --> 00:05:30,830
So don't apply, count, underscore.

79
00:05:31,400 --> 00:05:33,200
So this is exactly my function name.

80
00:05:33,540 --> 00:05:37,510
So if I'm going to execute it, it will fit into some values order.

81
00:05:37,580 --> 00:05:40,570
And here you will see this is my day.

82
00:05:40,620 --> 00:05:43,600
This is our and here I have some values.

83
00:05:43,610 --> 00:05:47,330
It means having this week and having this hour.

84
00:05:47,570 --> 00:05:50,050
I have that much number of count.

85
00:05:50,240 --> 00:05:52,150
Let's say I have to store it somewhere else.

86
00:05:52,210 --> 00:05:58,100
Let's say I'm going to say it is exactly my let's say because whatever name you want to assign, it's

87
00:05:58,100 --> 00:05:58,640
all up to you.

88
00:05:59,000 --> 00:06:00,770
So this is exactly my Bycroft.

89
00:06:00,770 --> 00:06:03,050
And after it, I'm also going to print it.

90
00:06:03,290 --> 00:06:03,880
That's it.

91
00:06:03,920 --> 00:06:04,480
That's OK.

92
00:06:04,760 --> 00:06:09,850
And after what I have to do, let's say I have to create it's pivot table.

93
00:06:09,860 --> 00:06:16,970
So far this what I'm going to do, whatever, because I have on this, I am basically going to call

94
00:06:16,970 --> 00:06:23,660
this stack operation that said it will convert it into my pivot table.

95
00:06:23,660 --> 00:06:27,290
So I'm just going to store it in, say, pivot and eat.

96
00:06:27,560 --> 00:06:28,490
Exactly.

97
00:06:28,490 --> 00:06:32,060
Let's say I have to print might be so just executed.

98
00:06:32,060 --> 00:06:40,190
And this is a beautiful pivot table where you have your data in the form of here you have all the indexes

99
00:06:40,400 --> 00:06:45,080
here, your Vectibix indexes and our become columns.

100
00:06:45,080 --> 00:06:51,590
And if, let's say in this in this matrix or in this data, let's say if you have to come up with some

101
00:06:51,590 --> 00:06:59,720
conclusion on what we did and on what our your rights or maximum are, you have a maximum count.

102
00:06:59,930 --> 00:07:03,390
So it is hard to visualize from this huge chunk of data.

103
00:07:03,710 --> 00:07:10,190
So in such scenarios, in such scenarios, your heat map is going to be pineal over here so that if

104
00:07:10,420 --> 00:07:15,350
you have to use your heat map here, here, I'm going to say S.A.S. dot heat map.

105
00:07:15,710 --> 00:07:18,400
And here you have to just mention your field.

106
00:07:18,620 --> 00:07:21,530
So I'm just going to mention my pivot and two.

107
00:07:21,830 --> 00:07:25,920
And if I'm going to execute it, let me execute and let me show you a thing.

108
00:07:26,570 --> 00:07:33,320
Now you'll see over here, this is your favorite table, but still it doesn't look that much user-friendly.

109
00:07:33,620 --> 00:07:36,790
So you have to just customize it for this.

110
00:07:36,800 --> 00:07:44,360
Let's say I'm going to say blt dot figger and here I have a parameter which is fixit, let's say my

111
00:07:44,360 --> 00:07:44,880
figures.

112
00:07:44,930 --> 00:07:52,030
I just again executed and now up to some greater extent it is somehow very good.

113
00:07:52,040 --> 00:07:58,310
And from this heat map you will see this is exactly what color bar and you will visualize over here

114
00:07:58,310 --> 00:08:04,160
in this almost in this evening time, almost in each and every day you have a rush.

115
00:08:04,430 --> 00:08:08,360
So that's a type of entrance you can easily fetch from this heat map.

116
00:08:08,510 --> 00:08:12,470
But you can't find this in friends from this Beattyville.

117
00:08:12,800 --> 00:08:21,100
So whenever you have a huge chunk of data at the time, your heat map is going to be final order almost

118
00:08:21,110 --> 00:08:25,460
in 90 percent of cases, even machine learning as well.

119
00:08:25,640 --> 00:08:28,420
So here what I'm going to do let's see here.

120
00:08:28,430 --> 00:08:35,180
My problem statement was I have to perform this heat map for our day and for a month and day and from

121
00:08:35,180 --> 00:08:36,730
month and week as well.

122
00:08:37,100 --> 00:08:40,660
So let's say I have to perform a similar operation and again and again.

123
00:08:40,940 --> 00:08:43,190
So why not try to just create a function?

124
00:08:43,190 --> 00:08:51,110
Because whenever you have to perform certain tasks again and again, the best way is to create a function

125
00:08:51,110 --> 00:08:56,690
over there so that if I have to define some function, let's say that function name is nothing, but

126
00:08:56,690 --> 00:08:58,820
let's say function, name is heightmap.

127
00:08:59,060 --> 00:09:03,290
So I'm just going to define some function and it will assume some parameters.

128
00:09:03,290 --> 00:09:04,540
I can define it later.

129
00:09:05,150 --> 00:09:08,980
So very first, I just need I just need some people.

130
00:09:09,030 --> 00:09:14,360
David, so let me just copy this code over here, which is exactly this one.

131
00:09:14,840 --> 00:09:19,000
And this is exactly code that I have copied and I have to do it here.

132
00:09:19,280 --> 00:09:19,670
Here.

133
00:09:19,670 --> 00:09:23,510
I have to just do some modification here.

134
00:09:23,510 --> 00:09:30,500
I'm going to say I have to see my very first column, but then I have column two and here I have to

135
00:09:30,500 --> 00:09:35,090
just set the set here, my column one here, my column two.

136
00:09:35,600 --> 00:09:42,080
After doing all these things, what I am going to do, I have to convert it into some B whatever for

137
00:09:42,080 --> 00:09:42,380
this.

138
00:09:42,380 --> 00:09:45,260
Either you can type manually or you can do copy paste.

139
00:09:45,260 --> 00:09:46,250
That's all up to you.

140
00:09:46,430 --> 00:09:53,060
So I have to just copy paste or they are just copy, just be so in disfavoured.

141
00:09:53,060 --> 00:09:54,770
You have your periodic table.

142
00:09:55,070 --> 00:09:58,910
After doing all these things, you have to just visualize your.

143
00:10:00,250 --> 00:10:07,300
That said, and here I'm just going to paste, and here you have to provide proper indentation, otherwise

144
00:10:07,300 --> 00:10:09,860
it will give us some added.

145
00:10:10,150 --> 00:10:16,990
And what I have to do, I have to simply return this heat map and warns if I'm going to execute it.

146
00:10:17,260 --> 00:10:22,030
Now, our problem is statement was I have to perform it for our.

147
00:10:22,120 --> 00:10:28,060
And so for this what I'm going to do, I'm just going to call this our heat map function, which is

148
00:10:28,060 --> 00:10:29,560
exactly this heat map.

149
00:10:29,830 --> 00:10:31,690
And here my very first parameter.

150
00:10:31,710 --> 00:10:37,930
Exactly the second parameter is exactly what that said, just executed.

151
00:10:37,930 --> 00:10:43,390
It will take some couple of seconds and it will return as my beautiful heat map in a while.

152
00:10:43,750 --> 00:10:48,280
And now you will figure out this is a beautiful heat map here.

153
00:10:48,430 --> 00:10:53,160
And from this beautiful heat map, you can definitely come up with a conclusion.

154
00:10:53,200 --> 00:10:53,680
Yeah.

155
00:10:54,160 --> 00:11:01,450
In each and every evening, almost in each and every day, you have certain kind of rush, whereas whereas

156
00:11:01,660 --> 00:11:05,410
in this midnight you don't have any kind of rush.

157
00:11:05,410 --> 00:11:11,470
Because I have I had this little bar over here and depending upon this color bar, I can definitely

158
00:11:11,470 --> 00:11:13,900
come up with some conclusion in a similar way.

159
00:11:13,900 --> 00:11:19,290
You can perform both the problem statement by just passing parameter.

160
00:11:19,300 --> 00:11:21,580
That's a very piece of cake lighting.

161
00:11:21,970 --> 00:11:23,890
So that is exactly the assignment.

162
00:11:23,890 --> 00:11:27,250
And you have to infer from this as well that it's not like that.

163
00:11:27,340 --> 00:11:29,920
You have to just pass this parameter and that's okay.

164
00:11:29,950 --> 00:11:37,630
You have to infer from this heat map as well, because if you're confused, because if your visual isn't

165
00:11:37,660 --> 00:11:42,390
going to conclude anything, then it makes no sense for analysis.

166
00:11:42,400 --> 00:11:45,990
So that's all about this session of the session very much.

167
00:11:46,000 --> 00:11:46,700
Thank you.

168
00:11:46,750 --> 00:11:47,690
Have a nice day.

169
00:11:47,710 --> 00:11:48,540
Keep learning.

170
00:11:48,550 --> 00:11:49,450
Keep going.

171
00:11:49,600 --> 00:11:50,470
Keep practicing.