1
00:00:00,560 --> 00:00:06,540
All so in the previous session, we have done some of the very beautiful analysis, we have deal with

2
00:00:06,540 --> 00:00:11,880
data processing stage, we have prepared our data for this beautiful pie chart.

3
00:00:12,150 --> 00:00:15,460
So in this session, we are basically going to deal with this problem.

4
00:00:15,510 --> 00:00:22,260
Statement in the very first one is I have to analyze customer on the basis of different different attributes

5
00:00:22,260 --> 00:00:23,550
and off the grid.

6
00:00:23,730 --> 00:00:31,470
I have to automate my all the analysis that I'm going to perform in this very first problem statement.

7
00:00:31,770 --> 00:00:35,190
So second one statement is a little bit tricky.

8
00:00:35,430 --> 00:00:43,520
So I'm going to show you how exactly an automated analysis by just writing a simple function in Python.

9
00:00:43,860 --> 00:00:50,400
So the very first one is I have to analyze customer on the basis of education, status, income and

10
00:00:50,400 --> 00:00:52,270
different different attributes as well.

11
00:00:52,830 --> 00:00:59,310
So what I have to do right over here very first and is going to use Gartley for so that I will provide

12
00:00:59,310 --> 00:01:01,420
you some interactive results.

13
00:01:01,830 --> 00:01:08,130
So let's say I'm going to use plotty and in this I'm going to call my box plot and inbox box.

14
00:01:08,140 --> 00:01:11,860
Got ready for if you are going to shift plus tab.

15
00:01:11,880 --> 00:01:13,890
So that is exactly my native.

16
00:01:14,400 --> 00:01:23,220
So here I'm going to see my data center and now let's say I have to analyze education and income.

17
00:01:24,000 --> 00:01:30,350
I can see what type of income my customers are generated that have different different background of

18
00:01:30,360 --> 00:01:31,890
education so far.

19
00:01:31,890 --> 00:01:37,830
This basically, I'm going to say on X axis, let's say I have education.

20
00:01:38,220 --> 00:01:40,230
So this is exactly my education.

21
00:01:40,470 --> 00:01:45,500
Very first, I'm going to check whether education is available in my native or not.

22
00:01:45,780 --> 00:01:48,990
So I'm simply going to say, DataDot Gollum's.

23
00:01:48,990 --> 00:01:54,050
So you will see education is available over here and now on Y-axis.

24
00:01:54,060 --> 00:01:55,950
Basically I need income.

25
00:01:55,950 --> 00:02:00,030
So here I'm going to see Onvia says I have income.

26
00:02:00,240 --> 00:02:03,770
Let's say I have to split my this box Volkskrant.

27
00:02:04,050 --> 00:02:10,470
So very first I'm just going to be executed and I will show you later how exactly you can split this

28
00:02:10,470 --> 00:02:14,150
bastard on the basis of, let's say, a personal loan.

29
00:02:14,400 --> 00:02:20,550
So for this, I have to use this visit underscored Colden parameters.

30
00:02:20,560 --> 00:02:23,970
So here you have to pass your personal loan.

31
00:02:24,150 --> 00:02:31,980
You will see this exactly is that feature on which on the basis of you have to split your box.

32
00:02:32,700 --> 00:02:34,830
So just copy paste over here.

33
00:02:34,830 --> 00:02:40,740
And if you are going to again execute it now, you will see for personal loan equals to zero.

34
00:02:40,740 --> 00:02:46,410
It means this is the scenario that a customer is not going to avail for a loan.

35
00:02:46,590 --> 00:02:55,440
So in such scenarios, a customer who has education background as one, it means basically he is undergraduate.

36
00:02:55,590 --> 00:03:02,790
So in case of undergraduate and he is not applying for a loan in such case, this exactly is a distribution

37
00:03:02,790 --> 00:03:03,940
of all the customers.

38
00:03:03,960 --> 00:03:10,860
Similarly, in case of if education background is one and the customer is going to apply for the loan.

39
00:03:11,010 --> 00:03:19,410
So this exactly is a distribution of the customers where maximum income is one nine five and here exactly

40
00:03:19,410 --> 00:03:25,330
minimum is 60 and median, which is exactly the middle value of the data.

41
00:03:25,620 --> 00:03:28,890
So this exactly is one that's a type of influence.

42
00:03:28,890 --> 00:03:35,120
How exactly you can fit inside for you this visa's or I can say Volkskrant.

43
00:03:35,130 --> 00:03:43,320
So from this box start, you can see income of the customers who are, well, personal to this one are

44
00:03:43,350 --> 00:03:47,600
almost same irrespective of their education background.

45
00:03:47,850 --> 00:03:51,300
Let's say I have to analyze this stuff in very depth.

46
00:03:51,600 --> 00:03:56,340
So in such case, I can say I'm just going to call this board here.

47
00:03:56,340 --> 00:04:00,930
I'm going to say S.A.C. or discard and here basically ready for this.

48
00:04:01,080 --> 00:04:02,910
I have to excuse my personal loans.

49
00:04:03,010 --> 00:04:05,040
I'm going to say personal loan.

50
00:04:05,190 --> 00:04:07,230
So this is exactly my condition.

51
00:04:07,410 --> 00:04:10,920
And now basically here I'm going to see close to zero.

52
00:04:11,100 --> 00:04:12,750
So this exactly is the filter.

53
00:04:12,930 --> 00:04:15,900
And now I have to pass this filtering mediator fame.

54
00:04:16,170 --> 00:04:19,200
So this will give me my entire data.

55
00:04:19,650 --> 00:04:27,840
And now on this data form, basically I have to excuse my income column, so I have to exit this income

56
00:04:28,020 --> 00:04:28,590
column.

57
00:04:28,830 --> 00:04:37,410
And if you are going to execute it now, you will see this exactly is a distribution of those customers,

58
00:04:37,560 --> 00:04:39,930
their personal loan equal to zero.

59
00:04:39,930 --> 00:04:42,910
It means they are not going to avail for the loan.

60
00:04:43,060 --> 00:04:48,840
Similarly, let's say I want distribution of those customers that are going to avail for the loan.

61
00:04:49,110 --> 00:04:51,480
So here I'm just going to copy paste in here.

62
00:04:51,720 --> 00:04:54,840
I'm just going to do some modifications over here.

63
00:04:55,080 --> 00:04:59,700
So if you are going to execute it, you will see the distributions are.

64
00:04:59,760 --> 00:05:06,590
We do have some mismatch, so in such case, what you guys can do, let's say I'm going to sign over

65
00:05:06,600 --> 00:05:15,000
here as histogram equals to Thors, similarly over here, I'm going to say histogram equals to that.

66
00:05:16,320 --> 00:05:22,710
So if, again, you are going to execute it now, you will see this type of distribution.

67
00:05:22,740 --> 00:05:28,410
Let's say I'm also going to assign some level because it is a little bit tricky if you are going to

68
00:05:28,410 --> 00:05:30,960
influence some from this result.

69
00:05:31,260 --> 00:05:36,890
So for the foreseeable value, I am going to assign some label and label.

70
00:05:36,900 --> 00:05:45,610
I'm going to say income with no personal income, with no personal loan.

71
00:05:45,780 --> 00:05:52,560
And in this case, I have to assign basically label as income with personal.

72
00:05:53,040 --> 00:05:56,280
So this exactly is a label for this one.

73
00:05:56,550 --> 00:05:59,790
So now what do you have to do to assign your labels?

74
00:05:59,980 --> 00:06:06,670
You have to just call your BLT dot and function from your plant.

75
00:06:07,380 --> 00:06:09,420
So this exactly is that.

76
00:06:09,540 --> 00:06:13,620
So now you will see the labels are in the middle of the.

77
00:06:14,500 --> 00:06:17,470
So let's say I'm going to set my own window.

78
00:06:17,480 --> 00:06:21,110
So for this, I'm basically going to call this bill or figure.

79
00:06:21,390 --> 00:06:25,480
And in this basically I have to set my own phagocytes.

80
00:06:25,830 --> 00:06:28,940
So here I'm going to say, let's say to my end.

81
00:06:29,310 --> 00:06:34,850
So if you are going to execute it now, you will see this beautiful result.

82
00:06:35,100 --> 00:06:41,970
So basically, this blue distribution represent the income of those customers, which did not avail

83
00:06:41,970 --> 00:06:43,530
for lone purpose.

84
00:06:43,530 --> 00:06:49,500
And this is exactly the distribution of those which have a will for the loan.

85
00:06:49,740 --> 00:06:52,050
So here you can in Frances.

86
00:06:52,080 --> 00:06:52,470
Yeah.

87
00:06:52,890 --> 00:07:02,070
Customers who have agreed personal loan seems to have higher income than those who didn't avail for

88
00:07:02,070 --> 00:07:02,720
the Boston.

89
00:07:02,730 --> 00:07:07,520
And that's how exactly you can influence from your results.

90
00:07:07,540 --> 00:07:15,300
So let's move ahead to the next one problem statement in which you have to automate your analysis.

91
00:07:15,300 --> 00:07:21,390
What exactly is the analysis that you have done over here by simply writing this code?

92
00:07:21,630 --> 00:07:25,430
Now you have to automate all these stuff.

93
00:07:25,800 --> 00:07:30,300
So what you guys can do, you can simply copy this entire blocks of code.

94
00:07:30,660 --> 00:07:38,250
Let's say for this, I have to create a new function, let's say name as plot to just be stored here.

95
00:07:38,580 --> 00:07:47,980
And now you have to simply paste it here and provide the right indentation because Python works on indentation.

96
00:07:48,390 --> 00:07:53,850
So now here I'm going to say the very first is my colon one.

97
00:07:54,180 --> 00:07:55,290
So exactly.

98
00:07:55,650 --> 00:08:03,540
This is exactly let's say I'm going to name this income as colon one, right in the column one.

99
00:08:04,160 --> 00:08:11,600
So this is also my column one, and now my personal loan becomes column two.

100
00:08:11,970 --> 00:08:19,020
So here I have to say this is my column too, and this exactly is also my column too.

101
00:08:19,230 --> 00:08:21,270
So I have done all this data.

102
00:08:21,390 --> 00:08:26,080
Now, in case of label, I have to also do some modification.

103
00:08:26,370 --> 00:08:33,300
So here I'm going to say whatever label I'm going to pass in my function that will get received when

104
00:08:33,300 --> 00:08:34,870
I'm going to call my function.

105
00:08:35,130 --> 00:08:41,100
So here in label, I have to just say label one.

106
00:08:41,640 --> 00:08:46,170
And here in case of label, I have to say just label two.

107
00:08:46,620 --> 00:08:56,100
And in case, if you have to assign some titles so you can see or title and let's say some assign some

108
00:08:56,100 --> 00:08:56,720
title.

109
00:08:57,120 --> 00:09:01,190
So of course that will get deceived by your function.

110
00:09:01,560 --> 00:09:03,060
So just execute it.

111
00:09:03,270 --> 00:09:09,790
And now to get your visa, you have to basically call these functions that you have written over here.

112
00:09:10,080 --> 00:09:13,260
So for this, you have to say just call a function plot.

113
00:09:13,590 --> 00:09:21,810
And now the very first one parameter, basically my income and the next one parameter is basically my

114
00:09:22,110 --> 00:09:23,560
personal loan.

115
00:09:24,030 --> 00:09:26,420
So this is my second parameter.

116
00:09:26,760 --> 00:09:30,700
And the third one parameter is basically your label.

117
00:09:30,730 --> 00:09:36,810
So if you are going to press shift plus tab, you will see this exactly as all the parameters that the

118
00:09:36,810 --> 00:09:40,500
function will receive because you have defined this function in such a way.

119
00:09:40,890 --> 00:09:43,450
So the third one is basically one label one.

120
00:09:43,710 --> 00:09:49,930
So this is exactly level one you can copy from here or you can manually type over there as well.

121
00:09:50,340 --> 00:09:59,230
So this exactly is my first label and my second label is basically income with both.

122
00:10:00,800 --> 00:10:06,880
So this exactly is my second Lupul, let's say, if you have to assign some of the titles.

123
00:10:07,200 --> 00:10:11,450
So in such case, you can assign, let's say, distribution of income.

124
00:10:11,460 --> 00:10:15,100
So I'm going to say income distribution.

125
00:10:15,380 --> 00:10:20,330
So just execute using oil, plus enter and congratulations.

126
00:10:20,330 --> 00:10:24,050
You have got your beautiful with what you have had before.

127
00:10:24,290 --> 00:10:25,550
So that's a pretty good way.

128
00:10:25,550 --> 00:10:31,880
How exactly you can automate the analysis by just writing this blocks of code, by just writing this

129
00:10:32,150 --> 00:10:35,120
blog function, by just calling this single function.

130
00:10:35,310 --> 00:10:39,550
You have got your beautiful results in a similar way.

131
00:10:39,560 --> 00:10:46,310
You can call this function multiple times depending upon what are the different different independent

132
00:10:46,310 --> 00:10:48,290
variables you have in your data.

133
00:10:48,350 --> 00:10:55,100
Let's say, again, you have to call this function in case of, let's say, credit card average.

134
00:10:55,130 --> 00:11:02,710
So if you are going to say here you have where I have this Sethe Abeed you feature basically.

135
00:11:02,720 --> 00:11:10,020
So here I'm just going to paste all the code and this time I'm going to see my income is not over there

136
00:11:10,040 --> 00:11:13,510
because I have to do analysis on a basis of security.

137
00:11:13,700 --> 00:11:18,950
The key, a reality, which is basically my credit card average.

138
00:11:19,250 --> 00:11:22,360
And now the second one is basically my personal loan.

139
00:11:22,640 --> 00:11:28,740
And this time this is exactly my credit card average here.

140
00:11:28,970 --> 00:11:32,990
So here I'm going to see credit card average.

141
00:11:32,990 --> 00:11:39,370
And here also I have to rhenium as credit card average with personal loan.

142
00:11:39,560 --> 00:11:44,900
And this time this is exactly credit card average distribution.

143
00:11:45,120 --> 00:11:51,400
So if you are going to execute it now, you will see this type of beautiful distribution.

144
00:11:51,620 --> 00:11:58,640
Now you will see the importance of automation, how exactly you can get your beautiful bisel by just

145
00:11:58,850 --> 00:12:07,330
writing some features in this blog function rather than writing all these blocks of code again and again.

146
00:12:07,640 --> 00:12:16,400
So if you have two in friends from this visa, you will see distribution in case of with no personal

147
00:12:16,400 --> 00:12:16,740
loan.

148
00:12:16,910 --> 00:12:23,780
So it is a little bit having some skewness and of course little Skewness in case of normal distribution.

149
00:12:24,050 --> 00:12:31,730
Similarly, in case of this one where I have a credit card with personal loan, it means person with

150
00:12:31,730 --> 00:12:38,640
credit card, average with personal loan will basically travel to this orange color distribution.

151
00:12:38,930 --> 00:12:43,000
Similarly, you guys can copy this code again.

152
00:12:43,280 --> 00:12:48,170
Let's say I have to again call this function for different features as well.

153
00:12:48,650 --> 00:12:58,730
Let's say in case of Martje get so here I have to simply write this feature name as mortgage and here

154
00:12:58,730 --> 00:13:03,310
I have to see mortgage of customers with no personal loan.

155
00:13:03,500 --> 00:13:06,650
So here I am going to see very first, just remove this.

156
00:13:06,860 --> 00:13:13,910
And here, let's say I'm going to see more mortgage of customers with no personal loans.

157
00:13:14,060 --> 00:13:19,300
And copy this and let's say you have to deal with as well.

158
00:13:19,730 --> 00:13:27,030
So market of customers with personal loan, let's say you have to assign some title.

159
00:13:27,090 --> 00:13:31,920
So here I'm going to say mortgage of customers distribution.

160
00:13:31,940 --> 00:13:40,850
So just execute it and you will get this type of distribution for mortgage of customers with no personal

161
00:13:40,850 --> 00:13:43,200
loan and having a personal loan.

162
00:13:43,490 --> 00:13:51,650
So if you have two friends from this visa, you can say pupal with high mortgage value or you can say

163
00:13:51,860 --> 00:13:56,770
more than four hundred k have a well, personal loan.

164
00:13:57,110 --> 00:14:03,400
So that's a type of influence how exactly you can fetch from your visa.

165
00:14:03,740 --> 00:14:05,660
So that's the power of automation.

166
00:14:05,960 --> 00:14:09,080
How exactly you can automate the analysis in a similar way.

167
00:14:09,080 --> 00:14:16,400
You can automate all that analysis by just writing these blocks of code and function in classes that

168
00:14:16,400 --> 00:14:21,970
exactly how Poinar how exactly floridly and all those advanced library works.

169
00:14:22,460 --> 00:14:23,900
So hope you like the session.

170
00:14:24,040 --> 00:14:24,680
Thank you.

171
00:14:24,890 --> 00:14:25,790
Have a nice day.

172
00:14:25,820 --> 00:14:26,630
Keep learning.

173
00:14:26,810 --> 00:14:27,560
Keep going.

174
00:14:28,070 --> 00:14:29,000
Keep motivating.