Dedicated to the Three Kingdoms lovers , I hope friends who like the Three Kingdoms can discuss it together , Deepen the understanding of the legendary Three Kingdoms era
Basic concepts of data analysis :
The data is divided into “ It's not measurable ” The data and “ Can be measured ” The data of .
Unmeasurable data is called “ Classified data ”(Category Data or Categorical Data.), And measurable data is called “ Numerical data ”(Numerical Data).
Group median :Class Midpoint
frequency :Frequency
Relative times :Relative Frequency
Relative times = The number of data in each group ÷ The total number of data
Frequency distribution table and histogram

Group spacing conceals the distribution of data within each group , To reflect the general level of data in each group , We usually use group median as a representative value of the group data (class midpoint). The midpoint between the upper and lower limits is called the group median , It is a simple average of the upper and lower limits of each group , That is, the group median value =( Lower limit + ceiling )/2.
If you meet the open group , The median value of the upper opening group is = Lower limit + Distance between adjacent groups /2; The median value of the lower opening group is = ceiling - Distance between adjacent groups /2.
There is a necessary assumption when using group median to represent a set of data , That is, the data of each group are evenly distributed in the group or symmetrically distributed on both sides of the group median . If the distribution of the actual data does not conform to this assumption , Using group median as a representative of a group of data will have a certain error .
Establish a data analysis environment :

SELECT CASE WHEN intelligence > 0
AND intelligence < 10 THEN '0-9'
WHEN intelligence >= 10
AND intelligence < 20 THEN '10-19'
WHEN intelligence >= 20
AND intelligence < 30 THEN '20-29'
WHEN intelligence >= 30
AND intelligence < 40 THEN '30-39'
WHEN intelligence >= 40
AND intelligence < 50 THEN '40-49'
WHEN intelligence >= 50
AND intelligence < 60 THEN '50-59'
WHEN intelligence >= 60
AND intelligence < 70 THEN '60-69'
WHEN intelligence >= 70
AND intelligence < 80 THEN '70-79'
WHEN intelligence >= 80
AND intelligence < 90 THEN '80-89'
WHEN intelligence >= 90
AND intelligence <= 100 THEN '90-100'
END grouping ,
COUNT(*) The number of
FROM FactSanguo11
GROUP BY CASE WHEN intelligence > 0
AND intelligence < 10 THEN '0-9'
WHEN intelligence >= 10
AND intelligence < 20 THEN '10-19'
WHEN intelligence >= 20
AND intelligence < 30 THEN '20-29'
WHEN intelligence >= 30
AND intelligence < 40 THEN '30-39'
WHEN intelligence >= 40
AND intelligence < 50 THEN '40-49'
WHEN intelligence >= 50
AND intelligence < 60 THEN '50-59'
WHEN intelligence >= 60
AND intelligence < 70 THEN '60-69'
WHEN intelligence >= 70
AND intelligence < 80 THEN '70-79'
WHEN intelligence >= 80
AND intelligence < 90 THEN '80-89'
WHEN intelligence >= 90
AND intelligence <= 100 THEN '90-100'
END
ORDER BY grouping SELECT *
FROM FactSanguo11
WHERE intelligence >= 90
AND intelligence <= 100
ORDER BY intelligence DESC

The intelligence distribution of the Three Kingdoms

Intelligence groups

Group median

The number of

Relative times

0-9

5

12

0.02

10-19

14.5

19

0.03

20-29

25

33

0.05

30-39

34.5

70

0.10

40-49

44.5

72

0.11

50-59

54.5

76

0.11

60-69

64.5

129

0.19

70-79

74.5

173

0.26

80-89

84.5

65

0.10

90-100

95

21

0.03

total

670

1.00

Histogram :

As you can see , The group spacing in the table above is 9. The reason for choosing 9, There are no mathematical rules , It's all up to me . you 're right , How much group distance should be set , According to the analyst's own judgment .
The number distribution table made by subjectively set group distance is not convincing , You can't make it public in front of others , Isn't there a way to make group distance according to mathematical principles ? Maybe someone will have such a question . in fact , There is a way .


Step by step 2 Based on the calculated group distance , Make the following number distribution table :

Intelligence groups

Group median

The number of

Relative times

0-10

5

13

0.02

11-20

15

18

0.03

21-30

25

39

0.06

31-40

35

71

0.11

41-50

45

70

0.10

51-60

55

78

0.12

61-70

65

146

0.22

71-80

75

160

0.24

81-90

85

58

0.09

91-100

95

17

0.03

total

670

1.02

Histogram :

 

《BI That little thing 》 More related articles on the analysis of the intelligence distribution of the characters in the Three Kingdoms

  1. 《BI That little thing — The art of data 》 indexes

    original ·<BI That little thing — The art of data > The tutorial is free Dear Garden Friends , Hello everyone , I am a Bobby, I'm learning BI And development of the project in the process of some insights and ideas , Organized and compiled some learning materials , Originally, it was just for internal learning , But for convenience ...

  2. 《BI That little thing 》Microsoft Clustering algorithm —— The identity of the Three Kingdoms

    What is cluster analysis ?  Cluster analysis is an exploratory data analysis method . Usually , We use cluster analysis to group seemingly disordered objects . classified , In order to better understand the object of study . Clustering results require high similarity of objects in a group , The similarity of objects between groups is low . Data in three countries ...

  3. 《BI That little thing 》Microsoft Decision tree algorithm —— Find out the distribution of the characteristics of the generals of the Three Kingdoms , Dedicated to the Three Kingdoms lovers

    According to the game < reflection 11> General data , Using decision tree analysis , Find out the distribution of the characteristics of the generals of the Three Kingdoms . The variables include command . Force . intelligence . Politics . charm . status . Variable description : command : The general's defensive power when he leads his troops to battle . The higher the commander is, the more he is attacked by ordinary attacks and the art of war ...

  4. 《BI That little thing 》 Bivariate correlation analysis —— The correlation coefficient

    for example ,“ The more intelligent the characters in the three kingdoms are , The higher the politics ”, or “ The higher the force is , The higher the command : Prepare the data analysis environment : SELECT * FROM FactSanguo11 WHERE full name IN ( N' Emperor Xu ', N' Xun you ...

  5. Characters_of_the_Three_Kingdoms - Structured data of Three Kingdoms people

    Characters_of_the_Three_Kingdoms - Structured data of Three Kingdoms people Structured data of Three Kingdoms people Why is there this project demand 1: Get rid of the long articles on the Internet : demand 2: I just want to check the name of the person ...

  6. 《BI That little thing 》 Using standard scoring and deviation —— Analyze the ranking of the comprehensive strength of the super first class commanders of the three countries Absolutely objective , Data speak

    Basic concepts of data analysis : Standard score : 1. No matter what the full score as a variable is , The average of its standard score is bound to be 0, And the standard deviation is bound to be 1.2. Whatever the unit of a variable is , The average of its standard score is bound to be 0, And the standard deviation is bound to be 1. Formula for : Deviation ...

  7. 《BI That little thing 》SSRS Charts and meters —— Radar Analysis of the three super class counselors 、 Commander in chief data ( illustrated )

    Radar Analysis of the three super class counselors . Commander in chief data , Dedicated to the Three Kingdoms lovers , I hope friends who like the Three Kingdoms can discuss it together , Deepen the understanding of the legendary Three Kingdoms era Building a data environment : -- Select the top-ranking counsellors of the Three Kingdoms TOP 10 data DECLARE @t1 TA ...

  8. 《BI That little thing 》 Three countries data analysis series —— An analysis of the force between the five tigers General of the Shu Han Dynasty and the five good generals of the Wei Dynasty , Absolute classical analysis

    Dedicated to the Three Kingdoms lovers , I hope friends who like the Three Kingdoms can discuss it together , Deepen the understanding of the legendary Three Kingdoms era Basic concepts of data analysis : Centralized trend analysis refers to the distribution of a large number of evaluation data , The concentration of evaluation data to a certain point . The overall (population) It means objective existence ...

  9. Microsoft Naive Bayes Algorithm —— The identity of the Three Kingdoms

    Microsoft Naive Bayes is SSAS The simplest algorithm in , Often used as a starting point for understanding the basic grouping of data . The general feature of this kind of processing is classification . This algorithm is called “ simple ”, Because all attributes are of the same importance , No one is higher than anyone . The name of Bayes ...

Random recommendation

  1. Git/GitHub First use experience and summary

    Git, A magical and strange thing , I didn't understand it until now , As one of my friends said , I can't use it now Git I'm really embarrassed to say that I did it myself IT Of . Simple speak , this Git Is the most advanced distributed version control system , What corresponds to him is well-known ...

  2. How Google TestsSoftware - Part Two

    In order for the "you buildit, you break it" motto to be real, there are roles beyond the ...

  3. vim Multi label , Many window

    Multi label Get into vim front vim -p < file name > Open the file as multiple tags . Such as vim -p * Edit all the files in the current directory , vim Editing :tabnew Add a label :tabc Close current t ...

  4. 【C++ Foundation 15 】 Inline function

    1. advantage Why use inline functions , Instead of using macro definitions , Although the macro itself uses the expansion to replace the stack pressing and stack returning operations of function calls , Improved code efficiency , But there are two problems : (1) Marginal effect The macro is just expanding the code , So in the priority of some operators ...

  5. Framework development ——AngularJS+MVC+Routing Summary of development steps ——5.14

    1. continue MVC The concept of : Including the preparation of route mapping ,Controller The content of , Specifically View page js The separation of . 2. combination AngularJS Make the front end , The back-end using Node.Js Writing , introduce MVC frame , Make rapid development . Step ...

  6. How to be in Android Studio It is specified in NDK Location ?

    How to be in Android Studio It is specified in NDK Location ? Problem description NDK It has been manually downloaded and unpacked locally : D:\Portable\android-ndk-r13b Every time you create support C++ Project time , They all suggest that NDK Not configured , ...

  7. This code ,c 1 second ,java 9 second ,c# 14 second , and python...

    Ah , I have to say that I have seen too many keyboard swordsmen recently , As a programmer, I always like to touch the sky with my upper lip , Blow with your lower lip touching the ground . I don't know how many languages I have used , Comment on each language , There are so many languages. How bad is that language . Maybe it's getting less... Over time ...

  8. golang Common mistakes

    import import unuse package: error : imported and not used: "os" := = c := 1 // error non- ...

  9. Explain profound theories in simple language QOS Detailed explanation ( turn )

    QOS Learning notes ( After working hours , These are summarized , My tired index finger is getting out of joint , It's still recovering , In order to improve the quality of the article , Hopefully that helped ! The article is too long , For convenience , I have attached the original article .) QOS, Service quality . seeing the name of a thing one thinks of its function , Just for ...

  10. RD340 Server installation windows2003 System

    RD340 Server installation windows2003 System cloud repair network