I just did it! Visualization of character relationships in Douluo continent

Today, brother Chen came to teach you from a novel / In the classics Extract names , Also on The relationship between names Make statistics （ In the same paragraph, names appear in pairs ）, According to the relationship between names Drawing diagrams --gephi

Core knowledge points ：

1. Extracting names from text
2. Statistics of the relationship between the characters in the text
3. Draw a network diagram

Have a look first effect ：

01 jieba Small example

At the beginning of the analysis 《 Doulo land 》 Before the novel , Let's start with a small example jieba The use of the library has an impression .

explain :

You can see the text content results jieba After the library participle , You can get every part of speech . We need names here , Just pick out nr Part of speech of , And count the number of times each word .

Here is a demonstration for you jieba Small examples of extracting names from text , The following is a novel 《 Doulo land 》 For example , Explain how to extract the names of the characters in it , And create a digraph , Finally, draw a figure diagram .

02 Extracting character relationships

1. Make a name dictionary

Some of the results are shown in the figure above , By extracting all the names in the novel , Before removal 100 And write from high to low frequency txt. But some of them are incomplete 、 It's useless 、 One character, more than one, etc . After sorting out the following .

2. Build character relationships

Through the construction of the character name in each paragraph appear in pairs of statistics . Finally, it's set up , The connection between character nodes and characters .

3. Save to csv

give the result as follows ：

03 Network of people

What we use here is gephi Drawing ,gephi The download address is as follows ：

https://gephi.org/

After downloading and installing , Start importing the just saved node.csv and edge.csv Data to draw a network of people

1. New project & Import data

New project -> choice Data and data tab, Click on Enter the number table , Adding nodes and edges csv data .

2. Adjust the relevant styles

3. Change the font , Display the corresponding label

4. Choose a way to automate the layout , preview , Then adjust the relevant parameters

5. Finally, click on the lower left corner to export the image

04 Summary

This paper explains how to extract the names of people in the text and count the relationship between people in the text , Finally, draw a network diagram , What you don't understand can be in Message below , Communicate together .