酷-代码正在运行,所以数据结构是清晰的!作为一种方法,我们为文章/作者和作者/合著者构建了联系矩阵。
作者列表:
如果你想描述文章和作者之间的关系,我想你需要每一篇文章的作者名单
authors = []
author_lists = [] #
for record in records:
au = record.get('AU', '?')
author_lists.append(au) #
for a in au:
if a not in authors: authors.append(a)
authors.sort()
print(authors)
麻木,大熊猫
-只是我习惯的工作方式
import numpy as np
import pandas as pd
import matplotlib.pylab as plt
AU = np.array(authors) # authors as np-array
NA = AU.shape[0] # number of authors
NL = len(author_lists) # number of articles/author lists
AUL = np.array(author_lists) # author lists as np-array
print('NA, NL', NA,NL)
连接性文章/作者
CON = np.zeros((NL,NA),dtype=int) # initializes connectivity matrix
for j in range(NL): # run through the article's author list
aul = np.array(AUL[j]) # get a single author list as np-array
z = np.zeros((NA),dtype=int)
for k in range(len(aul)): # get a singel author
z += (AU==aul[k]) # get it's position in the AU, add it up
CON[j,:] = z # insert the result in the connectivity matrix
#---- grafics --------
fig = plt.figure(figsize=(20,10)) ;
plt.spy(CON, marker ='s', color='chartreuse', markersize=5)
plt.xlabel('Authors'); plt.ylabel('Articles'); plt.title('Authors of the articles', fontweight='bold')
plt.show()
连接性作者/合著者
,得到的矩阵是对称的
df = pd.DataFrame(CON) # let's use pandas for the following step
ACON = np.zeros((NA,NA)) # initialize the conncetivity matrix
for j in range(NA): # run through the authors
df_a = df[df.iloc[:, j] >0] # give all rows with author j involved
w = np.array(df_a.sum()) # sum the rows, store it in np-array
ACON[j] = w # insert it in the connectivity matrix
#---- grafics --------
fig = plt.figure(figsize=(10,10)) ;
plt.spy(ACON, marker ='s', color='chartreuse', markersize=3)
plt.xlabel('Authors'); plt.ylabel('Authors'); plt.title('Authors that are co-authors', fontweight='bold')
plt.show()
用于图形
网络X
我认为你需要清楚的想法,你想要代表什么,因为有很多点和很多可能性(也许你会发布一个例子?)只有少数作者Circels在下面。
import networkx as nx
def set_edges(Q):
case = 'A'
if case=='A':
Q1 = np.roll(Q,shift=1)
Edges = np.vstack((Q,Q1)).T
return Edges
Q = nx.Graph()
Q.clear()
AT = np.triu(ACON) # only the tridiagonal is needed
fig = plt.figure(figsize=(7,7)) ;
for k in range (9):
iA = np.argwhere(AT[k]>0).ravel() # get the indices with AT{k}>0
Edges = set_edges(iA) # select the involved nodes and set the edges
Q.add_edges_from(Edges, with_labels=True)
nx.draw(Q, alpha=0.5)
plt.title('Co-author-ship', fontweight='bold')
plt.show()