当前位置：首页 > news >正文

简单PageRank —— 希拉里邮件门

news 来源：原创 2024/5/2 22:32:33

如何计算每个人物在邮件关系网络中的影响力?

我们用pagerank来查看，各个点的影响力，以及用nexworkx中的graph来展示其关系。

如图ABCD代表着4个网页，其中箭头指向表示，从某网页跳转到另一个网页，那么我们来计算一下这4个网页的影响力

pagerank算法原理就是：一个网页的影响力 = 所有入链集合的页面的加权影响力之和。

Google 的两位创始人都是斯坦福大学的博士生，他们提出的 PageRank 算法受到了论文影响力因子的评价启发。当一篇论文被引用的次数越多，证明这篇论文的影响力越大。正是这个想法解决了当时网页检索质量不高的问题

import matplotlib.pyplot as plt
import networkx as nx
G = nx.DiGraph()
# 有向图之间边的关系
edges = [("A", "B"), ("A", "C"), ("A", "D"), ("B", "A"), ("B", "D"), ("C", "A"), ("D", "B"), ("D", "C")]
for edge in edges:
    G.add_edge(edge[0], edge[1])
pagerank_list = nx.pagerank(G, alpha=1)#alpha为阻尼因子，alpha=0.85表示跳转率为15%
print("pagerank 值是：", pagerank_list)
nx.set_node_attributes(G,values=pagerank_list,name='pagerank_list')

# 绘制圆环图像
positions=nx.circular_layout(G)
#绘制反射图像
# positions=nx.spring_layout(G)
# 绘制节点
nx.draw_networkx_nodes(G, positions,  alpha=0.4)
# 绘制边
nx.draw_networkx_edges(G, positions,  alpha=0.2)
# 绘制节点的 label
nx.draw_networkx_labels(G, positions, font_size=10)
plt.show()

https://www.cnblogs.com/jpcflyer/p/11180263.html

接下来我们看下如何利用pagerank和graph来展示希拉里的邮件

import pandas as pd
import numpy as np
import networkx as nx
import matplotlib.pyplot as plt
from collections import defaultdict

emails = pd.read_csv("E:/数据学习网站/PageRank-master/input/Emails.csv")
file = pd.read_csv("E:/数据学习网站/PageRank-master/input/Aliases.csv")
aliases={}
for index,row in file.iterrows():
    aliases[row['Alias']]=row['PersonId']
# print(aliases)

file = pd.read_csv("E:/数据学习网站/PageRank-master/input/Persons.csv")
persons={}
for index,row in file.iterrows():
    persons[row['Id']]=row['Name']

# 单词间的转换
def unify_name(name):
    name =str(name).lower()
    name=name.replace(",","").split("@")[0]
    if name in aliases.keys():
        return persons[aliases[name]]
    return name

def show_graph(graph,layout='spring_layout'):
    if layout=="circular_layout":
        position=nx.circular_layout(graph)
    else:
        position=nx.spring_layout(graph)
    nodesize=[x['pagerank']*20000 for v,x in graph.node(data=True)]
    edgesize=[np.sqrt(e[2]['weight']) for e in graph.edges(data=True)]
    nx.draw_networkx_nodes(graph,position,node_size=nodesize,alpha=0.4)
    nx.draw_networkx_edges(graph,position,edge_size=edgesize,alpha=0.2)
    nx.draw_networkx_labels(graph,position,font_size=10)
    plt.show()

emails.MetadataTo=emails.MetadataTo.apply(unify_name)
emails.MetadataFrom=emails.MetadataFrom.apply(unify_name)

edges_weights_temp=defaultdict()
for row in zip(emails.MetadataTo,emails.MetadataFrom,emails.RawText):
    temp=(row[0],row[1])
    if temp not in edges_weights_temp:
        edges_weights_temp[temp]=1
    else:
        edges_weights_temp[temp]=edges_weights_temp[temp]+1

edges_weight=[(key[0],key[1],val) for key,val in edges_weights_temp.items()]

graph=nx.DiGraph()
graph.add_weighted_edges_from(edges_weight)
pagerank=nx.pagerank(graph)
nx.set_node_attributes(graph,name='pagerank',values=pagerank)
show_graph(graph)

pagerank_threshold=0.005
small_graph=graph.copy()
for n,p_rank in graph.node(data=True):
    if p_rank["pagerank"]<pagerank_threshold:
        small_graph.remove_node(n)
show_graph(small_graph,"circular_layout")