最终得到的结果的文件夹结构与题目要求相同

• GraphStat
  • _init_.py
  • NetworkBuilder
    • _init_.py
    • node.py
    • graph.py
    • stat.py
  • Visualization
    • _init_.py
    • plotnodes.py
    • plotgraph.py

node.py

#返回字典，key为节点的属性，值为对应的属性值def init_node(parameters,txt):attr = ['id','name','weight','occupation','others']node = {}line = txt[parameters+1].strip().split('\t')node = dict(zip(attr,line))return node#获取对应的节点属性，如度等
def get_degree(node):degree = 0with open('newmovies.txt',encoding='utf-8') as f:txt1 = f.readlines()[34286:] #34285for line in txt1:line = line.strip().split('\t')#print(line)if line[0]==node['id'] or line[1] == node['id']:degree +=1print('the degree of node %d = %d'%(node['id'],get_degree(node)))return degree#显示节点全部信息（利用format或者f函数）
def print_node(node):print(node)

node结点

[{'id': '0', 'name': '"Ann Blyth"', 'weight': '6035', 'occupation': 'starring', 'others': '1928 births;Living people;American film actors;American musical theatre actors;American child actors;People from Westchester County, New York;'}, {'id': '1', 'name': '"Karen Allen"', 'weight': '7467', 'occupation': 'starring', 'others': "American film actors;American stage actors;American video game actors;Bard College at Simon's Rock faculty;Illinois actors;People from Greene County, Illinois;Saturn Award winners;"}, {'id': '2', 'name': '"Mel Tormé"', 'weight': '18868', 'occupation': 'writer', 'others': '1925 births;1999 deaths

edges边

[('0', '4221'), ('0', '4390'), ('0', '2664'), ('0', '6885'), ('0', '989'), ('0', '7387'), ('1', '11814'), ('1', '3869'), ('1', '11348'), ('1', '9023')]

graph.py

import pickle#返回一个字典，分别存储节点信息和边信息
def init_graph(node_list,edges):dic = {}dic[str(node_list)] = edgesreturn dic#序列化图信息
def save_graph(graph):pickle.dumps(graph)#反序列化图信息
def load_graph(graph):pickle.loads(graph)

stat.py

#计算网络中的平均度
def cal_average_degree(graph):for k,v in graph.items():edges = v        return 2*len(edges)/34283#print(cal_average_degree(graph))#计算网络的度分布
def cal_degree_distribution(graph):add = 34283*cal_average_degree(graph)for k,v in graph.items():edges = v   degree = {}for num in edges:if eval(num[0]) not in degree:degree[eval(num[0])] = 1/addelse:degree[eval(num[0])] += 1/addif eval(num[1]) not in degree:degree[eval(num[1])] = 1/addelse:degree[eval(num[1])] += 1/add'''cnt=0for k,v in degree.items():cnt+=1print(k,v)if cnt>100:break'''return degree

平均度：8.308899454540152

结点的度的概率分布

{0: 7.723254719961804e-05, 4221: 0.0007372197687236266, 4390: 9.478539883589486e-05, 2664: 0.0005932863853061578, 6885: 7.021140654510731e-05, 989: 0.0004142472986161344, 7387: 0.0004598847128704545, 1: 8.425368785412877e-05, 11814: 1.4042281309021464e-05, 3869: 0.001358590716647833, 11348: 0.0004598847128704545, 9023: 3.5105703272553654e-05, 7353: 0.0002913773371621957, 11190: 0.0005932863853061578, 13214: 0.000512543267779285, 4562: 0.00033701475141651577, 5465: 0.00021765536028983264, 6106: 0.00042477900959790057, 7922: 0.0004879692754884976, 13175: 0.00014393338341746998, 2: 0.00010180653949040559, 14185: 0.0001228699614539378, 6938: 0.0008565791598503081, 6255: 0.0003194618997802388, 6826: 7.021140654510731e-05, 10597: 5.967969556334121e-05, 1870: 0.0002106342196353219, 6172: 2.8084562618042924e-05, 15364: 8.07431175268734e-05, 12753: 0.00014042281309021462,

plotnodes.py

import matplotlib.pyplot as plt#绘制图中节点属性的统计结果
def plot_nodes_attr(graph,feature):dic = {'name':1, 'occupation':3,'others':4}dic1 = {}for k,v in graph.items():node_list = eval(k)for node in node_list:dic1[node[feature]] = dic1.get(node[feature],0)+1key,value = [],[]for k,v in dic1.items():key.append(k)value.append(v)plt.pie(value,labels=key,autopct="%2.0f%%")plt.savefig('{}.png'.format(feature))plt.show()

plotgraph.py

import matplotlib.pyplot as pltdef cal_average_degree(graph):for k,v in graph.items():edges = v        return 2*len(edges)/34283#print(cal_average_degree(graph))#计算网络的度分布
def cal_degree_distribution(graph):add = 34283*cal_average_degree(graph)for k,v in graph.items():edges = v   degree = {}for num in edges:if eval(num[0]) not in degree:degree[eval(num[0])] = 1/addelse:degree[eval(num[0])] += 1/addif eval(num[1]) not in degree:degree[eval(num[1])] = 1/addelse:degree[eval(num[1])] += 1/add'''cnt=0for k,v in degree.items():cnt+=1print(k,v)if cnt>100:break'''return degreedef plotdegree_distribution(graph):  #度的分布degree = cal_degree_distribution(graph)degree = sorted(degree.items(),key = lambda x:x[0])#print(degree[:20])x,y = [],[]for num in degree[:50]:x.append(num[0])y.append(num[1])plt.bar(x,y)plt.xlabel('node')plt.ylabel('distribution probility')plt.legend('distribution')plt.title('the probility distribution of degree')plt.savefig('graph_distrbution.png',dpi=800)plt.show()

调用各函数，观察功能实现

from GraphStat.NetworkBuilder import node
from GraphStat.NetworkBuilder import graph
from GraphStat.NetworkBuilder import stat
avg = stat.cal_average_degree
dis = stat.cal_degree_distribution
from GraphStat.Visualization import plotgraph
from GraphStat.Visualization import plotnodeswith open('newmovies.txt',encoding='utf-8') as f:txt = f.readlines() #34285node_list = []
for i in range(34283):node_list.append(node.init_node(i,txt))edges = []
for line in txt[34285:]:line = line.strip().split('\t')edges.append((line[0],line[1]))graph1 = graph.init_graph(node_list,edges)
graph.save_graph(graph1)print(avg(graph1))
print(dis(graph1))
feature = input('please enter the feature:')plotnodes.plot_nodes_attr(graph1,feature)
plotgraph.plotdegree_distribution(graph1)