def get_industry_matrix(nameOfFile, size): matrix = [] try: num = size except IndexError: num = 504 #Collecting data from the industry.json. This file #gives the details of the industry with open(nameOfFile) as data_file: data = json.load(data_file) g = Graph() #Creating nodes for company in data.keys()[0:num]: g.add_nodes(company,data[company]) #Adding these nodes in a graph by considering #the links. In order to create the links and do significant #comparisons we take into consideration semantic analysis using NLP (spacy). #We compare the different descriptions about a particular company's industry #to other companies and check for the linkages in accordance to those values. g.link_all_industry() #Creating teh matrix for i in xrange(0,num): matrix.append([]) print(str(i)+"\t"+data.keys()[i]) for j in xrange(0,num): a = g.return_links(data.keys()[i],data.keys()[j]) if a is None: a = [] matrix[i].append(len(a)) #Alloting the scores in accordance to the number of links to a given #company mat = np.array(matrix,dtype=float) for i in xrange(0,num): for j in xrange(0,num): if i!=j: if(mat[i][i] != 0): mat[i][j] /= mat[i][i] for i in xrange(0,num): mat[i][i]=1 mat[i] = norm(mat[i],i,num) #mat = (np.round(mat,3)) #Giving the value a 40% percent for the final matrix mat = np.multiply(mat, 0.4) return mat
from graph import Node, Graph
matrix = []
try:
num = int(sys.argv[2])
except IndexError:
num = 504
with open(sys.argv[1]) as data_file:
data = json.load(data_file)
g = Graph()
for company in data.keys()[0:num]:
g.add_nodes(company,data[company])
g.link_all_industry()
for i in xrange(0,num):
matrix.append([])
# print(str(i)+"\t"+data.keys()[i])
for j in xrange(0,num):
a = g.return_links(data.keys()[i],data.keys()[j])
if a is None:
a = []
matrix[i].append(len(a))
mat = np.array(matrix,dtype=float)
for i in xrange(0,num):
for j in xrange(0,num):
