import numpy as np print ("Your numpy version: %6.6s (need at least 1.7.1)" % np.__version__)

# example # 1.2 create adjacency matrix H H = np.matrix([[1, 0, 2, 0, 4, 3], [3, 0, 1, 1, 0, 0], [2, 0, 4, 0, 1, 0], [0, 0, 1, 0, 0, 1], [8, 0, 3, 0, 5, 2], [0 ,0, 0, 0, 0, 0]])

# 1.3 Modify the Adjacency Matrix # set the diagonal to zero for i in range(6): H[i, i] = 0 print(H)

# normalize the matrix H = H/H.sum(axis=0) np.nan_to_num(H, copy=False, nan=0)

# 1.4 Identify the dangling nodes # create d dangling nodes d = 1 - H.sum(0)

# 1.5 Calculate the influence vector # article vector a = np.array([3/14, 2/14, 5/14, 1/14, 2/14, 1/14]) # influential vector pi = np.array([1/6, 1/6, 1/6, 1/6, 1/6, 1/6]) alpha = 0.85 epslon = 0.00001 residual = 1 max_iter = 100 iter_count = 0 # iteration to get fast while(residual >= epslon and iter_count < max_iter): pi_prime = alpha * np.matmul(H, pi) + ((alpha * np.matmul(d, pi))[0, 0] + 1 - alpha) * a pi_prime = np.squeeze(np.asarray(pi_prime)) # calculate l1 norm l1_norm = 0 for i, j in zip(pi, pi_prime): l1_norm += abs(i - j) residual = l1_norm pi = pi_prime iter_count += 1 temp = np.matmul(H, pi)

# 1.6 Calculate EF EF = 100 * temp / temp.sum(1) EF

# 1.1 Data Input m = 100 with open('./links.txt') as f: for l in f.readlines(): m = min(int(l.split()[0][:-1]), m) print(m) # start from 0 # matrix dimention should be 10748

adj_m = np.matrix([[0 for j in range(10748)] for i in range(10748)])

# 1.2 creating adjcent matrix with open('./links.txt') as f: for l in f.readlines(): i,j,k = l.split() i = int(i[:-1]) j = int(j[:-1]) k = int(k) adj_m[i,j] = k

# 1.3 # zero all diagnols for i in range(10748): adj_m[i, i] = 0

# normalize columns H = adj_m/adj_m.sum(axis=0)

# testings testing = np.matrix([[1,0], [1, 0]]) testing = testing/testing.sum(0) print(testing) np.nan_to_num(testing, copy=False, nan=0) print(testing) print(1-testing.sum(0))

# 1.4 find the dangling nodes np.nan_to_num(H, copy=False, nan=0) d = 1 - H.sum(0)

# 1.5 calculating influnece vector # article vector a = np.array([1/10748 for i in range(10748)]) # influential vector pi = np.array([1/10748 for i in range(10748)])

# iteration steps alpha = 0.85 epslon = 0.00001 residual = 1 max_iter = 100 iter_count = 0 while(residual >= epslon and iter_count < max_iter): pi_prime = alpha * np.matmul(H, pi) + ((alpha * np.matmul(d, pi))[0, 0] + 1 - alpha) * a pi_prime = np.squeeze(np.asarray(pi_prime)) # calculate l1 norm l1_norm = 0 for i, j in zip(pi, pi_prime): l1_norm += abs(i - j) residual = l1_norm pi = pi_prime iter_count += 1

# 1.6 Calculate EF temp = np.matmul(H, pi) EF = 100 * temp / temp.sum(1) import heapq index_hp = [] # format: [(EF score, article number), ...] for i in range(10748): heapq.heappush(index_hp, (EF[0, i], i)) if len(index_hp) > 20: heapq.heappop(index_hp) print(index_hp)