def main():
messages = Message.dataparser("data.csv")
authentication_result = {}
# print(len(messages))
for message in messages:
if message.nodeID in authentication_result:
if message.messagetype in [1, 2, 3, 4, 5, 8]:
authentication_result[message.nodeID][1] += 1
elif message.messagetype in [6, 7, 9]:
authentication_result[message.nodeID][0] += 1
else:
print("Message type invalid")
else:
if message.messagetype in [1, 2, 3, 4, 5, 8]:
authentication_result[message.nodeID] = [0, 1]
elif message.messagetype in [6, 7, 9]:
authentication_result[message.nodeID] = [1, 0]
else:
print("Message type invalid")
print(len(authentication_result))
for item in authentication_result.items():
if item[1][1] != 0:
item[1].append(item[1][0] / item[1][1])
else:
item[1].append(0)
sorted_d = sorted(authentication_result.items(), key=lambda x: x[1][2])
pprint.pprint(sorted_d)
def main():
messages = Message.dataparser("data.csv")
msg_type_counts = [0,0,0,0,0,0,0,0,0]
for message in messages:
msg_type_counts[message.messagetype - 1] += 1
print(msg_type_counts)
def main():
messages = Message.dataparser("data.csv")
# k_message_type_grams_list = node_target(messages)
# k_message_type_grams_list = IPaddress_target(messages)
k_message_type_grams_list = username_target(messages)
print(len(k_message_type_grams_list))
def main():
# Load the data from CSV file
messages = Message.dataparser("data.csv")
# Count number of accesses to a node from each IPAddress accessing that node
node_access_set = count_usage(messages)
# pprint.pprint(node_access_set)
# print(len(node_access_set))
# for nodeid in node_access_set.keys():
# print(nodeid + " " + str(len(node_access_set[nodeid])))
# Calculate the x and y co-ordinates for clustering.
x = []
y = []
counter = 1
plot_list = []
for nodeid in node_access_set.keys():
sum = 0
for IPAddress in node_access_set[nodeid].keys():
sum += node_access_set[nodeid][IPAddress]
plot_list.append([nodeid, len(node_access_set[nodeid]), sum])
x.append(counter)
# x.append(len(node_access_set[nodeid]))
y.append(sum)
counter += 1
if sum > 40000:
print(nodeid + "\t" + str(sum))
# for nodeid in node_access_set.keys():
# print(nodeid + " " + str(len(node_access_set[nodeid])))
# print(plot_list)
# print(len(plot_list))
# plt.scatter(x, y, s=2)
# plt.show()
# vertices_list = []
# for m, n in zip(x, y):
# vertices_list.append([float(m), float(n)])
# vertices = np.array(vertices_list)
# print(vertices.shape)
# centers = np.array([[0,0],[1000,0],[0,1000]])
# centers_gonzalez = LloydCluster(vertices, 3, centers)
# # centers_gonzalez = GonzalezCluster(vertices, 3, vertices[0])
# vertex2center = verticesCluster(vertices, centers_gonzalez)
# with open('gonzalez.csv', 'w') as f:
# for i in range(np.shape(vertices)[0]):
# f.write(','.join([str(elem) for elem in np.ndarray.tolist(vertices[i])]) + ',' +
# str(vertex2center[i]) + '\n')
file = "gonzalez.csv"
x = []
y = []
z = []
color = set()
colours = ["red", "green", "blue", "black"]
with open(file, "r") as csvfile:
reader = csv.reader(csvfile)
# print(reader)
for row in reader:
x.append(float(row[0]))
y.append(float(row[1]))
z.append(int(row[2]))
for num in z:
color.add(num)
color = list(color)
coldict = dict()
for col, num in zip(colours, color):
coldict[num] = col
# print(coldict)
# print(x)
# print(y)
# print(z)
# z = map(lambda x: coldict[x], z)
# print(list(z))
plt.scatter(x, y, c=z, cmap="Accent", s=6)
grey_patch = mpatches.Patch(color='grey', label='High risk nodes')
green_patch = mpatches.Patch(color='green', label='Moderate risk nodes')
black_patch = mpatches.Patch(color='black', label='Low risk nodes')
plt.legend(handles=[grey_patch, green_patch, black_patch])
plt.xlabel('#IPaddress')
plt.ylabel('#Access')
plt.title('Plot of #accesses vs #IPaddresses')
# m = ['ms1102', 'hp005', 'hp054', 'hp053', 'hp017']
# j = 0
# for i in range(len(y)):
# if y[i] > 40000:
# plt.annotate(m[j], (x[i], y[i]))
# j += 1
# if j > 4:
# break
plt.show()
