y = random.randint(int(-radii[index][1]) \
,int(radii[index][1]))
if (x**2 + y**2)**0.5 >= radii[index][0] and\
(x**2 + y**2)**0.5 <= radii[index][1]:
instanceCount += 1
features.append([x,y])
labels.append(label)
#Silhouette score
score = sklearn.metrics.silhouette_score(features, labels)
#Beta Values
betaV = beta(features,labels)
#Plotting
for i in range(len(features)):
if labels[i] == 0:
plt.plot(features[i][0],features[i][1],'bo')
else:
plt.plot(features[i][0],features[i][1],'ro')
#Saving
name = str(datasetNumber)
plt.savefig('plots/' + name + '.png')
plt.clf()
file = open('datasets/'+ name + '.txt','w')
home = os.getcwd()
datasetFolder = os.path.join(home, "datasets")
betaFile = open("betaValues2.txt", "w")
for i in range(600):
print(i)
fileName = os.path.join(datasetFolder, str(i) + ".txt")
file = open(fileName, 'r')
X = []
y = []
classDistribution = [0, 0]
for i in file:
i = i.strip("\n")
i = i.split(",")
temp = []
for j in range(len(i)):
if j == 2:
y.append(int(i[j]))
classDistribution[int(i[j])] += 1
else:
temp.append(int(i[j]))
X.append(temp)
file.close()
betaValue = beta(X, y, classDistribution)
for i in betaValue:
betaFile.write(str(i) + ",")
betaFile.write("\n")
betaFile.close()