def annealingSimulation(data_s,data_l,max_nodes,min_nodes,temperature=10000.0,cool=0.15,step=10):
#generate a random number to start
if min_nodes<0:
min_nodes=0
initial_random_number = random.randint(min_nodes,max_nodes)
nodeA = initial_random_number
while temperature>0.1:
direction = random.randint(-step,step)
nodeB = nodeA+direction
if nodeB>max_nodes:
nodeB = max_nodes
elif nodeB<min_nodes:
nodeB = min_nodes
#start to do the cross validation for number of nodeA
percentage = 0.05
size_training_set = len(data_s)
total_num_loop = 1
x = 0
total_num = 0
total_error = 0
while x<total_num_loop:
x=x+1
#start to create net classifier
print 'start to create NN'
print ('Hidden nodeA are %d' %(nodeA))
[sliced_training_data,sliced_testing_data,sliced_training_label,sliced_testing_label]=helper_cross_validation.spilteDataAndLabel(data_s,data_l,x,percentage,step=len(data_s))
[net,number_of_input_features,tfidf_vectorizer] = creatingNeuralNetwork(nodeA,sliced_training_data,sliced_training_label)
#start to testing
indata = np.zeros((len(sliced_testing_data),number_of_input_features))
for j,sentence in enumerate(sliced_testing_data):
indata[j,:] = tfidf_vectorizer.transform([sentence]).toarray()[0]
#testing the result
results = net(indata)
results_list = []
for r in results:
if r<0.5:
r=0
elif r>=0.5 and r <1.5:
r=1
elif r>=1.5:
r=2
results_list.append(r)
total_num = total_num+len(results_list)
index = 0
while index < len(results_list):
if results_list[index]!=sliced_testing_label[index]:
total_error = total_error+1
index = index+1
error_rateA = float(total_error)/float(total_num)
#cross validation for nodeB
percentage = 0.02
size_training_set = len(data_s)
#too much time occupied
total_num_loop = 1
x = 0
total_num = 0
total_error = 0
while x<total_num_loop:
x=x+1
#start to create net classifier
[sliced_training_data,sliced_testing_data,sliced_training_label,sliced_testing_label]=helper_cross_validation.spilteDataAndLabel(data_s,data_l,x,percentage,step=len(data_s))
print 'start to create NN'
print ('Hidden nodeB are %d' %(nodeB))
[net,number_of_input_features,tfidf_vectorizer] = creatingNeuralNetwork(nodeB,sliced_training_data,sliced_training_label)
#start to testing
indata = np.zeros((len(sliced_testing_data),number_of_input_features))
for j,sentence in enumerate(sliced_testing_data):
indata[j,:] = tfidf_vectorizer.transform([sentence]).toarray()[0]
#testing the result
results = net(indata)
results_list = []
for r in results:
if r<0.5:
r=0
elif r>=0.5 and r <1.5:
r=1
elif r>=1.5 and r<2.5:
r=2
elif r>=2.5 and r<3.5:
r=3
elif r>=3.5 and r<4.5:
r=4
else:
r=5
results_list.append(r)
total_num = total_num+len(results_list)
index = 0
while index < len(results_list):
if results_list[index]!=sliced_testing_label[index]:
total_error = total_error+1
index = index+1
error_rateB = float(total_error)/float(total_num)
p=pow(math.e,(-error_rateB-error_rateA)/temperature)
if (error_rateB<error_rateA or random.random()<p):
nodeA=nodeB
print ("Node number: %d, accurancy: %f" %(nodeB,1-error_rateB))
else:
print ("Node number: %d, accurancy: %f" %(nodeA,1-error_rateA))
#cooling a little bit
temperature=temperature*cool
return nodeA
total_testing_times = 0
error_testing_times = 0
size_training_set = len(training_set)
total_num_loop = int(size_training_set / step)
x = 0
# print ("There are %d loops" % (total_num_loop))
while x < total_num_loop:
x = x + 1
# print ("This is %d loop" % (x))
# start to slice array and train classifer
[
sliced_training_data,
sliced_testing_data,
sliced_training_label,
sliced_testing_label,
] = helper_cross_validation.spilteDataAndLabel(training_set, label_set, x, percentage, step=step)
training_feature = tfidf.fit_transform(sliced_training_data)
classifier.fit(training_feature, sliced_training_label)
# start to testing
indexOfTest = 0
testing_feature = tfidf.transform(sliced_testing_data)
test_result = classifier.predict(testing_feature)
while indexOfTest < len(sliced_testing_data):
total_testing_times = total_testing_times + 1
if test_result[indexOfTest] != sliced_testing_label[indexOfTest]:
error_testing_times = error_testing_times + 1
indexOfTest = indexOfTest + 1
successRatio = 1 - float(error_testing_times) / float(total_testing_times)
print ("Success Ratio is %f" % (successRatio))
while n<max_ngram:
n=n+1
print ("Max ngram is %d" % (n))
classifier = MultinomialNB()
tfidf = TfidfVectorizer(sublinear_tf=True, max_df=0.9, stop_words=None, token_pattern=pattern, ngram_range=(1, n))
total_testing_times = 0;
error_testing_times = 0;
size_training_set = len(training_set)
total_num_loop = int(size_training_set/step)
x = 0
# print ("There are %d loops" % (total_num_loop))
while x<total_num_loop:
x = x+1
# print ("This is %d loop" % (x))
#start to slice array and train classifer
[sliced_training_data,sliced_testing_data,sliced_training_label,sliced_testing_label]=helper_cross_validation.spilteDataAndLabel(
training_set,label_set,x,percentage,step=step)
training_feature = tfidf.fit_transform(sliced_training_data)
classifier.fit(training_feature, sliced_training_label)
#start to testing
indexOfTest = 0
testing_feature = tfidf.transform(sliced_testing_data)
test_result = classifier.predict(testing_feature)
while indexOfTest < len(sliced_testing_data):
total_testing_times = total_testing_times+1
if test_result[indexOfTest]!=sliced_testing_label[indexOfTest]:
error_testing_times = error_testing_times+1
indexOfTest=indexOfTest+1
successRatio =1-float(error_testing_times)/float(total_testing_times)
print ("Success Ratio is %f" % (successRatio))
