std_dict = bay.find_std(dict_info, mean_dict)
prior = bay.find_priors(dict_info)
#print(len(training_set))
#print(len(test_set))
_, predictions0 = bay.fun_bayes(training_set, test_set,
training_label, test_label)
acc_funbayes += _
micro_funbayes += f1_score(test_label,
predictions0,
average='micro')
macro_funbayes += f1_score(test_label,
predictions0,
average='macro')
_, predictions1 = nn.fun_knn(training_set, test_set,
training_label, test_label)
acc_funknn += _
micro_funknn += f1_score(test_label, predictions1, average='micro')
macro_funknn += f1_score(test_label, predictions1, average='macro')
_, predictions2 = nn.knn(training_set, training_label, test_set,
test_label)
acc_knn += _
micro_knn += f1_score(test_label, predictions2, average='micro')
macro_knn += f1_score(test_label, predictions2, average='macro')
_, predictions3 = bay.bayes(mean_dict, std_dict, test_set,
test_label, prior)
acc_bayes += _
micro_bayes += f1_score(test_label, predictions3, average='micro')
macro_bayes += f1_score(test_label, predictions3, average='macro')
def pubmed():
train = load_data("E:\\pubmed.csv")
m, n = train.shape
labels = load_data("E:\\pubmed_label.csv")
train_copy = train
list_k_fold = man_split(train_copy, labels, 5)
acc_bayes = 0
acc_funbayes = 0
acc_knn = 0
acc_funknn = 0
#print("done")
micro_bayes = 0
micro_funbayes = 0
micro_knn = 0
micro_funknn = 0
macro_bayes = 0
macro_funbayes = 0
macro_knn = 0
macro_funknn = 0
for k1 in range(5):
#print(k1)
#print("k1=",end=' ')
#print(k1)
test_set = []
training_set = []
training_label = []
test_label = []
prior = {}
label1 = []
#print(list_k_fold)
for i in range(5):
if i == k1:
label1.extend(list_k_fold[i])
#print("done")
for i2 in range(len(labels)):
if i2 in label1:
test_set.append(train_copy[i2])
test_label.append(labels[i2])
else:
training_set.append(train_copy[i2])
#print(trainset)
training_label.append(labels[i2])
#print("done")
dict_info = {}
dict_info = form_dict(training_set, training_label)
mean_dict = bay.find_mean(dict_info)
std_dict = bay.find_std(dict_info, mean_dict)
prior = bay.find_priors(dict_info)
_, predictions0 = bay.fun_bayes(training_set, test_set, training_label,
test_label)
acc_funbayes += _
micro_funbayes += f1_score(test_label, predictions0, average='micro')
macro_funbayes += f1_score(test_label, predictions0, average='macro')
#print(macro_funbayes)
#print("a")
_, predictions1 = nn.fun_knn(training_set, test_set, training_label,
test_label)
acc_funknn += _
micro_funknn += f1_score(test_label, predictions1, average='micro')
macro_funknn += f1_score(test_label, predictions1, average='macro')
#print("b")
_, predictions2 = nn.knn(training_set, training_label, test_set,
test_label)
acc_knn += _
micro_knn += f1_score(test_label, predictions2, average='micro')
macro_knn += f1_score(test_label, predictions2, average='macro')
_, predictions3 = bay.bayes(mean_dict, std_dict, test_set, test_label,
prior)
acc_bayes += _
micro_bayes += f1_score(test_label, predictions3, average='micro')
macro_bayes += f1_score(test_label, predictions3, average='macro')
#print("c")
file1.write("Test Accuracy on pubmed using inbuilt bayes ::" +
str(acc_funbayes / 5) + "\n")
file1.write("Test Accuracy on pubmed using inbuilt knn ::" +
str(acc_funknn / 5) + "\n")
file.write("Test Accuracy on pubmed using my bayes ::" +
str(acc_bayes / 5) + "\n")
file.write("Test Accuracy on pubmed using my knn ::" + str(acc_knn / 5) +
"\n \n")
file1.write("Test Macro F1 Score on pubmed using inbuilt bayes ::" +
str(macro_funbayes / 5) + "\n")
file1.write("Test Macro F1 Score on pubmed using inbuilt knn ::" +
str(macro_funknn / 5) + "\n")
file.write("Test Macro F1 Score on pubmed using my bayes ::" +
str(macro_bayes / 5) + "\n")
file.write("Test Macro F1 Score on pubmed using my knn ::" +
str(macro_knn / 5) + "\n \n")
file1.write("Test Micro F1 Score on pubmed using inbuilt bayes ::" +
str(micro_funbayes / 5) + "\n")
file1.write("Test Micro F1 Score on pubmed using inbuilt knn ::" +
str(micro_funknn / 5) + "\n")
file.write("Test Micro F1 Score on pubmed using my bayes ::" +
str(micro_bayes / 5) + "\n")
file.write("Test Micro F1 Score on pubmed using my knn ::" +
str(micro_knn / 5) + "\n \n")
def start(training_set11,training_label11,test_set,test_label,ii):
curr=os.getcwd()
final=os.path.join(curr,r'LSH_files')
if not os.path.exists(final):
os.makedirs(final)
file4=open(final + '/task7'+str(ii)+'.txt','w')
n,m=training_set11.shape
i3=2
x=[]
a=[]
b=[]
c=[]
list1=[]
list2=[]
list3=[]
list4=[]
list5=[]
list6=[]
while(i3<=m):
#print(i3,end=" ")
# list_k_fold=man_split(training_set11,training_label11,5)
train_copy=lsh_ac(training_set11,i3,ii)
test_copy=lsh_ac(test_set,i3,ii)
train_copy_pca=np.array(pca(training_set11,i3))
test_copy_pca=np.array(pca(test_set,i3))
#print(len(train_copy))
accuracy=0
micro=0
macro=0
accuracy_pca=0
micro_pca=0
macro_pca=0
#print("-------------")
#print(len(training_set))
find_dict=hash_iter1(train_copy,test_copy,20)
_,predictions=start_lsh(find_dict,train_copy,training_label11,test_copy,test_label)
#print(predictions)
accuracy+= _
micro+=f1_score(test_label,predictions,average='micro')
macro+=f1_score(test_label,predictions,average='macro')
_,pred1=nn.fun_knn(train_copy_pca,test_copy_pca,training_label11,test_label)
accuracy_pca+=_
micro_pca+=f1_score(test_label,pred1,average='micro')
macro_pca+=f1_score(test_label,pred1,average='macro')
x.append(i3)
list1.append(accuracy)
list2.append(macro)
list3.append(micro)
list4.append(accuracy_pca)
list5.append(macro_pca)
list6.append(micro_pca)
file4.write("Test Accuracy on dataset " + str(ii)+ " using LSH on d = "+str(i3)+"="+str(accuracy) +"\n")
file4.write("Test Accuracy on dataset " + str(ii)+ " using PCA on d = "+str(i3)+"="+str(accuracy_pca) +"\n")
file4.write("Macro Score on dataset " + str(ii)+ " using LSH on d = "+str(i3)+"="+str(macro) +"\n")
file4.write("Macro Score on dataset " + str(ii)+ " using PCA on d = "+str(i3)+"="+str(macro_pca) +"\n")
file4.write("Micro Score on dataset " + str(ii)+ " using LSH on d = "+str(i3)+"="+str(micro) +"\n")
file4.write("Micro Score on dataset " + str(ii)+ " using PCA on d = "+str(i3)+"="+str(micro_pca) +"\n")
i3=i3*2
print(accuracy)
# print(micro/5)
# print(macro/5)
# print(accuracy_pca/5)
# print(micro_pca/5)
# print(macro_pca/5)
a.append(list1)
a.append(list4)
b.append(list2)
b.append(list5)
c.append(list3)
c.append(list6)
plot(x,a,1+(3*(ii-1)))
plot(x,b,2+(3*(ii-1)))
plot(x,c,3+(3*(ii-1)))