def IR_Evaluation_Test(EDUs_Test, EDUs_Train, path_file_Test, path_file_Train, W1, WV, dim, activationFunc, iteration, OutputFile, numberofDoc):
precisions = []
TestFileList = os.listdir(path_file_Test)
TrainFileList = os.listdir(path_file_Train)
trainDocuments = []
trainDocuments_label = []
for tr in range(0, len(TrainFileList)):
EDUs_tr = EDUs_Train[TrainFileList[tr]]
EDUs_tr = update_EDU(EDUs_tr, W1, dim, activationFunc)
# path_File_train = path_file_Train + TrainFileList[tr]
# EDUs_train = readTree_att_NSWeight(path_File_train, W1_doc, WV, dim, activationFunc)
eduKeys = sortEduKey(EDUs_tr.keys(), reverse=True)
trainRep = EDUs_tr[str(eduKeys[0])].vector
trainDocuments.append(trainRep)
trainDocuments_label.append(TrainFileList[tr].split("-")[1])
trainDocuments = np.array(trainDocuments)
trainDocuments_label = np.array(trainDocuments_label)
#print trainDocuments_label
for te in range(0, len(TestFileList)):
EDUs_te = EDUs_Test[TestFileList[te]]
EDUs_te = update_EDU(EDUs_te, W1, dim, activationFunc)
eduKeys = sortEduKey(EDUs_te.keys(), reverse=True)
testRep = EDUs_te[str(eduKeys[0])].vector
testRep = np.array(testRep).reshape(1, -1)
if (np.isnan(testRep).any()):
print (TestFileList[te])
distances = cosine_similarity(testRep, trainDocuments)
main_label = TestFileList[te].split("-")[1]
predicted_labels = trainDocuments_label[(((distances.argsort())[0])[-1*numberofDoc:][::-1])]
print (predicted_labels)
predicted_labels = sorted(predicted_labels)
predicts = {x: predicted_labels.count(x) for x in predicted_labels}
main_predict = max(predicts.items(), key=operator.itemgetter(1))[0]
print (main_label, main_predict)
if main_label in predicts:
pre_main_label = float(predicts[main_label]) / (numberofDoc)
precisions.append(pre_main_label)
else:
precisions.append(0)
avg_pre = float(sum(precisions)) / len(precisions)
print ("average", avg_pre)
if (OutputFile!= None):
OutputFile.write("%s,%s\n" % (iteration, avg_pre))
def calculateError_validation(path_Folder, mode, WV, dim, W1 , W2, OutputFile, WSat, WNu, iteration, activationFunc):
posFileList_test = os.listdir(path_Folder + "pos/")
negFileList_test = os.listdir(path_Folder + "neg/")
numberofSamples_test = min(len(posFileList_test), len(negFileList_test))
sumErr=0.0
for k in range(0, numberofSamples_test):
path_File_test = path_Folder + "pos/" + posFileList_test[k]
EDUs = readTree_att_NSWeight(path_File_test, W1, WV, dim, WSat, WNu, activationFunc)
y = [1.0, 0]
eduKeys = sortEduKey(EDUs.keys(), reverse=True)
input2 = EDUs[str(eduKeys[0])].vector
y_in = feedforward(input2, W2)
output = feedforward_act(input2, W2, activationFunc)
sumErr += MSE(y, output)
path_File_test = path_Folder + "neg/" + negFileList_test[k]
#print negFileList_test[k]
EDUs = readTree_att_NSWeight(path_File_test, W1, WV, dim, WSat, WNu, activationFunc)
y = [0, 1.0]
eduKeys = sortEduKey(EDUs.keys(), reverse=True)
input2 = EDUs[str(eduKeys[0])].vector
y_in = feedforward(input2, W2)
output = feedforward_act(input2, W2, activationFunc)
sumErr += MSE(y, output)
totall_Err = sumErr/(2*numberofSamples_test)
return totall_Err
print iteration, " ", mode , " ", totall_Err
OutputFile.write("%s,%s,%s\n" % (iteration, mode, totall_Err))
def calculateError_validation_EDUs(allEDUs, mode, WV, dim, W1 , W2, OutputFile, WSat, WNu, iteration, activationFunc):
target_list = np.zeros([0, 2])
output_list = np.zeros([0, 2])
EDU_key = allEDUs.keys()
for EDUid in EDU_key:
EDUs = allEDUs [EDUid]
EDUs = update_EDU(EDUs, W1, WSat, WNu, dim, activationFunc)
if (len(EDUs) > 0 and EDUid>0):
y = [1.0, 0]
#eduKeys = sortEduKey(EDUs.keys(), reverse=True)
eduKeys = sortEduKey(EDUs.keys(), reverse=True)
input2 = EDUs[str(eduKeys[0])].vector
output = feedforward_act(input2, W2, global_outputActivation)
target_list = np.concatenate((target_list, [y]), 0)
output_list = np.concatenate((output_list, [output]), 0)
if (len(EDUs) > 0 and EDUid < 0):
y = [0, 1.0]
# eduKeys = sortEduKey(EDUs.keys(), reverse=True)
eduKeys = sortEduKey(EDUs.keys(), reverse=True)
input2 = EDUs[str(eduKeys[0])].vector
#y_in = feedforward(input2, W2)
output = feedforward_act(input2, W2, global_outputActivation)
target_list = np.concatenate((target_list, [y]), 0)
output_list = np.concatenate((output_list, [output]), 0)
totall_Err = MSE(target_list, output_list)
print(iteration, " ", mode , " ", totall_Err)
OutputFile.write("%s,%s,%s\n" % (iteration, mode, totall_Err))
return totall_Err
def test_AttWeight(path_Folder, mode, WV, dim, W1 , W2, OutputFile, WSat, WNu, iteration, activationFunc):
posFileList_test = os.listdir(path_Folder + "pos/")
negFileList_test = os.listdir(path_Folder + "neg/")
numberofSamples_test = min(len(posFileList_test), len(negFileList_test))
#numberofSamples_test=100
tp = 0
fp = 0
tn = 0
fn = 0
for k in range(0, numberofSamples_test):
path_File_test = path_Folder + "pos/" + posFileList_test[k]
#print posFileList_test[k]
EDUs = readTree_att_NSWeight(path_File_test, W1, WV, dim, WSat, WNu, activationFunc)
y = [1.0, 0]
eduKeys = sortEduKey(EDUs.keys(), reverse=True)
input2 = EDUs[str(eduKeys[0])].vector
# print "pos"
# print input2
y_in = feedforward(input2, W2)
output = feedforward_act(input2, W2, activationFunc)
#print output
if output[0] > output[1]:
tp += 1
else:
fn += 1
path_File_test = path_Folder + "neg/" + negFileList_test[k]
#print negFileList_test[k]
EDUs = readTree_att_NSWeight(path_File_test, W1, WV, dim, WSat, WNu, activationFunc)
eduKeys = sortEduKey(EDUs.keys(), reverse=True)
input2 = EDUs[str(eduKeys[0])].vector
# print "neg"
# print input2
y_in = feedforward(input2, W2)
output = feedforward_act(input2, W2, activationFunc)
if output[0] < output[1]:
tn += 1
else:
fp += 1
accuracy = float(tp + tn) / (tp + tn + fp + fn)
if (tp+fp) == 0:
precision = 0
else:
precision = float(tp) / (tp + fp)
recall = float(tp) / (tp + fn)
if (precision + recall) == 0:
F1 =0
else:
F1 = 2 * (float(precision * recall)) / (precision + recall)
print iteration, " ", mode , " ", tp, " ", tn, " ", fp, " ", fn, " ", accuracy, " ", precision, " ", recall, " ", F1
OutputFile.write("%s,%s,%s,%s,%s,%s,%s,%s,%s,%s\n" % (iteration, mode, tp, tn, fp, fn, accuracy, precision, recall, F1))
def train_for_each_Sample_AttWeight (EDUs, EDUs_test, y, W1, W21, W22, eta, dim, activationFunc, dropOutPercent):
W1_copy = W1.copy()
W21_copy = W21.copy()
W22_copy = W22.copy()
indexNode = dropOut(len(W1[0]), dropOutPercent)
#W1_doc = dropcolrow(W1, indexNode, False)
#indexNode = dropOut(len(W1_query[0]), dropOutPercent)
W1 = dropcolrow(W1, indexNode, False)
indexNode2 = []
indexNode2.extend(indexNode)
indexNode2.extend(indexNode*2)
W21 = dropcolrow(W21, indexNode2, True)
eduKeys_test = sortEduKey(EDUs_test.keys(), reverse=True)
input2_test = EDUs_test[str(eduKeys_test[0])].vector
eduKeys = sortEduKey(EDUs.keys(), reverse=True)
input2 = EDUs[str(eduKeys[0])].vector
input = (np.concatenate([input2, input2_test], 0))
#y_in1 = feedforward(input, W21)
output1 = feedforward_act(input, W21, activationFunc)
y_in = feedforward(output1, W22)
output = feedforward_act(output1, W22, global_outputActivation)
error_soft = softmax_error(y, output, y_in, global_outputActivation)
delta_W22 = calculate_deltaW(error_soft, output1)
error_hidden = non_softmax_error(error_soft, W22, input, W21, activationFunc)
delta_W21 = calculate_deltaW(error_hidden, input)
delta_W1_doc = BpthroughTree(EDUs, error_hidden, W1, W21, dim, activationFunc, True)
delta_W1_query = BpthroughTree(EDUs_test, error_hidden, W1, W21, dim, activationFunc, False)
#print ("=============== : ", np.sum(delta_W1_doc[:, indexNode]))
delta_W1_doc = dropcolrow(delta_W1_doc, indexNode, False)
delta_W1_query = dropcolrow(delta_W1_query, indexNode, False)
delta_W21 = dropcolrow(delta_W21, indexNode2, True)
delta_W = np.divide(np.add(delta_W1_doc, delta_W1_query), 2)
W21 = update_weight(eta, W21_copy, delta_W21)
W22 = update_weight(eta, W22_copy, delta_W22)
W1 = update_weight(eta, W1_copy, delta_W)
return W1, W21, W22
def calculateError_validation_pair(allEDUs, mode, WV, dim, W1, W21, W22, OutputFile, iteration, activationFunc, pairs):
#FileList = os.listdir(path_Folder)
numberofSamples = len(pairs)
target_list=[]
output_list=[]
for pair in pairs: #j in range(0, numberofSamples):
filenames = pair.split(' ')
#path_File_test = path_Folder + filenames[0]
EDUs_test = allEDUs[filenames[0]]#readTree_att_NSWeight(path_File_test, W1_query, WV, dim, activationFunc)
EDUs_test = update_EDU(EDUs_test, W1, dim, activationFunc)
eduKeys_test = sortEduKey(EDUs_test.keys(), reverse=True)
input2_test = EDUs_test[str(eduKeys_test[0])].vector
#path_File_test = path_Folder + filenames[1]
EDUs = allEDUs[filenames[1]]#readTree_att_NSWeight(path_File_test, W1_doc, WV, dim, activationFunc)
EDUs = update_EDU(EDUs, W1, dim, activationFunc)
eduKeys = sortEduKey(EDUs.keys(), reverse=True)
input2 = EDUs[str(eduKeys[0])].vector
input = np.concatenate([input2, input2_test], 0)
output1 = feedforward_act(input, W21, activationFunc)
output = feedforward_act(output1, W22, global_outputActivation)
if (filenames[0].split("-")[1] == filenames[1].split("-")[1]):
if len(W22[0]) == 1:
y = [1.0]
else:
y = [0.8, -0.8]
target_list.append(y)
output_list.append(output)
else:
if len(W22[0]) == 1:
y = [-1.0]
else:
y = [-0.8, 0.8]
target_list.append(y)
output_list.append(output)
totall_Err = MSE(output_list, target_list)
print(iteration, " ", mode , " ", totall_Err)
OutputFile.write("%s,%s,%s\n" % (iteration, mode, totall_Err))
return totall_Err
def calculateError_validation(path_Folder, mode, WV, dim, W1_doc, W1_query, W2, OutputFile, iteration, activationFunc):
FileList = os.listdir(path_Folder)
numberofSamples = len(FileList)
target_list=[]
output_list=[]
for j in range(0, numberofSamples):
path_File_test = path_Folder + FileList[j]
EDUs_test = readTree_att_NSWeight(path_File_test, W1_query, WV, dim, activationFunc)
eduKeys_test = sortEduKey(EDUs_test.keys(), reverse=True)
input2_test = EDUs_test[str(eduKeys_test[0])].vector
for k in range(0, numberofSamples):
path_File_test = path_Folder + FileList[k]
EDUs = readTree_att_NSWeight(path_File_test, W1_doc, WV, dim, activationFunc)
eduKeys = sortEduKey(EDUs.keys(), reverse=True)
input2 = EDUs[str(eduKeys[0])].vector
input = np.concatenate([input2, input2_test], 0)
output = feedforward_act(input, W2, global_outputActivation)
#print output
if (FileList[j].split("-")[1] == FileList[k].split("-")[1]):
y = [1.0]
target_list.append(y)
output_list.append(output)
else:
if (k % 5 == 0):
y = [0.0]
target_list.append(y)
output_list.append(output)
totall_Err = cross_entropy(target_list, output_list)
print(iteration, " ", mode , " ", totall_Err)
OutputFile.write("%s,%s,%s\n" % (iteration, mode, totall_Err))
return totall_Err
def train_for_each_Sample (EDUs, y, W1, W2, eta, activationFunc):
eduKeys = sortEduKey(EDUs.keys(), reverse=True)
input2 = EDUs[str(eduKeys[0])].vector
y_in = feedforward(input2, W2)
output = feedforward_act(input2, W2, activationFunc)
#print output
error_soft = softmax_error(y, output, y_in, activationFunc)
delta_W2 = calculate_deltaW(error_soft, input2)
delta_W1 = BpthroughTree(EDUs, error_soft, W1, W2, activationFunc)
W2 = update_weight(eta, W2, delta_W2)
W1 = update_weight(eta, W1, delta_W1)
return W1, W2
def plotDocs(EDUs_Test, name, labelColor):
labels = []
docRepresentaion = []
keys = EDUs_Test.keys()
i = 0
for key in keys:
label = key.split("-")[1]
labels.append(label)
EDUs_te = EDUs_Test[key]
#EDUs_te = update_EDU(EDUs_te, W1, "", activationFunc)
eduKeys = sortEduKey(EDUs_te.keys(), reverse=True)
#print (eduKeys)
testRep = EDUs_te[str(eduKeys[0])].vector
docRepresentaion.append(testRep)
scaler = MinMaxScaler()
X_embedded = TSNE(n_components=2).fit_transform(docRepresentaion)
#print (X_embedded)
scaler.fit(X_embedded)
#print(scaler.transform(X_embedded))
X_embedded = scaler.transform(X_embedded)
#print (X_embedded)
for label, x, y in zip(labels, X_embedded[:, 0], X_embedded[:, 1]):
#print (labelColor)
colorlabel = labelColor[label]
#print (colorlabel)
plt.annotate(label, xy=(x, y), color=colorlabel) #, xytext=(-20,20))#,
# textcoords='offset points', ha='right', va='bottom',
# bbox=dict(boxstyle='round,pad=0.5', fc='yellow', alpha=0.5),
# arrowprops=dict(arrowstyle = '->', connectionstyle='arc3,rad=0'))
pylab.savefig('fig' + name + '.png')
pylab.close()
plt.show()
def test_AttWeight_DrHarati_pair(allEDUs, mode, WV, dim, W1, W21, W22, OutputFile, iteration, activationFunc, pairs):
numberofSamples = len(pairs)
#numberofSamples_test = 50
tp = 0
fp = 0
tn = 0
fn = 0
sim = 0
notsim = 0
for pair in pairs: #j in range(0, numberofSamples):
filenames = pair.split(' ')
EDUs_test = allEDUs[filenames[0]]
EDUs_test = update_EDU(EDUs_test, W1, dim, activationFunc)
eduKeys_test = sortEduKey(EDUs_test.keys(), reverse=True)
input2_test = EDUs_test[str(eduKeys_test[0])].vector
EDUs = allEDUs[filenames[1]]
EDUs = update_EDU(EDUs, W1, dim, activationFunc)
eduKeys = sortEduKey(EDUs.keys(), reverse=True)
input2 = EDUs[str(eduKeys[0])].vector
input = np.concatenate([input2, input2_test], 0)
output1 = feedforward_act(input, W21, activationFunc)
output = feedforward_act(output1, W22, global_outputActivation)
if (filenames[0].split("-")[1] == filenames[1].split("-")[1]):
sim += 1
if (sim % 500 == 0):
print("Similar ", filenames[0].split("-")[1], filenames[1].split("-")[1], output)
#if output[0] > output[1]:
if (len(W22[0]) == 1):
if output[0] > 0:
# print("Similar ", filenames[0].split("-")[1], filenames[1].split("-")[1], output)
tp += 1
else:
# print("Similar ", filenames[0].split("-")[1], filenames[1].split("-")[1], output)
fn += 1
else:
if output[0] > output[1]:
# print("Similar ", filenames[0].split("-")[1], filenames[1].split("-")[1], output)
tp += 1
else:
# print("Similar ", filenames[0].split("-")[1], filenames[1].split("-")[1], output)
fn += 1
else:
notsim += 1
if (notsim % 500 == 0):
print("Not-Similar ", filenames[0].split("-")[1], filenames[1].split("-")[1], output)
#if output[0] < output[1]:
if (len(W22[0]) == 1):
if output[0] < 0:
# print("Not-Similar ", filenames[0].split("-")[1], filenames[1].split("-")[1], output)
tn += 1
else:
# print("Not-Similar ", filenames[0].split("-")[1], filenames[1].split("-")[1], output)
fp += 1
else:
if output[0] < output[1]:
# print("Not-Similar ", filenames[0].split("-")[1], filenames[1].split("-")[1], output)
tn += 1
else:
# print("Not-Similar ", filenames[0].split("-")[1], filenames[1].split("-")[1], output)
fp += 1
print (sim, notsim)
accuracy = float(tp + tn) / (tp + tn + fp + fn)
precision, recall, F1 = calculate_eval_metrics(tp, tn, fp, fn)
print(iteration, " ", mode , " ", tp, " ", tn, " ", fp, " ", fn, " ", accuracy, " ", precision, " ", recall, " ", F1)
OutputFile.write("%s,%s,%s,%s,%s,%s,%s,%s,%s,%s\n" % (iteration, mode, tp, tn, fp, fn, accuracy, precision, recall, F1))
def test_AttWeight_DrHarati(path_Folder, mode, WV, dim, W1 , W2, OutputFile, WSat, WNu, iteration, activationFunc):
posFileList_test = os.listdir(path_Folder + "pos/")
negFileList_test = os.listdir(path_Folder + "neg/")
numberofSamples_test = min(len(posFileList_test), len(negFileList_test))
#numberofSamples_test=100
tp = 0
fp = 0
tn = 0
fn = 0
for k in range(0, numberofSamples_test):
path_File_test = path_Folder + "pos/" + posFileList_test[k]
EDUs = readTree_att_NSWeight(path_File_test, W1, WV, dim, WSat, WNu, activationFunc)
y = [1.0, 0]
eduKeys = sortEduKey(EDUs.keys(), reverse=True)
input2 = EDUs[str(eduKeys[0])].vector
y_in = feedforward(input2, W2)
output = feedforward_act(input2, W2, activationFunc)
if output[0] == output[1]:
print "input", input2
# print "W2", W2[0, :]
# print "W1", W1[0, :]
# print "WN", WNu[0, :]
# print "WS", WSat[0, :]
# print "pos", output
if output[0] > output[1]:
#print "pos ", output
tp += 1
else:
fn += 1
path_File_test = path_Folder + "neg/" + negFileList_test[k]
EDUs = readTree_att_NSWeight(path_File_test, W1, WV, dim, WSat, WNu, activationFunc)
eduKeys = sortEduKey(EDUs.keys(), reverse=True)
input2 = EDUs[str(eduKeys[0])].vector
y_in = feedforward(input2, W2)
output = feedforward_act(input2, W2, activationFunc)
if output[0] == output[1]:
print "input", input2
# print "W2", W2[0, :]
# print "W1", W1[0,:]
# print "WN", WNu[0,:]
# print "WS", WSat[0,:]
# print "neg",output
if output[0] < output[1]:
#print "neg ", output
tn += 1
else:
fp += 1
accuracy = float(tp + tn) / (tp + tn + fp + fn)
precision, recall, F1 = calculate_eval_metrics(tp, tn, fp, fn)
print iteration, " ", mode , " ", tp, " ", tn, " ", fp, " ", fn, " ", accuracy, " ", precision, " ", recall, " ", F1
OutputFile.write("%s,%s,%s,%s,%s,%s,%s,%s,%s,%s\n" % (iteration, mode, tp, tn, fp, fn, accuracy, precision, recall, F1))
