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 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 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 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))