def full_grad_full(W1,b1,W2,b2,Wlabel,alpha,neg_list,pos_list,vocab,normalized):
#set up some functions for array manipulation
d = np.shape(W1)[0]
W = np.zeros((d,(2*d)+1))
W[:,:(2*d)] = W1
W[:,(2*d)] = b1
U = np.zeros((2*d,d+1))
U[:,:d] = W2
U[:,d] = b2
k = np.shape(Wlabel)[0]
V = np.zeros((k,d))
V[:,:d] = Wlabel
pars = (W,U,V)
#set up arrays that will hold the derivatives
dW = np.zeros(np.shape(W))
dU = np.zeros(np.shape(U))
dV = np.zeros(np.shape(Wlabel))
dVocab = np.zeros(np.shape(vocab))
#loop over neg_list
label = np.array([0.0,1.0])
for example in neg_list:
tree_stuff = tm.build_tree(example,label,vocab,W1,W2,b1,b2,Wlabel,normalized)
tree_meanings = tree_stuff[1]
treeinfo = tree_stuff[0]
#extra_ones = np.ones(np.shape(tree_meanings)[1])
#tree = np.vstack((tree_meanings,extra_ones))
Dlist = backprop_full(tree_meanings,treeinfo,label,pars,alpha,normalized)
dW+=Dlist[0]
dU+=Dlist[1]
dV+=Dlist[2]
dx = Dlist[3]
for i in range(len(example)):
voc_index = example[i] -1
dVocab[voc_index,:] += dx[i,:]
#loop over pos_list
label = np.array([1.0,0.0])
for example in pos_list:
tree_stuff = tm.build_tree(example,label,vocab,W1,W2,b1,b2,Wlabel,normalized)
tree_meanings = tree_stuff[1]
treeinfo = tree_stuff[0]
#extra_ones = np.ones(np.shape(tree_meanings)[1])
#tree = np.vstack((tree_meanings,extra_ones))
Dlist = backprop_full(tree_meanings,treeinfo,label,pars,alpha,normalized)
dW+=Dlist[0]
dU+=Dlist[1]
dV+=Dlist[2]
dx = Dlist[3]
for i in range(len(example)):
voc_index = example[i] - 1
dVocab[voc_index,:] += dx[i,:]
#divide by size of training set
dW /= float(len(neg_list) + len(pos_list))
dU /= float(len(neg_list) + len(pos_list))
dV /= float(len(neg_list) + len(pos_list))
dVocab /= float(len(neg_list) + len(pos_list))
return dW[:,:(2*d)],dW[:,(2*d)],dU[:,:d],dU[:,d],dV,dVocab
def phrase_ranking(neg_examples,pos_examples,vocab,W1,W2,b1,b2,Wlabel,normalized):
#first loop over neg_examples
phrase_list = []
score_list = []
meaning_list = []
label = np.array([0.0,1.0])
for example in neg_examples:
sub_phrase_list = []
sub_score_list = []
sub_meaning_list = []
N = len(example)
num_nodes = 2*N - 1
tree_stuff = tm.build_tree(example,label,vocab,W1,W2,b1,b2,Wlabel,normalized)
tree_info = tree_stuff[0]
tree_meanings = tree_stuff[1]
for i in range(N):
sub_phrase_list.append([example[i]])
for k in range(N,num_nodes):
left = tree_info[0,k]
right = tree_info[1,k]
phrase = sub_phrase_list[left] + sub_phrase_list[right]
sub_phrase_list.append(phrase)
for j in range(num_nodes):
predicted = tm.make_d(tree_meanings[:,j],Wlabel)
score = math.log(predicted[0]/predicted[1])
sub_score_list.append(score)
sub_meaning_list.append(tree_meanings[:,j])
score_list += sub_score_list
meaning_list += sub_meaning_list
phrase_list += sub_phrase_list
label = np.array([1.0,0.0])
for example in pos_examples:
sub_phrase_list = []
sub_score_list = []
sub_meaning_list = []
N = len(example)
num_nodes = 2*N - 1
tree_stuff = tm.build_tree(example,label,vocab,W1,W2,b1,b2,Wlabel,normalized)
tree_info = tree_stuff[0]
tree_meanings = tree_stuff[1]
for i in range(N):
sub_phrase_list.append([example[i]])
for k in range(N,num_nodes):
left = tree_info[0,k]
right = tree_info[1,k]
phrase = sub_phrase_list[left] + sub_phrase_list[right]
sub_phrase_list.append(phrase)
for j in range(num_nodes):
predicted = tm.make_d(tree_meanings[:,j],Wlabel)
score = math.log(predicted[0]/predicted[1])
sub_score_list.append(score)
sub_meaning_list.append(tree_meanings[:,j])
score_list += sub_score_list
meaning_list += sub_meaning_list
phrase_list += sub_phrase_list
return phrase_list,score_list,meaning_list
def compare_predict(W1,b1,W2,b2,Wlabel,pos_neg,example,vocab,normalized):
if(pos_neg == 1):
label = np.array([1.0,0.0])
else:
label = np.array([0.0,1.0])
data = tm.build_tree(example,label,vocab,W1,W2,b1,b2,Wlabel,normalized)
predictions = data[3]
top_predict = predictions[:,-1]
accurate = np.dot(label,top_predict)
if(accurate >= 0.5):
is_correct = 1.0
else:
is_correct = 0.0
return is_correct
