def work(model_name, dataset_name, pooling_mode):
print "model_name: ", model_name
print "dataset_name: ", dataset_name
print "pooling_mode: ", pooling_mode
print "Started!"
rng = numpy.random.RandomState(23455)
sentenceWordCount = T.ivector("sentenceWordCount")
corpus = T.matrix("corpus")
# docLabel = T.ivector('docLabel')
# for list-type data
layer0 = DocEmbeddingNNOneDoc(corpus, sentenceWordCount, rng, wordEmbeddingDim=200, \
sentenceLayerNodesNum=100, \
sentenceLayerNodesSize=[5, 200], \
docLayerNodesNum=100, \
docLayerNodesSize=[3, 100],
pooling_mode=pooling_mode)
layer1_output_num = 100
layer1 = HiddenLayer(
rng,
input=layer0.output,
n_in=layer0.outputDimension,
n_out=layer1_output_num,
activation=T.tanh
)
layer2 = LogisticRegression(input=layer1.output, n_in=100, n_out=2)
cost = layer2.negative_log_likelihood(1 - layer2.y_pred)
# calculate sentence sentence_score
sentence_grads = T.grad(cost, layer0.sentenceResults)
sentence_score = T.diag(T.dot(sentence_grads, T.transpose(layer0.sentenceResults)))
# calculate word sentence_score against the whole network
word_grad = T.grad(cost, corpus)
word_score = T.diag(T.dot(word_grad, T.transpose(corpus)))
# calculate word
cell_scores = T.grad(cost, layer1.output)
# calculate word score against cells
word_score_against_cell = [T.diag(T.dot(T.grad(layer1.output[i], corpus), T.transpose(corpus))) for i in xrange(layer1_output_num)]
# construct the parameter array.
params = layer2.params + layer1.params + layer0.params
# Load the parameters last time, optionally.
model_path = "data/" + dataset_name + "/model_100,100,100,100,parameters/" + pooling_mode + ".model"
loadParamsVal(model_path, params)
print "Compiling computing graph."
output_model = theano.function(
[corpus, sentenceWordCount],
[layer2.y_pred, sentence_score, word_score, layer1.output, cell_scores] + word_score_against_cell
)
print "Compiled."
input_filename = "data/" + dataset_name + "/train/small_text"
cr = CorpusReader(minDocSentenceNum=5, minSentenceWordNum=5, dataset=input_filename)
count = 0
while(count < cr.getDocNum()):
info = cr.getCorpus([count, count + 1])
count += 1
if info is None:
print "Pass"
continue
docMatrixes, _, sentenceWordNums, ids, sentences, _ = info
docMatrixes = numpy.matrix(
docMatrixes,
dtype=theano.config.floatX
)
sentenceWordNums = numpy.array(
sentenceWordNums,
dtype=numpy.int32
)
print "start to predict: %s." % ids[0]
info = output_model(docMatrixes, sentenceWordNums)
pred_y = info[0]
g = info[1]
word_scores = info[2]
cell_outputs = info[3]
cell_scores = info[4]
word_scores_against_cell = info[5:]
if len(word_scores_against_cell) != len(cell_outputs):
print "The dimension of word_socre and word are different."
raise Exception("The dimension of word_socre and word are different.")
print "End predicting."
print "Writing resfile."
score_sentence_list = zip(g, sentences)
score_sentence_list.sort(key=lambda x:-x[0])
current_doc_dir = "data/output/" + model_name + "/" + pooling_mode + "/" + dataset_name + "/" + str(pred_y[0]) + "/" + ids[0]
if not os.path.exists(current_doc_dir):
os.makedirs(current_doc_dir)
# sentence sentence_score
with codecs.open(current_doc_dir + "/sentence_score", "w", 'utf-8', "ignore") as f:
f .write("pred_y: %i\n" % pred_y[0])
for g0, s in score_sentence_list:
f.write("%f\t%s\n" % (g0, string.join(s, " ")))
wordList = list()
for s in sentences:
wordList.extend(s)
print "length of word_scores", len(word_scores)
print "length of wordList", len(wordList)
score_word_list = zip(wordList , word_scores)
with codecs.open(current_doc_dir + "/nn_word", "w", 'utf-8', "ignore") as f:
for word, word_score in score_word_list:
f.write("%s\t%f\n" % (word, word_score))
with codecs.open(current_doc_dir + "/nn_word_merged", "w", 'utf-8', "ignore") as f:
merged_score_word_list = merge_kv(score_word_list)
for word, word_score in merged_score_word_list:
f.write("%s\t%f\n" % (word, word_score))
if not os.path.exists(current_doc_dir + "/nc_word"):
os.makedirs(current_doc_dir + "/nc_word")
neu_num = 0
for w, c_output, c_score in zip(word_scores_against_cell, cell_outputs, cell_scores):
with codecs.open(current_doc_dir + "/nc_word/" + str(neu_num), "w", 'utf-8', "ignore") as f:
f.write("cell sentence_score: %lf\n" % c_output)
for word, word_score in zip(wordList, w):
f.write("%s\t%f\n" % (word, word_score))
merged_score_word_list = merge_kv(zip(wordList, w))
with codecs.open(current_doc_dir + "/nc_word/" + str(neu_num) + "_merged", "w", 'utf-8', "ignore") as f:
f.write("cell_scores: %lf\n" % c_score)
f.write("cell_output: %lf\n" % c_output)
for word, word_score in merged_score_word_list:
f.write("%s\t%f\n" % (word, word_score))
neu_num += 1
print "Written." + str(count)
print "All finished!"
def work(model_name, dataset_name, pooling_mode):
print "model_name: ", model_name
print "dataset_name: ", dataset_name
print "pooling_mode: ", pooling_mode
print "Started!"
rng = numpy.random.RandomState(23455)
sentenceWordCount = T.ivector("sentenceWordCount")
corpus = T.matrix("corpus")
# docLabel = T.ivector('docLabel')
# for list-type data
layer0 = DocEmbeddingNNOneDoc(
corpus,
sentenceWordCount,
rng,
wordEmbeddingDim=200,
sentenceLayerNodesNum=100,
sentenceLayerNodesSize=[5, 200],
docLayerNodesNum=100,
docLayerNodesSize=[3, 100],
pooling_mode=pooling_mode,
)
layer1_output_num = 100
layer1 = HiddenLayer(
rng, input=layer0.output, n_in=layer0.outputDimension, n_out=layer1_output_num, activation=T.tanh
)
layer2 = LogisticRegression(input=layer1.output, n_in=100, n_out=2)
cost = layer2.negative_log_likelihood(1 - layer2.y_pred)
# calculate sentence sentence_score
sentence_grads = T.grad(cost, layer0.sentenceResults)
sentence_score = T.diag(T.dot(sentence_grads, T.transpose(layer0.sentenceResults)))
# calculate word sentence_score against the whole network
word_grad = T.grad(cost, corpus)
word_score = T.diag(T.dot(word_grad, T.transpose(corpus)))
# calculate word
cell_scores = T.grad(cost, layer1.output)
# calculate word score against cells
word_score_against_cell = [
T.diag(T.dot(T.grad(layer1.output[i], corpus), T.transpose(corpus))) for i in xrange(layer1_output_num)
]
# construct the parameter array.
params = layer2.params + layer1.params + layer0.params
# Load the parameters last time, optionally.
model_path = "data/" + dataset_name + "/model_100,100,100,100,parameters/" + pooling_mode + ".model"
loadParamsVal(model_path, params)
print "Compiling computing graph."
output_model = theano.function(
[corpus, sentenceWordCount],
[layer2.y_pred, sentence_score, word_score, layer1.output, cell_scores] + word_score_against_cell,
)
print "Compiled."
input_filename = "data/" + dataset_name + "/train/small_text"
cr = CorpusReader(minDocSentenceNum=5, minSentenceWordNum=5, dataset=input_filename)
count = 0
while count < cr.getDocNum():
info = cr.getCorpus([count, count + 1])
count += 1
if info is None:
print "Pass"
continue
docMatrixes, _, sentenceWordNums, ids, sentences, _ = info
docMatrixes = numpy.matrix(docMatrixes, dtype=theano.config.floatX)
sentenceWordNums = numpy.array(sentenceWordNums, dtype=numpy.int32)
print "start to predict: %s." % ids[0]
info = output_model(docMatrixes, sentenceWordNums)
pred_y = info[0]
g = info[1]
word_scores = info[2]
cell_outputs = info[3]
cell_scores = info[4]
word_scores_against_cell = info[5:]
if len(word_scores_against_cell) != len(cell_outputs):
print "The dimension of word_socre and word are different."
raise Exception("The dimension of word_socre and word are different.")
print "End predicting."
print "Writing resfile."
score_sentence_list = zip(g, sentences)
score_sentence_list.sort(key=lambda x: -x[0])
current_doc_dir = (
"data/output/" + model_name + "/" + pooling_mode + "/" + dataset_name + "/" + str(pred_y[0]) + "/" + ids[0]
)
if not os.path.exists(current_doc_dir):
os.makedirs(current_doc_dir)
# sentence sentence_score
with codecs.open(current_doc_dir + "/sentence_score", "w", "utf-8", "ignore") as f:
f.write("pred_y: %i\n" % pred_y[0])
for g0, s in score_sentence_list:
f.write("%f\t%s\n" % (g0, string.join(s, " ")))
wordList = list()
for s in sentences:
wordList.extend(s)
print "length of word_scores", len(word_scores)
print "length of wordList", len(wordList)
score_word_list = zip(wordList, word_scores)
with codecs.open(current_doc_dir + "/nn_word", "w", "utf-8", "ignore") as f:
for word, word_score in score_word_list:
f.write("%s\t%f\n" % (word, word_score))
with codecs.open(current_doc_dir + "/nn_word_merged", "w", "utf-8", "ignore") as f:
merged_score_word_list = merge_kv(score_word_list)
for word, word_score in merged_score_word_list:
f.write("%s\t%f\n" % (word, word_score))
if not os.path.exists(current_doc_dir + "/nc_word"):
os.makedirs(current_doc_dir + "/nc_word")
neu_num = 0
for w, c_output, c_score in zip(word_scores_against_cell, cell_outputs, cell_scores):
with codecs.open(current_doc_dir + "/nc_word/" + str(neu_num), "w", "utf-8", "ignore") as f:
f.write("cell sentence_score: %lf\n" % c_output)
for word, word_score in zip(wordList, w):
f.write("%s\t%f\n" % (word, word_score))
merged_score_word_list = merge_kv(zip(wordList, w))
with codecs.open(current_doc_dir + "/nc_word/" + str(neu_num) + "_merged", "w", "utf-8", "ignore") as f:
f.write("cell_scores: %lf\n" % c_score)
f.write("cell_output: %lf\n" % c_output)
for word, word_score in merged_score_word_list:
f.write("%s\t%f\n" % (word, word_score))
neu_num += 1
print "Written." + str(count)
print "All finished!"
