def tern_convNN(trainSamples, trainTags, testSamples, testTags, embed_size,
epoc):
# prep data
# First set up word to index encoding
word_to_index = word2ix(trainSamples)
# Create encoded list of samples
encoded_samples = [encodeSample(s, word_to_index) for s in trainSamples]
# pad all samples
maximum_length = max(preprocess.get_max_len(trainSamples),
preprocess.get_max_len(testSamples))
padded_s = pad_sequences(encoded_samples,
maxlen=maximum_length,
padding='post')
testWord_to_ix = word2ix(testSamples)
encoded_test = [encodeSample(s, testWord_to_ix) for s in testSamples]
padded_t = pad_sequences(encoded_test,
maxlen=maximum_length,
padding='post')
# build model
model = Sequential()
model.add(
Embedding(len(word_to_index), embed_size, input_length=maximum_length))
model.add(Conv1D(64, 3, activation='relu'))
model.add(Conv1D(64, 3, activation='relu'))
model.add(MaxPooling1D(3))
model.add(Conv1D(128, 3, activation='relu'))
model.add(Conv1D(128, 3, activation='relu'))
model.add(GlobalAveragePooling1D())
model.add(Dropout(0.5))
model.add(Dense(3, activation='softmax'))
# test model
model.compile(loss='categorical_crossentropy',
optimizer='rmsprop',
metrics=['accuracy'])
earlystop = callbacks.EarlyStopping(monitor='accuracy',
min_delta=0,
patience=3)
model.fit(padded_s,
trainTags,
batch_size=16,
epochs=epoc,
callbacks=[earlystop])
#score = model.evaluate(padded_t, testTags, batch_size=16)
predictionProbs = model.predict(padded_t)
predictions = []
for p in predictionProbs:
p = p.tolist()
maxval = max(p)
predictions.append(index2rating[p.index(maxval)])
trueTags = []
for t in testTags:
maxval = max(t)
trueTags.append(index2rating[t.index(maxval)])
confusion = metrics.confusion_matrix(trueTags, predictions)
return confusion
def tern_basic(trainSamples, trainTags, testSamples, testTags, embed_size,
epoc):
# First set up word to index encoding
word_to_index = word2ix(trainSamples)
# Create encoded list of samples
encoded_samples = [encodeSample(s, word_to_index) for s in trainSamples]
# pad all samples
maximum_length = max(preprocess.get_max_len(trainSamples),
preprocess.get_max_len(testSamples))
padded = pad_sequences(encoded_samples,
maxlen=maximum_length,
padding='post')
# define the model
model = Sequential()
model.add(
Embedding(len(word_to_index), embed_size, input_length=maximum_length))
model.add(Flatten())
model.add(Dense(64, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(64, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(3, activation='softmax'))
sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
# compile
model.compile(optimizer=sgd,
loss='categorical_crossentropy',
metrics=['acc'])
# fit model
trainTags = np.asarray(trainTags)
earlystop = callbacks.EarlyStopping(monitor='acc',
min_delta=0,
patience=10)
model.fit(padded, trainTags, epochs=epoc, verbose=0, callbacks=[earlystop])
# prepare test data
testWord_to_ix = word2ix(testSamples)
encoded_test = [encodeSample(s, testWord_to_ix) for s in testSamples]
padded_test = pad_sequences(encoded_test,
maxlen=maximum_length,
padding='post')
# test
predictionProbs = model.predict(padded_test)
predictions = []
for p in predictionProbs:
p = p.tolist()
maxval = max(p)
predictions.append(index2rating[p.index(maxval)])
trueTags = []
for t in testTags:
maxval = max(t)
trueTags.append(index2rating[t.index(maxval)])
confusion = metrics.confusion_matrix(trueTags, predictions)
#score = model.evaluate(padded_test, testTags, verbose=1)
return confusion
def lstm(trainSamples, trainTags, testSamples, testTags, embed_size, epoc):
# prep data
# First set up word to index encoding
word_to_index = word2ix(trainSamples)
# Create encoded list of samples
encoded_samples = [encodeSample(s, word_to_index) for s in trainSamples]
# pad all samples
maximum_length = max(preprocess.get_max_len(trainSamples),
preprocess.get_max_len(testSamples))
padded_s = pad_sequences(encoded_samples,
maxlen=maximum_length,
padding='post')
testWord_to_ix = word2ix(testSamples)
encoded_test = [encodeSample(s, testWord_to_ix) for s in testSamples]
padded_t = pad_sequences(encoded_test,
maxlen=maximum_length,
padding='post')
# Make model
model = Sequential()
model.add(Embedding(len(word_to_index), output_dim=256))
model.add(LSTM(128))
model.add(Dropout(0.5))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy',
optimizer='rmsprop',
metrics=['accuracy'])
earlystop = callbacks.EarlyStopping(monitor='accuracy',
min_delta=0,
patience=3)
model.fit(padded_s,
trainTags,
batch_size=16,
epochs=epoc,
callbacks=[earlystop])
#score = model.evaluate(padded_t, testTags, batch_size=16)
predictions = model.predict(padded_t)
predictions[predictions >= 0.5] = 1
predictions[predictions < 0.5] = -1
confusion = metrics.confusion_matrix(testTags, predictions)
return confusion