def main():
print("Model_testing")
while True:
user = input(
"1. ARIMA\n2. Linear Regression\n3. Polynomial Regression\n4. SVR\n5. SVR_2\n6. Random Forest\n7. Quit\n"
)
if user == '1':
ARIMA.run()
elif user == '2':
Lin_reg.run()
elif user == '3':
Poly_reg.run()
elif user == '4':
SVR.run()
elif user == '5':
SVR_2.run()
elif user == '6':
RF.run()
elif user == '7':
break
print("\n----------MAIN-----------\n")
def main(run=1, force_run=False):
mkdir(_model_folder)
if not force_run and len(os.listdir(_model_folder)) > 0:
ans = input(
"Found something in '%s', which may be overwitten.\nProceed? [y/n]: "
% _model_folder)
if ans.lower() == 'n':
exit(-1)
for k in range(run):
samples = preprocessing.tp_sample.get_samples(_sample_folder)
if _name_filter is not None:
samples = [s for s in samples if s.batch_name in _name_filter]
print(np.var([get_label(s) for s in samples]))
random.shuffle(samples)
batches = preprocessing.batch_data(samples, cross_valid)
for i in range(cross_valid):
valid_samples = batches[i]
train_samples = []
savedir = "%s/%d/" % (_model_folder, i + 1)
mkdir(savedir)
for j in range(cross_valid):
if j != i:
train_samples.extend(batches[j])
if _filter_samples:
train_samples = preprocessing.score_portion(
train_samples, get_label, _high_portion, _low_portion)
train_texts = [sample.text for sample in train_samples]
valid_texts = [sample.text for sample in valid_samples]
train_matrix, valid_matrix, words = preprocessing.preprocess(
train_texts,
valid_texts,
savedir=savedir,
**_strategy_parameters)
train_labels = np.asarray(
[get_label(sample) for sample in train_samples])
valid_labels = np.asarray(
[get_label(sample) for sample in valid_samples])
model, valid_mse = None, None
if _model_type == "NN":
model = Neural_Network(_attributes,
_hidden_nodes=hidden_nodes,
_learning_rate=learning_rate)
valid_mse = model.train(train_matrix,
train_labels,
valid_matrix,
valid_labels,
max_iter=15000)
else:
model = SVR(**_svm_parameters)
valid_mse = model.train(train_matrix, train_labels,
valid_matrix, valid_labels)
model.save(savedir)
model.destroy()
print("Fold %2d: %.4f" % (i + 1, valid_mse))
def SVR_forecasting(dataset, lookBack, C=2.0, epsilon=0.01, plot_flag=False):
# normalize time series
scaler = MinMaxScaler(feature_range=(0, 1))
dataset = scaler.fit_transform(dataset)
# divide the series into training/testing samples
# NOTE: Not RNN format
train, test = util.divideTrainTest(dataset)
trainX, trainY = util.createSamples(train, lookBack, RNN=False)
testX, testY = util.createSamples(test, lookBack, RNN=False)
print("trainX shape is", trainX.shape)
print("trainY shape is", trainY.shape)
print("testX shape is", testX.shape)
print("testY shape is", testY.shape)
# buil model and train
SVRModel = SVR.SVRModel(C=C, epsilon=epsilon)
SVRModel.train(trainX, trainY)
# forecasting
trainPred = SVRModel.predict(trainX).reshape(-1, 1)
testPred = SVRModel.predict(testX).reshape(-1, 1)
# reverse the time series
trainPred = scaler.inverse_transform(trainPred)
trainY = scaler.inverse_transform(trainY)
testPred = scaler.inverse_transform(testPred)
testY = scaler.inverse_transform(testY)
# evaluate
MAE = eval.calcMAE(testY, testPred)
print("test MAE", MAE)
MRSE = eval.calcRMSE(testY, testPred)
print("test RMSE", MRSE)
MAPE = eval.calcMAPE(testY, testPred)
print("test MAPE", MAPE)
SMAPE = eval.calcSMAPE(testY, testPred)
print("test SMAPE", SMAPE)
if plot_flag:
util.plot(trainPred, trainY, testPred, testY)
return trainPred, testPred, MAE, MRSE, SMAPE
def main(run=1, force_run=False):
mkdir(_model_folder)
if not force_run and len(os.listdir(_model_folder)) > 0:
ans = input(
"Found something in '%s', which may be overwitten.\nProceed? [y/n]: "
% _model_folder)
if ans.lower() == 'n':
exit(-1)
for k in range(run):
samples = preprocessing.tp_sample.get_samples(_sample_folder)
if _name_filter is not None:
samples = [s for s in samples if s.batch_name in _name_filter]
print(np.var([get_label(s) for s in samples]))
random.shuffle(samples)
batches = preprocessing.batch_data(samples, _cross_valid)
for i in range(_cross_valid):
valid_samples = batches[i]
train_samples = []
savedir = "%s/%d/" % (_model_folder, i + 1)
mkdir(savedir)
for j in range(_cross_valid):
if j != i:
train_samples.extend(batches[j])
train_matrix = preprocessing.tb_similarity(train_samples,
chs=_tb_chs)
valid_matrix = preprocessing.tb_similarity(valid_samples,
chs=_tb_chs)
train_labels = np.asarray(
[get_label(sample) for sample in train_samples])
valid_labels = np.asarray(
[get_label(sample) for sample in valid_samples])
model = SVR(**_svm_parameters)
valid_mse = model.train(train_matrix, train_labels, valid_matrix,
valid_labels)
model.save(savedir)
model.destroy()
print("Fold %2d: %.4f" % (i + 1, valid_mse))
def main(run = 1, force_run = False):
mkdir(_model_folder)
if not force_run and len(os.listdir(_model_folder)) > 0:
ans = input("Found something in '%s', which may be overwitten.\nProceed? [y/n]: "%_model_folder)
if ans.lower() == 'n':
exit(-1)
for k in range(run):
samples = preprocessing.tp_sample.get_samples(_sample_folder)
if _name_filter is not None:
samples = [s for s in samples if s.batch_name in _name_filter]
print("Variance: %.3f"%np.var([get_label(s) for s in samples]))
random.shuffle(samples)
batches = preprocessing.batch_data(samples, _cross_valid)
for i in range(_cross_valid):
valid_samples = batches[i]
train_samples = []
savedir = "%s/%d/"%(_model_folder, i+1)
mkdir(savedir)
for j in range(_cross_valid):
if j != i:
train_samples.extend(batches[j])
train_texts = [sample.comment for sample in train_samples]
valid_texts = [sample.comment for sample in valid_samples]
train_matrix, valid_matrix, words = preprocessing.preprocess(train_texts, valid_texts, savedir = savedir, **_strategy_parameters)
#print("\tBag of words: %d"%len(words))
train_labels = np.asarray([get_label(sample) for sample in train_samples])
valid_labels = np.asarray([get_label(sample) for sample in valid_samples])
model, valid_mse = None, None
model = SVR(**_svm_parameters)
valid_mse = model.train(train_matrix, train_labels, valid_matrix, valid_labels)
model.save(savedir)
model.destroy()
print("Fold %2d: %.4f"%(i+1, valid_mse))
print("Train set distribution:", preprocessing.samples_statistics(train_samples, _sections, get_section))
print("Test set distribution:", preprocessing.samples_statistics(test_samples, _sections, get_section))
train_texts = [sample.text for sample in train_samples]
test_texts = [sample.text for sample in test_samples]
tfidf_vectorizer = get_tfidfVectorizer_of_essay_top_tf_words()
print("Vectorizer built..")
train_matrix, test_matrix, words = preprocessing.preprocess(train_texts, test_texts, savedir = _save_dir, words_src = tfidf_vectorizer, normalize_flag = False, reduction = _reduction, reduce_n_attr = _reduce_n_attr, stem_words = _stem_words)
for section in _sections:
train_labels = preprocessing.samples_to_binary(train_samples, [section], get_section)
test_labels = preprocessing.samples_to_binary(test_samples, [section], get_section)
model = SVR()
print("Training for %s section.. "%section)
model.train(train_matrix, train_labels)
predict = model.predict(test_matrix)
accuracy = 0
for i in range(predict.shape[0]):
if predict[i] >= 0.5:
predict[i] = 1
else:
predict[i] = 0
if predict[i] == test_labels[i]:
accuracy += 1.0
accuracy /= predict.shape[0]
model.save("%s/%s/"%(_save_dir,section))
print("Accuracy: %.3f"%accuracy)
selection="tfidf",
select_top=_textbook_words,
savedir=_save_dir,
words_src="textbook",
normalize_flag=False,
reduction=_reduction,
reduce_n_attr=_reduce_n_attr,
stem_words=_stem_words)
for section in _sections:
train_labels = preprocessing.samples_to_binary(train_samples, [section],
get_section)
test_labels = preprocessing.samples_to_binary(test_samples, [section],
get_section)
model = SVR()
print("Training for %s section.. " % section)
model.train(train_matrix, train_labels)
predict = model.predict(test_matrix)
accuracy = 0
for i in range(predict.shape[0]):
if predict[i] >= 0.5:
predict[i] = 1
else:
predict[i] = 0
if predict[i] == test_labels[i]:
accuracy += 1.0
accuracy /= predict.shape[0]
model.save("%s/%s/" % (_save_dir, section))
print("Accuracy: %.3f" % accuracy)