def main():
print("We're going to do some regression now")
# read data
print("Reading the data from ../data/ ; run me from /src")
fft_dict, fft_labels, ffts = utils.read_features(feature='fft')
mfc_dict, mfc_labels, mfcs = utils.read_features(feature='mfc')
# fit classifiers
lrc_fft = LogisticRegressionClassifier(ffts, fft_labels, fft_dict)
lrc_mfc = LogisticRegressionClassifier(mfcs, mfc_labels, mfc_dict)
# cross validate
print("training the first fft model with 10-fold CV")
lrc_fft.cross_validate(k=10)
# get high variance features and retrain
print("extracting features from that model/the fft data")
from sklearn.feature_selection import VarianceThreshold
sel = VarianceThreshold(0.01150)
fft_variance = sel.fit_transform(ffts)
lr_fftvar = LogisticRegressionClassifier(fft_variance, fft_labels,
fft_dict)
print("training the first reduced fft model with 10-fold CV")
lr.fftvar.cross_validate()
# try with fscores
print("training the mfcs with 10-fold CV")
lrc_mfc.cross_validate(10)
def main():
# Get the arguments
args = parse_arguments()
# Get the training parameters
class_size = args.class_size if args.class_size is not None else DEFAULT_CLASS_SIZE
# Get the train and dev feature files
train_files = args.train_files
dev_files = args.dev_files
# Create the list of models to train
models = []
if args.svm: models.append(svm.SVM())
if args.mlp: models.append(mlp.MLP(10))
# If there no development files, perform cross-validation
if dev_files == None:
train_data, train_labels = utils.read_features(train_files)
models = train_cross_validation(train_data, train_labels, models,
class_size)
# Otherwise use the development files
else:
train_data, train_labels = utils.read_features(train_files)
dev_data, dev_labels = utils.read_features(dev_files)
train(train_data, train_labels, dev_data, dev_labels)
def main():
# Get the arguments
args = parse_arguments()
# Get the training parameters
class_size = args.class_size if args.class_size is not None else DEFAULT_CLASS_SIZE
# Get the train and dev feature files
train_files = args.train_files
dev_files = args.dev_files
# Create the list of models to train
models = []
if args.svm: models.append(svm.SVM())
if args.mlp: models.append(mlp.MLP(10))
# If there no development files, perform cross-validation
if dev_files == None:
train_data, train_labels = utils.read_features(train_files)
models = train_cross_validation(train_data, train_labels, models, class_size)
# Otherwise use the development files
else:
train_data, train_labels = utils.read_features(train_files)
dev_data, dev_labels = utils.read_features(dev_files)
train(train_data, train_labels, dev_data, dev_labels)
def main():
"""
Parsing command lines, creating target matrix, fitting BANE and saving the embedding.
"""
args = parameter_parser()
tab_printer(args)
P = read_graph(args)
X = read_features(args)
model = BANE(args, P, X)
model.fit()
model.save_embedding()
def __init__(self, args):
"""
Initializing the training object.
:param args: Arguments parsed from command line.
"""
self.args = args
self.graph = read_graph(self.args.edge_path)
self.features = read_features(self.args.feature_path)
self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
self.initialize_model()
self.simulate_walks()
def execute_factorization():
"""
Reading the target matrix, running optimization and saving to hard drive.
"""
args = parameter_parser()
tab_printer(args)
X = read_features(args.input_path)
print("\nTraining started.\n")
model = ADMM_NMF(X, args)
model.optimize()
print("\nFactors saved.\n")
model.save_user_factors()
model.save_item_factors()
def main():
# Read the arguments
args = parse_arguments()
# Get the class size
class_size = args.class_size if args.class_size is not None else DEFAULT_CLASS_SIZE
# Read the features from the test files
test_files = args.test_files
# Ensure at least 1 test file is passed in
if test_files is None:
print 'Error. Please provide testing feature files'
exit(1)
test_data, test_labels = utils.read_features(test_files)
test_data, test_labels, map = utils.partition(test_data, test_labels,
class_size)
# Read and load the model
if args.svm:
model = svm.SVM()
model.load(args.model)
if args.mlp:
model = mlp.MLP(10)
model.load(args.model)
# Ensure a model was created
if model is None:
print 'Error. Model invalid'
exit(1)
# Test the model
predictions = model.predict(test_data)
accuracy = 1.0 * sum([
1
for label, predict in zip(test_labels, predictions) if label == predict
]) / len(predictions)
# Output results
print 'Accuracy is: ', accuracy
def main():
# Read the arguments
args = parse_arguments()
# Get the class size
class_size = args.class_size if args.class_size is not None else DEFAULT_CLASS_SIZE
# Read the features from the test files
test_files = args.test_files
# Ensure at least 1 test file is passed in
if test_files is None:
print 'Error. Please provide testing feature files'
exit(1)
test_data, test_labels = utils.read_features(test_files)
test_data, test_labels, map = utils.partition(test_data, test_labels, class_size)
# Read and load the model
if args.svm:
model = svm.SVM()
model.load(args.model)
if args.mlp:
model = mlp.MLP(10)
model.load(args.model)
# Ensure a model was created
if model is None:
print 'Error. Model invalid'
exit(1)
# Test the model
predictions = model.predict(test_data)
accuracy = 1.0*sum([1 for label, predict in zip(test_labels, predictions) if label == predict]) / len(predictions)
# Output results
print 'Accuracy is: ', accuracy
import naive_bayes_classifier as lib
clf = lib.NaiveBayesClassifier("hi")
# X=[[1,2],[3,4],[5,6]]
# y=[1, 2, 3]
# clf.train(X,y)
# category = clf.predict([1,2,3,4,5,6])
# print category
# import impl as nb
import utils as utils
import numpy as np
path = '20news-bydate-matlab/matlab'
features = utils.read_features("expanded.txt")
label_array = utils.read_label(path, 'train.label')
print len(label_array)
answer_label_array = utils.read_label(path, 'test.label')
test_features = utils.read_features("test_expanded.txt")
vocab = utils.read_vocab("vocabulary.txt")
#remove stop words
from stop_words import get_stop_words
stop_words = get_stop_words('en')
# vocab = set(vocab)
