def train_test_linear_regression(train_test_data,
show_plot=False,
save_model=False):
# Commented out, was doing this to compare different methods of cross validation
# # can use cross_validate instead of cross_val_score to evaluate more metrics than just R^2
# scoring = ["r2", "neg_mean_squared_error", "neg_root_mean_squared_error"]
# # 1) time series split
# tscv = TimeSeriesSplit(n_splits=5)
# print(tscv)
# # Below shows the timeseries splits if we want to see them
# for train, test in tscv.split(X_train):
# print("%s %s" % (train, test))
# ts_scores = cross_validate(LinearRegression(), X_train, y_train, cv=tscv, scoring=scoring)
# print(ts_scores)
# print("Loss: {0:.3f} (+/- {1:.3f})".format(ts_scores["test_r2"].mean(), ts_scores["test_r2"].std()))
# print("RMSE: {0:.3f} (+/- {1:.3f})".format(ts_scores["test_neg_root_mean_squared_error"].mean(), ts_scores["test_neg_root_mean_squared_error"].std()))
# print("MIn RMSE: {0:.3f}".format(min(ts_scores["test_neg_root_mean_squared_error"])))
# # 2) K-fold
# kfcv = KFold(n_splits=5)
# print(kfcv)
# kf_scores = cross_validate(LinearRegression(), X_train, y_train, cv=kfcv, scoring=scoring)
# print(kf_scores)
# print("Loss: {0:.3f} (+/- {1:.3f})".format(kf_scores["test_r2"].mean(), kf_scores["test_r2"].std()))
# print("RMSE: {0:.3f} (+/- {1:.3f})".format(kf_scores["test_neg_root_mean_squared_error"].mean(), kf_scores["test_neg_root_mean_squared_error"].std()))
# print("Min RMSE: {0:.3f}".format(min(kf_scores["test_neg_root_mean_squared_error"])))
model = models.LinearRegression()
best_params = model.get_best_params(train_test_data)
model.train(train_test_data.X_train,
train_test_data.y_train,
save_model=save_model)
model.display_metrics(train_test_data,
show_plot=show_plot,
selected_params=best_params)
def create_net(num_classes, dnn='resnet20', **kwargs):
ext = None
if dnn in ['resnet20', 'resnet56', 'resnet110']:
net = models.__dict__[dnn](num_classes=num_classes)
elif dnn == 'resnet50':
net = torchvision.models.resnet50(num_classes=num_classes)
elif dnn == 'resnet101':
net = torchvision.models.resnet101(num_classes=num_classes)
elif dnn == 'resnet152':
net = torchvision.models.resnet152(num_classes=num_classes)
elif dnn == 'densenet121':
net = torchvision.models.densenet121(num_classes=num_classes)
elif dnn == 'densenet161':
net = torchvision.models.densenet161(num_classes=num_classes)
elif dnn == 'densenet201':
net = torchvision.models.densenet201(num_classes=num_classes)
elif dnn == 'inceptionv4':
net = models.inceptionv4(num_classes=num_classes)
elif dnn == 'inceptionv3':
net = torchvision.models.inception_v3(num_classes=num_classes)
elif dnn == 'vgg16i': # vgg16 for imagenet
net = torchvision.models.vgg16(num_classes=num_classes)
elif dnn == 'googlenet':
net = models.googlenet()
elif dnn == 'mnistnet':
net = MnistNet()
elif dnn == 'fcn5net':
net = models.FCN5Net()
elif dnn == 'lenet':
net = models.LeNet()
elif dnn == 'lr':
net = models.LinearRegression()
elif dnn == 'vgg16':
net = models.VGG(dnn.upper())
elif dnn == 'alexnet':
#net = models.AlexNet()
net = torchvision.models.alexnet()
elif dnn == 'lstman4':
net, ext = models.LSTMAN4(datapath=kwargs['datapath'])
elif dnn == 'lstm':
# model = lstm(embedding_dim=args.hidden_size, num_steps=args.num_steps, batch_size=args.batch_size,
# vocab_size=vocab_size, num_layers=args.num_layers, dp_keep_prob=args.dp_keep_prob)
net = lstmpy.lstm(vocab_size=kwargs['vocab_size'],
batch_size=kwargs['batch_size'])
else:
errstr = 'Unsupport neural network %s' % dnn
logger.error(errstr)
raise errstr
return net, ext
def main():
parser = argparse.ArgumentParser()
parser.add_argument('-m', '--model', type=str, choices=models.available_models, dest='model_name')
args = parser.parse_args()
if args.model_name == "LinearRegression":
model = models.LinearRegression(1, 1, learning_rate=0.005)
x_train = np.array([[2.3], [4.4], [3.7], [6.1], [7.3], [2.1], [5.6], [7.7], [8.7], [4.1],
[6.7], [6.1], [7.5], [2.1], [7.2],
[5.6], [5.7], [7.7], [3.1]], dtype=np.float32)
y_train = np.array([[3.7], [4.76], [4.], [7.1], [8.6], [3.5], [5.4], [7.6], [7.9], [5.3],
[7.3], [7.5], [8.5], [3.2], [8.7],
[6.4], [6.6], [7.9], [5.3]], dtype=np.float32)
t_x = Tensor(x_train)
t_y = Tensor(y_train)
tensor_dataset = TensorDataset(t_x, t_y)
data_loader = DataLoader(tensor_dataset, batch_size=32)
model.run(data_loader, model)
elif args.model_name == "LogisticRegression":
X_train, y_train = load_iris(return_X_y=True)
t_x, t_y = torch.tensor(X_train, dtype=torch.float), torch.tensor(y_train, dtype=torch.long)
tensor_dataset = TensorDataset(t_x, t_y)
num_classes = len(set(y_train))
input_dim = X_train.shape[1]
data_loader = DataLoader(tensor_dataset, batch_size=32, shuffle=True)
model = models.LogisticRegression(input_dim, num_classes, learning_rate=0.01, epoch=1000)
model.run(data_loader, model)
elif args.model_name == "Convolution2D":
n_epoch = 5
tr_batch_size, ts_batch_size = 32, 1024
data_transform = Compose([ToTensor(), Normalize((0.1307,), (0.3081,))])
tr_mnist = MNIST(root=os.path.realpath('../../dataset/mnist'), train=True,
transform=data_transform, download=False)
ts_mnist = MNIST(root=os.path.realpath('../../dataset/mnist'), train=False,
transform=data_transform, download=False)
train_loader = DataLoader(tr_mnist, batch_size=tr_batch_size, shuffle=True)
test_loader = DataLoader(ts_mnist, batch_size=ts_batch_size, shuffle=True)
conv_net = models.Convolution2D(n_epoch=n_epoch, log_per_batch=1000, train_batch_size=tr_batch_size)
conv_net.run(train_loader, test_loader)
def create_net(num_classes, dnn='resnet20', **kwargs):
ext = None
if dnn in ['resnet20', 'resnet56', 'resnet110']:
net = models.__dict__[dnn](num_classes=num_classes)
elif dnn == 'resnet50':
#net = models.__dict__['resnet50'](num_classes=num_classes)
net = torchvision.models.resnet50(num_classes=num_classes)
elif dnn == 'inceptionv4':
net = models.inceptionv4(num_classes=num_classes)
elif dnn == 'inceptionv3':
net = torchvision.models.inception_v3(num_classes=num_classes)
elif dnn == 'vgg16i': # vgg16 for imagenet
net = torchvision.models.vgg16(num_classes=num_classes)
elif dnn == 'googlenet':
net = models.googlenet()
elif dnn == 'mnistnet':
net = MnistNet()
elif dnn == 'fcn5net':
net = models.FCN5Net()
elif dnn == 'lenet':
net = models.LeNet()
elif dnn == 'lr':
net = models.LinearRegression()
elif dnn == 'vgg16':
net = models.VGG(dnn.upper())
elif dnn == 'alexnet':
net = torchvision.models.alexnet()
elif dnn == 'lstman4':
net, ext = models.LSTMAN4(datapath=kwargs['datapath'])
elif dnn == 'lstm':
net = lstmpy.lstm(vocab_size=kwargs['vocab_size'],
batch_size=kwargs['batch_size'])
else:
errstr = 'Unsupport neural network %s' % dnn
logger.error(errstr)
raise errstr
return net, ext
t_features, t_targets = gen_data.gaussian_data(1000)
pred_targets = np.zeros(t_targets.shape)
for i in range(2000):
pred_targets[i] = clf.predict(t_features[i])
print(pred_targets)
print ("accuracy is %f" % (len(np.where( pred_targets[:] == t_targets)[0]) \
/2000.0))
'''
'''regression'''
weights = np.array([1.5, 2])
features, targets = gen_data.linear_data(weights, 1000, d=2)
clf = models.LinearRegression()
clf.fit_normal_equation(features, targets, add_intercept=True)
t_features, t_targets = gen_data.linear_data(weights, 200, d=2)
pred_targets = np.zeros(t_targets.shape)
for i in range(200):
pred_targets[i] = clf.predict(t_features[i])
n = pred_targets.size
pairs = np.hstack((pred_targets.reshape(n, 1), t_targets.reshape(n, 1)))
print pairs
print("loss is %f" % (np.mean(np.square(pred_targets - t_targets))/ \
np.mean(t_targets)))