def get(self):
data = super(System, self).get()
data['cpuInfoDto'] = random_data(
data['cpuInfoDto'], 'capacity',
'usedCapacity', 'freeCapacity', 600, 1600)
data['memInfoDto'] = random_data(
data['memInfoDto'], 'totalMemory',
'usedMemory', 'freeMemory', 3500, 4700)
return data
def test_est_propensity():
D = np.array([0, 0, 0, 1, 1, 1])
X = np.array([[7, 8], [3, 10], [7, 10], [4, 7], [5, 10], [9, 8]])
Y = random_data(D_cur=D, X_cur=X)
causal = c.CausalModel(Y, D, X)
causal.est_propensity()
lin = [0, 1]
qua = []
coef = np.array([6.8066090, -0.0244874, -0.7524939])
loglike = -3.626517
fitted = np.array([0.6491366, 0.3117840, 0.2911631,
0.8086407, 0.3013733, 0.6379023])
se = np.array([8.5373779, 0.4595191, 0.8106499])
keys = {'lin', 'qua', 'coef', 'loglike', 'fitted', 'se'}
assert_equal(causal.propensity['lin'], lin)
assert_equal(causal.propensity['qua'], qua)
assert np.allclose(causal.propensity['coef'], coef)
assert np.allclose(causal.propensity['loglike'], loglike)
assert np.allclose(causal.propensity['fitted'], fitted)
assert np.allclose(causal.propensity['se'], se)
assert_equal(set(causal.propensity.keys()), keys)
assert np.allclose(causal.raw_data['pscore'], fitted)
def test_select_qua_terms():
Y, D, X = random_data()
X_c_random, X_t_random = X[D == 0], X[D == 1]
lin1 = [0, 1]
C1 = np.inf
ans1 = []
assert_equal(p.select_qua_terms(X_c_random, X_t_random, lin1, C1), ans1)
lin2 = [1, 0]
C2 = 0
ans2 = [(1, 1), (1, 0), (0, 0)]
assert_equal(p.select_qua_terms(X_c_random, X_t_random, lin2, C2), ans2)
lin3 = [0]
C3 = -983.340
ans3 = [(0, 0)]
assert_equal(p.select_qua_terms(X_c_random, X_t_random, lin3, C3), ans3)
lin4 = []
C4 = 34.234
ans4 = []
assert_equal(p.select_qua_terms(X_c_random, X_t_random, lin4, C4), ans4)
X_c = np.array([[7, 8], [3, 10], [7, 10]])
X_t = np.array([[4, 7], [5, 10], [9, 8]])
lin5 = [0, 1]
C5 = 1.1
ans5 = [(1, 1), (0, 1), (0, 0)]
assert_equal(p.select_qua_terms(X_c, X_t, lin5, C5), ans5)
def test_select_lin():
Y, D, X = random_data(K=4)
X_c_random, X_t_random = X[D == 0], X[D == 1]
lin1 = [0, 1, 2, 3]
C1 = np.random.rand(1)
ans1 = [0, 1, 2, 3]
assert_equal(p.select_lin(X_c_random, X_t_random, lin1, C1), ans1)
X_c = np.array([[1, 2], [9, 7]])
X_t = np.array([[1, 4], [9, 6]])
lin2 = []
C2 = 0.07
ans2 = []
assert_equal(p.select_lin(X_c, X_t, lin2, C2), ans2)
lin3 = []
C3 = 0.06
ans3 = [1, 0]
assert_equal(p.select_lin(X_c, X_t, lin3, C3), ans3)
lin4 = [1]
C4 = 0.35
ans4 = [1]
assert_equal(p.select_lin(X_c, X_t, lin4, C4), ans4)
lin5 = [1]
C5 = 0.34
ans5 = [1, 0]
assert_equal(p.select_lin(X_c, X_t, lin5, C5), ans5)
def test_select_lin_terms():
Y, D, X = random_data(K=4)
X_c_random, X_t_random = X[D == 0], X[D == 1]
lin1 = [3, 0, 1]
C1 = np.inf
ans1 = [3, 0, 1]
assert_equal(p.select_lin_terms(X_c_random, X_t_random, lin1, C1), ans1)
lin2 = [2]
C2 = 0
ans2 = [2, 0, 1, 3]
assert_equal(p.select_lin_terms(X_c_random, X_t_random, lin2, C2), ans2)
lin3 = []
C3 = 0
ans3 = [0, 1, 2, 3]
assert_equal(p.select_lin_terms(X_c_random, X_t_random, lin3, C3), ans3)
lin4 = [3, 1]
C4 = -34.234
ans4 = [3, 1, 0, 2]
assert_equal(p.select_lin_terms(X_c_random, X_t_random, lin4, C4), ans4)
X_c = np.array([[1, 2], [9, 7]])
X_t = np.array([[1, 4], [9, 7]])
lin5 = []
C5 = 0.06
ans5 = [1, 0]
assert_equal(p.select_lin_terms(X_c, X_t, lin5, C5), ans5)
def test_est_propensity():
D = np.array([0, 0, 0, 1, 1, 1])
X = np.array([[7, 8], [3, 10], [7, 10], [4, 7], [5, 10], [9, 8]])
Y = random_data(D_cur=D, X_cur=X)
causal = c.CausalModel(Y, D, X)
causal.est_propensity(feature_names=[], exclude=[])
lin = [0, 1]
qua = []
coef = np.array([6.8066090, -0.0244874, -0.7524939])
loglike = -3.626517
fitted = np.array(
[0.6491366, 0.3117840, 0.2911631, 0.8086407, 0.3013733, 0.6379023])
se = np.array([8.5373779, 0.4595191, 0.8106499])
keys = {'lin', 'qua', 'coef', 'loglike', 'fitted', 'se'}
assert_equal(causal.propensity['lin'], lin)
assert_equal(causal.propensity['qua'], qua)
assert np.allclose(causal.propensity['coef'], coef)
assert np.allclose(causal.propensity['loglike'], loglike)
assert np.allclose(causal.propensity['fitted'], fitted)
assert np.allclose(causal.propensity['se'], se)
assert_equal(set(causal.propensity.keys()), keys)
assert np.allclose(causal.raw_data['pscore'], fitted)
def test_select_lin_terms(): Y, D, X = random_data(K=4) X_c_random, X_t_random = X[D==0], X[D==1] lin1 = [3, 0, 1] C1 = np.inf ans1 = [3, 0, 1] assert_equal(p.select_lin_terms(X_c_random, X_t_random, lin1, C1), ans1) lin2 = [2] C2 = 0 ans2 = [2, 0, 1, 3] assert_equal(p.select_lin_terms(X_c_random, X_t_random, lin2, C2), ans2) lin3 = [] C3 = 0 ans3 = [0, 1, 2, 3] assert_equal(p.select_lin_terms(X_c_random, X_t_random, lin3, C3), ans3) lin4 = [3, 1] C4 = -34.234 ans4 = [3, 1, 0, 2] assert_equal(p.select_lin_terms(X_c_random, X_t_random, lin4, C4), ans4) X_c = np.array([[1, 2], [9, 7]]) X_t = np.array([[1, 4], [9, 7]]) lin5 = [] C5 = 0.06 ans5 = [1, 0] assert_equal(p.select_lin_terms(X_c, X_t, lin5, C5), ans5)
def test_select_lin(): Y, D, X = random_data(K=4) X_c_random, X_t_random = X[D==0], X[D==1] lin1 = [0, 1, 2, 3] C1 = np.random.rand(1) ans1 = [0, 1, 2, 3] assert_equal(p.select_lin(X_c_random, X_t_random, lin1, C1), ans1) X_c = np.array([[1, 2], [9, 7]]) X_t = np.array([[1, 4], [9, 6]]) lin2 = [] C2 = 0.07 ans2 = [] assert_equal(p.select_lin(X_c, X_t, lin2, C2), ans2) lin3 = [] C3 = 0.06 ans3 = [1, 0] assert_equal(p.select_lin(X_c, X_t, lin3, C3), ans3) lin4 = [1] C4 = 0.35 ans4 = [1] assert_equal(p.select_lin(X_c, X_t, lin4, C4), ans4) lin5 = [1] C5 = 0.34 ans5 = [1, 0] assert_equal(p.select_lin(X_c, X_t, lin5, C5), ans5)
def test_select_qua_terms(): Y, D, X = random_data() X_c_random, X_t_random = X[D==0], X[D==1] lin1 = [0, 1] C1 = np.inf ans1 = [] assert_equal(p.select_qua_terms(X_c_random, X_t_random, lin1, C1), ans1) lin2 = [1, 0] C2 = 0 ans2 = [(1, 1), (1, 0), (0, 0)] assert_equal(p.select_qua_terms(X_c_random, X_t_random, lin2, C2), ans2) lin3 = [0] C3 = -983.340 ans3 = [(0, 0)] assert_equal(p.select_qua_terms(X_c_random, X_t_random, lin3, C3), ans3) lin4 = [] C4 = 34.234 ans4 = [] assert_equal(p.select_qua_terms(X_c_random, X_t_random, lin4, C4), ans4) X_c = np.array([[7, 8], [3, 10], [7, 10]]) X_t = np.array([[4, 7], [5, 10], [9, 8]]) lin5 = [0, 1] C5 = 1.1 ans5 = [(1, 1), (0, 1), (0, 0)] assert_equal(p.select_qua_terms(X_c, X_t, lin5, C5), ans5)
def __init__(self,
timesheet=None,
date=date.today(),
data=None,
div_size=DIV_SIZE,
total_time=TOTAL_TIME,
start_time=0):
"""
Inputs
------
div_size: The size of the time divisions of a particular day in minutes. A div_size that doesnt break down the day into whole number minute divisions is rounded to the nearest div_size that accomplishes this
data: The on/off light data that will be given by the microcontroller, 'random' for randome data, 'ones' for ones, deafult is zeros
date: the date of the data
"""
self.date = date
self.div_size = u.get_whole_div(div_size, FACTORS)
self.start_time = start_time
self.total_time = total_time
self.end_time = self.start_time + self.total_time - 5
if isinstance(timesheet, pd.DataFrame):
self.timesheet = timesheet
else:
if data is 'random':
data = u.random_data(self.div_size)
if data is 'ones':
data = np.full(total_time // self.div_size, 1)
self.timesheet = u.construct_dataframe(
data, self.div_size, self.date.strftime('%Y-%m-%d'),
self.total_time, self.start_time)
def main(args):
dNet = net.DigitRecNet()
optimizer = optim.SGD(dNet.parameters(), lr=args.lr, momentum=0.5)
criterion = torch.nn.NLLLoss()
if not args.train:
logging.info('-' * 50)
logging.info('Start testing ... ')
load_model(dNet, args.model_file, 'BestModel')
logging.info('finish load model: %s' % args.model_file)
test_x = utils.load_test_data(args.test_file, args.N, args.M)
logging.info('Load test : %d' % len(test_x))
test_input_x = Variable(torch.FloatTensor(test_x))
test_input_x = test_input_x.resize(test_input_x.size()[0], 1, args.N,
args.M)
only_test(dNet, test_input_x, args.result_file)
return
train_x, train_y = utils.load_data(args.train_file, args.N, args.M)
dev_x, dev_y = utils.load_data(args.dev_file, args.N, args.M)
logging.info('-' * 50)
logging.info('Load train : %d, Load dev : %d' % (len(train_x), len(dev_x)))
#train
logging.info('-' * 50)
logging.info('Start training ... ')
dev_input_x = Variable(torch.FloatTensor(dev_x))
dev_input_x = dev_input_x.resize(dev_input_x.size()[0], 1, args.N, args.M)
dev_pred_y = Variable(torch.LongTensor(dev_y))
best_accuracy = 0
for epoch_id in range(args.epoch):
logging.info('Epoch : %d' % epoch_id)
data = utils.random_data((train_x, train_y), args.batch_size)
for it, (input_x, pred_y) in enumerate(data):
input_x = Variable(torch.FloatTensor(input_x))
input_x = input_x.resize(input_x.size()[0], 1, args.N, args.M)
pred_y = Variable(torch.LongTensor(pred_y))
assert input_x.size()[0] == pred_y.size()[0]
optimizer.zero_grad()
output_x = dNet(input_x)
loss = criterion(output_x, pred_y)
loss.backward()
optimizer.step()
logging.info('Iteration (%d) loss : %.6f' % (it, loss))
if (it % args.iter_cnt == 0):
tmp_accuracy = test(dNet, dev_input_x, dev_pred_y)
if tmp_accuracy > best_accuracy:
best_accuracy = tmp_accuracy
save_model(dNet, epoch_id, args.model_file, 'Best')
logging.info(
"Epoch : %d, Accuarcy : %.2f%%, Best Accuatcy : %.2f%%" %
(epoch_id, tmp_accuracy, best_accuracy))
def test_select_qua(): Y, D, X = random_data() X_c_random, X_t_random = X[D==0], X[D==1] lin1 = [1, 0] qua1 = [(1, 0), (0, 0), (1, 1)] C1 = np.random.rand(1) ans1 = [(1, 0), (0, 0), (1, 1)] assert_equal(p.select_qua(X_c_random, X_t_random, lin1, qua1, C1), ans1) lin2 = [1] qua2 = [(1, 1)] C2 = np.random.rand(1) ans2 = [(1, 1)] assert_equal(p.select_qua(X_c_random, X_t_random, lin2, qua2, C2), ans2) X_c = np.array([[7, 8], [3, 10], [7, 10]]) X_t = np.array([[4, 7], [5, 10], [9, 8]]) lin3 = [0, 1] qua3 = [] C3 = 1.2 ans3 = [] assert_equal(p.select_qua(X_c, X_t, lin3, qua3, C3), ans3) lin4 = [0, 1] qua4 = [] C4 = 1.1 ans4 = [(1, 1), (0, 1), (0, 0)] assert_equal(p.select_qua(X_c, X_t, lin4, qua4, C4), ans4) lin5 = [0, 1] qua5 = [(1, 1)] C5 = 2.4 ans5 = [(1, 1)] assert_equal(p.select_qua(X_c, X_t, lin5, qua5, C5), ans5) lin6 = [0, 1] qua6 = [(1, 1)] C6 = 2.3 ans6 = [(1, 1), (0, 1), (0, 0)] assert_equal(p.select_qua(X_c, X_t, lin6, qua6, C6), ans6) lin7 = [0, 1] qua7 = [(1, 1), (0, 1)] C7 = 3.9 ans7 = [(1, 1), (0, 1)] assert_equal(p.select_qua(X_c, X_t, lin7, qua7, C7), ans7) lin8 = [0, 1] qua8 = [(1, 1), (0, 1)] C8 = 3.8 ans8 = [(1, 1), (0, 1), (0, 0)] assert_equal(p.select_qua(X_c, X_t, lin8, qua8, C8), ans8)
def test_select_qua():
Y, D, X = random_data()
X_c_random, X_t_random = X[D == 0], X[D == 1]
lin1 = [1, 0]
qua1 = [(1, 0), (0, 0), (1, 1)]
C1 = np.random.rand(1)
ans1 = [(1, 0), (0, 0), (1, 1)]
assert_equal(p.select_qua(X_c_random, X_t_random, lin1, qua1, C1), ans1)
lin2 = [1]
qua2 = [(1, 1)]
C2 = np.random.rand(1)
ans2 = [(1, 1)]
assert_equal(p.select_qua(X_c_random, X_t_random, lin2, qua2, C2), ans2)
X_c = np.array([[7, 8], [3, 10], [7, 10]])
X_t = np.array([[4, 7], [5, 10], [9, 8]])
lin3 = [0, 1]
qua3 = []
C3 = 1.2
ans3 = []
assert_equal(p.select_qua(X_c, X_t, lin3, qua3, C3), ans3)
lin4 = [0, 1]
qua4 = []
C4 = 1.1
ans4 = [(1, 1), (0, 1), (0, 0)]
assert_equal(p.select_qua(X_c, X_t, lin4, qua4, C4), ans4)
lin5 = [0, 1]
qua5 = [(1, 1)]
C5 = 2.4
ans5 = [(1, 1)]
assert_equal(p.select_qua(X_c, X_t, lin5, qua5, C5), ans5)
lin6 = [0, 1]
qua6 = [(1, 1)]
C6 = 2.3
ans6 = [(1, 1), (0, 1), (0, 0)]
assert_equal(p.select_qua(X_c, X_t, lin6, qua6, C6), ans6)
lin7 = [0, 1]
qua7 = [(1, 1), (0, 1)]
C7 = 3.9
ans7 = [(1, 1), (0, 1)]
assert_equal(p.select_qua(X_c, X_t, lin7, qua7, C7), ans7)
lin8 = [0, 1]
qua8 = [(1, 1), (0, 1)]
C8 = 3.8
ans8 = [(1, 1), (0, 1), (0, 0)]
assert_equal(p.select_qua(X_c, X_t, lin8, qua8, C8), ans8)
def test_propensity():
import causalinference.core.data as d
import causalinference.core.propensity as p
from utils import random_data
D = np.array([0, 0, 0, 1, 1, 1])
X = np.array([[7, 8], [3, 10], [7, 10], [4, 7], [5, 10], [9, 8]])
Y = random_data(D_cur=D, X_cur=X)
print Y
data = d.Data(Y, D, X)
propensity = p.Propensity(data, [0, 1], [])
print propensity
def test_propensity(): import causalinference.core.data as d import causalinference.core.propensity as p from utils import random_data D = np.array([0, 0, 0, 1, 1, 1]) X = np.array([[7, 8], [3, 10], [7, 10], [4, 7], [5, 10], [9, 8]]) Y = random_data(D_cur=D, X_cur=X) print Y data = d.Data(Y, D, X) propensity = p.Propensity(data, [0, 1], []) print propensity
def test_est_propensity_s():
D = np.array([0, 0, 0, 1, 1, 1])
X = np.array([[7, 8], [3, 10], [7, 10], [4, 7], [5, 10], [9, 8]])
Y = random_data(D_cur=D, X_cur=X)
causal = c.CausalModel(Y, D, X)
causal.est_propensity_s()
lin1 = [1]
qua1 = []
coef1 = np.array([6.5424027, -0.7392041])
loglike1 = -3.627939
fitted1 = np.array(
[0.6522105, 0.2995088, 0.2995088, 0.7970526, 0.2995088, 0.6522105])
se1 = np.array([6.8455179, 0.7641445])
keys = {'lin', 'qua', 'coef', 'loglike', 'fitted', 'se'}
assert_equal(causal.propensity['lin'], lin1)
assert_equal(causal.propensity['qua'], qua1)
assert np.allclose(causal.propensity['coef'], coef1)
assert np.allclose(causal.propensity['loglike'], loglike1)
assert np.allclose(causal.propensity['fitted'], fitted1)
assert np.allclose(causal.propensity['se'], se1)
assert_equal(set(causal.propensity.keys()), keys)
assert np.allclose(causal.raw_data['pscore'], fitted1)
causal.est_propensity_s([0, 1])
lin2 = [0, 1]
qua2 = []
coef2 = np.array([6.8066090, -0.0244874, -0.7524939])
loglike2 = -3.626517
fitted2 = np.array(
[0.6491366, 0.3117840, 0.2911631, 0.8086407, 0.3013733, 0.6379023])
se2 = np.array([8.5373779, 0.4595191, 0.8106499])
assert_equal(causal.propensity['lin'], lin2)
assert_equal(causal.propensity['qua'], qua2)
assert np.allclose(causal.propensity['coef'], coef2)
assert np.allclose(causal.propensity['loglike'], loglike2)
assert np.allclose(causal.propensity['fitted'], fitted2)
assert np.allclose(causal.propensity['se'], se2)
assert np.allclose(causal.raw_data['pscore'], fitted2)
def test_est_propensity_s():
D = np.array([0, 0, 0, 1, 1, 1])
X = np.array([[7, 8], [3, 10], [7, 10], [4, 7], [5, 10], [9, 8]])
Y = random_data(D_cur=D, X_cur=X)
causal = c.CausalModel(Y, D, X)
causal.est_propensity_s()
lin1 = [1]
qua1 = []
coef1 = np.array([6.5424027, -0.7392041])
loglike1 = -3.627939
fitted1 = np.array([0.6522105, 0.2995088, 0.2995088,
0.7970526, 0.2995088, 0.6522105])
se1 = np.array([6.8455179, 0.7641445])
keys = {'lin', 'qua', 'coef', 'loglike', 'fitted', 'se'}
assert_equal(causal.propensity['lin'], lin1)
assert_equal(causal.propensity['qua'], qua1)
assert np.allclose(causal.propensity['coef'], coef1)
assert np.allclose(causal.propensity['loglike'], loglike1)
assert np.allclose(causal.propensity['fitted'], fitted1)
assert np.allclose(causal.propensity['se'], se1)
assert_equal(set(causal.propensity.keys()), keys)
assert np.allclose(causal.raw_data['pscore'], fitted1)
causal.est_propensity_s([0,1])
lin2 = [0, 1]
qua2 = []
coef2 = np.array([6.8066090, -0.0244874, -0.7524939])
loglike2 = -3.626517
fitted2 = np.array([0.6491366, 0.3117840, 0.2911631,
0.8086407, 0.3013733, 0.6379023])
se2 = np.array([8.5373779, 0.4595191, 0.8106499])
assert_equal(causal.propensity['lin'], lin2)
assert_equal(causal.propensity['qua'], qua2)
assert np.allclose(causal.propensity['coef'], coef2)
assert np.allclose(causal.propensity['loglike'], loglike2)
assert np.allclose(causal.propensity['fitted'], fitted2)
assert np.allclose(causal.propensity['se'], se2)
assert np.allclose(causal.raw_data['pscore'], fitted2)
def causal_ATE():
from causalinference import CausalModel
from utils import random_data
D = np.array([0, 0, 0, 1, 1, 1])
X = np.array([[7, 8], [3, 10], [7, 10], [4, 7], [5, 10], [9, 8]])
Y = random_data(D_cur=D, X_cur=X)
print Y
causal = CausalModel(Y, D, X)
#causal.est_via_ols()
#print causal.estimates
causal.est_propensity_s()
print causal.propensity
# -*- coding: utf-8 -*-
#プロペンシティスコアを元に自分でマッチングすれば良い。
#estimated propensity scores
print causal.propensity['fitted']
def causal_ATE():
from causalinference import CausalModel
from utils import random_data
D = np.array([0, 0, 0, 1, 1, 1])
X = np.array([[7, 8], [3, 10], [7, 10], [4, 7], [5, 10], [9, 8]])
Y = random_data(D_cur=D, X_cur=X)
print Y
causal = CausalModel(Y, D, X)
#causal.est_via_ols()
#print causal.estimates
causal.est_propensity_s()
print causal.propensity
# -*- coding: utf-8 -*-
#プロペンシティスコアを元に自分でマッチングすれば良い。
#estimated propensity scores
print causal.propensity['fitted']
def test_propensityselect():
D = np.array([0, 0, 0, 1, 1, 1])
X = np.array([[7, 8], [3, 10], [7, 10], [4, 7], [5, 10], [9, 8]])
Y = random_data(D_cur=D, X_cur=X)
data = d.Data(Y, D, X)
propensity1 = p.PropensitySelect(data, [], 1, 2.71)
lin1 = [1]
qua1 = []
coef1 = np.array([6.5424027, -0.7392041])
loglike1 = -3.627939
fitted1 = np.array([0.6522105, 0.2995088, 0.2995088,
0.7970526, 0.2995088, 0.6522105])
se1 = np.array([6.8455179, 0.7641445])
keys = {'lin', 'qua', 'coef', 'loglike', 'fitted', 'se'}
assert_equal(propensity1['lin'], lin1)
assert_equal(propensity1['qua'], qua1)
assert np.allclose(propensity1['coef'], coef1)
assert np.allclose(propensity1['loglike'], loglike1)
assert np.allclose(propensity1['fitted'], fitted1)
assert np.allclose(propensity1['se'], se1)
assert_equal(set(propensity1.keys()), keys)
propensity2 = p.PropensitySelect(data, [0, 1], 1, 2.71)
lin2 = [0, 1]
qua2 = []
coef2 = np.array([6.8066090, -0.0244874, -0.7524939])
loglike2 = -3.626517
fitted2 = np.array([0.6491366, 0.3117840, 0.2911631,
0.8086407, 0.3013733, 0.6379023])
se2 = np.array([8.5373779, 0.4595191, 0.8106499])
assert_equal(propensity2['lin'], lin2)
assert_equal(propensity2['qua'], qua2)
assert np.allclose(propensity2['coef'], coef2)
assert np.allclose(propensity2['loglike'], loglike2)
assert np.allclose(propensity2['fitted'], fitted2)
assert np.allclose(propensity2['se'], se2)
def test_propensityselect():
D = np.array([0, 0, 0, 1, 1, 1])
X = np.array([[7, 8], [3, 10], [7, 10], [4, 7], [5, 10], [9, 8]])
Y = random_data(D_cur=D, X_cur=X)
data = d.Data(Y, D, X)
propensity1 = p.PropensitySelect(data, [], 1, 2.71)
lin1 = [1]
qua1 = []
coef1 = np.array([6.5424027, -0.7392041])
loglike1 = -3.627939
fitted1 = np.array(
[0.6522105, 0.2995088, 0.2995088, 0.7970526, 0.2995088, 0.6522105])
se1 = np.array([6.8455179, 0.7641445])
keys = {'lin', 'qua', 'coef', 'loglike', 'fitted', 'se'}
assert_equal(propensity1['lin'], lin1)
assert_equal(propensity1['qua'], qua1)
assert np.allclose(propensity1['coef'], coef1)
assert np.allclose(propensity1['loglike'], loglike1)
assert np.allclose(propensity1['fitted'], fitted1)
assert np.allclose(propensity1['se'], se1)
assert_equal(set(propensity1.keys()), keys)
propensity2 = p.PropensitySelect(data, [0, 1], 1, 2.71)
lin2 = [0, 1]
qua2 = []
coef2 = np.array([6.8066090, -0.0244874, -0.7524939])
loglike2 = -3.626517
fitted2 = np.array(
[0.6491366, 0.3117840, 0.2911631, 0.8086407, 0.3013733, 0.6379023])
se2 = np.array([8.5373779, 0.4595191, 0.8106499])
assert_equal(propensity2['lin'], lin2)
assert_equal(propensity2['qua'], qua2)
assert np.allclose(propensity2['coef'], coef2)
assert np.allclose(propensity2['loglike'], loglike2)
assert np.allclose(propensity2['fitted'], fitted2)
assert np.allclose(propensity2['se'], se2)
def test_propensity():
D = np.array([0, 0, 0, 1, 1, 1])
X = np.array([[7, 8], [3, 10], [7, 10], [4, 7], [5, 10], [9, 8]])
Y = random_data(D_cur=D, X_cur=X)
data = d.Data(Y, D, X)
propensity = p.Propensity(data, [0, 1], [])
lin = [0, 1]
qua = []
coef = np.array([6.8066090, -0.0244874, -0.7524939])
loglike = -3.626517
fitted = np.array([0.6491366, 0.3117840, 0.2911631,
0.8086407, 0.3013733, 0.6379023])
se = np.array([8.5373779, 0.4595191, 0.8106499])
keys = {'lin', 'qua', 'coef', 'loglike', 'fitted', 'se'}
assert_equal(propensity['lin'], lin)
assert_equal(propensity['qua'], qua)
assert np.allclose(propensity['coef'], coef)
assert np.allclose(propensity['loglike'], loglike)
assert np.allclose(propensity['fitted'], fitted)
assert np.allclose(propensity['se'], se)
assert_equal(set(propensity.keys()), keys)
def test_invite(self):
"""
"""
self.ip.src = utils.random_ip()
self.udp.sport = utils.random_port()
self.message.uri = 'sip:{0}@{1}'.format(utils.random_data(20),
utils.random_data(15))
self.message.method = 'INVITE'
self.message.headers = {
'Call-ID':
utils.random_tag(),
'CSeq':
'0 INVITE',
'From':
'"{0}" <sip:{1}@{2}>;tag={3}'.format(utils.random_data(10),
utils.random_data(20),
utils.random_data(15),
utils.random_tag()),
'Max-Forwards':
'{0}'.format(utils.random_number(2)),
'To':
'<sip:{0}@{1}>'.format(utils.random_data(20),
utils.random_data(15)),
'Via':
'SIP/2.0/UDP {0}:{1};branch={2};rport'.format(
utils.random_ip(), utils.random_port(), utils.random_tag()),
'Content-Length':
'0',
'User-Agent':
'{0}'.format(utils.random_data(30)),
'Contact':
'<sip:{0}@{1}:{2};transport=UDP>;'
'q=1.00;agentid="{3}";'
'methods="INVITE,NOTIFY,MESSAGE,ACK,BYE,CANCEL";'
'expires={4}'.format(utils.random_data(20), utils.random_ip(),
utils.random_data(20), utils.random_tag(),
utils.random_number(2)),
'Authorization':
'Digest username="******", '
'realm="{2}", '
'nonce="{3}", '
'uri="sip:{4}", '
'qop=auth, nc=00000001, '
'cnonce="{5}", '
'response="{6}", '
'opaque=""'.format(utils.random_data(20), utils.random_data(15),
utils.random_data(15), utils.random_tag(),
utils.random_data(15), utils.random_tag(),
utils.random_data(32))
}
train_writer = tf.summary.FileWriter(savepath + 'train', sess.graph)
test_writer = tf.summary.FileWriter(savepath + 'test')
"""
training session
"""
weight = z_c_mean.get_shape().as_list()[1] * z_c_mean.get_shape().as_list(
)[2] # this is to normalize the loss shown in the terminal against the receptive field
for step in range(start_step, start_step + training_step):
if step % 20000 == 0 or step == start_step:
print('Starting @step %s' % step)
batch = random_data(MRtrain,
batchsize=batchsize)[:batchsize, 22:22 + imageshape[0],
17:17 + imageshape[1]]
batch = np.expand_dims(batch, axis=-1)
t_los, p_los, con_los, w_los, c_los, _ = sess.run(
[t_loss, p_loss, con_loss, w_loss, c_loss, optimization],
feed_dict={x: batch.reshape(batchsize, -1)})
if step == 0 or os.path.isdir(savepath + 'model') == 0:
os.makedirs(os.path.join(savepath, 'model', ''))
if step % 5000 == 0 and step >= start_step or step == start_step + training_step - 1:
model_path = saver.save(sess,
savepath + 'model/model.ckpt',
