class TestHomeassistant(unittest.TestCase):
def setUp(self):
# set of observations
self.ctrl = Controller()
self.ctrl.set_dataset(Dataset.HASS)
self.ctrl.load_dataset()
self.hass_obj = self.ctrl._dataset #type: DatasetHomeassistant
# algo = self.get_sel_algorithm()
# dataset = self.get_dataset_by_name(dataset_name)
# ctrl, dk, hmm_model = self._init_model_on_dataset(algo, dataset)
# ctrl.set_dataset(dk)
#
# if dataset_name == DATASET_NAME_HASS:
# # get activities
# act_list = []
# for act in Activity.objects.all():
# act_list.append(act.name)
# dev_list = []
# for dev in Device.objects.all():
# if dev.location is not None:
# dev_list.append(dev.component.name + "." + dev.name)
# print('*'*100)
# print(act_list)
# print(dev_list)
# print('*'*100)
# ctrl.set_custom_state_list(act_list)
# ctrl.set_custom_obs_list(dev_list)
#
# ctrl.load_dataset()
# ctrl.register_model(hmm_model)
def tearDown(self):
pass
def test_load_data(self):
pass
def test_print_hass_df(self):
df = self.hass_obj._df
print(DatasetHomeassistant.format_mat_full(df))
def test_hashmaps(self):
print(self.hass_obj.get_state_lbl_hashmap())
print(self.hass_obj.get_obs_lbl_hashmap())
def test_get_train_seqs(self):
tr_seqs = self.hass_obj.get_train_seq()
print(tr_seqs)
print(self.hass_obj.decode_obs_seq(tr_seqs))
def test_get_test_seq(self):
test_seqs = self.hass_obj._test_seqs
print(test_seqs)
lbl_seqs, obs_seqs = self.hass_obj.get_test_labels_and_seq()
print('-' * 20)
print('lbl_seqs: ', lbl_seqs)
print('obs_seqs: ', obs_seqs)
def _create_ctrl_for_normal_dataset(self, algorithm, dataset):
"""
generates an instance of controller and model
:param algorithm:
:param dataset:
:return:
"""
from hassbrain_algorithm.controller import Controller
ctrl = Controller(settings.HASSBRAIN_ALGO_CONFIG) # type: Controller
dk = self.train_get_ds_type_by_name(dataset.class_name)
ctrl.set_dataset(dk)
model_object = self._create_class_from_name(ctrl, algorithm)
ctrl.load_dataset()
ctrl.register_model(model_object)
return ctrl
def main():
dk = DK
data_name = DATA_NAME
# set of observations
ctrl_config = {
'datasets': {
'kasteren': {
'path_to_config':
'/home/cmeier/code/data/hassbrain/datasets/kasteren/config.yaml'
},
'hass_testing': {
'path_to_config':
'/home/cmeier/code/data/hassbrain/datasets/hass_testing/config.yaml'
},
'hass_testing2': {
'path_to_config':
'/home/cmeier/code/data/hassbrain/datasets/hass_testing2/config.yaml'
},
'hass_chris': {
'path_to_config':
'/home/cmeier/code/data/hassbrain/datasets/hass_chris/config.yaml'
}
}
}
ctrl = Controller(config=ctrl_config)
params = {
'repr': DATA_TYPE,
'data_format': 'bernoulli',
'test_selection': TEST_SEL,
'test_day': TEST_DAY,
'freq': TIME_DIFF
}
ctrl.set_dataset(data_name=data_name, data_type=dk, params=params)
ctrl.load_dataset()
tmp1 = ctrl._dataset.get_dev_stats()
tmp2 = ctrl._dataset.get_act_stats()
#ctrl.save_dataset(DATASET_FILE_PATH)
#print('filepath: ', DATASET_FILE_PATH)
print('*' * 10)
class TestDatasetPendigits(unittest.TestCase):
def setUp(self):
# set of observations
self.cm = Controller()
self.cm.load_dataset(Dataset.PENDIGITS)
self.pd = self.cm._dataset # type: DatasetPendigits
def tearDown(self):
pass
def test_plotting(self):
self.pd.load_data()
self.pd.plot_example(12)
def test_create_train_sequences(self):
self.pd.load_data()
enc_data, lengths = self.pd._create_train_seq(1)
def test_get_double_strokes(self):
self.pd.load_data()
digit_data = self.pd._get_train_data_where_double_strokes(9)
cnt = 0
for example in digit_data:
cnt += 1
self.pd._plotUniPenData(example)
if cnt == 50:
break
def test_train_seq_number(self):
self.pd.load_data()
for numn in range(0, 40):
digit_data = self.pd._get_train_data_by_number(numn)
for ex in range(0, 10):
print('~' * 100)
example = digit_data[ex + 5]
print(example)
self.pd._plotUniPenData(example)
def test_create_test_sequences(self):
self.pd.load_data()
enc_data, lengths = self.pd._create_test_seq(0)
self.assertEqual(59, len(enc_data))
self.assertEqual(59, lengths[0])
def test_generate_points_plot_0(self):
seq = [
8, 1, 1, 0, 0, 0, 7, 7, 6, 6, 6, 5, 5, 4, 4, 4, 3, 3, 3, 2, 2, 2,
1, 1, 9, 8, 1, 1, 1, 1, 1, 1
]
self.pd.plot_obs_seq(seq, 0)
def test_generate_points_plot_1(self):
seq = [
8, 2, 1, 1, 1, 1, 1, 0, 6, 5, 5, 5, 5, 6, 5, 9, 8, 0, 0, 0, 0, 0,
0, 0
]
self.pd.plot_obs_seq(seq, 1)
def test_generate_points_plot_4(self):
seq = [
8, 6, 6, 6, 6, 6, 6, 6, 7, 7, 0, 0, 1, 0, 7, 0, 0, 0, 9, 8, 6, 6,
6, 6, 6, 6, 6
]
self.pd.plot_obs_seq(seq, 4)
def test_generate_points_plot_5(self):
seq = [
8, 6, 6, 6, 6, 6, 7, 0, 0, 0, 0, 7, 6, 6, 6, 6, 5, 5, 5, 4, 4, 4,
4, 9, 8, 0, 0, 0, 0, 0, 0
]
self.pd.plot_obs_seq(seq, 5)
def test_generate_points_plot_7(self):
seq = [
8, 0, 0, 0, 0, 7, 6, 5, 5, 5, 5, 5, 5, 5, 5, 9, 8, 0, 0, 0, 0, 0, 0
]
self.pd.plot_obs_seq(seq, 7)
def test_generate_points_plot_8(self):
seq = [
8, 2, 1, 1, 0, 0, 7, 7, 6, 6, 6, 5, 5, 4, 4, 3, 3, 2, 9, 8, 2, 1,
1, 0, 0, 7, 7, 6, 6, 5, 5, 4, 4, 3, 3, 2
]
self.pd.plot_obs_seq(seq, 8)
def test_generate_points_plot_9(self):
seq = [
8, 3, 4, 5, 6, 6, 7, 0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 6, 9, 8, 7,
6, 6, 6, 6, 5, 5, 5, 4, 4, 3
]
self.pd.plot_obs_seq(seq, 9)
def test_directions_to_points(self):
stepsize = 5
self.pd._resolution = 8
x0 = self.pd._new_point_x(0, 0, stepsize)
y0 = self.pd._new_point_y(0, 0, stepsize)
x1 = self.pd._new_point_x(0, 1, stepsize)
y1 = self.pd._new_point_y(0, 1, stepsize)
x2 = self.pd._new_point_x(0, 2, stepsize)
y2 = self.pd._new_point_y(0, 2, stepsize)
x3 = self.pd._new_point_x(0, 3, stepsize)
y3 = self.pd._new_point_y(0, 3, stepsize)
x4 = self.pd._new_point_x(0, 4, stepsize)
y4 = self.pd._new_point_y(0, 4, stepsize)
x5 = self.pd._new_point_x(0, 5, stepsize)
y5 = self.pd._new_point_y(0, 5, stepsize)
x6 = self.pd._new_point_x(0, 6, stepsize)
y6 = self.pd._new_point_y(0, 6, stepsize)
x7 = self.pd._new_point_x(0, 7, stepsize)
y7 = self.pd._new_point_y(0, 7, stepsize)
self.assertEqual(5.000, round(x0, 3))
self.assertEqual(0.000, round(y0, 3))
self.assertEqual(3.536, round(x1, 3))
self.assertEqual(3.536, round(y1, 3))
self.assertEqual(0.000, round(x2, 3))
self.assertEqual(5.000, round(y2, 3))
self.assertEqual(-3.536, round(x3, 3))
self.assertEqual(3.536, round(y3, 3))
self.assertEqual(-5.000, round(x4, 3))
self.assertEqual(0.000, round(y4, 3))
self.assertEqual(-3.536, round(x5, 3))
self.assertEqual(-3.536, round(y5, 3))
self.assertEqual(0.000, round(x6, 3))
self.assertEqual(-5.000, round(y6, 3))
self.assertEqual(3.536, round(x7, 3))
self.assertEqual(-3.536, round(y7, 3))
def test_points_to_direction(self):
# directions 0 - 7
# number of classes the direction can have
c = 8
## ---- 0 degree
direc = self.pd._points_to_direction(c, 0, 0, 1, 0)
self.assertEqual(0, direc)
## ---- 45 degree
direc = self.pd._points_to_direction(c, 0, 0, 1, 1)
self.assertEqual(1, direc)
## ---- 90 degree
direc = self.pd._points_to_direction(c, 0, 0, 0, 1)
self.assertEqual(2, direc)
## ---- 135 degree
direc = self.pd._points_to_direction(c, 0, 0, -1, 1)
self.assertEqual(3, direc)
## ---- 180 degree
direc = self.pd._points_to_direction(c, 0, 0, -1, 0)
self.assertEqual(4, direc)
## ---- 225 degree
direc = self.pd._points_to_direction(c, 0, 0, -1, -1)
self.assertEqual(5, direc)
## ---- 270 degree
direc = self.pd._points_to_direction(c, 0, 0, 0, -1)
self.assertEqual(6, direc)
## ---- 315 degree
direc = self.pd._points_to_direction(c, 0, 0, 1, -1)
self.assertEqual(7, direc)
# random other angles
# ---- 52 degree
direc = self.pd._points_to_direction(c, 0, 0, 0.61, 0.79)
self.assertEqual(1, direc)
## ---- 100 degree
direc = self.pd._points_to_direction(c, 0, 0, -0.18, 0.98)
self.assertEqual(2, direc)
# ---- 291 degree
direc = self.pd._points_to_direction(c, 0, 0, 0.36, -0.93)
self.assertEqual(6, direc)
# ----- 350 degree
direc = self.pd._points_to_direction(c, 0, 0, 0.98, -0.17)
self.assertEqual(0, direc)
def test_points_to_direction_2(self):
c = 8
# check if direction correct after pen is set on table or
# after pen is removed from table
xp = 0
yp = 0
# ----- 350 degree
direc = self.pd._points_to_direction(c, xp, yp, 0.98, -0.17)
self.assertEqual(0, direc)
class TestPendigitsModel(unittest.TestCase):
def setUp(self):
self.ctrl = Controller()
self.ctrl.load_dataset(Dataset.PENDIGITS)
pd_model = ModelPendigits(self.ctrl, "test")
self.ctrl.register_model(pd_model)
self.dset = self.ctrl._dataset # type: DatasetPendigits
self.pd_model = self.ctrl._model
def test_init_hmms(self):
self.ctrl.init_model_on_dataset()
def test_save_hmms(self):
self.ctrl.init_model_on_dataset()
self.ctrl.save_model()
def test_load_hmms(self):
self.ctrl.load_model()
# attention manually refresh reference
self.pd_model = self.ctrl._model
def test_train_hmms(self):
self.ctrl.init_model_on_dataset()
self.ctrl.train_model()
def test_train_n_save_hmms(self):
self.ctrl.init_model_on_dataset()
self.ctrl.train_model()
self.ctrl.save_model()
def test_pre_bench_hmms(self):
self.ctrl.load_model()
self.pd_model = self.ctrl._model
y_true, y_pred = self.pd_model.create_pred_act_seqs(self.dset)
def test_bench_hmms(self):
self.ctrl.load_model()
self.pd_model = self.ctrl._model
self.ctrl.register_benchmark()
rep = self.ctrl.create_report(conf_matrix=True,
accuracy=True,
precision=True,
recall=True,
f1=True)
print(rep)
def test_generate_obs(self):
self.ctrl.load_model()
self.pd_model = self.ctrl._model
self.ctrl.generate_observations()
def test_generate_obs_n_plot(self):
# numbers that were good in benchmark (desc):
# [0,8,4,9,3,7]
self.ctrl.load_model()
ds = self.ctrl._dataset # type: DatasetPendigits
pdmod = self.ctrl._model # type: ModelPendigits
num = 1
zero_start = [8, 1, 1]
one_start = [8, 2, 1, 1, 1]
start_seq = one_start
hmm = pdmod._model_dict[num]
hmm.set_format_full(True)
print(hmm)
pdmod.select_number(num)
seq = pdmod.generate_observations(start_seq)
ds.plot_obs_seq(seq, num)
def tearDown(self):
pass
class TestHomeassistantModelHMMLogScaled(unittest.TestCase):
# Model part
def setUp(self):
# set of observations
self.ctrl = Controller()
self.ctrl.set_dataset(Dataset.HASS_TESTING)
self.hass_obj = self.ctrl._dataset #type: DatasetHomeassistant
self.hmm_model = HMMForward(self.ctrl)
def tearDown(self):
pass
def test_load_custom_lists_modelHMM(self):
custom_state_list = ['sleeping', 'cooking']
custom_obs_list = [
'binary_sensor.motion_bed', 'binary_sensor.motion_mirror',
'binary_sensor.motion_pc', 'switch.test_switch_1',
'light.test_light'
]
hmm_model = self.hmm_model
self.ctrl.set_custom_state_list(custom_state_list)
self.ctrl.set_custom_obs_list(custom_obs_list)
self.ctrl.load_dataset()
self.ctrl.register_model(hmm_model)
self.ctrl.init_model_on_dataset()
hmm_model._hmm.set_format_full(True)
print(self.ctrl._model)
def test_load_modelHMM(self):
self.ctrl.load_dataset()
hmm_model = self.hmm_model
self.ctrl.register_model(hmm_model)
self.ctrl.init_model_on_dataset()
hmm_model._hmm.set_format_full(True)
print(self.ctrl._model)
print(self.hass_obj.get_obs_lbl_hashmap())
print(self.hass_obj.get_state_lbl_hashmap())
def test_train_modelHMM(self):
self.ctrl.load_dataset()
hmm_model = self.hmm_model
self.ctrl.register_model(hmm_model)
self.ctrl.init_model_on_dataset()
hmm_model._hmm.set_format_full(True)
print(self.ctrl._model)
self.ctrl.train_model()
print(self.ctrl._model)
def test_bench_modelHMM(self):
self.ctrl.load_dataset()
hmm_model = self.hmm_model
self.ctrl.register_model(hmm_model)
self.ctrl.init_model_on_dataset()
hmm_model._hmm.set_format_full(True)
print(self.ctrl._model)
self.ctrl.register_benchmark()
self.ctrl.train_model()
print(self.ctrl._model)
report = self.ctrl.create_report(conf_matrix=True,
accuracy=True,
precision=True,
recall=True,
f1=True)
print(report)
def test_classify(self):
self.ctrl.load_dataset()
hmm_model = self.hmm_model
self.ctrl.register_model(hmm_model)
self.ctrl.init_model_on_dataset()
self.ctrl.train_model()
hmm_model._hmm.set_format_full(True)
print(hmm_model)
print('-' * 10)
obs_seq = [('binary_sensor.motion_bed', 0),
('binary_sensor.motion_mirror', 1),
('binary_sensor.motion_bed', 0)]
pred_state = hmm_model.classify(obs_seq)
print('#' * 100)
print(pred_state)
def test_classify_multi(self):
"""
used to test for classification of multiple labels
"""
self.ctrl.load_dataset()
hmm_model = self.hmm_model
self.ctrl.register_model(hmm_model)
self.ctrl.init_model_on_dataset()
self.ctrl.train_model()
hmm_model._hmm.set_format_full(True)
print(hmm_model)
print('-' * 10)
obs_seq = [('binary_sensor.motion_bed', 0),
('binary_sensor.motion_mirror', 1)
] #, ('binary_sensor.motion_bed', 0)]
act_state_dict = hmm_model.classify_multi(obs_seq)
print('#' * 100)
print(act_state_dict)
#print(act_state_dict)
#print(hmm_model.get_state_label_list())
def test_pred_next_obs_single(self):
self.ctrl.load_dataset()
hmm_model = self.hmm_model
self.ctrl.register_model(hmm_model)
self.ctrl.init_model_on_dataset()
self.ctrl.train_model()
hmm_model._hmm.set_format_full(True)
#print(hmm_model)
print('#' * 100)
obs_seq = [('binary_sensor.motion_bed', 0),
('binary_sensor.motion_mirror', 1),
('binary_sensor.motion_bed', 0)]
tupel = hmm_model.predict_next_obs(obs_seq)
print(tupel)
def test_pred_next_obs_multi(self):
hmm_model = self.hmm_model
self.ctrl.load_dataset()
self.ctrl.register_model(hmm_model)
self.ctrl.init_model_on_dataset()
self.ctrl.train_model()
hmm_model._hmm.set_format_full(True)
print(hmm_model)
print('#' * 100)
obs_seq = [('binary_sensor.motion_bed', 0),
('binary_sensor.motion_mirror', 1),
('binary_sensor.motion_bed', 0)]
#arr = hmm_model.predict_next_obs_arr(obs_seq)
print(hmm_model._obs_lbl_hashmap)
print(hmm_model._obs_lbl_rev_hashmap)
res_dict = hmm_model.predict_prob_xnp1(obs_seq)
print(hmm_model._obs_lbl_hashmap)
print(hmm_model._obs_lbl_rev_hashmap)
res_dict = hmm_model.predict_prob_xnp1(obs_seq)
print(hmm_model._obs_lbl_hashmap)
print(hmm_model._obs_lbl_rev_hashmap)
print('#' * 100)
print(res_dict)
class TestController(unittest.TestCase):
def setUp(self):
# set of observations
self.ctrl = Controller() # type: Controller
#self.hmm_model = ModelHMM(self.ctrl)
#self.hmm_model = ModelHMM_scaled(self.ctrl)
#self.hmm_model = ModelHMM_log(self.ctrl)
self.hmm_model = ModelHMM_log_scaled(self.ctrl)
def tearDown(self):
pass
def test_ctrl_get_bench_metrics(self):
hmm_model = self.hmm_model
dk = Dataset.KASTEREN
self.ctrl.load_dataset(dk)
self.ctrl.register_model(hmm_model)
self.ctrl.init_model_on_dataset()
self.ctrl.register_benchmark()
self.ctrl.register
# render
#dot = self.ctrl.render_model()
#dot.render('test.gv', view=True)
self.ctrl.train_model(True)
print(self.ctrl.get_bench_metrics())
def test_ctrl_train_seqs(self):
hmm_model = self.hmm_model
dk = Dataset.KASTEREN
self.ctrl.set_dataset(dk)
self.ctrl.load_dataset()
self.ctrl.register_model(hmm_model)
self.ctrl.init_model_on_dataset()
self.ctrl.register_benchmark()
# render
#dot = self.ctrl.render_model()
#dot.render('test.gv', view=True)
self.ctrl.train_model()
report = self.ctrl.create_report(conf_matrix=True,
accuracy=True,
precision=True,
recall=True,
f1=True)
print(self.ctrl._model)
print(report)
#self.ctrl.show_plot()
def test_ctrl_presentation(self):
hmm_model = self.hmm_model
dk = Dataset.KASTEREN
self.ctrl.load_dataset(dk)
self.ctrl.register_model(hmm_model)
self.ctrl.init_model_on_dataset()
self.ctrl.register_benchmark()
# render
#dot = self.ctrl.render_model()
#dot.render('test.gv', view=True)
self.ctrl.train_model(True)
report = self.ctrl.create_report(conf_matrix=True,
accuracy=True,
precision=True,
recall=True,
f1=True)
print(self.ctrl._model)
print(report)
#self.ctrl.show_plot()
# render
#dot = self.ctrl.render_model()
#dot.render('test.gv', view=True)
def test_generate_visualization(self):
hmm_model = self.hmm_model
dk = Dataset.KASTEREN
self.ctrl.set_dataset(dk)
self.ctrl.load_dataset()
self.ctrl.register_model(hmm_model)
self.ctrl.init_model_on_dataset()
hmm_model._hmm.set_format_full(True)
print('state_label_hm: ', hmm_model._state_lbl_hashmap)
print('state_label_rev_hm: ', hmm_model._state_lbl_rev_hashmap)
self.ctrl.save_visualization_to_file(
'/home/cmeier/code/tmp/visualization.png')
def test_bench_train_loss(self):
hmm_model = self.hmm_model
dk = Dataset.KASTEREN
self.ctrl.set_dataset(dk)
self.ctrl.load_dataset()
self.ctrl.register_model(hmm_model)
self.ctrl.init_model_on_dataset()
self.ctrl.register_benchmark()
self.ctrl.register_loss_file_path(
'/home/cmeier/code/tmp/kasteren/train_loss.log')
self.ctrl.train_model()
self.ctrl.save_model(
'/home/cmeier/code/tmp/kasteren/kasteren_model.joblib')
def test_bench_reports_conf_matrix(self):
hmm_model = self.hmm_model
dk = Dataset.KASTEREN
self.ctrl.load_dataset(dk)
self.ctrl.register_model(hmm_model)
self.ctrl.init_model_on_dataset()
self.ctrl.register_benchmark()
self.ctrl.train_model()
report = self.ctrl.create_report(conf_matrix=True)
print(report)
def test_bench_reports(self):
hmm_model = self.hmm_model
dk = Dataset.KASTEREN
self.ctrl.load_dataset(dk)
self.ctrl.register_model(hmm_model)
self.ctrl.init_model_on_dataset()
self.ctrl.register_benchmark()
self.ctrl.train_model()
report = self.ctrl.create_report(conf_matrix=True,
accuracy=True,
precision=True,
recall=True,
f1=True)
print(report)
#self.ctrl.show_plot()
def test_bench_q_fct(self):
hmm_model = self.hmm_model
dk = Dataset.KASTEREN
self.ctrl.load_dataset(dk)
self.ctrl.register_model(hmm_model)
self.ctrl.init_model_on_dataset()
self.ctrl.register_benchmark()
print(self.ctrl._model)
# use dataset Kasteren and q_fct
self.ctrl.train_model(True)
report = self.ctrl.create_report()
print(self.ctrl._model)
print(report)
#self.ctrl.show_plot()
def test_om(self):
#plt.figure(figsize=(10,6))
#self.pom.plot()
hmm_model = self.hmm_model
dk = Dataset.KASTEREN
self.ctrl.load_dataset(dk)
self.ctrl.register_model(hmm_model)
self.ctrl.init_model_on_dataset()
dot = self.ctrl.render_model()
dot.render('test.gv', view=True)
def test_train_model(self):
hmm_model = self.hmm_model
dk = Dataset.KASTEREN
self.ctrl.set_dataset(dk)
self.ctrl.load_dataset()
self.ctrl.register_model(hmm_model)
self.ctrl.init_model_on_dataset()
#print(hmm_model._hmm)
self.ctrl.train_model()
print('#' * 200)
print(hmm_model)
hmm_model._hmm.set_str_exp(True)
hmm_model._hmm.set_format_full(True)
print(hmm_model)
#print(hmm_model._hmm.verify_transition_matrix())
#print(hmm_model._hmm.verify_emission_matrix())
#self._bench._model.draw()
#self.ctrl.register_benchmark()
#report = self.ctrl.create_report(True, True, True, True, True)
#print(report)
#self._bench.show_plot()
def test_save_model(self):
hmm_model = self.hmm_model
dk = Dataset.KASTEREN
self.ctrl.load_dataset(dk)
self.ctrl.register_model(hmm_model)
self.ctrl.init_model_on_dataset()
hmm_model._hmm.set_format_full(True)
self.ctrl.train_model()
self.ctrl.save_model()
def test_init_model(self):
hmm_model = self.hmm_model
dk = Dataset.KASTEREN
self.ctrl.set_dataset(dk)
self.ctrl.load_dataset()
self.ctrl.register_model(hmm_model)
self.ctrl.init_model_on_dataset()
hmm_model._hmm.set_format_full(True)
print(self.ctrl._model)
def test_load_model(self):
hmm_model = self.hmm_model
dk = Dataset.KASTEREN
self.ctrl.set_dataset(dk)
self.ctrl.load_dataset()
self.ctrl.register_model(hmm_model)
self.ctrl.load_model()
print(self.ctrl._model)
class TestHomeassistantModelHMMLogScaled(unittest.TestCase):
# Model part
def setUp(self):
# set of observations
self.ctrl = Controller()
self.ctrl.set_dataset(Dataset.HASS_TESTING)
self.hass_obj = self.ctrl._dataset #type: DatasetHomeassistant
self.hmm_model = PreConfHMM(self.ctrl)
def tearDown(self):
pass
def test_load_custom_lists_modelHMM(self):
custom_state_list = ['sleeping', 'cooking']
custom_obs_list = [
'binary_sensor.motion_bed',
'binary_sensor.motion_mirror',
'binary_sensor.motion_pc',
'switch.test_switch_1',
'light.test_light'
]
hmm_model = self.hmm_model
self.ctrl.set_custom_state_list(custom_state_list)
self.ctrl.set_custom_obs_list(custom_obs_list)
self.ctrl.load_dataset()
self.ctrl.register_model(hmm_model)
self.ctrl.init_model_on_dataset()
hmm_model._hmm.set_format_full(True)
print(self.ctrl._model)
def test_load_modelHMM(self):
self.ctrl.load_dataset()
hmm_model = self.hmm_model
self.ctrl.register_model(hmm_model)
self.ctrl.init_model_on_dataset()
hmm_model._hmm.set_format_full(True)
print(self.ctrl._model)
print(self.hass_obj.get_obs_lbl_hashmap())
print(self.hass_obj.get_state_lbl_hashmap())
def test_train_modelHMM(self):
self.ctrl.load_dataset()
hmm_model = self.hmm_model
self.ctrl.register_model(hmm_model)
self.ctrl.init_model_on_dataset()
hmm_model._hmm.set_format_full(True)
print(self.ctrl._model)
self.ctrl.train_model()
print(self.ctrl._model)
def test_bench_modelHMM(self):
self.ctrl.load_dataset()
hmm_model = self.hmm_model
self.ctrl.register_model(hmm_model)
self.ctrl.init_model_on_dataset()
hmm_model._hmm.set_format_full(True)
print(self.ctrl._model)
self.ctrl.register_benchmark()
self.ctrl.train_model()
print(self.ctrl._model)
report = self.ctrl.create_report(
conf_matrix=True,
accuracy=True,
precision=True,
recall=True,
f1=True
)
print(report)
def test_classify(self):
self.ctrl.load_dataset()
hmm_model = self.hmm_model
self.ctrl.register_model(hmm_model)
self.ctrl.init_model_on_dataset()
self.ctrl.train_model()
hmm_model._hmm.set_format_full(True)
print(hmm_model)
print('-'*10)
obs_seq = [('binary_sensor.motion_bed', 0), ('binary_sensor.motion_mirror', 1), ('binary_sensor.motion_bed', 0)]
pred_state = hmm_model.classify(obs_seq)
print('#'*100)
print(pred_state)
def test_classify_multi(self):
"""
used to test for classification of multiple labels
"""
self.ctrl.load_dataset()
hmm_model = self.hmm_model
self.ctrl.register_model(hmm_model)
self.ctrl.init_model_on_dataset()
self.ctrl.train_model()
hmm_model._hmm.set_format_full(True)
print(hmm_model)
print('-'*10)
obs_seq = [('binary_sensor.motion_bed', 0), ('binary_sensor.motion_mirror', 1)]#, ('binary_sensor.motion_bed', 0)]
act_state_dict = hmm_model.classify_multi(obs_seq)
print('#'*100)
print(act_state_dict)
#print(act_state_dict)
#print(hmm_model.get_state_label_list())
def test_pred_next_obs_single(self):
self.ctrl.load_dataset()
hmm_model = self.hmm_model
self.ctrl.register_model(hmm_model)
self.ctrl.init_model_on_dataset()
self.ctrl.train_model()
hmm_model._hmm.set_format_full(True)
#print(hmm_model)
print('#'*100)
obs_seq = [('binary_sensor.motion_bed', 0), ('binary_sensor.motion_mirror', 1), ('binary_sensor.motion_bed', 0)]
tupel = hmm_model.predict_next_obs(obs_seq)
print(tupel)
def test_pred_next_obs_multi(self):
hmm_model = self.hmm_model
self.ctrl.load_dataset()
self.ctrl.register_model(hmm_model)
self.ctrl.init_model_on_dataset()
self.ctrl.train_model()
hmm_model._hmm.set_format_full(True)
print(hmm_model)
print('#'*100)
obs_seq = [('binary_sensor.motion_bed', 0), ('binary_sensor.motion_mirror', 1), ('binary_sensor.motion_bed', 0)]
#arr = hmm_model.predict_next_obs_arr(obs_seq)
print(hmm_model._obs_lbl_hashmap)
print(hmm_model._obs_lbl_rev_hashmap)
res_dict = hmm_model.predict_prob_xnp1(obs_seq)
print(hmm_model._obs_lbl_hashmap)
print(hmm_model._obs_lbl_rev_hashmap)
res_dict = hmm_model.predict_prob_xnp1(obs_seq)
print(hmm_model._obs_lbl_hashmap)
print(hmm_model._obs_lbl_rev_hashmap)
print('#'*100)
print(res_dict)
def test_encode_loc_data(self):
loc_data = [ {
"name" : "loc1",
"activities" : ['cooking'],
"devices" : ['binary_sensor.motion_hallway', 'binary_sensor.motion_mirror'],
},
{"name" : "loc2",
"activities" : ['cooking', 'eating'],
"devices" : [],
},
{"name" : "loc3",
"activities" : ['sleeping'],
"devices" : ['binary_sensor.motion_bed'],
},
]
hmm_model = self.hmm_model
self.ctrl.load_dataset()
self.ctrl.register_model(hmm_model)
self.ctrl.init_model_on_dataset()
hmm_model._hmm.set_format_full(True)
#print('state_hm: ', hmm_model._state_lbl_hashmap)
#print('obs_hm: ', hmm_model._obs_lbl_hashmap)
#print('raw_loc_data: \t' + str(loc_data))
enc_loc_data = hmm_model._encode_location_data(loc_data)
#print('#'*100)
#print('enc_loc_data: \t' + str(enc_loc_data))
def test_encode_act_data(self):
act_data = [
{"name" : "cooking",
"day_of_week" : 2,
"start" : datetime.time.fromisoformat("06:15:00"),
"end" : datetime.time.fromisoformat("08:45:00")
},
{"name" : "eating",
"day_of_week" : 1,
"start" : datetime.time.fromisoformat("06:15:00"),
"end" : datetime.time.fromisoformat("08:45:00")
},
{"name" : "eating",
"day_of_week" : 1,
"start" : datetime.time.fromisoformat("08:46:00"),
"end" : datetime.time.fromisoformat("10:00:00")
},
]
hmm_model = self.hmm_model
self.ctrl.load_dataset()
self.ctrl.register_model(hmm_model)
self.ctrl.init_model_on_dataset()
print('raw_act_data: \t' + str(act_data))
print('state_hm: ', hmm_model._state_lbl_hashmap)
print('obs_hm: ', hmm_model._obs_lbl_hashmap)
print('#'*100)
enc_act_data = hmm_model._encode_act_data(act_data)
print('enc_act_data: \t' + str(enc_act_data))
def test_init(self):
loc_data = [ {
"name" : "loc1",
"activities" : ['cooking'],
"devices" : ['binary_sensor.motion_hallway', 'binary_sensor.motion_mirror'],
},
{"name" : "loc2",
"activities" : ['cooking', 'eating'],
"devices" : [],
},
{"name" : "loc3",
"activities" : ['sleeping'],
"devices" : ['binary_sensor.motion_bed'],
},
]
act_data = [
{"name" : "sleeping",
"day_of_week" : 0,
"start" : datetime.time.fromisoformat("04:00:00"),
"end" : datetime.time.fromisoformat("06:15:00")
},
{"name" : "cooking",
"day_of_week" : 0,
"start" : datetime.time.fromisoformat("06:15:00"),
"end" : datetime.time.fromisoformat("08:45:00")
},
{"name" : "eating",
"day_of_week" : 0,
"start" : datetime.time.fromisoformat("08:46:00"),
"end" : datetime.time.fromisoformat("10:00:00")
},
{"name" : "sleeping",
"day_of_week" : 0,
"start" : datetime.time.fromisoformat("12:00:00"),
"end" : datetime.time.fromisoformat("13:00:00")
},
{"name" : "sleeping",
"day_of_week" : 1,
"start" : datetime.time.fromisoformat("02:00:00"),
"end" : datetime.time.fromisoformat("06:30:00")
},
{"name" : "cooking",
"day_of_week" : 1,
"start" : datetime.time.fromisoformat("12:00:00"),
"end" : datetime.time.fromisoformat("13:00:00")
},
{"name" : "cooking",
"day_of_week" : 2,
"start" : datetime.time.fromisoformat("19:00:00"),
"end" : datetime.time.fromisoformat("00:00:00")
},
{"name" : "cooking",
"day_of_week" : 2,
"start" : datetime.time.fromisoformat("23:00:00"),
"end" : datetime.time.fromisoformat("00:00:00")
},
{"name" : "sleeping",
"day_of_week" : 2,
"start" : datetime.time.fromisoformat("00:00:00"),
"end" : datetime.time.fromisoformat("03:00:00")
},
]
hmm_model = self.hmm_model
self.ctrl.load_dataset()
self.ctrl.register_model(hmm_model)
self.ctrl.register_location_info(loc_data)
print('raw_act_data: \t' + str(act_data))
print('state_hm: ', hmm_model._state_lbl_hashmap)
#print('obs_hm: ', hmm_model._obs_lbl_hashmap)
self.ctrl.register_activity_info(act_data)
#print('#'*100)
#enc_act_data = hmm_model._encode_act_data(act_data)
#print('enc_act_data: \t' + str(enc_act_data))
self.ctrl.init_model_on_dataset()
hmm = hmm_model._hmm
hmm.set_format_full(True)
self.assertAlmostEqual(1.0, Probs.prob_to_norm(hmm._pi.sum()), 6)
self.assertTrue(hmm.verify_emission_matrix())
self.assertTrue(hmm.verify_transition_matrix())