def HiddenSpaceGenerator(cls, X, n_components):
"""This method creates more features by training a HiddenMarkovModel
on the game statistics, then returns the hidden state space of each
timestep/game as a new feature. HOWEVER, note that this doesn't
return a list of features, instead it returns a HMM that can generate
more features but can still be used for classification also.
Arguments:
X: the input features (with a series_idx)
n_components: The number of hidden state space variables to
initialize. Note that (sadly) pomegranate does not implement
continuous HMMs, so it will discretize every continuous
variable by K-means so then the outputted space will be
discrete.
"""
# the last series id, none are negative so we will get a new one
last_series_idx = -1
# restrict down, but since a temporal we need to make a list of entries
_X = []
for row in X:
if row[0] != last_series_idx:
# create a new series to train on, start with empty input
# series then add to them while the row has the same index
last_series_idx = row[0]
_X.append(np.full((0, X.shape[1] - 1), None, dtype=None))
# add the datapoint to the current series
_X[-1] = np.vstack((_X[-1], row[1:]))
# now train an HMM to the data
return HiddenMarkovModel.from_samples(MultivariateGaussianDistribution,
n_components, _X)
def hmm(df, emissions, n_states, algorithm):
model = HiddenMarkovModel.from_samples(
distribution=MultivariateGaussianDistribution,
n_components=n_states,
X=df[emissions].to_numpy(),
algorithm=algorithm,
verbose=True,
)
return model
def hmm(df, num_states):
"HMM program"
# df['value']=df['value'].replace(0,np.nan) #this removes unmappable areas of chr
# df_dropna=df.dropna(subset=['value']) #this removes unmappable areas of chr (NaN is otherwise considered 0)
vals = df["value"].values
model = HiddenMarkovModel.from_samples(NormalDistribution,
X=[vals],
n_components=num_states)
states = model.predict(vals)
# Rename states to increase with mean signal
order = np.argsort(df['value'].groupby(states).mean())
states = [order[s] for s in states]
df["state"] = states
df['state'][np.isnan(df['value'])] = np.nan
return df
def generate(
genre_folder: str,
bpm: int,
beats: int,
steps: int,
onset: str,
components: int,
regex: str,
output: str,
include: bool,
):
"""
This command generates a new unique beat, based on the audio files in the given input folder.
"""
audios = util.read_audio_files(include, Path(genre_folder), regex)
sequences, samples = util.create_knowledge_base(
audios, OnsetAlgorithm(onset.lower()), beats, steps
)
# Create the model
# sequences = [add_up_ones(seq) for seq in sequences]
model: HiddenMarkovModel = HiddenMarkovModel.from_samples(
DiscreteDistribution,
n_components=components,
X=sequences,
algorithm="viterbi",
verbose=True,
name="groover",
)
# model: MarkovChain = MarkovChain.from_samples(X=sequences)
# lengths: List[int] = [len(x) for x in sequences]
sequence = model.sample(length=beats * steps)
sequence = sequences[0]
print(sequence)
# sequence = ones(sequence)
# print(len(sequence))
print(
"BPM: {}, Beats: {}, Steps:{}, Onset Algorithm: {}".format(
bpm, beats, steps, onset
)
)
# Save the beat
util.create_beat(sequence, samples, bpm, beats, steps).save(Path(output))
def run_test(arg, k):
np.random.seed(k)
exp_type = arg['type']
N = arg['N']
alpha = arg['alpha']
n_comp = arg['n_comp']
norm_params = arg['norm_params']
save_dir = arg['dir']
sequence = generator.Sequence(N, alpha, type=exp_type, params=norm_params)
labels = list(map(myutils.rename_state, sequence.path))
model = HiddenMarkovModel.from_samples(DiscreteDistribution,
n_components=n_comp,
X=[sequence.sequence],
labels=[labels],
algorithm='labeled')
return model, sequence.sequence
def fit_hmm(self,
signal_arrays,
state_vectors,
distribution,
state_transition_threshold=1e-4,
**kwargs):
# We want to bunch together artefact states with their
# corresponding "clean" states.
state_vectors = [np.abs(vec) for vec in state_vectors]
# remove 'undefined' samples
# TODO: let pomegranate handle that
signal_arrays = [
arr[vec != 0] for arr, vec in zip(signal_arrays, state_vectors)
]
state_vectors = [vec[vec != 0] for vec in state_vectors]
# Pomegranate expects string labels for valid states and None for invalid states.
# labels = [[str(state) if state != 0 else None for state in vec] for vec in state_vectors]
labels = [[str(state) for state in vec] for vec in state_vectors]
# construct matching state names
# state_names = [str(state) for state in np.unique(np.concatenate(state_vectors)) if state != 0]
state_names = [
str(state) for state in np.unique(np.concatenate(state_vectors))
]
# fit HMM states to transformed signals
signals = [self.transform(arr) for arr in signal_arrays]
hmm = HiddenMarkovModel.from_samples(distribution=distribution,
n_components=len(state_names),
X=signals,
labels=labels,
algorithm='labeled',
state_names=state_names,
**kwargs)
if state_transition_threshold > 0.:
new_hmm = _sparsify_hmm(hmm, state_transition_threshold)
return new_hmm
else:
return hmm
def fit(self, X, y=None):
X_processed = self._check_and_preprocess(X, True)
self.hmmmodel = HiddenMarkovModel.from_samples(
NormalDistribution,
self.n_states,
X_processed,
algorithm="baum-welch",
n_jobs=8,
verbose=self.verbose,
batches_per_epoch=20,
max_iterations=self.max_iterations)
self.hmmmodel.bake()
self.decision_scores_ = np.zeros(X.shape[0])
for i, sequence in enumerate(X_processed):
self.decision_scores_[i] = -self.hmmmodel.log_probability(sequence)
self._process_decision_scores()
def fit(self, data):
"""
Fits a model---learns transition and emission probabilities
Arguments:
data: list of SMILES
"""
list_data = [list(smiles) for smiles in data]
self.model = HiddenMarkovModel.from_samples(
DiscreteDistribution, n_components=self.n_components,
end_state=True, X=list_data,
init='kmeans||', verbose=self.verbose, n_jobs=self.n_jobs,
max_iterations=self.epochs,
batches_per_epoch=self.batches_per_epoch,
random_state=self.seed
)
self.fitted = True
return self
def create_casas7_HMM_with_prepared_train_and_test_based_on_seq_of_activities(
train_set, list_of_persons_in_train, test_set,
list_of_persons_in_test):
'''
create a single HMM for all of persons
train_set = an ndarray that has train_set for each person separately
test_set =
'''
#concatinate train_sets and test_sets of all of people
number_of_persons = len(train_set)
final_train_set = train_set[0]
final_test_set = test_set[0]
final_train_set_labels = list_of_persons_in_train[0]
final_test_set_labels = list_of_persons_in_test[0]
#print(type(final_train_set) , type(train_set) , type(train_set[1]))
for per in range(1, number_of_persons):
final_train_set = np.concatenate((final_train_set, train_set[per]),
axis=0)
final_test_set = np.concatenate((final_test_set, test_set[per]),
axis=0)
final_train_set_labels = np.concatenate(
(final_train_set_labels, list_of_persons_in_train[per]), axis=0)
final_test_set_labels = np.concatenate(
(final_test_set_labels, list_of_persons_in_test[per]), axis=0)
#r = np.shape(final_train_set)
#for i in range(r[0]):
# print(np.shape(final_train_set[i]))
#final_train_set = np.array([[1,2,3,0,0] , [1,2,0,0,0]], dtype = np.ndarray)
#final_train_set_labels = np.array([1,2] , dtype= np.ndarray)
print(type(final_train_set[11]), np.shape(final_train_set[11]))
print(final_train_set[0:2])
model = HiddenMarkovModel.from_samples(
DiscreteDistribution,
n_components=2,
X=final_train_set,
labels=final_train_set_labels,
algorithm='labeled'
) # according to my tests :D n_components is number of hidden states
print(model)
#return 0
#test
'''predicted_labels = np.zeros_like(actual_labels)
def create_hmm_from_sample(file_address):
#data, _ , _ = read_sequence_based_CSV_file_with_activity(file_address = file_address, has_header = True , separate_data_based_on_persons = False )
#data = read_data_from_CSV_file(dest_file = file_address, data_type = np.int , has_header = True , return_as_pandas_data_frame = False )
'''
data = np.delete(data , 2, 1)
data = np.delete(data , 2, 1)
data = np.delete(data , 0, 1)
data = np.delete(data , 0, 1)
data = np.delete(data , 0, 1)
print(np.shape(data))
'''
#print(data)
data = np.array([['a', 'b'], ['a', 'b']])
data = np.array([[np.array([1, 2, 3]),
np.array([1, 1, 1])],
[np.array([1, 1, 2]),
np.array([1, 2, 2])]])
data = [
np.array([[1, 2, 3], [1, 2, 3]], np.int32),
np.array([[1, 2, 3], [1, 2, 3]], np.int32),
np.array([[1, 2, 3], [1, 2, 3]], np.int32)
]
print(data)
#data = np.array([[['a' , 'b'] , ['a' , 'a']] , [['a' , 'b'] , ['b' , 'b']]])
#data = create_sequence_of_sensor_events_based_on_activity(address_to_read = file_address, has_header = False, address_for_save = " ", isSave = False)#read_data_from_CSV_file(dest_file = file_address, data_type = numpy.int , has_header = False , return_as_pandas_data_frame = False )
model = HiddenMarkovModel.from_samples(
MultivariateDistribution, n_components=3, X=data
) # according to my tests :D n_components is number of hidden states
#print(model)
#print(model._baum_welch_summarize())
#model.plot()
'''
print("dense_transition_matrix:" , model.dense_transition_matrix())
print("edge_count:" , model.edge_count())
print("edges:" , model.edges)
print("name:" , model.name)
print("state_count:" , model.state_count())
'''
print(model)
def create_casas7_hmm(file_address, has_activity):
if has_activity:
list_of_data, list_of_persons, _ = read_sequence_based_CSV_file_with_activity(
file_address=file_address,
has_header=True,
separate_data_based_on_persons=False)
else:
list_of_data, list_of_persons = read_sequence_based_CSV_file_without_activity(
file_address=file_address,
has_header=True,
separate_data_based_on_persons=False)
model = ""
try:
model = HiddenMarkovModel.from_samples(DiscreteDistribution,
n_components=5,
X=list_of_data,
algorithm='baum-welch')
#model = HiddenMarkovModel.from_samples(DiscreteDistribution, n_components=2, X=list_of_data , labels = list_of_persons , algorithm = 'labeled' )
except KeyError:
print('there is an exception')
print(model)
#print((list_of_persons[0]))
print("np.shape(list_of_data):", np.shape(list_of_data))
#print(model._baum_welch_summarize())
model.plot()
print("dense_transition_matrix:", model.dense_transition_matrix())
print("edge_count:", model.edge_count())
print("edges:", model.edges)
print("name:", model.name)
print("state_count:", model.state_count())
#print("summarize:" , model.summarize())
print(model.thaw())
def run(arg, k):
np.random.seed(k)
exp_type = arg['type']
N = arg['N']
alpha = arg['alpha']
n_comp = arg['n_comp']
norm_params = arg['norm_params']
an_params = arg['an_params']
save_dir = arg['dir']
mean = arg['mean']
variance = arg['varience']
anomal_mean = arg['anomal_mean']
anomal_variance = arg['anomal_varience']
norm_gen = generator.Sequence(N,
alpha,
type=exp_type,
params=norm_params,
mean=mean,
variance=variance)
norm_signal = norm_gen.sequence
an_gen = generator.Sequence(N,
alpha,
type=exp_type,
params=an_params,
mean=anomal_mean,
variance=anomal_variance)
an_signal = an_gen.sequence
# an_signal[180:200] = np.random.normal(2,0.02,20)
an_labels = list(map(myutils.rename_state, an_gen.path))
labels = list(map(myutils.rename_state, norm_gen.path))
if exp_type == 'continue':
model = HiddenMarkovModel.from_samples(NormalDistribution,
n_components=n_comp,
X=[norm_signal],
labels=[labels],
algorithm='labeled')
an_model = HiddenMarkovModel.from_samples(NormalDistribution,
n_components=n_comp,
X=[an_signal],
labels=[an_labels],
algorithm='labeled')
else:
model = HiddenMarkovModel.from_samples(DiscreteDistribution,
n_components=n_comp,
X=[norm_signal],
labels=[labels],
algorithm='labeled')
an_model = HiddenMarkovModel.from_samples(DiscreteDistribution,
n_components=n_comp,
X=[an_signal])
# model = HiddenMarkovModel.from_samples(DiscreteDistribution, n_components = n_comp, X = [norm_signal])
# an_model = HiddenMarkovModel.from_samples(DiscreteDistribution, n_components = n_comp, X = [an_signal])
l1 = model.log_probability(norm_signal)
l2 = model.log_probability(an_signal)
cdir = os.getcwd()
path = cdir + '/' + arg['dir']
try:
os.mkdir(path)
except:
pass
with open(path + '/log_' + str(k) + '.txt', 'w') as file:
out = myutils.print_model_distribution(model)
file.write(out)
out = myutils.print_model_distribution(an_model)
file.write(out)
file.write('l_normal = {} l_anomal = {}'.format(l1, l2))
# out = myutils.print_model_distribution(model_2)
# file.write(out)
# file.write(str(an_model.to_json()))
# fig_sub = plt.figure(figsize = (18,5.9))
fig_sub = plt.figure(figsize=(16, 5.9))
ax2 = fig_sub.add_axes([0.12, 0.1, 0.07, 0.8])
ax2.plot([1] * len([l1]), l1, 'b.', markersize=12)
ax2.plot([1] * len([l2]), l2, 'r.', markersize=12)
# ax2.plot([1], normal_score, 'g*', markersize=12)
ax2.set_ylabel('log probability')
# ax2.set_xlim(0.9, 1.2)
ax2.set_xticks([0.95, 1, 1.05])
ax2.set_xticklabels(['', '', ''])
ax = fig_sub.add_axes([0.24, 0.1, 0.74, 0.8])
ax.plot(norm_signal, 'b', label='Normal') #Ошибка в цветах
ax.plot(an_signal, 'r', label='Abnormal')
ax.set_xlabel('Time', )
# ax.grid()
plt.legend(loc=1)
plt.tight_layout()
plt.savefig(path + '/plot' + str(k) + '.png', dpi=180)
plt.close()
# ax.set_y
print(' {}, {}'.format(l1, l2))
print('На аномальной')
l1 = an_model.log_probability(norm_signal)
l2 = an_model.log_probability(an_signal)
print(' {}, {}'.format(l1, l2))
print(' Норма\n {}'.format(model.predict_proba(an_signal)))
anomal_variance = variance
write_log(N, N_train, norm_params, mean, variance, an_params, anomal_mean,
anomal_variance)
sequence = generator.Sequence(N_train,
alpha,
type='continue',
params=norm_params,
mean=mean,
variance=variance)
normal_signal = sequence.sequence
labels = list(map(myutils.rename_state, sequence.path))
model = HiddenMarkovModel.from_samples(NormalDistribution,
n_components=n_comp,
X=[normal_signal],
labels=[labels],
algorithm='labeled')
# model = HiddenMarkovModel.from_samples(GeneralMixtureModel, n_components = n_comp, X = [normal_signal],
# labels = [labels], algorithm='labeled')
# fig = plt.figure(num = 1000, figsize=(15,4))
# plt.plot(normal_signal,'b')
# plt.plot([x / 3 for x in sequence.path], 'r')
# plt.savefig('Graphs/path.png')
# plt.close('all')
pool = Pool(N_pool)
with open('model.txt', 'w') as file:
out = print_model_distribution(model)
file.write(out)
params = [
anormal_seq[start:stop] = [new_s] * (stop - start)
# n_count = 5
# anormal_seq[20:20+n_count] = ['b']*n_count
# print('Длина нормальной ',len(normal_seq),', аномальной ', len(anormal_seq))
#Модель
# model_hmm = MarkovChain.from_samples([normal_seq]);
gc.collect()
print(normal_seq[-5:])
labels = list(map(myutils.rename_state, sequence.path))
# plt.plot(normal_seq)
# # break
model_hmm = HiddenMarkovModel.from_samples(DiscreteDistribution,
n_components=len(alpha),
X=[normal_seq],
labels=[labels],
algorithm='labeled')
# model_hmm = HiddenMarkovModel.from_samples(DiscreteDistribution,n_components = len(alpha),X=[normal_seq]);
# model_hmm.bake()
experiment_discret(model=model_hmm,
normal_seq=normal_seq[:N],
anormal_seq=anormal_seq,
N=N,
num_launch=i)
# Вывод в файл
file.write(str(i) + '\n')
if isinstance(model_hmm, HiddenMarkovModel):
mixture = BayesianGaussianMixture(n_components=32)
mixture.fit(wv.vectors)
labels = mixture.predict(wv.vectors)
plt.hist(labels, bins=32)
# <codecell>
word_to_label = {}
for word in wv.vocab:
idx = wv.vocab[word].index
word_to_label[word] = labels[idx]
def _text_to_seq(text):
return np.array([word_to_label[word] for word in text])
sequences = [_text_to_seq(text) for text in texts]
# <codecell>
hmm = HiddenMarkovModel.from_samples(
NormalDistribution, # TODO: identify discrete distribution
n_components=16,
X=sequences)
# <codecell>
hmm.dense_transition_matrix()
# <codecell>
