class HMMGestureMonitor (GestureMonitor): def __init__ (self, _train_ms_list, _gesture_name, FeatureExtractor=AVFeatureExtractor): GestureMonitor.__init__ (self, _train_ms_list, _gesture_name, FeatureExtractor) def train (self, motion_sequences): dfs = [ms.get_dataframe () for ms in motion_sequences] examples = [self.feature_extractor.extract (df) for df in dfs] examples = [e for e in examples if not np.isnan(np.sum(e))] self.hmm = GaussianHMM (n_components=5).fit (examples) self.score_threshold = GMScoreThreshold (self.hmm.score, examples) self.window_timespans = self.calculate_window_timespans (motion_sequences) def classify_window_df (self, window_df): features = self.feature_extractor.extract (window_df) score = self.score_threshold.classify (features) return score def get_current_reaction (self): scores = [self.hmm.score (self.feature_extractor.extract(window_df)) for window_df in self.get_window_dfs ()] if len(scores) > 0: return np.max(scores) else: return None
def get_hmms(self):
for gesture_type in self.gesture_types:
print_status("Get_Hmms",
"Fitting for gesture_type: " + gesture_type)
### Step 1: fill hmm_examples appropriately ###
hmm_examples = []
for gesture in self.gestures[gesture_type]:
hmm_rep = gesture.get_hmm_rep()
hmm_examples.append(hmm_rep)
### Step 2: fit parameters for the hmm ###
hmm = GaussianHMM(self.num_hmm_states)
hmm.fit(hmm_examples)
### Step 3: store the hmm in self.hmms ###
self.hmms[gesture_type] = hmm
print_inner_status(
gesture_type,
"predicted the following sequences: (score: sequence)")
for example in hmm_examples:
print " ", hmm.score(example), ": ", hmm.predict(example)
def get_hmms (self):
for gesture_type in self.gesture_types:
print_status ("Get_Hmms", "Fitting for gesture_type: " + gesture_type)
### Step 1: fill hmm_examples appropriately ###
hmm_examples = []
for gesture in self.gestures[gesture_type]:
hmm_rep = gesture.get_hmm_rep ()
hmm_examples.append (hmm_rep)
### Step 2: fit parameters for the hmm ###
hmm = GaussianHMM (self.num_hmm_states)
hmm.fit (hmm_examples)
### Step 3: store the hmm in self.hmms ###
self.hmms[gesture_type] = hmm
print_inner_status (gesture_type, "predicted the following sequences: (score: sequence)")
for example in hmm_examples:
print " ", hmm.score (example), ": ", hmm.predict (example)
def train_hmm(X):
hmm = GaussianHMM(n_components=8)
hmm.fit(X);
print hmm.score(X[0])
print np.shape(X[0])
return hmm
np.linalg.cholesky(covs[i])
print np.linalg.eigvals(covs[i])
tmat, smat = get_tmat_and_smat(pre_states, end=False, start=False)
print tmat, smat
model = GaussianHMM(n_components=n_states, n_iter=n_iter, covariance_type=cov_type, startprob=smat, transmat=tmat, init_params='mc')
model.means_ = means
model.covars_ = covs
sum_inital_ll = 0.0
sum_initial_score = 0.0
sum_initial_map = 0.0
remove_idx = []
for idx, feat_from_list in enumerate(feats_as_list):
if np.shape(feat_from_list)[0] > n_states:
initial_ll, initial_best_seq = model.decode(feat_from_list)
initial_map, initial_best_sep_map = model.decode(feat_from_list, algorithm='map')
sum_initial_score += model.score(feat_from_list)
sum_inital_ll += initial_ll
sum_initial_map += initial_map
else:
remove_idx.append(idx)
print 'too few samples in file', list_of_patient_file_paths[idx], np.shape(feat_from_list)
print 'initial viterbi log-likelihood,', sum_inital_ll
print 'initial score log-likelihood,', sum_initial_score
print 'initial map log-likelihood', sum_initial_map
remove_idx.sort()
remove_idx.reverse()
print 'removing...', remove_idx
for r in remove_idx:
del feats_as_list[r]
model.fit(feats_as_list)
sum_final_ll = 0.0
covars[covars==0] = 1e-5
model = GaussianHMM(numState, covariance_type="tied", n_iter=1000, init_params='abdefghijklnopqrstuvwxyzABDEFGHIJKLNOPQRSTUVWXYZ')
model.means_ = means
model.covars_ = covars
print("Fitting model...")
sys.stdout.flush()
model.fit(data)
print("Decoding states...")
sys.stdout.flush()
# do a loop over everything and record in one long array
states = np.array([])
score = 0
for i in range(0, len(data)):
hidden_states = model.decode(data[i])
states = np.append(states, hidden_states[1])
score = score + model.score(data[i])
print("Saving data...")
sys.stdout.flush()
# save the states and LLH
np.savetxt("data/substates/%s%d/%d/rep_%d_states.txt" % (basepath,stateNum,numState,repInx), states, fmt="%d")
with open("data/substates/%s%d/%d/rep_%d_LLH.txt" % (basepath,stateNum,numState,repInx), 'w') as f:
f.write(str(score))
saveobject(model, "data/substates/%s%d/%d/rep_%d.pk" % (basepath,stateNum,numState,repInx))
print "Number of states:", sys.argv[1]
print("Loading data...")
sys.stdout.flush()
data = np.loadtxt("data/scikit-BG3Kc-K56ac.tsv", skiprows=1)
model = GaussianHMM(int(sys.argv[1]), covariance_type="tied", n_iter=1000)
print("Fitting model...")
sys.stdout.flush()
model.fit([data])
print("Decoding states...")
sys.stdout.flush()
hidden_states = model.decode(data)
llh = model.score(data)
print("Saving data...")
sys.stdout.flush()
# save the states and LLH
np.savetxt("scikit-states-all.txt", hidden_states[1], fmt="%d")
np.savetxt("scikit-states-all-LLH.txt", [llh], fmt="%f")
# save the actual object
def saveobject(obj, filename):
with open(filename, 'wb') as output:
pickle.dump(obj, output, pickle.HIGHEST_PROTOCOL)
saveobject(model, r'scikit-model.pk')
