def FV_RF(self):
print("\nrunning Random Forest on Fisher Vectors")
ae = AutoEncoder('fv_gmm', 0)
with smart_open(os.path.join(ae.save_dir, 'model_list.txt'),
'rb',
encoding='utf-8') as model_path:
for line_no, line in enumerate(model_path):
line = str(line).replace('\n', '')
print(line_no, '\t', line[65:])
feature_name = line[65:] + '_%d' % self.kernel
if os.path.isfile(
os.path.join(
line, 'X_train_tree_%d.npy' %
self.kernel)) and os.path.isfile(
os.path.join(
line, 'X_dev_tree_%d.npy' % self.kernel)):
X_train = np.load(
os.path.join(line,
'X_train_tree_%d.npy' % self.kernel))
X_dev = np.load(
os.path.join(line, 'X_dev_tree_%d.npy' % self.kernel))
y_train = np.load(os.path.join(line, 'label_train.npy'))
y_dev = np.load(os.path.join(line, 'label_dev.npy'))
print(X_train.shape, X_dev.shape)
random_forest = RandomForest(feature_name,
X_train,
y_train,
X_dev,
y_dev,
test=False)
random_forest.run()
y_pred_train, y_pred_dev = random_forest.evaluate()
get_UAR(y_pred_train,
y_train,
np.array([]),
'RF',
feature_name,
'single',
train_set=True,
test=False)
get_UAR(y_pred_dev,
y_dev,
np.array([]),
'RF',
feature_name,
'single',
test=False)
def run_MFCC(self):
"""run classifier on MFCC feature (single modality)
"""
print("\nbuilding a classifier on MFCC features (both frame-level and session-level)")
X_train, y_train, train_inst, X_dev, y_dev, dev_inst = load_proc_baseline_feature('MFCC', verbose=True)
if self.model_name == 'RF_cv':
y_train, y_dev = np.ravel(y_train), np.ravel(y_dev)
train_inst, dev_inst = np.ravel(train_inst), np.ravel(dev_inst)
X = np.vstack((X_train, X_dev))
y = np.hstack((y_train, y_dev))
inst = np.hstack((train_inst, dev_inst))
assert len(X) == len(y) == len(inst)
cv_ids = k_fold_cv(len(X))
cv_res = []
for (ids_train, ids_dev) in cv_ids:
X_train = X[ids_train]
y_train = y[ids_train]
X_dev = X[ids_dev]
y_dev = y[ids_dev]
dev_inst = inst[ids_dev]
RF_MFCC = RandomForest(self.feature_name, X_train, y_train, X_dev, y_dev, baseline=True, test=self.test)
RF_MFCC.run()
y_pred_train, y_pred_dev = RF_MFCC.evaluate()
_, session_res = get_UAR(y_pred_dev, y_dev, dev_inst, self.model_name, self.feature_name, 'baseline', baseline=True, test=True)
cv_res.append(session_res)
save_cv_results(cv_res, self.model_name, self.feature_name, 'baseline')
print("\nupsampling training data to address class imbalance")
X_train, y_train, train_inst = upsample(X_train, y_train, train_inst)
print("\nobtaining sparse matrix for better classification")
# X_train = sp.csr_matrix(np.vstack((X_train, X_dev)))
# X_dev = sp.csr_matrix(X_dev)
# y_train = np.hstack((y_train, y_dev))
X_train, X_dev = sp.csr_matrix(X_train), sp.csr_matrix(X_dev)
if self.model_name == 'SVM':
SVM_MFCC = LinearSVM(self.feature_name, X_train, y_train, X_dev, y_dev, baseline=True, test=self.test)
SVM_MFCC.run()
y_pred_train, y_pred_dev = SVM_MFCC.evaluate()
elif self.model_name == 'RF':
RF_MFCC = RandomForest(self.feature_name, X_train, y_train, X_dev, y_dev, baseline=True, test=self.test)
RF_MFCC.run()
y_pred_train, y_pred_dev = RF_MFCC.evaluate()
get_UAR(y_pred_train, y_train, train_inst, self.model_name, self.feature_name, 'baseline', baseline=True, train_set=True, test=self.test)
get_UAR(y_pred_dev, y_dev, dev_inst, self.model_name, self.feature_name, 'baseline', baseline=True, test=self.test)
if not self.test:
get_post_probability(y_pred_dev, y_dev, dev_inst, np.array([]), self.model_name, self.feature_name)
def RF(self):
print(
"\nrunning RF on features selected with RF with doc2vec embeddings"
)
feature_path = smart_open('./pre-trained/fusion/feature_list.txt',
'rb',
encoding='utf-8')
feature_list = []
for _, line in enumerate(feature_path):
feature_list.append(str(line).replace('\n', ''))
for _ in range(3):
for feature in feature_list:
_, _, y_dev, y_train = load_label()
y_train = y_train.astype('int')
y_dev = y_dev.astype('int')
X_train = np.load(
os.path.join('pre-trained', 'fusion', feature,
'X_train.npy'))
X_dev = np.load(
os.path.join('pre-trained', 'fusion', feature,
'X_dev.npy'))
random_forest = RandomForest(feature,
X_train,
y_train,
X_dev,
y_dev,
test=False)
random_forest.run()
y_pred_train, y_pred_dev = random_forest.evaluate()
get_UAR(y_pred_train,
y_train,
np.array([]),
'RF',
feature,
'multiple',
train_set=True,
test=False)
get_UAR(y_pred_dev,
y_dev,
np.array([]),
'RF',
feature,
'multiple',
test=False)
def run_AU(self):
"""run classifier on AU feature (single modality)
"""
print("\nbuilding a classifier on AU features (already session-level)")
X_train, y_train, _, X_dev, y_dev, _ = load_proc_baseline_feature('AU', verbose=True)
if self.model_name == 'RF_cv':
X = np.vstack((X_train, X_dev))
y = np.hstack((y_train, y_dev))
assert len(X) == len(y)
cv_ids = k_fold_cv(len(X))
cv_res = []
for (ids_train, ids_dev) in cv_ids:
X_train = X[ids_train]
y_train = y[ids_train]
X_dev = X[ids_dev]
y_dev = y[ids_dev]
RF_MFCC = RandomForest(self.feature_name, X_train, y_train, X_dev, y_dev, baseline=True, test=self.test)
RF_MFCC.run()
y_pred_train, y_pred_dev = RF_MFCC.evaluate()
_, session_res = get_UAR(y_pred_dev, y_dev, np.array([]), self.model_name, self.feature_name, 'baseline', baseline=True, test=True)
cv_res.append(session_res)
save_cv_results(cv_res, self.model_name, self.feature_name, 'baseline')
print("\nupsampling training data to address class imbalance")
X_train, y_train, _ = upsample(X_train, y_train, np.array([]))
print("\nobtaining sparse matrix for better classification")
# X_train = sp.csr_matrix(np.vstack((X_train, X_dev)))
# X_dev = sp.csr_matrix(X_dev)
# y_train = np.hstack((y_train, y_dev))
X_train, X_dev = sp.csr_matrix(X_train), sp.csr_matrix(X_dev)
if self.model_name == 'SVM':
SVM_AU = LinearSVM(self.feature_name, X_train, y_train, X_dev, y_dev, baseline=True, test=self.test)
SVM_AU.run()
y_pred_train, y_pred_dev = SVM_AU.evaluate()
session_prob = SVM_AU.get_session_probability()
elif self.model_name == 'RF':
RF_AU = RandomForest(self.feature_name, X_train, y_train, X_dev, y_dev, baseline=True, test=self.test)
RF_AU.run()
y_pred_train, y_pred_dev = RF_AU.evaluate()
session_prob = RF_AU.get_session_probability()
get_UAR(y_pred_train, y_train, np.array([]), self.model_name, self.feature_name, 'baseline', baseline=True, train_set=True, test=self.test)
get_UAR(y_pred_dev, y_dev, np.array([]), self.model_name, self.feature_name, 'baseline', baseline=True, test=self.test)
def TEXT_RF(self):
print("\nrunning Random Forest on document embeddings")
text2vec = Text2Vec()
with smart_open(os.path.join(
text2vec.model_config['doc2vec']['save_dir'],
'model_list.txt'),
'rb',
encoding='utf-8') as model_path:
for line_no, line in enumerate(model_path):
line = str(line).replace('\n', '')
print(line_no, '\t', line[68:])
X_train = np.load(os.path.join(line, 'vectors_train.npy'))
X_dev = np.load(os.path.join(line, 'vectors_dev.npy'))
y_train = np.load(os.path.join(line, 'labels_train.npy'))
y_dev = np.load(os.path.join(line, 'labels_dev.npy'))
y_train = np.ravel(y_train)
y_dev = np.ravel(y_dev)
random_forest = RandomForest(line[68:],
X_train,
y_train,
X_dev,
y_dev,
baseline=False)
random_forest.run()
y_pred_train, y_pred_dev = random_forest.evaluate()
get_UAR(y_pred_train,
y_train,
np.array([]),
'RF',
line[68:],
'single',
baseline=False,
train_set=True)
get_UAR(y_pred_dev,
y_dev,
np.array([]),
'RF',
line[68:],
'single',
baseline=False)