def get_data_by_id(feature_table, gender=False):
sql_handler = SqlHandler()
feature = sql_handler.get_df(feature_table)
feature['ID'] = feature['ID'].apply(pd.to_numeric) #转为数值
train = sql_handler.get_df(config.tbl_train_ros_set)
dev = sql_handler.get_df(config.tbl_develop_set)
test = sql_handler.get_df(config.tbl_test_set)
if not gender:
train_set = merge_df_by_id(
train, feature) #合并特征csv和PHQcsv 调用了之前的函数 merge_df_by_id()
dev_set = merge_df_by_id(dev, feature) #合并特征csv和PHQcsv
test_set = merge_df_by_id(test, feature)
return train_set, dev_set, test_set
else: #考虑性别因素
train_male = train[train['Gender'] == 1]
train_female = train[train['Gender'] == 0]
dev_male = dev[dev['Gender'] == 1]
dev_female = dev[dev['Gender'] == 0]
test_male = test[test['Gender'] == 1]
test_female = test[test['Gender'] == 0]
train_male = merge_df_by_id(train_male, feature)
train_female = merge_df_by_id(train_female, feature)
dev_male = merge_df_by_id(dev_male, feature)
dev_female = merge_df_by_id(dev_female, feature)
test_male = merge_df_by_id(test_male, feature)
test_female = merge_df_by_id(test_female, feature)
return train_male, dev_male, test_male, train_female, dev_female, test_female
def get_data_multi_modality(tables, gender=False):
"""gather data from different tables in every modality
and generate train set and dev dev set of them.
"""
sql_handler = SqlHandler()
audio_df, video_df, text_df = [], [], []
for tb in tables:
if tb in AUDIO_TABLE:
audio_df.append(sql_handler.get_df(tb)) #从数据库提取特征存入list
elif tb in VIDEO_TABLE:
video_df.append(sql_handler.get_df(tb))
elif tb in TEXT_TABLE:
text_df.append(sql_handler.get_df(tb))
else:
pass
audio_merge_df = merge_dfs_by_id(audio_df)
video_merge_df = merge_dfs_by_id(video_df)
text_merge_df = merge_dfs_by_id(text_df)
train = sql_handler.get_df(config.tbl_train_ros_set)
dev = sql_handler.get_df(config.tbl_develop_set)
if not gender: #不考虑性别
data_dct = {
'audio_train': merge_df_by_id(train, audio_merge_df),
'audio_dev': merge_df_by_id(dev, audio_merge_df),
'vedio_train': merge_df_by_id(train, video_merge_df),
'vedio_dev': merge_df_by_id(dev, video_merge_df),
'text_train': merge_df_by_id(train, text_merge_df),
'text_dev': merge_df_by_id(dev, text_merge_df)
}
else: #考虑性别
train_male = train[train['Gender'] == 1]
train_female = train[train['Gender'] == 0]
dev_male = dev[dev['Gender'] == 1]
dev_female = dev[dev['Gender'] == 0]
data_dct = {
'male': {
'audio_train': merge_df_by_id(train_male, audio_merge_df),
'audio_dev': merge_df_by_id(dev_male, audio_merge_df),
'vedio_train': merge_df_by_id(train_male, video_merge_df),
'vedio_dev': merge_df_by_id(dev_male, video_merge_df),
'text_train': merge_df_by_id(train_male, text_merge_df),
'text_dev': merge_df_by_id(dev_male, text_merge_df)
},
'female': {
'audio_train': merge_df_by_id(train_female, audio_merge_df),
'audio_dev': merge_df_by_id(dev_female, audio_merge_df),
'vedio_train': merge_df_by_id(train_female, video_merge_df),
'vedio_dev': merge_df_by_id(dev_female, video_merge_df),
'text_train': merge_df_by_id(train_female, text_merge_df),
'text_dev': merge_df_by_id(dev_female, text_merge_df)
}
}
return data_dct
def get_data_by_id(feature_table, gender=False):
sql_handler = SqlHandler()
feature = sql_handler.get_df(feature_table)
feature['ID'] = feature['ID'].apply(pd.to_numeric)
train = sql_handler.get_df(config.tbl_training_set)
dev = sql_handler.get_df(config.tbl_develop_set)
if not gender:
train_set = merge_df_by_id(train, feature)
dev_set = merge_df_by_id(dev, feature)
return train_set, dev_set
else:
train_male = train[train['Gender'] == 1]
train_female = train[train['Gender'] == 0]
dev_male = train[train['Gender'] == 1]
dev_female = train[train['Gender'] == 0]
train_male = merge_df_by_id(train_male, feature)
train_female = merge_df_by_id(train_female, feature)
dev_male = merge_df_by_id(dev_male, feature)
dev_female = merge_df_by_id(dev_female, feature)
return train_male, dev_male, train_female, dev_female
def createCodebook(feature_name):
"""
COVAREP, FORMANT, FAUs ,***p.CSV->stack dataframe -> create codebook ->extract all files' features
java -jar openXBOW.jar -i examples/example2/llds.csPv -o bow.csv -a 1 -log -c kmeans++ -size 100 -B codebook -writeName -writeTimeStamp
"""
sqlhandler = SqlHandler()
train = sqlhandler.get_df(config.tbl_training_set)
dev = sqlhandler.get_df(config.tbl_develop_set)
trainID = train['Participant_ID'].values
devID = dev['Participant_ID'].values
trainDev = np.hstack([trainID, devID])
folds = np.random.choice(trainDev, 20,
replace=False) # for video 50, for audio 20
window_size = 4
hop_size = 1
openxbow = 'java -jar E:/openXBOW/openXBOW.jar '
openxbow_options = '-writeName -writeTimeStamp -t ' + str(
window_size) + ' ' + str(hop_size)
codebook_out = 'E:/openXBOW/codebooks/'
openxbow_options_codebook = f'-size 100 -a 1 -log -B {codebook_out}{feature_name}_codebook '
if feature_name == 'faus':
for fold in folds:
path = config.data_dir + str(fold) + '_P/' + str(
fold) + '_' + SUFFIX['au']
feature = np.loadtxt(path, delimiter=',', skiprows=1)
success = feature[:, 3] == 1
feature = feature[success, 1:18]
feature = np.delete(feature, [1, 2], axis=1)
save_features(codebook_out + 'fausTrainDevRandom.csv',
feature,
append=True,
instname=str(fold))
os.system(openxbow+ f'-standardizeInput -i {codebook_out}fausTrainDevRandom.csv '+openxbow_options_codebook+\
openxbow_options+ ' -c kmeans++'+ f' -o {codebook_out}temp.csv')
elif feature_name == 'gaze_pose':
for fold in folds:
path1 = config.data_dir + str(fold) + '_P/' + str(
fold) + '_' + SUFFIX['gaze']
path2 = config.data_dir + str(fold) + '_P/' + str(
fold) + '_' + SUFFIX['pose']
gaze_data = pd.read_csv(path1)
pose_data = pd.read_csv(path2)
if fold in [367, 396, 432]:
temp = np.all(pose_data.values != ' -1.#IND',
axis=1) #['367_', '396_', '432_'] 缺失 存在异常值
data = pd.merge(
gaze_data,
pose_data) #key = frame timestamps confidence success
data = data[temp]
data.iloc[:, -6:] = data.iloc[:, -6:].applymap(
lambda x: float(x[1:]))
else:
data = pd.merge(gaze_data, pose_data)
success = data[' success'] == 1
data = data.values[:, 1:]
data = np.delete(data, [1, 2], axis=1)
data = data[success]
save_features(codebook_out + 'gazePoseTrainDevRandom.csv',
data,
append=True,
instname=str(fold))
os.system(openxbow+ f'-standardizeInput -i {codebook_out}gazeposeTrainDevRandom.csv '+openxbow_options_codebook+\
openxbow_options+ ' -c kmeans++'+ f' -o {codebook_out}temp.csv')
elif feature_name == 'covarep':
for fold in folds:
path = config.data_dir + str(fold) + '_P/' + str(
fold) + '_' + SUFFIX['covarep']
data = np.loadtxt(path, delimiter=',')
timestamp = np.arange(0, data.shape[0]).reshape(data.shape[0], 1)
timestamp = timestamp / 100
data = np.hstack([timestamp, data])
data = data[data[:, 2] == 1]
data = np.delete(data, 2, axis=1)
data[np.isnan(data)] = 0
data[np.isinf(data)] = 0
save_features(codebook_out + 'covarepTrainDevRandom.csv',
data,
append=True,
instname=str(fold))
os.system(openxbow+ f'-standardizeInput -i {codebook_out}covarepTrainDevRandom.csv '+openxbow_options_codebook+\
openxbow_options+ ' -c kmeans++'+ f' -o {codebook_out}temp.csv')
else:
for fold in folds:
path = config.data_dir + str(fold) + '_P/' + str(
fold) + '_' + SUFFIX['formant']
data = np.loadtxt(path, delimiter=',')
timestamp = np.arange(0, data.shape[0]).reshape(data.shape[0], 1)
timestamp = timestamp / 100
data = np.hstack([timestamp, data])
data[np.isnan(data)] = 0
data[np.isinf(data)] = 0
save_features(codebook_out + 'formantTrainDevRandom.csv',
data,
append=True,
instname=str(fold))
os.system(openxbow+ f'-standardizeInput -i {codebook_out}formantTrainDevRandom.csv '+openxbow_options_codebook+\
openxbow_options+ ' -c kmeans++'+ f' -o {codebook_out}temp.csv')